diff options
Diffstat (limited to 'include/linux')
354 files changed, 19620 insertions, 6088 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e4da5e35e29c..d2445fa9999f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -53,11 +53,24 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) return adev ? adev->handle : NULL; } -#define ACPI_COMPANION(dev) acpi_node((dev)->fwnode) +#define ACPI_COMPANION(dev) to_acpi_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) +/** + * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with + * the PCI-defined class-code information + * + * @_cls : the class, subclass, prog-if triple for this device + * @_msk : the class mask for this device + * + * This macro is used to create a struct acpi_device_id that matches a + * specific PCI class. The .id and .driver_data fields will be left + * initialized with the default value. + */ +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk), + static inline bool has_acpi_companion(struct device *dev) { return is_acpi_node(dev->fwnode); @@ -158,6 +171,16 @@ typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif +static inline bool invalid_logical_cpuid(u32 cpuid) +{ + return (int)cpuid < 0; +} + +static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) +{ + return phys_id == PHYS_CPUID_INVALID; +} + #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu); @@ -243,54 +266,21 @@ extern bool wmi_has_guid(const char *guid); #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 -#if defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE) - -extern long acpi_video_get_capabilities(acpi_handle graphics_dev_handle); +extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); -extern void acpi_video_dmi_promote_vendor(void); -extern void acpi_video_dmi_demote_vendor(void); -extern int acpi_video_backlight_support(void); -extern int acpi_video_display_switch_support(void); - -#else - -static inline long acpi_video_get_capabilities(acpi_handle graphics_dev_handle) -{ - return 0; -} - -static inline long acpi_is_video_device(acpi_handle handle) -{ - return 0; -} - -static inline void acpi_video_dmi_promote_vendor(void) -{ -} - -static inline void acpi_video_dmi_demote_vendor(void) -{ -} - -static inline int acpi_video_backlight_support(void) -{ - return 0; -} - -static inline int acpi_video_display_switch_support(void) -{ - return 0; -} - -#endif /* defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE) */ - extern int acpi_blacklisted(void); extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d); extern void acpi_osi_setup(char *str); +extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_NUMA +int acpi_map_pxm_to_online_node(int pxm); int acpi_get_node(acpi_handle handle); #else +static inline int acpi_map_pxm_to_online_node(int pxm) +{ + return 0; +} static inline int acpi_get_node(acpi_handle handle) { return 0; @@ -440,6 +430,7 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 extern void acpi_early_init(void); +extern void acpi_subsystem_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); @@ -465,6 +456,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *); #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), struct fwnode_handle; @@ -473,7 +465,7 @@ static inline bool is_acpi_node(struct fwnode_handle *fwnode) return false; } -static inline struct acpi_device *acpi_node(struct fwnode_handle *fwnode) +static inline struct acpi_device *to_acpi_node(struct fwnode_handle *fwnode) { return NULL; } @@ -494,6 +486,7 @@ static inline const char *acpi_dev_name(struct acpi_device *adev) } static inline void acpi_early_init(void) { } +static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { @@ -569,6 +562,11 @@ static inline int acpi_device_modalias(struct device *dev, return -ENODEV; } +static inline bool acpi_check_dma(struct acpi_device *adev, bool *coherent) +{ + return false; +} + #define ACPI_PTR(_ptr) (NULL) #endif /* !CONFIG_ACPI */ @@ -721,6 +719,8 @@ static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) if (adev) adev->driver_gpios = NULL; } + +int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index); #else static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) @@ -728,6 +728,11 @@ static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, return -ENXIO; } static inline void acpi_dev_remove_driver_gpios(struct acpi_device *adev) {} + +static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) +{ + return -ENXIO; +} #endif /* Device properties */ diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index a899402a5a0e..52f3b7da4f2d 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -43,8 +43,8 @@ struct alarm { void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); -int alarm_start(struct alarm *alarm, ktime_t start); -int alarm_start_relative(struct alarm *alarm, ktime_t start); +void alarm_start(struct alarm *alarm, ktime_t start); +void alarm_start_relative(struct alarm *alarm, ktime_t start); void alarm_restart(struct alarm *alarm); int alarm_try_to_cancel(struct alarm *alarm); int alarm_cancel(struct alarm *alarm); diff --git a/include/linux/amba/sp810.h b/include/linux/amba/sp810.h index c7df89f99115..58fe9e8b6fd7 100644 --- a/include/linux/amba/sp810.h +++ b/include/linux/amba/sp810.h @@ -2,7 +2,7 @@ * ARM PrimeXsys System Controller SP810 header file * * Copyright (C) 2009 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> + * Viresh Kumar <vireshk@kernel.org> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/include/linux/ata.h b/include/linux/ata.h index b666b773e111..d2992bfa1706 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -45,6 +45,7 @@ enum { ATA_SECT_SIZE = 512, ATA_MAX_SECTORS_128 = 128, ATA_MAX_SECTORS = 256, + ATA_MAX_SECTORS_1024 = 1024, ATA_MAX_SECTORS_LBA48 = 65535,/* TODO: 65536? */ ATA_MAX_SECTORS_TAPE = 65535, @@ -384,8 +385,6 @@ enum { SATA_SSP = 0x06, /* Software Settings Preservation */ SATA_DEVSLP = 0x09, /* Device Sleep */ - SETFEATURE_SENSE_DATA = 0xC3, /* Sense Data Reporting feature */ - /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, ATA_SET_MAX_PASSWD = 0x01, @@ -529,8 +528,6 @@ struct ata_bmdma_prd { #define ata_id_cdb_intr(id) (((id)[ATA_ID_CONFIG] & 0x60) == 0x20) #define ata_id_has_da(id) ((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4)) #define ata_id_has_devslp(id) ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8)) -#define ata_id_has_ncq_autosense(id) \ - ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7)) static inline bool ata_id_has_hipm(const u16 *id) { @@ -704,23 +701,19 @@ static inline bool ata_id_wcache_enabled(const u16 *id) static inline bool ata_id_has_read_log_dma_ext(const u16 *id) { + /* Word 86 must have bit 15 set */ if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 3); -} -static inline bool ata_id_has_sense_reporting(const u16 *id) -{ - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) - return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 6); -} + /* READ LOG DMA EXT support can be signaled either from word 119 + * or from word 120. The format is the same for both words: Bit + * 15 must be cleared, bit 14 set and bit 3 set. + */ + if ((id[ATA_ID_COMMAND_SET_3] & 0xC008) == 0x4008 || + (id[ATA_ID_COMMAND_SET_4] & 0xC008) == 0x4008) + return true; -static inline bool ata_id_sense_reporting_enabled(const u16 *id) -{ - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) - return false; - return id[ATA_ID_COMMAND_SET_4] & (1 << 6); + return false; } /** diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h new file mode 100644 index 000000000000..a23209b43842 --- /dev/null +++ b/include/linux/backing-dev-defs.h @@ -0,0 +1,256 @@ +#ifndef __LINUX_BACKING_DEV_DEFS_H +#define __LINUX_BACKING_DEV_DEFS_H + +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/rbtree.h> +#include <linux/spinlock.h> +#include <linux/percpu_counter.h> +#include <linux/percpu-refcount.h> +#include <linux/flex_proportions.h> +#include <linux/timer.h> +#include <linux/workqueue.h> + +struct page; +struct device; +struct dentry; + +/* + * Bits in bdi_writeback.state + */ +enum wb_state { + WB_registered, /* bdi_register() was done */ + WB_writeback_running, /* Writeback is in progress */ + WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ +}; + +enum wb_congested_state { + WB_async_congested, /* The async (write) queue is getting full */ + WB_sync_congested, /* The sync queue is getting full */ +}; + +typedef int (congested_fn)(void *, int); + +enum wb_stat_item { + WB_RECLAIMABLE, + WB_WRITEBACK, + WB_DIRTIED, + WB_WRITTEN, + NR_WB_STAT_ITEMS +}; + +#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) + +/* + * For cgroup writeback, multiple wb's may map to the same blkcg. Those + * wb's can operate mostly independently but should share the congested + * state. To facilitate such sharing, the congested state is tracked using + * the following struct which is created on demand, indexed by blkcg ID on + * its bdi, and refcounted. + */ +struct bdi_writeback_congested { + unsigned long state; /* WB_[a]sync_congested flags */ + atomic_t refcnt; /* nr of attached wb's and blkg */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct backing_dev_info *bdi; /* the associated bdi */ + int blkcg_id; /* ID of the associated blkcg */ + struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ +#endif +}; + +/* + * Each wb (bdi_writeback) can perform writeback operations, is measured + * and throttled, independently. Without cgroup writeback, each bdi + * (bdi_writeback) is served by its embedded bdi->wb. + * + * On the default hierarchy, blkcg implicitly enables memcg. This allows + * using memcg's page ownership for attributing writeback IOs, and every + * memcg - blkcg combination can be served by its own wb by assigning a + * dedicated wb to each memcg, which enables isolation across different + * cgroups and propagation of IO back pressure down from the IO layer upto + * the tasks which are generating the dirty pages to be written back. + * + * A cgroup wb is indexed on its bdi by the ID of the associated memcg, + * refcounted with the number of inodes attached to it, and pins the memcg + * and the corresponding blkcg. As the corresponding blkcg for a memcg may + * change as blkcg is disabled and enabled higher up in the hierarchy, a wb + * is tested for blkcg after lookup and removed from index on mismatch so + * that a new wb for the combination can be created. + */ +struct bdi_writeback { + struct backing_dev_info *bdi; /* our parent bdi */ + + unsigned long state; /* Always use atomic bitops on this */ + unsigned long last_old_flush; /* last old data flush */ + + struct list_head b_dirty; /* dirty inodes */ + struct list_head b_io; /* parked for writeback */ + struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ + spinlock_t list_lock; /* protects the b_* lists */ + + struct percpu_counter stat[NR_WB_STAT_ITEMS]; + + struct bdi_writeback_congested *congested; + + unsigned long bw_time_stamp; /* last time write bw is updated */ + unsigned long dirtied_stamp; + unsigned long written_stamp; /* pages written at bw_time_stamp */ + unsigned long write_bandwidth; /* the estimated write bandwidth */ + unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ + + /* + * The base dirty throttle rate, re-calculated on every 200ms. + * All the bdi tasks' dirty rate will be curbed under it. + * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit + * in small steps and is much more smooth/stable than the latter. + */ + unsigned long dirty_ratelimit; + unsigned long balanced_dirty_ratelimit; + + struct fprop_local_percpu completions; + int dirty_exceeded; + + spinlock_t work_lock; /* protects work_list & dwork scheduling */ + struct list_head work_list; + struct delayed_work dwork; /* work item used for writeback */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct percpu_ref refcnt; /* used only for !root wb's */ + struct fprop_local_percpu memcg_completions; + struct cgroup_subsys_state *memcg_css; /* the associated memcg */ + struct cgroup_subsys_state *blkcg_css; /* and blkcg */ + struct list_head memcg_node; /* anchored at memcg->cgwb_list */ + struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + + union { + struct work_struct release_work; + struct rcu_head rcu; + }; +#endif +}; + +struct backing_dev_info { + struct list_head bdi_list; + unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ + unsigned int capabilities; /* Device capabilities */ + congested_fn *congested_fn; /* Function pointer if device is md/dm */ + void *congested_data; /* Pointer to aux data for congested func */ + + char *name; + + unsigned int min_ratio; + unsigned int max_ratio, max_prop_frac; + + /* + * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are + * any dirty wbs, which is depended upon by bdi_has_dirty(). + */ + atomic_long_t tot_write_bandwidth; + + struct bdi_writeback wb; /* the root writeback info for this bdi */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ + struct rb_root cgwb_congested_tree; /* their congested states */ + atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */ +#else + struct bdi_writeback_congested *wb_congested; +#endif + wait_queue_head_t wb_waitq; + + struct device *dev; + + struct timer_list laptop_mode_wb_timer; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debug_dir; + struct dentry *debug_stats; +#endif +}; + +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + +void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); +void set_wb_congested(struct bdi_writeback_congested *congested, int sync); + +static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + clear_wb_congested(bdi->wb.congested, sync); +} + +static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + set_wb_congested(bdi->wb.congested, sync); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * wb_tryget - try to increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + return percpu_ref_tryget(&wb->refcnt); + return true; +} + +/** + * wb_get - increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline void wb_get(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_get(&wb->refcnt); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_put(&wb->refcnt); +} + +/** + * wb_dying - is a wb dying? + * @wb: bdi_writeback of interest + * + * Returns whether @wb is unlinked and being drained. + */ +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return percpu_ref_is_dying(&wb->refcnt); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + return true; +} + +static inline void wb_get(struct bdi_writeback *wb) +{ +} + +static inline void wb_put(struct bdi_writeback *wb) +{ +} + +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return false; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +#endif /* __LINUX_BACKING_DEV_DEFS_H */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index aff923ae8c4b..0fe9df983ab7 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -8,106 +8,14 @@ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H -#include <linux/percpu_counter.h> -#include <linux/log2.h> -#include <linux/flex_proportions.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> -#include <linux/timer.h> +#include <linux/blkdev.h> #include <linux/writeback.h> -#include <linux/atomic.h> -#include <linux/sysctl.h> -#include <linux/workqueue.h> - -struct page; -struct device; -struct dentry; - -/* - * Bits in backing_dev_info.state - */ -enum bdi_state { - BDI_async_congested, /* The async (write) queue is getting full */ - BDI_sync_congested, /* The sync queue is getting full */ - BDI_registered, /* bdi_register() was done */ - BDI_writeback_running, /* Writeback is in progress */ -}; - -typedef int (congested_fn)(void *, int); - -enum bdi_stat_item { - BDI_RECLAIMABLE, - BDI_WRITEBACK, - BDI_DIRTIED, - BDI_WRITTEN, - NR_BDI_STAT_ITEMS -}; - -#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) - -struct bdi_writeback { - struct backing_dev_info *bdi; /* our parent bdi */ - - unsigned long last_old_flush; /* last old data flush */ - - struct delayed_work dwork; /* work item used for writeback */ - struct list_head b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ - struct list_head b_dirty_time; /* time stamps are dirty */ - spinlock_t list_lock; /* protects the b_* lists */ -}; - -struct backing_dev_info { - struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ - unsigned long state; /* Always use atomic bitops on this */ - unsigned int capabilities; /* Device capabilities */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ - - char *name; - - struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; - - unsigned long bw_time_stamp; /* last time write bw is updated */ - unsigned long dirtied_stamp; - unsigned long written_stamp; /* pages written at bw_time_stamp */ - unsigned long write_bandwidth; /* the estimated write bandwidth */ - unsigned long avg_write_bandwidth; /* further smoothed write bw */ - - /* - * The base dirty throttle rate, re-calculated on every 200ms. - * All the bdi tasks' dirty rate will be curbed under it. - * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit - * in small steps and is much more smooth/stable than the latter. - */ - unsigned long dirty_ratelimit; - unsigned long balanced_dirty_ratelimit; - - struct fprop_local_percpu completions; - int dirty_exceeded; - - unsigned int min_ratio; - unsigned int max_ratio, max_prop_frac; - - struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */ - - struct list_head work_list; - - struct device *dev; - - struct timer_list laptop_mode_wb_timer; - -#ifdef CONFIG_DEBUG_FS - struct dentry *debug_dir; - struct dentry *debug_stats; -#endif -}; - -struct backing_dev_info *inode_to_bdi(struct inode *inode); +#include <linux/blk-cgroup.h> +#include <linux/backing-dev-defs.h> +#include <linux/slab.h> int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -116,99 +24,100 @@ __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); -void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - enum wb_reason reason); -void bdi_start_background_writeback(struct backing_dev_info *bdi); -void bdi_writeback_workfn(struct work_struct *work); -int bdi_has_dirty_io(struct backing_dev_info *bdi); -void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); +void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, + bool range_cyclic, enum wb_reason reason); +void wb_start_background_writeback(struct bdi_writeback *wb); +void wb_workfn(struct work_struct *work); +void wb_wakeup_delayed(struct bdi_writeback *wb); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; -static inline int wb_has_dirty_io(struct bdi_writeback *wb) +static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { - return !list_empty(&wb->b_dirty) || - !list_empty(&wb->b_io) || - !list_empty(&wb->b_more_io); + return test_bit(WB_has_dirty_io, &wb->state); +} + +static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + /* + * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are + * any dirty wbs. See wb_update_write_bandwidth(). + */ + return atomic_long_read(&bdi->tot_write_bandwidth); } -static inline void __add_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item, s64 amount) +static inline void __add_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item, s64 amount) { - __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); + __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __inc_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, 1); + __add_wb_stat(wb, item, 1); } -static inline void inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __inc_bdi_stat(bdi, item); + __inc_wb_stat(wb, item); local_irq_restore(flags); } -static inline void __dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __dec_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, -1); + __add_wb_stat(wb, item, -1); } -static inline void dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __dec_bdi_stat(bdi, item); + __dec_wb_stat(wb, item); local_irq_restore(flags); } -static inline s64 bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - return percpu_counter_read_positive(&bdi->bdi_stat[item]); + return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 __wb_stat_sum(struct bdi_writeback *wb, + enum wb_stat_item item) { - return percpu_counter_sum_positive(&bdi->bdi_stat[item]); + return percpu_counter_sum_positive(&wb->stat[item]); } -static inline s64 bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { s64 sum; unsigned long flags; local_irq_save(flags); - sum = __bdi_stat_sum(bdi, item); + sum = __wb_stat_sum(wb, item); local_irq_restore(flags); return sum; } -extern void bdi_writeout_inc(struct backing_dev_info *bdi); +extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ -static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi) +static inline unsigned long wb_stat_error(struct bdi_writeback *wb) { #ifdef CONFIG_SMP - return nr_cpu_ids * BDI_STAT_BATCH; + return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif @@ -232,50 +141,57 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * + * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 +#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) extern struct backing_dev_info noop_backing_dev_info; -int writeback_in_progress(struct backing_dev_info *bdi); - -static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits) +/** + * writeback_in_progress - determine whether there is writeback in progress + * @wb: bdi_writeback of interest + * + * Determine whether there is writeback waiting to be handled against a + * bdi_writeback. + */ +static inline bool writeback_in_progress(struct bdi_writeback *wb) { - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, bdi_bits); - return (bdi->state & bdi_bits); + return test_bit(WB_writeback_running, &wb->state); } -static inline int bdi_read_congested(struct backing_dev_info *bdi) +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { - return bdi_congested(bdi, 1 << BDI_sync_congested); -} + struct super_block *sb; -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << BDI_async_congested); + if (!inode) + return &noop_backing_dev_info; + + sb = inode->i_sb; +#ifdef CONFIG_BLOCK + if (sb_is_blkdev_sb(sb)) + return blk_get_backing_dev_info(I_BDEV(inode)); +#endif + return sb->s_bdi; } -static inline int bdi_rw_congested(struct backing_dev_info *bdi) +static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - return bdi_congested(bdi, (1 << BDI_sync_congested) | - (1 << BDI_async_congested)); -} + struct backing_dev_info *bdi = wb->bdi; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; + if (bdi->congested_fn) + return bdi->congested_fn(bdi->congested_data, cong_bits); + return wb->congested->state & cong_bits; +} -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); long wait_iff_congested(struct zone *zone, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, @@ -319,4 +235,336 @@ static inline int bdi_sched_wait(void *word) return 0; } -#endif /* _LINUX_BACKING_DEV_H */ +#ifdef CONFIG_CGROUP_WRITEBACK + +struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); +void wb_congested_put(struct bdi_writeback_congested *congested); +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp); +void wb_memcg_offline(struct mem_cgroup *memcg); +void wb_blkcg_offline(struct blkcg *blkcg); +int inode_congested(struct inode *inode, int cong_bits); + +/** + * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode + * @inode: inode of interest + * + * cgroup writeback requires support from both the bdi and filesystem. + * Test whether @inode has both. + */ +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + + return bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && + (inode->i_sb->s_iflags & SB_I_CGROUPWB); +} + +/** + * wb_find_current - find wb for %current on a bdi + * @bdi: bdi of interest + * + * Find the wb of @bdi which matches both the memcg and blkcg of %current. + * Must be called under rcu_read_lock() which protects the returend wb. + * NULL if not found. + */ +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + struct cgroup_subsys_state *memcg_css; + struct bdi_writeback *wb; + + memcg_css = task_css(current, memory_cgrp_id); + if (!memcg_css->parent) + return &bdi->wb; + + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + + /* + * %current's blkcg equals the effective blkcg of its memcg. No + * need to use the relatively expensive cgroup_get_e_css(). + */ + if (likely(wb && wb->blkcg_css == task_css(current, blkio_cgrp_id))) + return wb; + return NULL; +} + +/** + * wb_get_create_current - get or create wb for %current on a bdi + * @bdi: bdi of interest + * @gfp: allocation mask + * + * Equivalent to wb_get_create() on %current's memcg. This function is + * called from a relatively hot path and optimizes the common cases using + * wb_find_current(). + */ +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + struct bdi_writeback *wb; + + rcu_read_lock(); + wb = wb_find_current(bdi); + if (wb && unlikely(!wb_tryget(wb))) + wb = NULL; + rcu_read_unlock(); + + if (unlikely(!wb)) { + struct cgroup_subsys_state *memcg_css; + + memcg_css = task_get_css(current, memory_cgrp_id); + wb = wb_get_create(bdi, memcg_css, gfp); + css_put(memcg_css); + } + return wb; +} + +/** + * inode_to_wb_is_valid - test whether an inode has a wb associated + * @inode: inode of interest + * + * Returns %true if @inode has a wb associated. May be called without any + * locking. + */ +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return inode->i_wb; +} + +/** + * inode_to_wb - determine the wb of an inode + * @inode: inode of interest + * + * Returns the wb @inode is currently associated with. The caller must be + * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the + * associated wb's list_lock. + */ +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(debug_locks && + (!lockdep_is_held(&inode->i_lock) && + !lockdep_is_held(&inode->i_mapping->tree_lock) && + !lockdep_is_held(&inode->i_wb->list_lock))); +#endif + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction + * @inode: target inode + * @lockedp: temp bool output param, to be passed to the end function + * + * The caller wants to access the wb associated with @inode but isn't + * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This + * function determines the wb associated with @inode and ensures that the + * association doesn't change until the transaction is finished with + * unlocked_inode_to_wb_end(). + * + * The caller must call unlocked_inode_to_wb_end() with *@lockdep + * afterwards and can't sleep during transaction. IRQ may or may not be + * disabled on return. + */ +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + rcu_read_lock(); + + /* + * Paired with store_release in inode_switch_wb_work_fn() and + * ensures that we see the new wb if we see cleared I_WB_SWITCH. + */ + *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + + if (unlikely(*lockedp)) + spin_lock_irq(&inode->i_mapping->tree_lock); + + /* + * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock. + * inode_to_wb() will bark. Deref directly. + */ + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_end - end inode wb access transaction + * @inode: target inode + * @locked: *@lockedp from unlocked_inode_to_wb_begin() + */ +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ + if (unlikely(locked)) + spin_unlock_irq(&inode->i_mapping->tree_lock); + + rcu_read_unlock(); +} + +struct wb_iter { + int start_blkcg_id; + struct radix_tree_iter tree_iter; + void **slot; +}; + +static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter, + struct backing_dev_info *bdi) +{ + struct radix_tree_iter *titer = &iter->tree_iter; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (iter->start_blkcg_id >= 0) { + iter->slot = radix_tree_iter_init(titer, iter->start_blkcg_id); + iter->start_blkcg_id = -1; + } else { + iter->slot = radix_tree_next_slot(iter->slot, titer, 0); + } + + if (!iter->slot) + iter->slot = radix_tree_next_chunk(&bdi->cgwb_tree, titer, 0); + if (iter->slot) + return *iter->slot; + return NULL; +} + +static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter, + struct backing_dev_info *bdi, + int start_blkcg_id) +{ + iter->start_blkcg_id = start_blkcg_id; + + if (start_blkcg_id) + return __wb_iter_next(iter, bdi); + else + return &bdi->wb; +} + +/** + * bdi_for_each_wb - walk all wb's of a bdi in ascending blkcg ID order + * @wb_cur: cursor struct bdi_writeback pointer + * @bdi: bdi to walk wb's of + * @iter: pointer to struct wb_iter to be used as iteration buffer + * @start_blkcg_id: blkcg ID to start iteration from + * + * Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending + * blkcg ID order starting from @start_blkcg_id. @iter is struct wb_iter + * to be used as temp storage during iteration. rcu_read_lock() must be + * held throughout iteration. + */ +#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ + for ((wb_cur) = __wb_iter_init(iter, bdi, start_blkcg_id); \ + (wb_cur); (wb_cur) = __wb_iter_next(iter, bdi)) + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + return false; +} + +static inline struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) +{ + atomic_inc(&bdi->wb_congested->refcnt); + return bdi->wb_congested; +} + +static inline void wb_congested_put(struct bdi_writeback_congested *congested) +{ + if (atomic_dec_and_test(&congested->refcnt)) + kfree(congested); +} + +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + return &bdi->wb; +} + +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + return &bdi->wb; +} + +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return true; +} + +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ + return &inode_to_bdi(inode)->wb; +} + +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + return inode_to_wb(inode); +} + +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ +} + +static inline void wb_memcg_offline(struct mem_cgroup *memcg) +{ +} + +static inline void wb_blkcg_offline(struct blkcg *blkcg) +{ +} + +struct wb_iter { + int next_id; +}; + +#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ + for ((iter)->next_id = (start_blkcg_id); \ + ({ (wb_cur) = !(iter)->next_id++ ? &(bdi)->wb : NULL; }); ) + +static inline int inode_congested(struct inode *inode, int cong_bits) +{ + return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +static inline int inode_read_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_sync_congested); +} + +static inline int inode_write_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_async_congested); +} + +static inline int inode_rw_congested(struct inode *inode) +{ + return inode_congested(inode, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) +{ + return wb_congested(&bdi->wb, cong_bits); +} + +static inline int bdi_read_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_sync_congested); +} + +static inline int bdi_write_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_async_congested); +} + +static inline int bdi_rw_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +#endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/backlight.h b/include/linux/backlight.h index adb14a8616df..1e7a69adbe6f 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -117,12 +117,16 @@ struct backlight_device { int use_count; }; -static inline void backlight_update_status(struct backlight_device *bd) +static inline int backlight_update_status(struct backlight_device *bd) { + int ret = -ENOENT; + mutex_lock(&bd->update_lock); if (bd->ops && bd->ops->update_status) - bd->ops->update_status(bd); + ret = bd->ops->update_status(bd); mutex_unlock(&bd->update_lock); + + return ret; } extern struct backlight_device *backlight_device_register(const char *name, diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 0e97856b2cff..14eea946e640 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -74,5 +74,6 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev, #define BGPIOF_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ #define BGPIOF_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ #define BGPIOF_BIG_ENDIAN_BYTE_ORDER BIT(3) +#define BGPIOF_READ_OUTPUT_REG_SET BIT(4) /* reg_set stores output value */ #endif /* __BASIC_MMIO_GPIO_H */ diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h index b12b07e75929..2793652fbf66 100644 --- a/include/linux/bcm47xx_nvram.h +++ b/include/linux/bcm47xx_nvram.h @@ -10,11 +10,17 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/vmalloc.h> -#ifdef CONFIG_BCM47XX +#ifdef CONFIG_BCM47XX_NVRAM int bcm47xx_nvram_init_from_mem(u32 base, u32 lim); int bcm47xx_nvram_getenv(const char *name, char *val, size_t val_len); int bcm47xx_nvram_gpio_pin(const char *name); +char *bcm47xx_nvram_get_contents(size_t *val_len); +static inline void bcm47xx_nvram_release_contents(char *nvram) +{ + vfree(nvram); +}; #else static inline int bcm47xx_nvram_init_from_mem(u32 base, u32 lim) { @@ -29,6 +35,15 @@ static inline int bcm47xx_nvram_gpio_pin(const char *name) { return -ENOTSUPP; }; + +static inline char *bcm47xx_nvram_get_contents(size_t *val_len) +{ + return NULL; +}; + +static inline void bcm47xx_nvram_release_contents(char *nvram) +{ +}; #endif #endif /* __BCM47XX_NVRAM_H */ diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e34f906647d3..2ff4a9961e1d 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -305,6 +305,15 @@ int __bcma_driver_register(struct bcma_driver *drv, struct module *owner); extern void bcma_driver_unregister(struct bcma_driver *drv); +/* module_bcma_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit() + */ +#define module_bcma_driver(__bcma_driver) \ + module_driver(__bcma_driver, bcma_driver_register, \ + bcma_driver_unregister) + /* Set a fallback SPROM. * See kdoc at the function definition for complete documentation. */ extern int bcma_arch_register_fallback_sprom( diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 5ba6918ca20b..9657f11d48a7 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -246,7 +246,18 @@ static inline void bcma_core_pci_power_save(struct bcma_bus *bus, bool up) } #endif +#ifdef CONFIG_BCMA_DRIVER_PCI_HOSTMODE extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); extern int bcma_core_pci_plat_dev_init(struct pci_dev *dev); +#else +static inline int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev) +{ + return -ENOTSUPP; +} +static inline int bcma_core_pci_plat_dev_init(struct pci_dev *dev) +{ + return -ENOTSUPP; +} +#endif #endif /* LINUX_BCMA_DRIVER_PCI_H_ */ diff --git a/include/linux/bio.h b/include/linux/bio.h index da3a127c9958..5e963a6d7c14 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -290,7 +290,21 @@ static inline unsigned bio_segments(struct bio *bio) * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ -#define bio_get(bio) atomic_inc(&(bio)->bi_cnt) +static inline void bio_get(struct bio *bio) +{ + bio->bi_flags |= (1 << BIO_REFFED); + smp_mb__before_atomic(); + atomic_inc(&bio->__bi_cnt); +} + +static inline void bio_cnt_set(struct bio *bio, unsigned int count) +{ + if (count != 1) { + bio->bi_flags |= (1 << BIO_REFFED); + smp_mb__before_atomic(); + } + atomic_set(&bio->__bi_cnt, count); +} enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ @@ -413,7 +427,6 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) } extern void bio_endio(struct bio *, int); -extern void bio_endio_nodec(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); @@ -469,9 +482,12 @@ extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h new file mode 100644 index 000000000000..1b62d768c7df --- /dev/null +++ b/include/linux/blk-cgroup.h @@ -0,0 +1,650 @@ +#ifndef _BLK_CGROUP_H +#define _BLK_CGROUP_H +/* + * Common Block IO controller cgroup interface + * + * Based on ideas and code from CFQ, CFS and BFQ: + * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> + * + * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> + * Paolo Valente <paolo.valente@unimore.it> + * + * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> + * Nauman Rafique <nauman@google.com> + */ + +#include <linux/cgroup.h> +#include <linux/u64_stats_sync.h> +#include <linux/seq_file.h> +#include <linux/radix-tree.h> +#include <linux/blkdev.h> +#include <linux/atomic.h> + +/* Max limits for throttle policy */ +#define THROTL_IOPS_MAX UINT_MAX + +#ifdef CONFIG_BLK_CGROUP + +enum blkg_rwstat_type { + BLKG_RWSTAT_READ, + BLKG_RWSTAT_WRITE, + BLKG_RWSTAT_SYNC, + BLKG_RWSTAT_ASYNC, + + BLKG_RWSTAT_NR, + BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, +}; + +struct blkcg_gq; + +struct blkcg { + struct cgroup_subsys_state css; + spinlock_t lock; + + struct radix_tree_root blkg_tree; + struct blkcg_gq *blkg_hint; + struct hlist_head blkg_list; + + struct blkcg_policy_data *pd[BLKCG_MAX_POLS]; + + struct list_head all_blkcgs_node; +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif +}; + +struct blkg_stat { + struct u64_stats_sync syncp; + uint64_t cnt; +}; + +struct blkg_rwstat { + struct u64_stats_sync syncp; + uint64_t cnt[BLKG_RWSTAT_NR]; +}; + +/* + * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a + * request_queue (q). This is used by blkcg policies which need to track + * information per blkcg - q pair. + * + * There can be multiple active blkcg policies and each has its private + * data on each blkg, the size of which is determined by + * blkcg_policy->pd_size. blkcg core allocates and frees such areas + * together with blkg and invokes pd_init/exit_fn() methods. + * + * Such private data must embed struct blkg_policy_data (pd) at the + * beginning and pd_size can't be smaller than pd. + */ +struct blkg_policy_data { + /* the blkg and policy id this per-policy data belongs to */ + struct blkcg_gq *blkg; + int plid; + + /* used during policy activation */ + struct list_head alloc_node; +}; + +/* + * Policies that need to keep per-blkcg data which is independent + * from any request_queue associated to it must specify its size + * with the cpd_size field of the blkcg_policy structure and + * embed a blkcg_policy_data in it. cpd_init() is invoked to let + * each policy handle per-blkcg data. + */ +struct blkcg_policy_data { + /* the policy id this per-policy data belongs to */ + int plid; +}; + +/* association between a blk cgroup and a request queue */ +struct blkcg_gq { + /* Pointer to the associated request_queue */ + struct request_queue *q; + struct list_head q_node; + struct hlist_node blkcg_node; + struct blkcg *blkcg; + + /* + * Each blkg gets congested separately and the congestion state is + * propagated to the matching bdi_writeback_congested. + */ + struct bdi_writeback_congested *wb_congested; + + /* all non-root blkcg_gq's are guaranteed to have access to parent */ + struct blkcg_gq *parent; + + /* request allocation list for this blkcg-q pair */ + struct request_list rl; + + /* reference count */ + atomic_t refcnt; + + /* is this blkg online? protected by both blkcg and q locks */ + bool online; + + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; + + struct rcu_head rcu_head; +}; + +typedef void (blkcg_pol_init_cpd_fn)(const struct blkcg *blkcg); +typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg); +typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg); +typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg); +typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg); +typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg); + +struct blkcg_policy { + int plid; + /* policy specific private data size */ + size_t pd_size; + /* policy specific per-blkcg data size */ + size_t cpd_size; + /* cgroup files for the policy */ + struct cftype *cftypes; + + /* operations */ + blkcg_pol_init_cpd_fn *cpd_init_fn; + blkcg_pol_init_pd_fn *pd_init_fn; + blkcg_pol_online_pd_fn *pd_online_fn; + blkcg_pol_offline_pd_fn *pd_offline_fn; + blkcg_pol_exit_pd_fn *pd_exit_fn; + blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; +}; + +extern struct blkcg blkcg_root; +extern struct cgroup_subsys_state * const blkcg_root_css; + +struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q); +struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q); +int blkcg_init_queue(struct request_queue *q); +void blkcg_drain_queue(struct request_queue *q); +void blkcg_exit_queue(struct request_queue *q); + +/* Blkio controller policy registration */ +int blkcg_policy_register(struct blkcg_policy *pol); +void blkcg_policy_unregister(struct blkcg_policy *pol); +int blkcg_activate_policy(struct request_queue *q, + const struct blkcg_policy *pol); +void blkcg_deactivate_policy(struct request_queue *q, + const struct blkcg_policy *pol); + +void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, + u64 (*prfill)(struct seq_file *, + struct blkg_policy_data *, int), + const struct blkcg_policy *pol, int data, + bool show_total); +u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat *rwstat); +u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off); +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off); + +u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off); +struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, + int off); + +struct blkg_conf_ctx { + struct gendisk *disk; + struct blkcg_gq *blkg; + u64 v; +}; + +int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, + const char *input, struct blkg_conf_ctx *ctx); +void blkg_conf_finish(struct blkg_conf_ctx *ctx); + + +static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct blkcg, css) : NULL; +} + +static inline struct blkcg *task_blkcg(struct task_struct *tsk) +{ + return css_to_blkcg(task_css(tsk, blkio_cgrp_id)); +} + +static inline struct blkcg *bio_blkcg(struct bio *bio) +{ + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + return task_blkcg(current); +} + +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return task_get_css(task, blkio_cgrp_id); +} + +/** + * blkcg_parent - get the parent of a blkcg + * @blkcg: blkcg of interest + * + * Return the parent blkcg of @blkcg. Can be called anytime. + */ +static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) +{ + return css_to_blkcg(blkcg->css.parent); +} + +/** + * blkg_to_pdata - get policy private data + * @blkg: blkg of interest + * @pol: policy of interest + * + * Return pointer to private data associated with the @blkg-@pol pair. + */ +static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, + struct blkcg_policy *pol) +{ + return blkg ? blkg->pd[pol->plid] : NULL; +} + +static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, + struct blkcg_policy *pol) +{ + return blkcg ? blkcg->pd[pol->plid] : NULL; +} + +/** + * pdata_to_blkg - get blkg associated with policy private data + * @pd: policy private data of interest + * + * @pd is policy private data. Determine the blkg it's associated with. + */ +static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) +{ + return pd ? pd->blkg : NULL; +} + +/** + * blkg_path - format cgroup path of blkg + * @blkg: blkg of interest + * @buf: target buffer + * @buflen: target buffer length + * + * Format the path of the cgroup of @blkg into @buf. + */ +static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) +{ + char *p; + + p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); + if (!p) { + strncpy(buf, "<unavailable>", buflen); + return -ENAMETOOLONG; + } + + memmove(buf, p, buf + buflen - p); + return 0; +} + +/** + * blkg_get - get a blkg reference + * @blkg: blkg to get + * + * The caller should be holding an existing reference. + */ +static inline void blkg_get(struct blkcg_gq *blkg) +{ + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); +} + +void __blkg_release_rcu(struct rcu_head *rcu); + +/** + * blkg_put - put a blkg reference + * @blkg: blkg to put + */ +static inline void blkg_put(struct blkcg_gq *blkg) +{ + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); +} + +struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, + bool update_hint); + +/** + * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants + * @d_blkg: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @p_blkg: target blkg to walk descendants of + * + * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU + * read locked. If called under either blkcg or queue lock, the iteration + * is guaranteed to include all and only online blkgs. The caller may + * update @pos_css by calling css_rightmost_descendant() to skip subtree. + * @p_blkg is included in the iteration and the first node to be visited. + */ +#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q, false))) + +/** + * blkg_for_each_descendant_post - post-order walk of a blkg's descendants + * @d_blkg: loop cursor pointing to the current descendant + * @pos_css: used for iteration + * @p_blkg: target blkg to walk descendants of + * + * Similar to blkg_for_each_descendant_pre() but performs post-order + * traversal instead. Synchronization rules are the same. @p_blkg is + * included in the iteration and the last node to be visited. + */ +#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q, false))) + +/** + * blk_get_rl - get request_list to use + * @q: request_queue of interest + * @bio: bio which will be attached to the allocated request (may be %NULL) + * + * The caller wants to allocate a request from @q to use for @bio. Find + * the request_list to use and obtain a reference on it. Should be called + * under queue_lock. This function is guaranteed to return non-%NULL + * request_list. + */ +static inline struct request_list *blk_get_rl(struct request_queue *q, + struct bio *bio) +{ + struct blkcg *blkcg; + struct blkcg_gq *blkg; + + rcu_read_lock(); + + blkcg = bio_blkcg(bio); + + /* bypass blkg lookup and use @q->root_rl directly for root */ + if (blkcg == &blkcg_root) + goto root_rl; + + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ + blkg = blkg_lookup_create(blkcg, q); + if (unlikely(IS_ERR(blkg))) + goto root_rl; + + blkg_get(blkg); + rcu_read_unlock(); + return &blkg->rl; +root_rl: + rcu_read_unlock(); + return &q->root_rl; +} + +/** + * blk_put_rl - put request_list + * @rl: request_list to put + * + * Put the reference acquired by blk_get_rl(). Should be called under + * queue_lock. + */ +static inline void blk_put_rl(struct request_list *rl) +{ + /* root_rl may not have blkg set */ + if (rl->blkg && rl->blkg->blkcg != &blkcg_root) + blkg_put(rl->blkg); +} + +/** + * blk_rq_set_rl - associate a request with a request_list + * @rq: request of interest + * @rl: target request_list + * + * Associate @rq with @rl so that accounting and freeing can know the + * request_list @rq came from. + */ +static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) +{ + rq->rl = rl; +} + +/** + * blk_rq_rl - return the request_list a request came from + * @rq: request of interest + * + * Return the request_list @rq is allocated from. + */ +static inline struct request_list *blk_rq_rl(struct request *rq) +{ + return rq->rl; +} + +struct request_list *__blk_queue_next_rl(struct request_list *rl, + struct request_queue *q); +/** + * blk_queue_for_each_rl - iterate through all request_lists of a request_queue + * + * Should be used under queue_lock. + */ +#define blk_queue_for_each_rl(rl, q) \ + for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q))) + +static inline void blkg_stat_init(struct blkg_stat *stat) +{ + u64_stats_init(&stat->syncp); +} + +/** + * blkg_stat_add - add a value to a blkg_stat + * @stat: target blkg_stat + * @val: value to add + * + * Add @val to @stat. The caller is responsible for synchronizing calls to + * this function. + */ +static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) +{ + u64_stats_update_begin(&stat->syncp); + stat->cnt += val; + u64_stats_update_end(&stat->syncp); +} + +/** + * blkg_stat_read - read the current value of a blkg_stat + * @stat: blkg_stat to read + * + * Read the current value of @stat. This function can be called without + * synchroniztion and takes care of u64 atomicity. + */ +static inline uint64_t blkg_stat_read(struct blkg_stat *stat) +{ + unsigned int start; + uint64_t v; + + do { + start = u64_stats_fetch_begin_irq(&stat->syncp); + v = stat->cnt; + } while (u64_stats_fetch_retry_irq(&stat->syncp, start)); + + return v; +} + +/** + * blkg_stat_reset - reset a blkg_stat + * @stat: blkg_stat to reset + */ +static inline void blkg_stat_reset(struct blkg_stat *stat) +{ + stat->cnt = 0; +} + +/** + * blkg_stat_merge - merge a blkg_stat into another + * @to: the destination blkg_stat + * @from: the source + * + * Add @from's count to @to. + */ +static inline void blkg_stat_merge(struct blkg_stat *to, struct blkg_stat *from) +{ + blkg_stat_add(to, blkg_stat_read(from)); +} + +static inline void blkg_rwstat_init(struct blkg_rwstat *rwstat) +{ + u64_stats_init(&rwstat->syncp); +} + +/** + * blkg_rwstat_add - add a value to a blkg_rwstat + * @rwstat: target blkg_rwstat + * @rw: mask of REQ_{WRITE|SYNC} + * @val: value to add + * + * Add @val to @rwstat. The counters are chosen according to @rw. The + * caller is responsible for synchronizing calls to this function. + */ +static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, + int rw, uint64_t val) +{ + u64_stats_update_begin(&rwstat->syncp); + + if (rw & REQ_WRITE) + rwstat->cnt[BLKG_RWSTAT_WRITE] += val; + else + rwstat->cnt[BLKG_RWSTAT_READ] += val; + if (rw & REQ_SYNC) + rwstat->cnt[BLKG_RWSTAT_SYNC] += val; + else + rwstat->cnt[BLKG_RWSTAT_ASYNC] += val; + + u64_stats_update_end(&rwstat->syncp); +} + +/** + * blkg_rwstat_read - read the current values of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Read the current snapshot of @rwstat and return it as the return value. + * This function can be called without synchronization and takes care of + * u64 atomicity. + */ +static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat) +{ + unsigned int start; + struct blkg_rwstat tmp; + + do { + start = u64_stats_fetch_begin_irq(&rwstat->syncp); + tmp = *rwstat; + } while (u64_stats_fetch_retry_irq(&rwstat->syncp, start)); + + return tmp; +} + +/** + * blkg_rwstat_total - read the total count of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Return the total count of @rwstat regardless of the IO direction. This + * function can be called without synchronization and takes care of u64 + * atomicity. + */ +static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat tmp = blkg_rwstat_read(rwstat); + + return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; +} + +/** + * blkg_rwstat_reset - reset a blkg_rwstat + * @rwstat: blkg_rwstat to reset + */ +static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) +{ + memset(rwstat->cnt, 0, sizeof(rwstat->cnt)); +} + +/** + * blkg_rwstat_merge - merge a blkg_rwstat into another + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's counts to @to. + */ +static inline void blkg_rwstat_merge(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + struct blkg_rwstat v = blkg_rwstat_read(from); + int i; + + u64_stats_update_begin(&to->syncp); + for (i = 0; i < BLKG_RWSTAT_NR; i++) + to->cnt[i] += v.cnt[i]; + u64_stats_update_end(&to->syncp); +} + +#else /* CONFIG_BLK_CGROUP */ + +struct blkcg { +}; + +struct blkg_policy_data { +}; + +struct blkcg_policy_data { +}; + +struct blkcg_gq { +}; + +struct blkcg_policy { +}; + +#define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) + +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return NULL; +} + +#ifdef CONFIG_BLOCK + +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline int blkcg_init_queue(struct request_queue *q) { return 0; } +static inline void blkcg_drain_queue(struct request_queue *q) { } +static inline void blkcg_exit_queue(struct request_queue *q) { } +static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } +static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } +static inline int blkcg_activate_policy(struct request_queue *q, + const struct blkcg_policy *pol) { return 0; } +static inline void blkcg_deactivate_policy(struct request_queue *q, + const struct blkcg_policy *pol) { } + +static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } + +static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, + struct blkcg_policy *pol) { return NULL; } +static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } +static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } +static inline void blkg_get(struct blkcg_gq *blkg) { } +static inline void blkg_put(struct blkcg_gq *blkg) { } + +static inline struct request_list *blk_get_rl(struct request_queue *q, + struct bio *bio) { return &q->root_rl; } +static inline void blk_put_rl(struct request_list *rl) { } +static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } +static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } + +#define blk_queue_for_each_rl(rl, q) \ + for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) + +#endif /* CONFIG_BLOCK */ +#endif /* CONFIG_BLK_CGROUP */ +#endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2056a99b92f8..37d1602c4f7a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -96,6 +96,7 @@ typedef void (exit_request_fn)(void *, struct request *, unsigned int, typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); +typedef void (busy_tag_iter_fn)(struct request *, void *, bool); struct blk_mq_ops { /* @@ -182,6 +183,7 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *); struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); +struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags); enum { BLK_MQ_UNIQUE_TAG_BITS = 16, @@ -224,6 +226,8 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, void *priv); +void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, + void *priv); void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b7299febc4b4..7303b3405520 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -65,7 +65,7 @@ struct bio { unsigned int bi_seg_front_size; unsigned int bi_seg_back_size; - atomic_t bi_remaining; + atomic_t __bi_remaining; bio_end_io_t *bi_end_io; @@ -92,7 +92,7 @@ struct bio { unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ - atomic_t bi_cnt; /* pin count */ + atomic_t __bi_cnt; /* pin count */ struct bio_vec *bi_io_vec; /* the actual vec list */ @@ -112,16 +112,15 @@ struct bio { * bio flags */ #define BIO_UPTODATE 0 /* ok after I/O completion */ -#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ -#define BIO_EOF 2 /* out-out-bounds error */ -#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ -#define BIO_CLONED 4 /* doesn't own data */ -#define BIO_BOUNCED 5 /* bio is a bounce bio */ -#define BIO_USER_MAPPED 6 /* contains user pages */ -#define BIO_EOPNOTSUPP 7 /* not supported */ -#define BIO_NULL_MAPPED 8 /* contains invalid user pages */ -#define BIO_QUIET 9 /* Make BIO Quiet */ -#define BIO_SNAP_STABLE 10 /* bio data must be snapshotted during write */ +#define BIO_SEG_VALID 1 /* bi_phys_segments valid */ +#define BIO_CLONED 2 /* doesn't own data */ +#define BIO_BOUNCED 3 /* bio is a bounce bio */ +#define BIO_USER_MAPPED 4 /* contains user pages */ +#define BIO_NULL_MAPPED 5 /* contains invalid user pages */ +#define BIO_QUIET 6 /* Make BIO Quiet */ +#define BIO_SNAP_STABLE 7 /* bio data must be snapshotted during write */ +#define BIO_CHAIN 8 /* chained bio, ->bi_remaining in effect */ +#define BIO_REFFED 9 /* bio has elevated ->bi_cnt */ /* * Flags starting here get preserved by bio_reset() - this includes diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7f9a516f24de..d4068c17d0df 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -12,7 +12,7 @@ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> -#include <linux/backing-dev.h> +#include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/bio.h> @@ -22,15 +22,13 @@ #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> - -#include <asm/scatterlist.h> +#include <linux/scatterlist.h> struct module; struct scsi_ioctl_command; struct request_queue; struct elevator_queue; -struct request_pm_state; struct blk_trace; struct request; struct sg_io_hdr; @@ -75,18 +73,7 @@ struct request_list { enum rq_cmd_type_bits { REQ_TYPE_FS = 1, /* fs request */ REQ_TYPE_BLOCK_PC, /* scsi command */ - REQ_TYPE_SENSE, /* sense request */ - REQ_TYPE_PM_SUSPEND, /* suspend request */ - REQ_TYPE_PM_RESUME, /* resume request */ - REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ - REQ_TYPE_SPECIAL, /* driver defined type */ - /* - * for ATA/ATAPI devices. this really doesn't belong here, ide should - * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver - * private REQ_LB opcodes to differentiate what type of request this is - */ - REQ_TYPE_ATA_TASKFILE, - REQ_TYPE_ATA_PC, + REQ_TYPE_DRV_PRIV, /* driver defined types from here */ }; #define BLK_MAX_CDB 16 @@ -108,7 +95,7 @@ struct request { struct blk_mq_ctx *mq_ctx; u64 cmd_flags; - enum rq_cmd_type_bits cmd_type; + unsigned cmd_type; unsigned long atomic_flags; int cpu; @@ -216,19 +203,6 @@ static inline unsigned short req_get_ioprio(struct request *req) return req->ioprio; } -/* - * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME - * requests. Some step values could eventually be made generic. - */ -struct request_pm_state -{ - /* PM state machine step value, currently driver specific */ - int pm_step; - /* requested PM state value (S1, S2, S3, S4, ...) */ - u32 pm_state; - void* data; /* for driver use */ -}; - #include <linux/elevator.h> struct blk_queue_ctx; @@ -469,7 +443,7 @@ struct request_queue { struct mutex sysfs_lock; int bypass_depth; - int mq_freeze_depth; + atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; @@ -610,10 +584,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) (((rq)->cmd_flags & REQ_STARTED) && \ ((rq)->cmd_type == REQ_TYPE_FS)) -#define blk_pm_request(rq) \ - ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ - (rq)->cmd_type == REQ_TYPE_PM_RESUME) - #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) /* rq->queuelist of dequeued request must be list_empty() */ @@ -821,32 +791,12 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); -extern void blk_queue_bio(struct request_queue *q, struct bio *bio); - -/* - * A queue has just exitted congestion. Note this in the global counter of - * congested queues, and wake up anyone who was waiting for requests to be - * put back. - */ -static inline void blk_clear_queue_congested(struct request_queue *q, int sync) -{ - clear_bdi_congested(&q->backing_dev_info, sync); -} - -/* - * A queue has just entered congestion. Flag that in the queue's VM-visible - * state flags and increment the global gounter of congested queues. - */ -static inline void blk_set_queue_congested(struct request_queue *q, int sync) -{ - set_bdi_congested(&q->backing_dev_info, sync); -} - extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); extern void __blk_run_queue(struct request_queue *q); +extern void __blk_run_queue_uncond(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern void blk_run_queue_async(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, @@ -935,7 +885,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors) + if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) return blk_queue_get_max_sectors(q, rq->cmd_flags); return min(blk_max_size_offset(q, blk_rq_pos(rq)), @@ -1056,6 +1006,7 @@ bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); +extern void blk_set_queue_dying(struct request_queue *); /* * block layer runtime pm functions diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 0995c2de8162..f589222bfa87 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -357,12 +357,12 @@ extern void *alloc_large_system_hash(const char *tablename, /* Only NUMA needs hash distribution. 64bit NUMA architectures have * sufficient vmalloc space. */ -#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT) -#define HASHDIST_DEFAULT 1 +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ #else -#define HASHDIST_DEFAULT 0 +#define hashdist (0) #endif -extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif /* _LINUX_BOOTMEM_H */ diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index 86c12c93e3cf..8fdcb783197d 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,7 +2,6 @@ #define _LINUX_BH_H #include <linux/preempt.h> -#include <linux/preempt_mask.h> #ifdef CONFIG_TRACE_IRQFLAGS extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d5cda067115a..4383476a0d48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -105,7 +105,8 @@ struct bpf_verifier_ops { */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type); - u32 (*convert_ctx_access)(int dst_reg, int src_reg, int ctx_off, + u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, struct bpf_insn *insn); }; @@ -123,15 +124,41 @@ struct bpf_prog_aux { const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; - struct work_struct work; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; +struct bpf_array { + struct bpf_map map; + u32 elem_size; + /* 'ownership' of prog_array is claimed by the first program that + * is going to use this map or by the first program which FD is stored + * in the map to make sure that all callers and callees have the same + * prog_type and JITed flag + */ + enum bpf_prog_type owner_prog_type; + bool owner_jited; + union { + char value[0] __aligned(8); + struct bpf_prog *prog[0] __aligned(8); + }; +}; +#define MAX_TAIL_CALL_CNT 32 + +u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); +void bpf_prog_array_map_clear(struct bpf_map *map); +bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +const struct bpf_func_proto *bpf_get_trace_printk_proto(void); + #ifdef CONFIG_BPF_SYSCALL void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); +void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); @@ -160,5 +187,10 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; +extern const struct bpf_func_proto bpf_tail_call_proto; +extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; +extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; +extern const struct bpf_func_proto bpf_get_current_comm_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index ae2982c0f7a6..697ca7795bd9 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -1,6 +1,13 @@ #ifndef _LINUX_BRCMPHY_H #define _LINUX_BRCMPHY_H +#include <linux/phy.h> + +/* All Broadcom Ethernet switches have a pseudo-PHY at address 30 which is used + * to configure the switch internal registers via MDIO accesses. + */ +#define BRCM_PSEUDO_PHY_ADDR 30 + #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 #define PHY_ID_BCM5241 0x0143bc30 @@ -17,7 +24,7 @@ #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 -#define PHY_ID_BCM7425 0x03625e60 +#define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7439_2 0xae025080 diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 73b45225a7ca..e6797ded700e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -317,6 +317,13 @@ sb_getblk(struct super_block *sb, sector_t block) return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } + +static inline struct buffer_head * +sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) +{ + return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); +} + static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 3daf5ed392c9..2189935075b4 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -19,7 +19,7 @@ enum cache_type { /** * struct cacheinfo - represent a cache leaf node * @type: type of the cache - data, inst or unified - * @level: represents the hierarcy in the multi-level cache + * @level: represents the hierarchy in the multi-level cache * @coherency_line_size: size of each cache line usually representing * the minimum amount of data that gets transferred from memory * @number_of_sets: total number of sets, a set is a collection of cache diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index b6a52a4b457a..51bb6532785c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -27,10 +27,12 @@ /** * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on + * @skbcnt: atomic counter to have an unique id together with skb pointer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; + int skbcnt; struct can_frame cf[0]; }; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 30f92cefaa72..9ebee53d3bf5 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -43,9 +43,9 @@ struct ceph_options { int flags; struct ceph_fsid fsid; struct ceph_entity_addr my_addr; - int mount_timeout; - int osd_idle_ttl; - int osd_keepalive_timeout; + unsigned long mount_timeout; /* jiffies */ + unsigned long osd_idle_ttl; /* jiffies */ + unsigned long osd_keepalive_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -63,9 +63,9 @@ struct ceph_options { /* * defaults */ -#define CEPH_MOUNT_TIMEOUT_DEFAULT 60 -#define CEPH_OSD_KEEPALIVE_DEFAULT 5 -#define CEPH_OSD_IDLE_TTL_DEFAULT 60 +#define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) +#define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) @@ -93,13 +93,9 @@ enum { CEPH_MOUNT_SHUTDOWN, }; -/* - * subtract jiffies - */ -static inline unsigned long time_sub(unsigned long a, unsigned long b) +static inline unsigned long ceph_timeout_jiffies(unsigned long timeout) { - BUG_ON(time_after(b, a)); - return (long)a - (long)b; + return timeout ?: MAX_SCHEDULE_TIMEOUT; } struct ceph_mds_client; @@ -178,6 +174,7 @@ static inline int calc_pages_for(u64 off, u64 len) extern struct kmem_cache *ceph_inode_cachep; extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e15499422fdc..37753278987a 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -8,6 +8,7 @@ #include <linux/radix-tree.h> #include <linux/uio.h> #include <linux/workqueue.h> +#include <net/net_namespace.h> #include <linux/ceph/types.h> #include <linux/ceph/buffer.h> @@ -56,6 +57,7 @@ struct ceph_messenger { struct ceph_entity_addr my_enc_addr; atomic_t stopping; + possible_net_t net; bool nocrc; bool tcp_nodelay; @@ -267,6 +269,7 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr, u64 required_features, bool nocrc, bool tcp_nodelay); +extern void ceph_messenger_fini(struct ceph_messenger *msgr); extern void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 61b19c46bdb3..7506b485bb6d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -249,7 +249,7 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); extern void osd_req_op_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode); + unsigned int which, u16 opcode, u32 flags); extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *, unsigned int which, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h new file mode 100644 index 000000000000..93755a629299 --- /dev/null +++ b/include/linux/cgroup-defs.h @@ -0,0 +1,501 @@ +/* + * linux/cgroup-defs.h - basic definitions for cgroup + * + * This file provides basic type and interface. Include this file directly + * only if necessary to avoid cyclic dependencies. + */ +#ifndef _LINUX_CGROUP_DEFS_H +#define _LINUX_CGROUP_DEFS_H + +#include <linux/limits.h> +#include <linux/list.h> +#include <linux/idr.h> +#include <linux/wait.h> +#include <linux/mutex.h> +#include <linux/rcupdate.h> +#include <linux/percpu-refcount.h> +#include <linux/percpu-rwsem.h> +#include <linux/workqueue.h> + +#ifdef CONFIG_CGROUPS + +struct cgroup; +struct cgroup_root; +struct cgroup_subsys; +struct cgroup_taskset; +struct kernfs_node; +struct kernfs_ops; +struct kernfs_open_file; +struct seq_file; + +#define MAX_CGROUP_TYPE_NAMELEN 32 +#define MAX_CGROUP_ROOT_NAMELEN 64 +#define MAX_CFTYPE_NAME 64 + +/* define the enumeration of all cgroup subsystems */ +#define SUBSYS(_x) _x ## _cgrp_id, +enum cgroup_subsys_id { +#include <linux/cgroup_subsys.h> + CGROUP_SUBSYS_COUNT, +}; +#undef SUBSYS + +/* bits in struct cgroup_subsys_state flags field */ +enum { + CSS_NO_REF = (1 << 0), /* no reference counting for this css */ + CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ + CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ +}; + +/* bits in struct cgroup flags field */ +enum { + /* Control Group requires release notifications to userspace */ + CGRP_NOTIFY_ON_RELEASE, + /* + * Clone the parent's configuration when creating a new child + * cpuset cgroup. For historical reasons, this option can be + * specified at mount time and thus is implemented here. + */ + CGRP_CPUSET_CLONE_CHILDREN, +}; + +/* cgroup_root->flags */ +enum { + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ +}; + +/* cftype->flags */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ + + /* internal flags, do not use outside cgroup core proper */ + __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ + __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ +}; + +/* + * Per-subsystem/per-cgroup state maintained by the system. This is the + * fundamental structural building block that controllers deal with. + * + * Fields marked with "PI:" are public and immutable and may be accessed + * directly without synchronization. + */ +struct cgroup_subsys_state { + /* PI: the cgroup that this css is attached to */ + struct cgroup *cgroup; + + /* PI: the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; + + /* PI: the parent css */ + struct cgroup_subsys_state *parent; + + /* siblings list anchored at the parent's ->children */ + struct list_head sibling; + struct list_head children; + + /* + * PI: Subsys-unique ID. 0 is unused and root is always 1. The + * matching css can be looked up using css_from_id(). + */ + int id; + + unsigned int flags; + + /* + * Monotonically increasing unique serial number which defines a + * uniform order among all csses. It's guaranteed that all + * ->children lists are in the ascending order of ->serial_nr and + * used to allow interrupting and resuming iterations. + */ + u64 serial_nr; + + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; +}; + +/* + * A css_set is a structure holding pointers to a set of + * cgroup_subsys_state objects. This saves space in the task struct + * object and speeds up fork()/exit(), since a single inc/dec and a + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. + */ +struct css_set { + /* Reference count */ + atomic_t refcount; + + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; + + /* + * Lists running through all tasks using this cgroup group. + * mg_tasks lists tasks which belong to this cset but are in the + * process of being migrated out or in. Protected by + * css_set_rwsem, but, during migration, once tasks are moved to + * mg_tasks, it can be read safely while holding cgroup_mutex. + */ + struct list_head tasks; + struct list_head mg_tasks; + + /* + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. + */ + struct list_head cgrp_links; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; + + /* + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). + */ + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* + * List of csets participating in the on-going migration either as + * source or destination. Protected by cgroup_mutex. + */ + struct list_head mg_preload_node; + struct list_head mg_node; + + /* + * If this cset is acting as the source of migration the following + * two fields are set. mg_src_cgrp is the source cgroup of the + * on-going migration and mg_dst_cset is the destination cset the + * target tasks on this cset should be migrated to. Protected by + * cgroup_mutex. + */ + struct cgroup *mg_src_cgrp; + struct css_set *mg_dst_cset; + + /* + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. + */ + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; +}; + +struct cgroup { + /* self css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state self; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * idr allocated in-hierarchy ID. + * + * ID 0 is not used, the ID of the root cgroup is always 1, and a + * new cgroup will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. + */ + int id; + + /* + * If this cgroup contains any tasks, it contributes one to + * populated_cnt. All children with non-zero popuplated_cnt of + * their own contribute one. The count is zero iff there's no task + * in this cgroup or its subtree. + */ + int populated_cnt; + + struct kernfs_node *kn; /* cgroup kernfs entry */ + struct kernfs_node *procs_kn; /* kn for "cgroup.procs" */ + struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ + + /* + * The bitmask of subsystems enabled on the child cgroups. + * ->subtree_control is the one configured through + * "cgroup.subtree_control" while ->child_subsys_mask is the + * effective one which may have more subsystems enabled. + * Controller knobs are made available iff it's enabled in + * ->subtree_control. + */ + unsigned int subtree_control; + unsigned int child_subsys_mask; + + /* Private pointers for each registered subsystem */ + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + + struct cgroup_root *root; + + /* + * List of cgrp_cset_links pointing at css_sets with tasks in this + * cgroup. Protected by css_set_lock. + */ + struct list_head cset_links; + + /* + * On the default hierarchy, a css_set for a cgroup with some + * susbsys disabled will point to css's which are associated with + * the closest ancestor which has the subsys enabled. The + * following lists all css_sets which point to this cgroup's css + * for the given subsystem. + */ + struct list_head e_csets[CGROUP_SUBSYS_COUNT]; + + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; + + /* used to wait for offlining of csses */ + wait_queue_head_t offline_waitq; + + /* used to schedule release agent */ + struct work_struct release_agent_work; +}; + +/* + * A cgroup_root represents the root of a cgroup hierarchy, and may be + * associated with a kernfs_root to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroup_root { + struct kernfs_root *kf_root; + + /* The bitmask of subsystems attached to this hierarchy */ + unsigned int subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* The root cgroup. Root is destroyed on its release. */ + struct cgroup cgrp; + + /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ + atomic_t nr_cgrps; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* Hierarchy-specific flags */ + unsigned int flags; + + /* IDs for cgroups in this hierarchy */ + struct idr cgroup_idr; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + +/* + * struct cftype: handler definitions for cgroup control files + * + * When reading/writing to a file: + * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_path.dentry->d_fsdata + */ +struct cftype { + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period. Zero length string indicates + * end of cftype array. + */ + char name[MAX_CFTYPE_NAME]; + int private; + /* + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + umode_t mode; + + /* + * The maximum length of string, excluding trailing nul, that can + * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. + */ + size_t max_write_len; + + /* CFTYPE_* flags */ + unsigned int flags; + + /* + * Fields used for internal bookkeeping. Initialized automatically + * during registration. + */ + struct cgroup_subsys *ss; /* NULL for cgroup core files */ + struct list_head node; /* anchored at ss->cfts */ + struct kernfs_ops *kf_ops; + + /* + * read_u64() is a shortcut for the common case of returning a + * single integer. Use it in place of read() + */ + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); + /* + * read_s64() is a signed version of read_u64() + */ + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); + + /* generic seq_file read interface */ + int (*seq_show)(struct seq_file *sf, void *v); + + /* optional ops, implement all or none */ + void *(*seq_start)(struct seq_file *sf, loff_t *ppos); + void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); + void (*seq_stop)(struct seq_file *sf, void *v); + + /* + * write_u64() is a shortcut for the common case of accepting + * a single integer (as parsed by simple_strtoull) from + * userspace. Use in place of write(); return 0 or error. + */ + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); + /* + * write_s64() is a signed version of write_u64() + */ + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); + + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. Use + * of_css/cft() to access the associated css and cft. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lockdep_key; +#endif +}; + +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ +struct cgroup_subsys { + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_released)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_e_css_changed)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*fork)(struct task_struct *task); + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task); + void (*bind)(struct cgroup_subsys_state *root_css); + + int disabled; + int early_init; + + /* + * If %false, this subsystem is properly hierarchical - + * configuration, resource accounting and restriction on a parent + * cgroup cover those of its children. If %true, hierarchy support + * is broken in some ways - some subsystems ignore hierarchy + * completely while others are only implemented half-way. + * + * It's now disallowed to create nested cgroups if the subsystem is + * broken and cgroup core will emit a warning message on such + * cases. Eventually, all subsystems will be made properly + * hierarchical and this will go away. + */ + bool broken_hierarchy; + bool warned_broken_hierarchy; + + /* the following two fields are initialized automtically during boot */ + int id; + const char *name; + + /* link to parent, protected by cgroup_lock() */ + struct cgroup_root *root; + + /* idr for css->id */ + struct idr css_idr; + + /* + * List of cftypes. Each entry is the first entry of an array + * terminated by zero length name. + */ + struct list_head cfts; + + /* + * Base cftypes which are automatically registered. The two can + * point to the same array. + */ + struct cftype *dfl_cftypes; /* for the default hierarchy */ + struct cftype *legacy_cftypes; /* for the legacy hierarchies */ + + /* + * A subsystem may depend on other subsystems. When such subsystem + * is enabled on a cgroup, the depended-upon subsystems are enabled + * together if available. Subsystems enabled due to dependency are + * not visible to userland until explicitly enabled. The following + * specifies the mask of subsystems that this one depends on. + */ + unsigned int depends_on; +}; + +extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; + +/** + * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_begin() and allows cgroup operations to + * synchronize against threadgroup changes using a percpu_rw_semaphore. + */ +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + percpu_down_read(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_end(). Counterpart of + * cgroup_threadcgroup_change_begin(). + */ +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + percpu_up_read(&cgroup_threadgroup_rwsem); +} + +#else /* CONFIG_CGROUPS */ + +#define CGROUP_SUBSYS_COUNT 0 + +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {} +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} + +#endif /* CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_DEFS_H */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b9cb94c3102a..a593e299162e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -11,94 +11,200 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> -#include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/rwsem.h> -#include <linux/idr.h> -#include <linux/workqueue.h> #include <linux/fs.h> -#include <linux/percpu-refcount.h> #include <linux/seq_file.h> #include <linux/kernfs.h> -#include <linux/wait.h> + +#include <linux/cgroup-defs.h> #ifdef CONFIG_CGROUPS -struct cgroup_root; -struct cgroup_subsys; -struct cgroup; +/* a css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys *ss; -extern int cgroup_init_early(void); -extern int cgroup_init(void); -extern void cgroup_fork(struct task_struct *p); -extern void cgroup_post_fork(struct task_struct *p); -extern void cgroup_exit(struct task_struct *p); -extern int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry); + struct list_head *cset_pos; + struct list_head *cset_head; -extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, - struct pid *pid, struct task_struct *tsk); + struct list_head *task_pos; + struct list_head *tasks_head; + struct list_head *mg_tasks_head; +}; -/* define the enumeration of all cgroup subsystems */ -#define SUBSYS(_x) _x ## _cgrp_id, -enum cgroup_subsys_id { +extern struct cgroup_root cgrp_dfl_root; +extern struct css_set init_css_set; + +#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> - CGROUP_SUBSYS_COUNT, -}; #undef SUBSYS +bool css_has_online_children(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); +struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); + +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); + +int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); + +char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); +int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk); + +void cgroup_fork(struct task_struct *p); +void cgroup_post_fork(struct task_struct *p); +void cgroup_exit(struct task_struct *p); + +int cgroup_init_early(void); +int cgroup_init(void); + /* - * Per-subsystem/per-cgroup state maintained by the system. This is the - * fundamental structural building block that controllers deal with. + * Iteration helpers and macros. + */ + +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); +struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); + +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); + +/** + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Fields marked with "PI:" are public and immutable and may be accessed - * directly without synchronization. + * Walk @parent's children. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. */ -struct cgroup_subsys_state { - /* PI: the cgroup that this css is attached to */ - struct cgroup *cgroup; - - /* PI: the cgroup subsystem that this css is attached to */ - struct cgroup_subsys *ss; - - /* reference count - access via css_[try]get() and css_put() */ - struct percpu_ref refcnt; - - /* PI: the parent css */ - struct cgroup_subsys_state *parent; - - /* siblings list anchored at the parent's ->children */ - struct list_head sibling; - struct list_head children; - - /* - * PI: Subsys-unique ID. 0 is unused and root is always 1. The - * matching css can be looked up using css_from_id(). - */ - int id; - - unsigned int flags; - - /* - * Monotonically increasing unique serial number which defines a - * uniform order among all csses. It's guaranteed that all - * ->children lists are in the ascending order of ->serial_nr and - * used to allow interrupting and resuming iterations. - */ - u64 serial_nr; - - /* percpu_ref killing and RCU release */ - struct rcu_head rcu_head; - struct work_struct destroy_work; -}; +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -/* bits in struct cgroup_subsys_state flags field */ -enum { - CSS_NO_REF = (1 << 0), /* no reference counting for this css */ - CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ - CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ -}; +/** + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk + * + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * For example, the following guarantees that a descendant can't escape + * state updates of its ancestors. + * + * my_online(@css) + * { + * Lock @css's parent and @css; + * Inherit state from the parent; + * Unlock both. + * } + * + * my_update_state(@css) + * { + * css_for_each_descendant_pre(@pos, @css) { + * Lock @pos; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; + * Unlock @pos; + * } + * } + * + * As long as the inheriting step, including checking the parent state, is + * enclosed inside @pos locking, double-locking the parent isn't necessary + * while inheriting. The state update to the parent is guaranteed to be + * visible by walking order and, as long as inheriting operations to the + * same @pos are atomic to each other, multiple updates racing each other + * still result in the correct state. It's guaranateed that at least one + * inheritance happens for any css after the latest update to its parent. + * + * If checking parent's state requires locking the parent, each inheriting + * iteration should lock and unlock both @pos->parent and @pos. + * + * Alternatively, a subsystem may choose to use a single global lock to + * synchronize ->css_online() and ->css_offline() against tree-walking + * operations. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. + */ +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) + +/** + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk + * + * Similar to css_for_each_descendant_pre() but performs post-order + * traversal instead. @root is included in the iteration and the last + * node to be visited. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * Note that the walk visibility guarantee example described in pre-order + * walk doesn't apply the same to post-order walks. + */ +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) + +/** + * cgroup_taskset_for_each - iterate cgroup_taskset + * @task: the loop cursor + * @tset: taskset to iterate + */ +#define cgroup_taskset_for_each(task, tset) \ + for ((task) = cgroup_taskset_first((tset)); (task); \ + (task) = cgroup_taskset_next((tset))) + +/* + * Inline functions. + */ /** * css_get - obtain a reference on the specified css @@ -185,309 +291,112 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } -/* bits in struct cgroup flags field */ -enum { - /* Control Group requires release notifications to userspace */ - CGRP_NOTIFY_ON_RELEASE, - /* - * Clone the parent's configuration when creating a new child - * cpuset cgroup. For historical reasons, this option can be - * specified at mount time and thus is implemented here. - */ - CGRP_CPUSET_CLONE_CHILDREN, -}; - -struct cgroup { - /* self css with NULL ->ss, points back to this cgroup */ - struct cgroup_subsys_state self; - - unsigned long flags; /* "unsigned long" so bitops work */ - - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - - /* - * If this cgroup contains any tasks, it contributes one to - * populated_cnt. All children with non-zero popuplated_cnt of - * their own contribute one. The count is zero iff there's no task - * in this cgroup or its subtree. - */ - int populated_cnt; - - struct kernfs_node *kn; /* cgroup kernfs entry */ - struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ - - /* - * The bitmask of subsystems enabled on the child cgroups. - * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. - */ - unsigned int subtree_control; - unsigned int child_subsys_mask; - - /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; - - struct cgroup_root *root; - - /* - * List of cgrp_cset_links pointing at css_sets with tasks in this - * cgroup. Protected by css_set_lock. - */ - struct list_head cset_links; - - /* - * On the default hierarchy, a css_set for a cgroup with some - * susbsys disabled will point to css's which are associated with - * the closest ancestor which has the subsys enabled. The - * following lists all css_sets which point to this cgroup's css - * for the given subsystem. - */ - struct list_head e_csets[CGROUP_SUBSYS_COUNT]; - - /* - * list of pidlists, up to two for each namespace (one for procs, one - * for tasks); created on demand. - */ - struct list_head pidlists; - struct mutex pidlist_mutex; - - /* used to wait for offlining of csses */ - wait_queue_head_t offline_waitq; - - /* used to schedule release agent */ - struct work_struct release_agent_work; -}; - -#define MAX_CGROUP_ROOT_NAMELEN 64 - -/* cgroup_root->flags */ -enum { - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ - CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ - CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ -}; - -/* - * A cgroup_root represents the root of a cgroup hierarchy, and may be - * associated with a kernfs_root to form an active hierarchy. This is - * internal to cgroup core. Don't access directly from controllers. +/** + * task_css_set_check - obtain a task's css_set with extra access conditions + * @task: the task to obtain css_set for + * @__c: extra condition expression to be passed to rcu_dereference_check() + * + * A task's css_set is RCU protected, initialized and exited while holding + * task_lock(), and can only be modified while holding both cgroup_mutex + * and task_lock() while the task is alive. This macro verifies that the + * caller is inside proper critical section and returns @task's css_set. + * + * The caller can also specify additional allowed conditions via @__c, such + * as locks used during the cgroup_subsys::attach() methods. */ -struct cgroup_root { - struct kernfs_root *kf_root; - - /* The bitmask of subsystems attached to this hierarchy */ - unsigned int subsys_mask; - - /* Unique id for this hierarchy. */ - int hierarchy_id; - - /* The root cgroup. Root is destroyed on its release. */ - struct cgroup cgrp; - - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ - atomic_t nr_cgrps; - - /* A list running through the active hierarchies */ - struct list_head root_list; - - /* Hierarchy-specific flags */ - unsigned int flags; - - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - - /* The path to use for release notifications. */ - char release_agent_path[PATH_MAX]; - - /* The name for this hierarchy - may be empty */ - char name[MAX_CGROUP_ROOT_NAMELEN]; -}; +#ifdef CONFIG_PROVE_RCU +extern struct mutex cgroup_mutex; +extern struct rw_semaphore css_set_rwsem; +#define task_css_set_check(task, __c) \ + rcu_dereference_check((task)->cgroups, \ + lockdep_is_held(&cgroup_mutex) || \ + lockdep_is_held(&css_set_rwsem) || \ + ((task)->flags & PF_EXITING) || (__c)) +#else +#define task_css_set_check(task, __c) \ + rcu_dereference((task)->cgroups) +#endif -/* - * A css_set is a structure holding pointers to a set of - * cgroup_subsys_state objects. This saves space in the task struct - * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire cgroup - * set for a task. +/** + * task_css_check - obtain css for (task, subsys) w/ extra access conds + * @task: the target task + * @subsys_id: the target subsystem ID + * @__c: extra condition expression to be passed to rcu_dereference_check() + * + * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The + * synchronization rules are the same as task_css_set_check(). */ +#define task_css_check(task, subsys_id, __c) \ + task_css_set_check((task), (__c))->subsys[(subsys_id)] -struct css_set { - - /* Reference count */ - atomic_t refcount; - - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock - */ - struct hlist_node hlist; - - /* - * Lists running through all tasks using this cgroup group. - * mg_tasks lists tasks which belong to this cset but are in the - * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to - * mg_tasks, it can be read safely while holding cgroup_mutex. - */ - struct list_head tasks; - struct list_head mg_tasks; - - /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. - */ - struct list_head cgrp_links; - - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; - - /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). - */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; - - /* - * List of csets participating in the on-going migration either as - * source or destination. Protected by cgroup_mutex. - */ - struct list_head mg_preload_node; - struct list_head mg_node; - - /* - * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. - */ - struct cgroup *mg_src_cgrp; - struct css_set *mg_dst_cset; - - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* For RCU-protected deletion */ - struct rcu_head rcu_head; -}; - -/* - * struct cftype: handler definitions for cgroup control files +/** + * task_css_set - obtain a task's css_set + * @task: the task to obtain css_set for * - * When reading/writing to a file: - * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata - * - the 'cftype' of the file is file->f_path.dentry->d_fsdata + * See task_css_set_check(). */ +static inline struct css_set *task_css_set(struct task_struct *task) +{ + return task_css_set_check(task, false); +} -/* cftype->flags */ -enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ - CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ +/** + * task_css - obtain css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * See task_css_check(). + */ +static inline struct cgroup_subsys_state *task_css(struct task_struct *task, + int subsys_id) +{ + return task_css_check(task, subsys_id, false); +} - /* internal flags, do not use outside cgroup core proper */ - __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ - __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ -}; +/** + * task_get_css - find and get the css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Find the css for the (@task, @subsys_id) combination, increment a + * reference on and return it. This function is guaranteed to return a + * valid css. + */ +static inline struct cgroup_subsys_state * +task_get_css(struct task_struct *task, int subsys_id) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + while (true) { + css = task_css(task, subsys_id); + if (likely(css_tryget_online(css))) + break; + cpu_relax(); + } + rcu_read_unlock(); + return css; +} -#define MAX_CFTYPE_NAME 64 - -struct cftype { - /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. - */ - char name[MAX_CFTYPE_NAME]; - int private; - /* - * If not 0, file mode is set to this value, otherwise it will - * be figured out automatically - */ - umode_t mode; - - /* - * The maximum length of string, excluding trailing nul, that can - * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. - */ - size_t max_write_len; - - /* CFTYPE_* flags */ - unsigned int flags; - - /* - * Fields used for internal bookkeeping. Initialized automatically - * during registration. - */ - struct cgroup_subsys *ss; /* NULL for cgroup core files */ - struct list_head node; /* anchored at ss->cfts */ - struct kernfs_ops *kf_ops; - - /* - * read_u64() is a shortcut for the common case of returning a - * single integer. Use it in place of read() - */ - u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); - /* - * read_s64() is a signed version of read_u64() - */ - s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); - - /* generic seq_file read interface */ - int (*seq_show)(struct seq_file *sf, void *v); - - /* optional ops, implement all or none */ - void *(*seq_start)(struct seq_file *sf, loff_t *ppos); - void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); - void (*seq_stop)(struct seq_file *sf, void *v); - - /* - * write_u64() is a shortcut for the common case of accepting - * a single integer (as parsed by simple_strtoull) from - * userspace. Use in place of write(); return 0 or error. - */ - int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, - u64 val); - /* - * write_s64() is a signed version of write_u64() - */ - int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, - s64 val); - - /* - * write() is the generic write callback which maps directly to - * kernfs write operation and overrides all other operations. - * Maximum write size is determined by ->max_write_len. Use - * of_css/cft() to access the associated css and cft. - */ - ssize_t (*write)(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif -}; +/** + * task_css_is_root - test whether a task belongs to the root css + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Test whether @task belongs to the root css on the specified subsystem. + * May be invoked in any context. + */ +static inline bool task_css_is_root(struct task_struct *task, int subsys_id) +{ + return task_css_check(task, subsys_id, true) == + init_css_set.subsys[subsys_id]; +} -extern struct cgroup_root cgrp_dfl_root; -extern struct css_set init_css_set; +static inline struct cgroup *task_cgroup(struct task_struct *task, + int subsys_id) +{ + return task_css(task, subsys_id)->cgroup; +} /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy @@ -604,367 +513,22 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); - -int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cftype *cfts); - -bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); - -/* - * Control Group taskset, used to pass around set of tasks to cgroup_subsys - * methods. - */ -struct cgroup_taskset; -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); - -/** - * cgroup_taskset_for_each - iterate cgroup_taskset - * @task: the loop cursor - * @tset: taskset to iterate - */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) - -/* - * Control Group subsystem type. - * See Documentation/cgroups/cgroups.txt for details - */ - -struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); - int (*css_online)(struct cgroup_subsys_state *css); - void (*css_offline)(struct cgroup_subsys_state *css); - void (*css_released)(struct cgroup_subsys_state *css); - void (*css_free)(struct cgroup_subsys_state *css); - void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); - - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup_subsys_state *css, - struct cgroup_subsys_state *old_css, - struct task_struct *task); - void (*bind)(struct cgroup_subsys_state *root_css); - - int disabled; - int early_init; - - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy; - bool warned_broken_hierarchy; - - /* the following two fields are initialized automtically during boot */ - int id; -#define MAX_CGROUP_TYPE_NAMELEN 32 - const char *name; - - /* link to parent, protected by cgroup_lock() */ - struct cgroup_root *root; - - /* idr for css->id */ - struct idr css_idr; - - /* - * List of cftypes. Each entry is the first entry of an array - * terminated by zero length name. - */ - struct list_head cfts; - - /* - * Base cftypes which are automatically registered. The two can - * point to the same array. - */ - struct cftype *dfl_cftypes; /* for the default hierarchy */ - struct cftype *legacy_cftypes; /* for the legacy hierarchies */ - - /* - * A subsystem may depend on other subsystems. When such subsystem - * is enabled on a cgroup, the depended-upon subsystems are enabled - * together if available. Subsystems enabled due to dependency are - * not visible to userland until explicitly enabled. The following - * specifies the mask of subsystems that this one depends on. - */ - unsigned int depends_on; -}; - -#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; -#include <linux/cgroup_subsys.h> -#undef SUBSYS - -/** - * task_css_set_check - obtain a task's css_set with extra access conditions - * @task: the task to obtain css_set for - * @__c: extra condition expression to be passed to rcu_dereference_check() - * - * A task's css_set is RCU protected, initialized and exited while holding - * task_lock(), and can only be modified while holding both cgroup_mutex - * and task_lock() while the task is alive. This macro verifies that the - * caller is inside proper critical section and returns @task's css_set. - * - * The caller can also specify additional allowed conditions via @__c, such - * as locks used during the cgroup_subsys::attach() methods. - */ -#ifdef CONFIG_PROVE_RCU -extern struct mutex cgroup_mutex; -extern struct rw_semaphore css_set_rwsem; -#define task_css_set_check(task, __c) \ - rcu_dereference_check((task)->cgroups, \ - lockdep_is_held(&cgroup_mutex) || \ - lockdep_is_held(&css_set_rwsem) || \ - ((task)->flags & PF_EXITING) || (__c)) -#else -#define task_css_set_check(task, __c) \ - rcu_dereference((task)->cgroups) -#endif - -/** - * task_css_check - obtain css for (task, subsys) w/ extra access conds - * @task: the target task - * @subsys_id: the target subsystem ID - * @__c: extra condition expression to be passed to rcu_dereference_check() - * - * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The - * synchronization rules are the same as task_css_set_check(). - */ -#define task_css_check(task, subsys_id, __c) \ - task_css_set_check((task), (__c))->subsys[(subsys_id)] - -/** - * task_css_set - obtain a task's css_set - * @task: the task to obtain css_set for - * - * See task_css_set_check(). - */ -static inline struct css_set *task_css_set(struct task_struct *task) -{ - return task_css_set_check(task, false); -} - -/** - * task_css - obtain css for (task, subsys) - * @task: the target task - * @subsys_id: the target subsystem ID - * - * See task_css_check(). - */ -static inline struct cgroup_subsys_state *task_css(struct task_struct *task, - int subsys_id) -{ - return task_css_check(task, subsys_id, false); -} - -/** - * task_css_is_root - test whether a task belongs to the root css - * @task: the target task - * @subsys_id: the target subsystem ID - * - * Test whether @task belongs to the root css on the specified subsystem. - * May be invoked in any context. - */ -static inline bool task_css_is_root(struct task_struct *task, int subsys_id) -{ - return task_css_check(task, subsys_id, true) == - init_css_set.subsys[subsys_id]; -} - -static inline struct cgroup *task_cgroup(struct task_struct *task, - int subsys_id) -{ - return task_css(task, subsys_id)->cgroup; -} - -struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *parent); - -struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); - -/** - * css_for_each_child - iterate through children of a css - * @pos: the css * to use as the loop cursor - * @parent: css whose children to walk - * - * Walk @parent's children. Must be called under rcu_read_lock(). - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_child(pos, parent) \ - for ((pos) = css_next_child(NULL, (parent)); (pos); \ - (pos) = css_next_child((pos), (parent))) - -struct cgroup_subsys_state * -css_next_descendant_pre(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); - -struct cgroup_subsys_state * -css_rightmost_descendant(struct cgroup_subsys_state *pos); - -/** - * css_for_each_descendant_pre - pre-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @root: css whose descendants to walk - * - * Walk @root's descendants. @root is included in the iteration and the - * first node to be visited. Must be called under rcu_read_lock(). - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * For example, the following guarantees that a descendant can't escape - * state updates of its ancestors. - * - * my_online(@css) - * { - * Lock @css's parent and @css; - * Inherit state from the parent; - * Unlock both. - * } - * - * my_update_state(@css) - * { - * css_for_each_descendant_pre(@pos, @css) { - * Lock @pos; - * if (@pos == @css) - * Update @css's state; - * else - * Verify @pos is alive and inherit state from its parent; - * Unlock @pos; - * } - * } - * - * As long as the inheriting step, including checking the parent state, is - * enclosed inside @pos locking, double-locking the parent isn't necessary - * while inheriting. The state update to the parent is guaranteed to be - * visible by walking order and, as long as inheriting operations to the - * same @pos are atomic to each other, multiple updates racing each other - * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any css after the latest update to its parent. - * - * If checking parent's state requires locking the parent, each inheriting - * iteration should lock and unlock both @pos->parent and @pos. - * - * Alternatively, a subsystem may choose to use a single global lock to - * synchronize ->css_online() and ->css_offline() against tree-walking - * operations. - * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_descendant_pre(pos, css) \ - for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ - (pos) = css_next_descendant_pre((pos), (css))) - -struct cgroup_subsys_state * -css_next_descendant_post(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); - -/** - * css_for_each_descendant_post - post-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @css: css whose descendants to walk - * - * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. @root is included in the iteration and the last - * node to be visited. - * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. - * - * Note that the walk visibility guarantee example described in pre-order - * walk doesn't apply the same to post-order walks. - */ -#define css_for_each_descendant_post(pos, css) \ - for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ - (pos) = css_next_descendant_post((pos), (css))) - -bool css_has_online_children(struct cgroup_subsys_state *css); - -/* A css_task_iter should be treated as an opaque object */ -struct css_task_iter { - struct cgroup_subsys *ss; - - struct list_head *cset_pos; - struct list_head *cset_head; - - struct list_head *task_pos; - struct list_head *tasks_head; - struct list_head *mg_tasks_head; -}; - -void css_task_iter_start(struct cgroup_subsys_state *css, - struct css_task_iter *it); -struct task_struct *css_task_iter_next(struct css_task_iter *it); -void css_task_iter_end(struct css_task_iter *it); - -int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); - -struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); -struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, - struct cgroup_subsys *ss); - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; -static inline int cgroup_init_early(void) { return 0; } -static inline int cgroup_init(void) { return 0; } +static inline void css_put(struct cgroup_subsys_state *css) {} +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) { return 0; } +static inline int cgroupstats_build(struct cgroupstats *stats, + struct dentry *dentry) { return -EINVAL; } + static inline void cgroup_fork(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {} static inline void cgroup_exit(struct task_struct *p) {} -static inline int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry) -{ - return -EINVAL; -} - -static inline void css_put(struct cgroup_subsys_state *css) {} - -/* No cgroups - nothing to do */ -static inline int cgroup_attach_task_all(struct task_struct *from, - struct task_struct *t) -{ - return 0; -} +static inline int cgroup_init_early(void) { return 0; } +static inline int cgroup_init(void) { return 0; } #endif /* !CONFIG_CGROUPS */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index df695313f975..78842f46f152 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -31,6 +31,7 @@ #define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */ #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */ #define CLK_GET_ACCURACY_NOCACHE BIT(8) /* do not use the cached clk accuracy */ +#define CLK_RECALC_NEW_RATES BIT(9) /* recalc rates after notifications */ struct clk_hw; struct clk_core; @@ -209,7 +210,7 @@ struct clk_ops { struct clk_init_data { const char *name; const struct clk_ops *ops; - const char **parent_names; + const char * const *parent_names; u8 num_parents; unsigned long flags; }; @@ -426,12 +427,14 @@ extern const struct clk_ops clk_mux_ops; extern const struct clk_ops clk_mux_ro_ops; struct clk *clk_register_mux(struct device *dev, const char *name, - const char **parent_names, u8 num_parents, unsigned long flags, + const char * const *parent_names, u8 num_parents, + unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_mux_flags, spinlock_t *lock); struct clk *clk_register_mux_table(struct device *dev, const char *name, - const char **parent_names, u8 num_parents, unsigned long flags, + const char * const *parent_names, u8 num_parents, + unsigned long flags, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); @@ -457,7 +460,7 @@ struct clk_fixed_factor { unsigned int div; }; -extern struct clk_ops clk_fixed_factor_ops; +extern const struct clk_ops clk_fixed_factor_ops; struct clk *clk_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); @@ -518,7 +521,7 @@ struct clk_composite { }; struct clk *clk_register_composite(struct device *dev, const char *name, - const char **parent_names, int num_parents, + const char * const *parent_names, int num_parents, struct clk_hw *mux_hw, const struct clk_ops *mux_ops, struct clk_hw *rate_hw, const struct clk_ops *rate_ops, struct clk_hw *gate_hw, const struct clk_ops *gate_ops, @@ -589,6 +592,7 @@ long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, unsigned long max_rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_p); +void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) { @@ -624,6 +628,8 @@ struct clk *of_clk_src_simple_get(struct of_phandle_args *clkspec, void *data); struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data); int of_clk_get_parent_count(struct device_node *np); +int of_clk_parent_fill(struct device_node *np, const char **parents, + unsigned int size); const char *of_clk_get_parent_name(struct device_node *np, int index); void of_clk_init(const struct of_device_id *matches); diff --git a/include/linux/clk.h b/include/linux/clk.h index 68c16a6bedb3..0df4a51e1a78 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -306,6 +306,20 @@ void devm_clk_put(struct device *dev, struct clk *clk); * @clk: clock source * @rate: desired clock rate in Hz * + * This answers the question "if I were to pass @rate to clk_set_rate(), + * what clock rate would I end up with?" without changing the hardware + * in any way. In other words: + * + * rate = clk_round_rate(clk, r); + * + * and: + * + * clk_set_rate(clk, r); + * rate = clk_get_rate(clk); + * + * are equivalent except the former does not modify the clock hardware + * in any way. + * * Returns rounded clock rate in Hz, or negative errno. */ long clk_round_rate(struct clk *clk, unsigned long rate); @@ -471,19 +485,6 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } -/** - * clk_add_alias - add a new clock alias - * @alias: name for clock alias - * @alias_dev_name: device name - * @id: platform specific clock name - * @dev: device - * - * Allows using generic clock names for drivers by adding a new alias. - * Assumes clkdev, see clkdev.h for more info. - */ -int clk_add_alias(const char *alias, const char *alias_dev_name, char *id, - struct device *dev); - struct device_node; struct of_phandle_args; diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index 94bad77eeb4a..08bffcc466de 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -22,6 +22,7 @@ struct clk_lookup { const char *dev_id; const char *con_id; struct clk *clk; + struct clk_hw *clk_hw; }; #define CLKDEV_INIT(d, n, c) \ @@ -32,15 +33,19 @@ struct clk_lookup { } struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); + const char *dev_fmt, ...) __printf(3, 4); void clkdev_add(struct clk_lookup *cl); void clkdev_drop(struct clk_lookup *cl); +struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id, + const char *dev_fmt, ...) __printf(3, 4); + void clkdev_add_table(struct clk_lookup *, size_t); -int clk_add_alias(const char *, const char *, char *, struct device *); +int clk_add_alias(const char *, const char *, const char *, struct device *); -int clk_register_clkdev(struct clk *, const char *, const char *, ...); +int clk_register_clkdev(struct clk *, const char *, const char *, ...) + __printf(3, 4); int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t); #ifdef CONFIG_COMMON_CLK diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 96c280b2c263..597a1e836f22 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -37,12 +37,15 @@ enum clock_event_mode { * reached from DETACHED or SHUTDOWN. * ONESHOT: Device is programmed to generate event only once. Can be reached * from DETACHED or SHUTDOWN. + * ONESHOT_STOPPED: Device was programmed in ONESHOT mode and is temporarily + * stopped. */ enum clock_event_state { CLOCK_EVT_STATE_DETACHED, CLOCK_EVT_STATE_SHUTDOWN, CLOCK_EVT_STATE_PERIODIC, CLOCK_EVT_STATE_ONESHOT, + CLOCK_EVT_STATE_ONESHOT_STOPPED, }; /* @@ -84,12 +87,13 @@ enum clock_event_state { * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE - * @state: current state of the device, assigned by the core code + * @state_use_accessors:current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. * @set_state_periodic: switch state to periodic, if !set_mode * @set_state_oneshot: switch state to oneshot, if !set_mode + * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode * @set_state_shutdown: switch state to shutdown, if !set_mode * @tick_resume: resume clkevt device, if !set_mode * @broadcast: function to broadcast events @@ -113,7 +117,7 @@ struct clock_event_device { u32 mult; u32 shift; enum clock_event_mode mode; - enum clock_event_state state; + enum clock_event_state state_use_accessors; unsigned int features; unsigned long retries; @@ -121,11 +125,12 @@ struct clock_event_device { * State transition callback(s): Only one of the two groups should be * defined: * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_state_{shutdown|periodic|oneshot}(), tick_resume(). + * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume(). */ void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); + int (*set_state_oneshot_stopped)(struct clock_event_device *); int (*set_state_shutdown)(struct clock_event_device *); int (*tick_resume)(struct clock_event_device *); @@ -144,6 +149,32 @@ struct clock_event_device { struct module *owner; } ____cacheline_aligned; +/* Helpers to verify state of a clockevent device */ +static inline bool clockevent_state_detached(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_DETACHED; +} + +static inline bool clockevent_state_shutdown(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_SHUTDOWN; +} + +static inline bool clockevent_state_periodic(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_PERIODIC; +} + +static inline bool clockevent_state_oneshot(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT; +} + +static inline bool clockevent_state_oneshot_stopped(struct clock_event_device *dev) +{ + return dev->state_use_accessors == CLOCK_EVT_STATE_ONESHOT_STOPPED; +} + /* * Calculate a multiplication factor for scaled math, which is used to convert * nanoseconds based values to clock ticks: diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d27d0152271f..278dd279a7a8 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -181,7 +181,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); -extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); diff --git a/include/linux/compat.h b/include/linux/compat.h index ab25814690bc..a76c9172b2eb 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -424,7 +424,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); -extern int compat_printk(const char *fmt, ...); +extern __printf(1, 2) int compat_printk(const char *fmt, ...); extern void sigset_from_compat(sigset_t *set, const compat_sigset_t *compat); extern void sigset_to_compat(compat_sigset_t *compat, const sigset_t *set); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 371e560d13cf..dfaa7b3e9ae9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -5,9 +5,9 @@ /* * Common definitions for all gcc versions go here. */ -#define GCC_VERSION (__GNUC__ * 10000 \ - + __GNUC_MINOR__ * 100 \ - + __GNUC_PATCHLEVEL__) +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) /* Optimization barrier */ @@ -46,55 +46,63 @@ * the inline assembly constraint from =g to =r, in this particular * case either is valid. */ -#define RELOC_HIDE(ptr, off) \ - ({ unsigned long __ptr; \ - __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ - (typeof(ptr)) (__ptr + (off)); }) +#define RELOC_HIDE(ptr, off) \ +({ \ + unsigned long __ptr; \ + __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ + (typeof(ptr)) (__ptr + (off)); \ +}) /* Make the optimizer believe the variable can be manipulated arbitrarily. */ -#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var)) +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) #ifdef __CHECKER__ -#define __must_be_array(arr) 0 +#define __must_be_array(a) 0 #else /* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old: */ -#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -# define inline inline __attribute__((always_inline)) notrace -# define __inline__ __inline__ __attribute__((always_inline)) notrace -# define __inline __inline __attribute__((always_inline)) notrace +#define inline inline __attribute__((always_inline)) notrace +#define __inline__ __inline__ __attribute__((always_inline)) notrace +#define __inline __inline __attribute__((always_inline)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ -# define inline inline notrace -# define __inline__ __inline__ notrace -# define __inline __inline notrace +#define inline inline notrace +#define __inline__ __inline__ notrace +#define __inline __inline notrace #endif -#define __deprecated __attribute__((deprecated)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) +#define __always_inline inline __attribute__((always_inline)) +#define noinline __attribute__((noinline)) + +#define __deprecated __attribute__((deprecated)) +#define __packed __attribute__((packed)) +#define __weak __attribute__((weak)) +#define __alias(symbol) __attribute__((alias(#symbol))) /* - * it doesn't make sense on ARM (currently the only user of __naked) to trace - * naked functions because then mcount is called without stack and frame pointer - * being set up and there is no chance to restore the lr register to the value - * before mcount was called. + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + * + * The asm() bodies of naked functions often depend on standard calling + * conventions, therefore they must be noinline and noclone. * - * The asm() bodies of naked functions often depend on standard calling conventions, - * therefore they must be noinline and noclone. GCC 4.[56] currently fail to enforce - * this, so we must do so ourselves. See GCC PR44290. + * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. + * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) noinline __noclone notrace -#define __noreturn __attribute__((noreturn)) +#define __noreturn __attribute__((noreturn)) /* * From the GCC manual: @@ -106,19 +114,130 @@ * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define noinline __attribute__((noinline)) -#define __attribute_const__ __attribute__((__const__)) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) - -#define __gcc_header(x) #x -#define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h) -#define gcc_header(x) _gcc_header(x) -#include gcc_header(__GNUC__) +#define __pure __attribute__((pure)) +#define __aligned(x) __attribute__((aligned(x))) +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) +#define __attribute_const__ __attribute__((__const__)) +#define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) + +/* gcc version specific checks */ + +#if GCC_VERSION < 30200 +# error Sorry, your compiler is too old - please upgrade it. +#endif + +#if GCC_VERSION < 30300 +# define __used __attribute__((__unused__)) +#else +# define __used __attribute__((__used__)) +#endif + +#ifdef CONFIG_GCOV_KERNEL +# if GCC_VERSION < 30400 +# error "GCOV profiling support for gcc versions below 3.4 not included" +# endif /* __GNUC_MINOR__ */ +#endif /* CONFIG_GCOV_KERNEL */ + +#if GCC_VERSION >= 30400 +#define __must_check __attribute__((warn_unused_result)) +#endif + +#if GCC_VERSION >= 40000 + +/* GCC 4.1.[01] miscompiles __weak */ +#ifdef __KERNEL__ +# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 +# error Your version of gcc miscompiles the __weak directive +# endif +#endif + +#define __used __attribute__((__used__)) +#define __compiler_offsetof(a, b) \ + __builtin_offsetof(a, b) + +#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#endif + +#if GCC_VERSION >= 40300 +/* Mark functions as cold. gcc will assume any path leading to a call + * to them will be unlikely. This means a lot of manual unlikely()s + * are unnecessary now for any paths leading to the usual suspects + * like BUG(), printk(), panic() etc. [but let's keep them for now for + * older compilers] + * + * Early snapshots of gcc 4.3 don't support this and we can't detect this + * in the preprocessor, but we can live with this because they're unreleased. + * Maketime probing would be overkill here. + * + * gcc also has a __attribute__((__hot__)) to move hot functions into + * a special section, but I don't see any sense in this right now in + * the kernel context + */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ +#endif /* GCC_VERSION >= 40300 */ + +#if GCC_VERSION >= 40500 +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +#endif /* GCC_VERSION >= 40500 */ + +#if GCC_VERSION >= 40600 +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) +#endif + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#if GCC_VERSION >= 40400 +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#endif +#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) +#define __HAVE_BUILTIN_BSWAP16__ +#endif +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#if GCC_VERSION >= 50000 +#define KASAN_ABI_VERSION 4 +#elif GCC_VERSION >= 40902 +#define KASAN_ABI_VERSION 3 +#endif + +#endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) #define __noclone /* not needed */ @@ -129,5 +248,3 @@ * code */ #define uninitialized_var(x) x = x - -#define __always_inline inline __attribute__((always_inline)) diff --git a/include/linux/compiler-gcc3.h b/include/linux/compiler-gcc3.h deleted file mode 100644 index 7d89febe4d79..000000000000 --- a/include/linux/compiler-gcc3.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead." -#endif - -#if GCC_VERSION < 30200 -# error Sorry, your compiler is too old - please upgrade it. -#endif - -#if GCC_VERSION >= 30300 -# define __used __attribute__((__used__)) -#else -# define __used __attribute__((__unused__)) -#endif - -#if GCC_VERSION >= 30400 -#define __must_check __attribute__((warn_unused_result)) -#endif - -#ifdef CONFIG_GCOV_KERNEL -# if GCC_VERSION < 30400 -# error "GCOV profiling support for gcc versions below 3.4 not included" -# endif /* __GNUC_MINOR__ */ -#endif /* CONFIG_GCOV_KERNEL */ diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h deleted file mode 100644 index 769e19864632..000000000000 --- a/include/linux/compiler-gcc4.h +++ /dev/null @@ -1,91 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc4.h> directly, include <linux/compiler.h> instead." -#endif - -/* GCC 4.1.[01] miscompiles __weak */ -#ifdef __KERNEL__ -# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 -# error Your version of gcc miscompiles the __weak directive -# endif -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a,b) __builtin_offsetof(a,b) - -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 -# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#endif - -#if GCC_VERSION >= 40300 -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ -#endif /* GCC_VERSION >= 40300 */ - -#if GCC_VERSION >= 40500 -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -#endif /* GCC_VERSION >= 40500 */ - -#if GCC_VERSION >= 40600 -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) -#endif - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#if GCC_VERSION >= 40400 -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#endif -#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) -#define __HAVE_BUILTIN_BSWAP16__ -#endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#if GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 -#endif diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h deleted file mode 100644 index efee493714eb..000000000000 --- a/include/linux/compiler-gcc5.h +++ /dev/null @@ -1,67 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ - -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#define __HAVE_BUILTIN_BSWAP16__ -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#define KASAN_ABI_VERSION 4 diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 0c9a2f2c2802..d4c71132d07f 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -13,10 +13,12 @@ /* Intel ECC compiler doesn't support gcc specific asm stmts. * It uses intrinsics to do the equivalent things. */ +#undef barrier #undef barrier_data #undef RELOC_HIDE #undef OPTIMIZER_HIDE_VAR +#define barrier() __memory_barrier() #define barrier_data(ptr) barrier() #define RELOC_HIDE(ptr, off) \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 867722591be2..e08a6ae7c0a4 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,6 +17,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __pmem __attribute__((noderef, address_space(5))) #ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) #else @@ -42,6 +43,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __cond_lock(x,c) (c) # define __percpu # define __rcu +# define __pmem #endif /* Indirect macros required for expanded argument pasting, eg. __LINE__. */ @@ -250,7 +252,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) #define WRITE_ONCE(x, val) \ - ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; }) + ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) + +/** + * READ_ONCE_CTRL - Read a value heading a control dependency + * @x: The value to be read, heading the control dependency + * + * Control dependencies are tricky. See Documentation/memory-barriers.txt + * for important information on how to use them. Note that in many cases, + * use of smp_load_acquire() will be much simpler. Control dependencies + * should be avoided except on the hottest of hotpaths. + */ +#define READ_ONCE_CTRL(x) \ +({ \ + typeof(x) __val = READ_ONCE(x); \ + smp_read_barrier_depends(); /* Enforce control dependency. */ \ + __val; \ +}) #endif /* __KERNEL__ */ @@ -450,13 +468,28 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * with an explicit memory barrier or atomic instruction that provides the * required ordering. * - * If possible use READ_ONCE/ASSIGN_ONCE instead. + * If possible use READ_ONCE()/WRITE_ONCE() instead. */ #define __ACCESS_ONCE(x) ({ \ __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \ (volatile typeof(x) *)&(x); }) #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) +/** + * lockless_dereference() - safely load a pointer for later dereference + * @p: The pointer to load + * + * Similar to rcu_dereference(), but for situations where the pointed-to + * object's lifetime is managed by something other than RCU. That + * "something other" might be reference counting or simple immortality. + */ +#define lockless_dereference(p) \ +({ \ + typeof(p) _________p1 = READ_ONCE(p); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) + /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ #ifdef CONFIG_KPROBES # define __kprobes __attribute__((__section__(".kprobes.text"))) diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 34025df61829..63a36e89d0eb 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -64,14 +64,14 @@ struct config_item { struct dentry *ci_dentry; }; -extern int config_item_set_name(struct config_item *, const char *, ...); +extern __printf(2, 3) +int config_item_set_name(struct config_item *, const char *, ...); static inline char *config_item_name(struct config_item * item) { return item->ci_name; } -extern void config_item_init(struct config_item *); extern void config_item_init_type_name(struct config_item *item, const char *name, struct config_item_type *type); diff --git a/include/linux/console.h b/include/linux/console.h index 9f50fb413c11..bd194343c346 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -115,6 +115,7 @@ static inline int con_debug_leave(void) #define CON_BOOT (8) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ #define CON_BRL (32) /* Used for a braille device */ +#define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ struct console { char name[16]; diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index e859c98d1767..e329ee2667e1 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -104,6 +104,7 @@ struct vc_data { unsigned int vc_resize_user; /* resize request from user */ unsigned int vc_bell_pitch; /* Console bell pitch */ unsigned int vc_bell_duration; /* Console bell duration */ + unsigned short vc_cur_blink_ms; /* Cursor blink duration */ struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 2821838256b4..b96bd299966f 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -14,8 +14,6 @@ extern void context_tracking_enter(enum ctx_state state); extern void context_tracking_exit(enum ctx_state state); extern void context_tracking_user_enter(void); extern void context_tracking_user_exit(void); -extern void __context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next); static inline void user_enter(void) { @@ -51,19 +49,11 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) -{ - if (context_tracking_is_enabled()) - __context_tracking_task_switch(prev, next); -} #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 6b7b96a32b75..678ecdf90cf6 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -12,6 +12,7 @@ struct context_tracking { * may be further optimized using static keys. */ bool active; + int recursion; enum ctx_state { CONTEXT_KERNEL = 0, CONTEXT_USER, diff --git a/include/linux/cper.h b/include/linux/cper.h index 76abba4b238e..dcacb1a72e26 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -340,7 +340,27 @@ struct cper_ia_proc_ctx { __u64 mm_reg_addr; }; -/* Memory Error Section */ +/* Old Memory Error Section UEFI 2.1, 2.2 */ +struct cper_sec_mem_err_old { + __u64 validation_bits; + __u64 error_status; + __u64 physical_addr; + __u64 physical_addr_mask; + __u16 node; + __u16 card; + __u16 module; + __u16 bank; + __u16 device; + __u16 row; + __u16 column; + __u16 bit_pos; + __u64 requestor_id; + __u64 responder_id; + __u64 target_id; + __u8 error_type; +}; + +/* Memory Error Section UEFI >= 2.3 */ struct cper_sec_mem_err { __u64 validation_bits; __u64 error_status; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c0fb6b1b4712..23c30bdcca86 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -40,9 +40,10 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern struct device *cpu_device_create(struct device *parent, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...); +extern __printf(4, 5) +struct device *cpu_device_create(struct device *parent, void *drvdata, + const struct attribute_group **groups, + const char *fmt, ...); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index bd955270d5aa..c156f5082758 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,6 +28,9 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +typedef int (*get_static_t)(cpumask_t *cpumask, int interval, + unsigned long voltage, u32 *power); + #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. @@ -36,6 +39,10 @@ struct thermal_cooling_device * cpufreq_cooling_register(const struct cpumask *clip_cpus); +struct thermal_cooling_device * +cpufreq_power_cooling_register(const struct cpumask *clip_cpus, + u32 capacitance, get_static_t plat_static_func); + /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. @@ -45,6 +52,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus); struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus); + +struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, @@ -52,6 +65,15 @@ of_cpufreq_cooling_register(struct device_node *np, { return ERR_PTR(-ENOSYS); } + +static inline struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func) +{ + return NULL; +} #endif /** @@ -68,11 +90,28 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus) return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * +cpufreq_power_cooling_register(const struct cpumask *clip_cpus, + u32 capacitance, get_static_t plat_static_func) +{ + return NULL; +} + +static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus) { return ERR_PTR(-ENOSYS); } + +static inline struct thermal_cooling_device * +of_cpufreq_power_cooling_register(struct device_node *np, + const struct cpumask *clip_cpus, + u32 capacitance, + get_static_t plat_static_func) +{ + return NULL; +} + static inline void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2ee4888c1f47..bde1e567b3a9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -62,10 +62,13 @@ struct cpufreq_policy { /* CPUs sharing clock, require sw coordination */ cpumask_var_t cpus; /* Online CPUs only */ cpumask_var_t related_cpus; /* Online + Offline CPUs */ + cpumask_var_t real_cpus; /* Related and present */ unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ - unsigned int cpu; /* cpu nr of CPU managing this policy */ + unsigned int cpu; /* cpu managing this policy, must be online */ + unsigned int kobj_cpu; /* cpu managing sysfs files, can be offline */ + struct clk *clk; struct cpufreq_cpuinfo cpuinfo;/* see above */ @@ -80,6 +83,7 @@ struct cpufreq_policy { struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ + char last_governor[CPUFREQ_NAME_LEN]; /* last governor used */ struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 9c5e89254796..d075d34279df 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -151,10 +151,6 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); -extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev); -extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, - struct cpuidle_device *dev); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else @@ -190,16 +186,28 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } +static inline struct cpuidle_driver *cpuidle_get_cpu_driver( + struct cpuidle_device *dev) {return NULL; } +#endif + +#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) +extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev); +extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, + struct cpuidle_device *dev); +#else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } -static inline struct cpuidle_driver *cpuidle_get_cpu_driver( - struct cpuidle_device *dev) {return NULL; } #endif +/* kernel/sched/idle.c */ +extern void sched_idle_set_state(struct cpuidle_state *idle_state); +extern void default_idle_call(void); + #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a); #else diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 27e285b92b5f..59915ea5373c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -151,10 +151,8 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask, return 1; } -static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp) +static inline unsigned int cpumask_local_spread(unsigned int i, int node) { - set_bit(0, cpumask_bits(dstp)); - return 0; } @@ -208,7 +206,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); -int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp); +unsigned int cpumask_local_spread(unsigned int i, int node); /** * for_each_cpu - iterate over every cpu in a mask diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h index 84920f3cc83e..a9953c762eee 100644 --- a/include/linux/crc-itu-t.h +++ b/include/linux/crc-itu-t.h @@ -3,7 +3,7 @@ * * Implements the standard CRC ITU-T V.41: * Width 16 - * Poly 0x0x1021 (x^16 + x^12 + x^15 + 1) + * Poly 0x1021 (x^16 + x^12 + x^15 + 1) * Init 0 * * This source code is licensed under the GNU General Public License, diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index cf53d0773ce3..d81961e9e37d 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -9,5 +9,6 @@ extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); extern __u16 crc_t10dif(unsigned char const *, size_t); +extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t); #endif diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 48a1a7d100f1..48b49305716b 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -1,7 +1,11 @@ #ifndef CEPH_CRUSH_CRUSH_H #define CEPH_CRUSH_CRUSH_H -#include <linux/types.h> +#ifdef __KERNEL__ +# include <linux/types.h> +#else +# include "crush_compat.h" +#endif /* * CRUSH is a pseudo-random data distribution algorithm that @@ -20,7 +24,11 @@ #define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ #define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ +#define CRUSH_MAX_RULESET (1<<8) /* max crush ruleset number */ +#define CRUSH_MAX_RULES CRUSH_MAX_RULESET /* should be the same as max rulesets */ +#define CRUSH_MAX_DEVICE_WEIGHT (100u * 0x10000u) +#define CRUSH_MAX_BUCKET_WEIGHT (65535u * 0x10000u) #define CRUSH_ITEM_UNDEF 0x7ffffffe /* undefined result (internal use only) */ #define CRUSH_ITEM_NONE 0x7fffffff /* no result */ @@ -108,6 +116,15 @@ enum { }; extern const char *crush_bucket_alg_name(int alg); +/* + * although tree was a legacy algorithm, it has been buggy, so + * exclude it. + */ +#define CRUSH_LEGACY_ALLOWED_BUCKET_ALGS ( \ + (1 << CRUSH_BUCKET_UNIFORM) | \ + (1 << CRUSH_BUCKET_LIST) | \ + (1 << CRUSH_BUCKET_STRAW)) + struct crush_bucket { __s32 id; /* this'll be negative */ __u16 type; /* non-zero; type=0 is reserved for devices */ @@ -174,7 +191,7 @@ struct crush_map { /* choose local attempts using a fallback permutation before * re-descent */ __u32 choose_local_fallback_tries; - /* choose attempts before giving up */ + /* choose attempts before giving up */ __u32 choose_total_tries; /* attempt chooseleaf inner descent once for firstn mode; on * reject retry outer descent. Note that this does *not* @@ -187,6 +204,25 @@ struct crush_map { * that want to limit reshuffling, a value of 3 or 4 will make the * mappings line up a bit better with previous mappings. */ __u8 chooseleaf_vary_r; + +#ifndef __KERNEL__ + /* + * version 0 (original) of straw_calc has various flaws. version 1 + * fixes a few of them. + */ + __u8 straw_calc_version; + + /* + * allowed bucket algs is a bitmask, here the bit positions + * are CRUSH_BUCKET_*. note that these are *bits* and + * CRUSH_BUCKET_* values are not, so we need to or together (1 + * << CRUSH_BUCKET_WHATEVER). The 0th bit is not used to + * minimize confusion (bucket type values start at 1). + */ + __u32 allowed_bucket_algs; + + __u32 *choose_tries; +#endif }; diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h index 91e884230d5d..d1d90258242e 100644 --- a/include/linux/crush/hash.h +++ b/include/linux/crush/hash.h @@ -1,6 +1,12 @@ #ifndef CEPH_CRUSH_HASH_H #define CEPH_CRUSH_HASH_H +#ifdef __KERNEL__ +# include <linux/types.h> +#else +# include "crush_compat.h" +#endif + #define CRUSH_HASH_RJENKINS1 0 #define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1 diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index eab367446eea..5dfd5b1125d2 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -8,7 +8,7 @@ * LGPL2 */ -#include <linux/crush/crush.h> +#include "crush.h" extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); extern int crush_do_rule(const struct crush_map *map, diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 10df5d2d093a..81ef938b0a8e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -53,6 +53,7 @@ #define CRYPTO_ALG_TYPE_SHASH 0x00000009 #define CRYPTO_ALG_TYPE_AHASH 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c +#define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_PCOMPRESS 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e @@ -101,6 +102,12 @@ #define CRYPTO_ALG_INTERNAL 0x00002000 /* + * Temporary flag used to prevent legacy AEAD implementations from + * being used by user-space. + */ +#define CRYPTO_ALG_AEAD_NEW 0x00004000 + +/* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_REQ_MASK 0x000fff00 @@ -138,9 +145,9 @@ struct crypto_async_request; struct crypto_aead; struct crypto_blkcipher; struct crypto_hash; -struct crypto_rng; struct crypto_tfm; struct crypto_type; +struct aead_request; struct aead_givcrypt_request; struct skcipher_givcrypt_request; @@ -175,32 +182,6 @@ struct ablkcipher_request { void *__ctx[] CRYPTO_MINALIGN_ATTR; }; -/** - * struct aead_request - AEAD request - * @base: Common attributes for async crypto requests - * @assoclen: Length in bytes of associated data for authentication - * @cryptlen: Length of data to be encrypted or decrypted - * @iv: Initialisation vector - * @assoc: Associated data - * @src: Source data - * @dst: Destination data - * @__ctx: Start of private context data - */ -struct aead_request { - struct crypto_async_request base; - - unsigned int assoclen; - unsigned int cryptlen; - - u8 *iv; - - struct scatterlist *assoc; - struct scatterlist *src; - struct scatterlist *dst; - - void *__ctx[] CRYPTO_MINALIGN_ATTR; -}; - struct blkcipher_desc { struct crypto_blkcipher *tfm; void *info; @@ -294,7 +275,7 @@ struct ablkcipher_alg { }; /** - * struct aead_alg - AEAD cipher definition + * struct old_aead_alg - AEAD cipher definition * @maxauthsize: Set the maximum authentication tag size supported by the * transformation. A transformation may support smaller tag sizes. * As the authentication tag is a message digest to ensure the @@ -319,7 +300,7 @@ struct ablkcipher_alg { * All fields except @givencrypt , @givdecrypt , @geniv and @ivsize are * mandatory and must be filled. */ -struct aead_alg { +struct old_aead_alg { int (*setkey)(struct crypto_aead *tfm, const u8 *key, unsigned int keylen); int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize); @@ -426,40 +407,12 @@ struct compress_alg { unsigned int slen, u8 *dst, unsigned int *dlen); }; -/** - * struct rng_alg - random number generator definition - * @rng_make_random: The function defined by this variable obtains a random - * number. The random number generator transform must generate - * the random number out of the context provided with this - * call. - * @rng_reset: Reset of the random number generator by clearing the entire state. - * With the invocation of this function call, the random number - * generator shall completely reinitialize its state. If the random - * number generator requires a seed for setting up a new state, - * the seed must be provided by the consumer while invoking this - * function. The required size of the seed is defined with - * @seedsize . - * @seedsize: The seed size required for a random number generator - * initialization defined with this variable. Some random number - * generators like the SP800-90A DRBG does not require a seed as the - * seeding is implemented internally without the need of support by - * the consumer. In this case, the seed size is set to zero. - */ -struct rng_alg { - int (*rng_make_random)(struct crypto_rng *tfm, u8 *rdata, - unsigned int dlen); - int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen); - - unsigned int seedsize; -}; - #define cra_ablkcipher cra_u.ablkcipher #define cra_aead cra_u.aead #define cra_blkcipher cra_u.blkcipher #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress -#define cra_rng cra_u.rng /** * struct crypto_alg - definition of a cryptograpic cipher algorithm @@ -505,7 +458,7 @@ struct rng_alg { * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all - * trasnformation types. There are multiple options: + * transformation types. There are multiple options: * &crypto_blkcipher_type, &crypto_ablkcipher_type, * &crypto_ahash_type, &crypto_aead_type, &crypto_rng_type. * This field might be empty. In that case, there are no common @@ -555,11 +508,10 @@ struct crypto_alg { union { struct ablkcipher_alg ablkcipher; - struct aead_alg aead; + struct old_aead_alg aead; struct blkcipher_alg blkcipher; struct cipher_alg cipher; struct compress_alg compress; - struct rng_alg rng; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); @@ -567,7 +519,7 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; -}; +} CRYPTO_MINALIGN_ATTR; /* * Algorithm registration interface. @@ -602,21 +554,6 @@ struct ablkcipher_tfm { unsigned int reqsize; }; -struct aead_tfm { - int (*setkey)(struct crypto_aead *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct aead_request *req); - int (*decrypt)(struct aead_request *req); - int (*givencrypt)(struct aead_givcrypt_request *req); - int (*givdecrypt)(struct aead_givcrypt_request *req); - - struct crypto_aead *base; - - unsigned int ivsize; - unsigned int authsize; - unsigned int reqsize; -}; - struct blkcipher_tfm { void *iv; int (*setkey)(struct crypto_tfm *tfm, const u8 *key, @@ -655,19 +592,11 @@ struct compress_tfm { u8 *dst, unsigned int *dlen); }; -struct rng_tfm { - int (*rng_gen_random)(struct crypto_rng *tfm, u8 *rdata, - unsigned int dlen); - int (*rng_reset)(struct crypto_rng *tfm, u8 *seed, unsigned int slen); -}; - #define crt_ablkcipher crt_u.ablkcipher -#define crt_aead crt_u.aead #define crt_blkcipher crt_u.blkcipher #define crt_cipher crt_u.cipher #define crt_hash crt_u.hash #define crt_compress crt_u.compress -#define crt_rng crt_u.rng struct crypto_tfm { @@ -675,12 +604,10 @@ struct crypto_tfm { union { struct ablkcipher_tfm ablkcipher; - struct aead_tfm aead; struct blkcipher_tfm blkcipher; struct cipher_tfm cipher; struct hash_tfm hash; struct compress_tfm compress; - struct rng_tfm rng; } crt_u; void (*exit)(struct crypto_tfm *tfm); @@ -694,10 +621,6 @@ struct crypto_ablkcipher { struct crypto_tfm base; }; -struct crypto_aead { - struct crypto_tfm base; -}; - struct crypto_blkcipher { struct crypto_tfm base; }; @@ -714,10 +637,6 @@ struct crypto_hash { struct crypto_tfm base; }; -struct crypto_rng { - struct crypto_tfm base; -}; - enum { CRYPTOA_UNSPEC, CRYPTOA_ALG, @@ -1194,400 +1113,6 @@ static inline void ablkcipher_request_set_crypt( } /** - * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API - * - * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD - * (listed as type "aead" in /proc/crypto) - * - * The most prominent examples for this type of encryption is GCM and CCM. - * However, the kernel supports other types of AEAD ciphers which are defined - * with the following cipher string: - * - * authenc(keyed message digest, block cipher) - * - * For example: authenc(hmac(sha256), cbc(aes)) - * - * The example code provided for the asynchronous block cipher operation - * applies here as well. Naturally all *ablkcipher* symbols must be exchanged - * the *aead* pendants discussed in the following. In addtion, for the AEAD - * operation, the aead_request_set_assoc function must be used to set the - * pointer to the associated data memory location before performing the - * encryption or decryption operation. In case of an encryption, the associated - * data memory is filled during the encryption operation. For decryption, the - * associated data memory must contain data that is used to verify the integrity - * of the decrypted data. Another deviation from the asynchronous block cipher - * operation is that the caller should explicitly check for -EBADMSG of the - * crypto_aead_decrypt. That error indicates an authentication error, i.e. - * a breach in the integrity of the message. In essence, that -EBADMSG error - * code is the key bonus an AEAD cipher has over "standard" block chaining - * modes. - */ - -static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm) -{ - return (struct crypto_aead *)tfm; -} - -/** - * crypto_alloc_aead() - allocate AEAD cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * AEAD cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for an AEAD. The returned struct - * crypto_aead is the cipher handle that is required for any subsequent - * API invocation for that AEAD. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask); - -static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_aead() - zeroize and free aead handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_aead(struct crypto_aead *tfm) -{ - crypto_free_tfm(crypto_aead_tfm(tfm)); -} - -static inline struct aead_tfm *crypto_aead_crt(struct crypto_aead *tfm) -{ - return &crypto_aead_tfm(tfm)->crt_aead; -} - -/** - * crypto_aead_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the aead referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->ivsize; -} - -/** - * crypto_aead_authsize() - obtain maximum authentication data size - * @tfm: cipher handle - * - * The maximum size of the authentication data for the AEAD cipher referenced - * by the AEAD cipher handle is returned. The authentication data size may be - * zero if the cipher implements a hard-coded maximum. - * - * The authentication data may also be known as "tag value". - * - * Return: authentication data size / tag size in bytes - */ -static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->authsize; -} - -/** - * crypto_aead_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the AEAD referenced with the cipher handle is returned. - * The caller may use that information to allocate appropriate memory for the - * data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm)); -} - -static inline unsigned int crypto_aead_alignmask(struct crypto_aead *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_aead_tfm(tfm)); -} - -static inline u32 crypto_aead_get_flags(struct crypto_aead *tfm) -{ - return crypto_tfm_get_flags(crypto_aead_tfm(tfm)); -} - -static inline void crypto_aead_set_flags(struct crypto_aead *tfm, u32 flags) -{ - crypto_tfm_set_flags(crypto_aead_tfm(tfm), flags); -} - -static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags) -{ - crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags); -} - -/** - * crypto_aead_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the AEAD referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, - unsigned int keylen) -{ - struct aead_tfm *crt = crypto_aead_crt(tfm); - - return crt->setkey(crt->base, key, keylen); -} - -/** - * crypto_aead_setauthsize() - set authentication data size - * @tfm: cipher handle - * @authsize: size of the authentication data / tag in bytes - * - * Set the authentication data size / tag size. AEAD requires an authentication - * tag (or MAC) in addition to the associated data. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize); - -static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) -{ - return __crypto_aead_cast(req->base.tfm); -} - -/** - * crypto_aead_encrypt() - encrypt plaintext - * @req: reference to the aead_request handle that holds all information - * needed to perform the cipher operation - * - * Encrypt plaintext data using the aead_request handle. That data structure - * and how it is filled with data is discussed with the aead_request_* - * functions. - * - * IMPORTANT NOTE The encryption operation creates the authentication data / - * tag. That data is concatenated with the created ciphertext. - * The ciphertext memory size is therefore the given number of - * block cipher blocks + the size defined by the - * crypto_aead_setauthsize invocation. The caller must ensure - * that sufficient memory is available for the ciphertext and - * the authentication tag. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_aead_encrypt(struct aead_request *req) -{ - return crypto_aead_crt(crypto_aead_reqtfm(req))->encrypt(req); -} - -/** - * crypto_aead_decrypt() - decrypt ciphertext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Decrypt ciphertext data using the aead_request handle. That data structure - * and how it is filled with data is discussed with the aead_request_* - * functions. - * - * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the - * authentication data / tag. That authentication data / tag - * must have the size defined by the crypto_aead_setauthsize - * invocation. - * - * - * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD - * cipher operation performs the authentication of the data during the - * decryption operation. Therefore, the function returns this error if - * the authentication of the ciphertext was unsuccessful (i.e. the - * integrity of the ciphertext or the associated data was violated); - * < 0 if an error occurred. - */ -static inline int crypto_aead_decrypt(struct aead_request *req) -{ - if (req->cryptlen < crypto_aead_authsize(crypto_aead_reqtfm(req))) - return -EINVAL; - - return crypto_aead_crt(crypto_aead_reqtfm(req))->decrypt(req); -} - -/** - * DOC: Asynchronous AEAD Request Handle - * - * The aead_request data structure contains all pointers to data required for - * the AEAD cipher operation. This includes the cipher handle (which can be - * used by multiple aead_request instances), pointer to plaintext and - * ciphertext, asynchronous callback function, etc. It acts as a handle to the - * aead_request_* API calls in a similar way as AEAD handle to the - * crypto_aead_* API calls. - */ - -/** - * crypto_aead_reqsize() - obtain size of the request data structure - * @tfm: cipher handle - * - * Return: number of bytes - */ -static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm) -{ - return crypto_aead_crt(tfm)->reqsize; -} - -/** - * aead_request_set_tfm() - update cipher handle reference in request - * @req: request handle to be modified - * @tfm: cipher handle that shall be added to the request handle - * - * Allow the caller to replace the existing aead handle in the request - * data structure with a different one. - */ -static inline void aead_request_set_tfm(struct aead_request *req, - struct crypto_aead *tfm) -{ - req->base.tfm = crypto_aead_tfm(crypto_aead_crt(tfm)->base); -} - -/** - * aead_request_alloc() - allocate request data structure - * @tfm: cipher handle to be registered with the request - * @gfp: memory allocation flag that is handed to kmalloc by the API call. - * - * Allocate the request data structure that must be used with the AEAD - * encrypt and decrypt API calls. During the allocation, the provided aead - * handle is registered in the request data structure. - * - * Return: allocated request handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm, - gfp_t gfp) -{ - struct aead_request *req; - - req = kmalloc(sizeof(*req) + crypto_aead_reqsize(tfm), gfp); - - if (likely(req)) - aead_request_set_tfm(req, tfm); - - return req; -} - -/** - * aead_request_free() - zeroize and free request data structure - * @req: request data structure cipher handle to be freed - */ -static inline void aead_request_free(struct aead_request *req) -{ - kzfree(req); -} - -/** - * aead_request_set_callback() - set asynchronous callback function - * @req: request handle - * @flags: specify zero or an ORing of the flags - * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and - * increase the wait queue beyond the initial maximum size; - * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep - * @compl: callback function pointer to be registered with the request handle - * @data: The data pointer refers to memory that is not used by the kernel - * crypto API, but provided to the callback function for it to use. Here, - * the caller can provide a reference to memory the callback function can - * operate on. As the callback function is invoked asynchronously to the - * related functionality, it may need to access data structures of the - * related functionality which can be referenced using this pointer. The - * callback function can access the memory via the "data" field in the - * crypto_async_request data structure provided to the callback function. - * - * Setting the callback function that is triggered once the cipher operation - * completes - * - * The callback function is registered with the aead_request handle and - * must comply with the following template - * - * void callback_function(struct crypto_async_request *req, int error) - */ -static inline void aead_request_set_callback(struct aead_request *req, - u32 flags, - crypto_completion_t compl, - void *data) -{ - req->base.complete = compl; - req->base.data = data; - req->base.flags = flags; -} - -/** - * aead_request_set_crypt - set data buffers - * @req: request handle - * @src: source scatter / gather list - * @dst: destination scatter / gather list - * @cryptlen: number of bytes to process from @src - * @iv: IV for the cipher operation which must comply with the IV size defined - * by crypto_aead_ivsize() - * - * Setting the source data and destination data scatter / gather lists. - * - * For encryption, the source is treated as the plaintext and the - * destination is the ciphertext. For a decryption operation, the use is - * reversed - the source is the ciphertext and the destination is the plaintext. - * - * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption, - * the caller must concatenate the ciphertext followed by the - * authentication tag and provide the entire data stream to the - * decryption operation (i.e. the data length used for the - * initialization of the scatterlist and the data length for the - * decryption operation is identical). For encryption, however, - * the authentication tag is created while encrypting the data. - * The destination buffer must hold sufficient space for the - * ciphertext and the authentication tag while the encryption - * invocation must only point to the plaintext data size. The - * following code snippet illustrates the memory usage - * buffer = kmalloc(ptbuflen + (enc ? authsize : 0)); - * sg_init_one(&sg, buffer, ptbuflen + (enc ? authsize : 0)); - * aead_request_set_crypt(req, &sg, &sg, ptbuflen, iv); - */ -static inline void aead_request_set_crypt(struct aead_request *req, - struct scatterlist *src, - struct scatterlist *dst, - unsigned int cryptlen, u8 *iv) -{ - req->src = src; - req->dst = dst; - req->cryptlen = cryptlen; - req->iv = iv; -} - -/** - * aead_request_set_assoc() - set the associated data scatter / gather list - * @req: request handle - * @assoc: associated data scatter / gather list - * @assoclen: number of bytes to process from @assoc - * - * For encryption, the memory is filled with the associated data. For - * decryption, the memory must point to the associated data. - */ -static inline void aead_request_set_assoc(struct aead_request *req, - struct scatterlist *assoc, - unsigned int assoclen) -{ - req->assoc = assoc; - req->assoclen = assoclen; -} - -/** * DOC: Synchronous Block Cipher API * * The synchronous block cipher API is used with the ciphers of type diff --git a/include/linux/cryptouser.h b/include/linux/cryptouser.h deleted file mode 100644 index 4abf2ea6a887..000000000000 --- a/include/linux/cryptouser.h +++ /dev/null @@ -1,105 +0,0 @@ -/* - * Crypto user configuration API. - * - * Copyright (C) 2011 secunet Security Networks AG - * Copyright (C) 2011 Steffen Klassert <steffen.klassert@secunet.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -/* Netlink configuration messages. */ -enum { - CRYPTO_MSG_BASE = 0x10, - CRYPTO_MSG_NEWALG = 0x10, - CRYPTO_MSG_DELALG, - CRYPTO_MSG_UPDATEALG, - CRYPTO_MSG_GETALG, - __CRYPTO_MSG_MAX -}; -#define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1) -#define CRYPTO_NR_MSGTYPES (CRYPTO_MSG_MAX + 1 - CRYPTO_MSG_BASE) - -#define CRYPTO_MAX_NAME CRYPTO_MAX_ALG_NAME - -/* Netlink message attributes. */ -enum crypto_attr_type_t { - CRYPTOCFGA_UNSPEC, - CRYPTOCFGA_PRIORITY_VAL, /* __u32 */ - CRYPTOCFGA_REPORT_LARVAL, /* struct crypto_report_larval */ - CRYPTOCFGA_REPORT_HASH, /* struct crypto_report_hash */ - CRYPTOCFGA_REPORT_BLKCIPHER, /* struct crypto_report_blkcipher */ - CRYPTOCFGA_REPORT_AEAD, /* struct crypto_report_aead */ - CRYPTOCFGA_REPORT_COMPRESS, /* struct crypto_report_comp */ - CRYPTOCFGA_REPORT_RNG, /* struct crypto_report_rng */ - CRYPTOCFGA_REPORT_CIPHER, /* struct crypto_report_cipher */ - __CRYPTOCFGA_MAX - -#define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) -}; - -struct crypto_user_alg { - char cru_name[CRYPTO_MAX_ALG_NAME]; - char cru_driver_name[CRYPTO_MAX_ALG_NAME]; - char cru_module_name[CRYPTO_MAX_ALG_NAME]; - __u32 cru_type; - __u32 cru_mask; - __u32 cru_refcnt; - __u32 cru_flags; -}; - -struct crypto_report_larval { - char type[CRYPTO_MAX_NAME]; -}; - -struct crypto_report_hash { - char type[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int digestsize; -}; - -struct crypto_report_cipher { - char type[CRYPTO_MAX_ALG_NAME]; - unsigned int blocksize; - unsigned int min_keysize; - unsigned int max_keysize; -}; - -struct crypto_report_blkcipher { - char type[CRYPTO_MAX_NAME]; - char geniv[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - -struct crypto_report_aead { - char type[CRYPTO_MAX_NAME]; - char geniv[CRYPTO_MAX_NAME]; - unsigned int blocksize; - unsigned int maxauthsize; - unsigned int ivsize; -}; - -struct crypto_report_comp { - char type[CRYPTO_MAX_NAME]; -}; - -struct crypto_report_rng { - char type[CRYPTO_MAX_NAME]; - unsigned int seedsize; -}; - -#define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \ - sizeof(struct crypto_report_blkcipher)) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index df334cbacc6d..d67ae119cf4e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -160,6 +160,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); + struct inode *(*d_select_inode)(struct dentry *, unsigned); } ____cacheline_aligned; /* @@ -225,6 +226,7 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ +#define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ extern seqlock_t rename_lock; @@ -325,7 +327,8 @@ static inline unsigned d_count(const struct dentry *dentry) /* * helper function for dentry_operations.d_dname() members */ -extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern __printf(4, 5) +char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); @@ -505,6 +508,11 @@ static inline bool d_really_is_positive(const struct dentry *dentry) return dentry->d_inode != NULL; } +static inline int simple_positive(struct dentry *dentry) +{ + return d_really_is_positive(dentry) && !d_unhashed(dentry); +} + extern void d_set_fallthru(struct dentry *dentry); static inline bool d_is_fallthru(const struct dentry *dentry) diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index cb25af461054..420311bcee38 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -45,7 +45,6 @@ extern struct dentry *arch_debugfs_dir; /* declared over in file.c */ extern const struct file_operations debugfs_file_operations; -extern const struct inode_operations debugfs_link_operations; struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, diff --git a/include/linux/device.h b/include/linux/device.h index 6558af90c8fe..a2b4ea70a946 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -196,12 +196,41 @@ extern struct kset *bus_get_kset(struct bus_type *bus); extern struct klist *bus_get_device_klist(struct bus_type *bus); /** + * enum probe_type - device driver probe type to try + * Device drivers may opt in for special handling of their + * respective probe routines. This tells the core what to + * expect and prefer. + * + * @PROBE_DEFAULT_STRATEGY: Used by drivers that work equally well + * whether probed synchronously or asynchronously. + * @PROBE_PREFER_ASYNCHRONOUS: Drivers for "slow" devices which + * probing order is not essential for booting the system may + * opt into executing their probes asynchronously. + * @PROBE_FORCE_SYNCHRONOUS: Use this to annotate drivers that need + * their probe routines to run synchronously with driver and + * device registration (with the exception of -EPROBE_DEFER + * handling - re-probing always ends up being done asynchronously). + * + * Note that the end goal is to switch the kernel to use asynchronous + * probing by default, so annotating drivers with + * %PROBE_PREFER_ASYNCHRONOUS is a temporary measure that allows us + * to speed up boot process while we are validating the rest of the + * drivers. + */ +enum probe_type { + PROBE_DEFAULT_STRATEGY, + PROBE_PREFER_ASYNCHRONOUS, + PROBE_FORCE_SYNCHRONOUS, +}; + +/** * struct device_driver - The basic device driver structure * @name: Name of the device driver. * @bus: The bus which the device of this driver belongs to. * @owner: The module owner. * @mod_name: Used for built-in modules. * @suppress_bind_attrs: Disables bind/unbind via sysfs. + * @probe_type: Type of the probe (synchronous or asynchronous) to use. * @of_match_table: The open firmware table. * @acpi_match_table: The ACPI match table. * @probe: Called to query the existence of a specific device, @@ -235,6 +264,7 @@ struct device_driver { const char *mod_name; /* used for built-in modules */ bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ + enum probe_type probe_type; const struct of_device_id *of_match_table; const struct acpi_device_id *acpi_match_table; @@ -607,8 +637,9 @@ extern int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); -extern char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, - va_list ap); +extern __printf(3, 0) +char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, + va_list ap); extern __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) @@ -975,17 +1006,16 @@ extern int __must_check device_bind_driver(struct device *dev); extern void device_release_driver(struct device *dev); extern int __must_check device_attach(struct device *dev); extern int __must_check driver_attach(struct device_driver *drv); +extern void device_initial_probe(struct device *dev); extern int __must_check device_reprobe(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern struct device *device_create_vargs(struct class *cls, - struct device *parent, - dev_t devt, - void *drvdata, - const char *fmt, - va_list vargs); +extern __printf(5, 0) +struct device *device_create_vargs(struct class *cls, struct device *parent, + dev_t devt, void *drvdata, + const char *fmt, va_list vargs); extern __printf(5, 6) struct device *device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, @@ -1269,4 +1299,26 @@ static void __exit __driver##_exit(void) \ } \ module_exit(__driver##_exit); +/** + * builtin_driver() - Helper macro for drivers that don't do anything + * special in init and have no exit. This eliminates some boilerplate. + * Each driver may only use this macro once, and calling it replaces + * device_initcall (or in some cases, the legacy __initcall). This is + * meant to be a direct parallel of module_driver() above but without + * the __exit stuff that is not used for builtin cases. + * + * @__driver: driver name + * @__register: register function for this driver type + * @...: Additional arguments to be passed to __register + * + * Use this macro to construct bus specific macros for registering + * drivers, and do not use it on its own. + */ +#define builtin_driver(__driver, __register, ...) \ +static int __init __driver##_init(void) \ +{ \ + return __register(&(__driver) , ##__VA_ARGS__); \ +} \ +device_initcall(__driver##_init); + #endif /* _DEVICE_H_ */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 2f0b431b73e0..f98bd7068d55 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -115,6 +115,8 @@ struct dma_buf_ops { * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. * @exp_name: name of the exporter; useful for debugging. + * @owner: pointer to exporter module; used for refcounting when exporter is a + * kernel module. * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. * @resv: reservation object linked to this dma-buf @@ -129,6 +131,7 @@ struct dma_buf { unsigned vmapping_counter; void *vmap_ptr; const char *exp_name; + struct module *owner; struct list_head list_node; void *priv; struct reservation_object *resv; @@ -164,7 +167,8 @@ struct dma_buf_attachment { /** * struct dma_buf_export_info - holds information needed to export a dma_buf - * @exp_name: name of the exporting module - useful for debugging. + * @exp_name: name of the exporter - useful for debugging. + * @owner: pointer to exporter module - used for refcounting kernel module * @ops: Attach allocator-defined dma buf ops to the new buffer * @size: Size of the buffer * @flags: mode flags for the file @@ -176,6 +180,7 @@ struct dma_buf_attachment { */ struct dma_buf_export_info { const char *exp_name; + struct module *owner; const struct dma_buf_ops *ops; size_t size; int flags; @@ -187,7 +192,8 @@ struct dma_buf_export_info { * helper macro for exporters; zeros and fills in most common values */ #define DEFINE_DMA_BUF_EXPORT_INFO(a) \ - struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME } + struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \ + .owner = THIS_MODULE } /** * get_dma_buf - convenience wrapper for get_file. diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h new file mode 100644 index 000000000000..3edc99294bf6 --- /dev/null +++ b/include/linux/dma/pxa-dma.h @@ -0,0 +1,27 @@ +#ifndef _PXA_DMA_H_ +#define _PXA_DMA_H_ + +enum pxad_chan_prio { + PXAD_PRIO_HIGHEST = 0, + PXAD_PRIO_NORMAL, + PXAD_PRIO_LOW, + PXAD_PRIO_LOWEST, +}; + +struct pxad_param { + unsigned int drcmr; + enum pxad_chan_prio prio; +}; + +struct dma_chan; + +#ifdef CONFIG_PXA_DMA +bool pxad_filter_fn(struct dma_chan *chan, void *param); +#else +static inline bool pxad_filter_fn(struct dma_chan *chan, void *param) +{ + return false; +} +#endif + +#endif /* _PXA_DMA_H_ */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index ad419757241f..e2f5eb419976 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -65,6 +65,7 @@ enum dma_transaction_type { DMA_PQ, DMA_XOR_VAL, DMA_PQ_VAL, + DMA_MEMSET, DMA_INTERRUPT, DMA_SG, DMA_PRIVATE, @@ -122,10 +123,18 @@ enum dma_transfer_direction { * chunk and before first src/dst address for next chunk. * Ignored for dst(assumed 0), if dst_inc is true and dst_sgl is false. * Ignored for src(assumed 0), if src_inc is true and src_sgl is false. + * @dst_icg: Number of bytes to jump after last dst address of this + * chunk and before the first dst address for next chunk. + * Ignored if dst_inc is true and dst_sgl is false. + * @src_icg: Number of bytes to jump after last src address of this + * chunk and before the first src address for next chunk. + * Ignored if src_inc is true and src_sgl is false. */ struct data_chunk { size_t size; size_t icg; + size_t dst_icg; + size_t src_icg; }; /** @@ -222,6 +231,16 @@ struct dma_chan_percpu { }; /** + * struct dma_router - DMA router structure + * @dev: pointer to the DMA router device + * @route_free: function to be called when the route can be disconnected + */ +struct dma_router { + struct device *dev; + void (*route_free)(struct device *dev, void *route_data); +}; + +/** * struct dma_chan - devices supply DMA channels, clients use them * @device: ptr to the dma device who supplies this channel, always !%NULL * @cookie: last cookie value returned to client @@ -232,6 +251,8 @@ struct dma_chan_percpu { * @local: per-cpu pointer to a struct dma_chan_percpu * @client_count: how many clients are using this channel * @table_count: number of appearances in the mem-to-mem allocation table + * @router: pointer to the DMA router structure + * @route_data: channel specific data for the router * @private: private data for certain client-channel associations */ struct dma_chan { @@ -247,6 +268,11 @@ struct dma_chan { struct dma_chan_percpu __percpu *local; int client_count; int table_count; + + /* DMA router */ + struct dma_router *router; + void *route_data; + void *private; }; @@ -570,6 +596,7 @@ struct dma_tx_state { * @copy_align: alignment shift for memcpy operations * @xor_align: alignment shift for xor operations * @pq_align: alignment shift for pq operations + * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @src_addr_widths: bit mask of src addr widths the device supports @@ -588,6 +615,7 @@ struct dma_tx_state { * @device_prep_dma_xor_val: prepares a xor validation operation * @device_prep_dma_pq: prepares a pq operation * @device_prep_dma_pq_val: prepares a pqzero_sum operation + * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. @@ -620,6 +648,7 @@ struct dma_device { u8 copy_align; u8 xor_align; u8 pq_align; + u8 fill_align; #define DMA_HAS_PQ_CONTINUE (1 << 15) int dev_id; @@ -650,6 +679,9 @@ struct dma_device { struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, enum sum_check_flags *pqres, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memset)( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_sg)( @@ -745,6 +777,17 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags) +{ + if (!chan || !chan->device) + return NULL; + + return chan->device->device_prep_dma_memset(chan, dest, value, + len, flags); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( struct dma_chan *chan, struct scatterlist *dst_sg, unsigned int dst_nents, @@ -820,6 +863,12 @@ static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1, return dmaengine_check_align(dev->pq_align, off1, off2, len); } +static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->fill_align, off1, off2, len); +} + static inline void dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) { @@ -874,6 +923,33 @@ static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags) BUG(); } +static inline size_t dmaengine_get_icg(bool inc, bool sgl, size_t icg, + size_t dir_icg) +{ + if (inc) { + if (dir_icg) + return dir_icg; + else if (sgl) + return icg; + } + + return 0; +} + +static inline size_t dmaengine_get_dst_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->dst_inc, xt->dst_sgl, + chunk->icg, chunk->dst_icg); +} + +static inline size_t dmaengine_get_src_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->src_inc, xt->src_sgl, + chunk->icg, chunk->src_icg); +} + /* --- public DMA engine API --- */ #ifdef CONFIG_DMA_ENGINE diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h index 52456aa566a0..e1043f79122f 100644 --- a/include/linux/dmapool.h +++ b/include/linux/dmapool.h @@ -11,8 +11,8 @@ #ifndef LINUX_DMAPOOL_H #define LINUX_DMAPOOL_H +#include <linux/scatterlist.h> #include <asm/io.h> -#include <asm/scatterlist.h> struct device; diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 30624954dec5..e9bc9292bd3a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -185,33 +185,85 @@ static inline int dmar_device_remove(void *handle) struct irte { union { + /* Shared between remapped and posted mode*/ struct { - __u64 present : 1, - fpd : 1, - dst_mode : 1, - redir_hint : 1, - trigger_mode : 1, - dlvry_mode : 3, - avail : 4, - __reserved_1 : 4, - vector : 8, - __reserved_2 : 8, - dest_id : 32; + __u64 present : 1, /* 0 */ + fpd : 1, /* 1 */ + __res0 : 6, /* 2 - 6 */ + avail : 4, /* 8 - 11 */ + __res1 : 3, /* 12 - 14 */ + pst : 1, /* 15 */ + vector : 8, /* 16 - 23 */ + __res2 : 40; /* 24 - 63 */ + }; + + /* Remapped mode */ + struct { + __u64 r_present : 1, /* 0 */ + r_fpd : 1, /* 1 */ + dst_mode : 1, /* 2 */ + redir_hint : 1, /* 3 */ + trigger_mode : 1, /* 4 */ + dlvry_mode : 3, /* 5 - 7 */ + r_avail : 4, /* 8 - 11 */ + r_res0 : 4, /* 12 - 15 */ + r_vector : 8, /* 16 - 23 */ + r_res1 : 8, /* 24 - 31 */ + dest_id : 32; /* 32 - 63 */ + }; + + /* Posted mode */ + struct { + __u64 p_present : 1, /* 0 */ + p_fpd : 1, /* 1 */ + p_res0 : 6, /* 2 - 7 */ + p_avail : 4, /* 8 - 11 */ + p_res1 : 2, /* 12 - 13 */ + p_urgent : 1, /* 14 */ + p_pst : 1, /* 15 */ + p_vector : 8, /* 16 - 23 */ + p_res2 : 14, /* 24 - 37 */ + pda_l : 26; /* 38 - 63 */ }; __u64 low; }; union { + /* Shared between remapped and posted mode*/ struct { - __u64 sid : 16, - sq : 2, - svt : 2, - __reserved_3 : 44; + __u64 sid : 16, /* 64 - 79 */ + sq : 2, /* 80 - 81 */ + svt : 2, /* 82 - 83 */ + __res3 : 44; /* 84 - 127 */ + }; + + /* Posted mode*/ + struct { + __u64 p_sid : 16, /* 64 - 79 */ + p_sq : 2, /* 80 - 81 */ + p_svt : 2, /* 82 - 83 */ + p_res3 : 12, /* 84 - 95 */ + pda_h : 32; /* 96 - 127 */ }; __u64 high; }; }; +static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) +{ + dst->present = src->present; + dst->fpd = src->fpd; + dst->avail = src->avail; + dst->pst = src->pst; + dst->vector = src->vector; + dst->sid = src->sid; + dst->sq = src->sq; + dst->svt = src->svt; +} + +#define PDA_LOW_BIT 26 +#define PDA_HIGH_BIT 32 + enum { IRQ_REMAP_XAPIC_MODE, IRQ_REMAP_X2APIC_MODE, @@ -227,6 +279,7 @@ extern void dmar_msi_read(int irq, struct msi_msg *msg); extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern irqreturn_t dmar_fault(int irq, void *dev_id); -extern int arch_setup_dmar_msi(unsigned int irq); +extern int dmar_alloc_hwirq(int id, int node, void *arg); +extern void dmar_free_hwirq(int irq); #endif /* __DMAR_H__ */ diff --git a/include/linux/dmi.h b/include/linux/dmi.h index f820f0a336c9..5055ac34142d 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -2,6 +2,7 @@ #define __DMI_H__ #include <linux/list.h> +#include <linux/kobject.h> #include <linux/mod_devicetable.h> /* enum dmi_field is in mod_devicetable.h */ @@ -74,7 +75,7 @@ struct dmi_header { u8 type; u8 length; u16 handle; -}; +} __packed; struct dmi_device { struct list_head list; @@ -93,6 +94,7 @@ struct dmi_dev_onboard { int devfn; }; +extern struct kobject *dmi_kobj; extern int dmi_check_system(const struct dmi_system_id *list); const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); diff --git a/include/linux/efi.h b/include/linux/efi.h index af5be0368dec..85ef051ac6fb 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -85,7 +85,8 @@ typedef struct { #define EFI_MEMORY_MAPPED_IO 11 #define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12 #define EFI_PAL_CODE 13 -#define EFI_MAX_MEMORY_TYPE 14 +#define EFI_PERSISTENT_MEMORY 14 +#define EFI_MAX_MEMORY_TYPE 15 /* Attribute values: */ #define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ @@ -96,6 +97,8 @@ typedef struct { #define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ #define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ #define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ +#define EFI_MEMORY_MORE_RELIABLE \ + ((u64)0x0000000000010000ULL) /* higher reliability */ #define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ #define EFI_MEMORY_DESCRIPTOR_VERSION 1 @@ -583,6 +586,9 @@ void efi_native_runtime_setup(void); #define EFI_FILE_INFO_ID \ EFI_GUID( 0x9576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) +#define EFI_SYSTEM_RESOURCE_TABLE_GUID \ + EFI_GUID( 0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 ) + #define EFI_FILE_SYSTEM_GUID \ EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b ) @@ -823,6 +829,7 @@ extern struct efi { unsigned long fw_vendor; /* fw_vendor */ unsigned long runtime; /* runtime table */ unsigned long config_table; /* config tables */ + unsigned long esrt; /* ESRT table */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -864,6 +871,7 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos extern void efi_late_init(void); extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); +extern void efi_find_mirror(void); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} @@ -875,6 +883,11 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern int efi_config_init(efi_config_table_type_t *arch_tables); +#ifdef CONFIG_EFI_ESRT +extern void __init efi_esrt_init(void); +#else +static inline void efi_esrt_init(void) { } +#endif extern int efi_config_parse_tables(void *config_tables, int count, int sz, efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); @@ -882,12 +895,15 @@ extern u32 efi_mem_type (unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); +extern u64 efi_mem_desc_end(efi_memory_desc_t *md); +extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); extern void efi_get_time(struct timespec *now); extern void efi_reserve_boot_services(void); extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose); extern struct efi_memory_map memmap; +extern struct kobject *efi_kobj; extern int efi_reboot_quirk_mode; extern bool efi_poweroff_required(void); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 45a91474487d..638b324f0291 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -39,6 +39,7 @@ typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct reques typedef int (elevator_init_fn) (struct request_queue *, struct elevator_type *e); typedef void (elevator_exit_fn) (struct elevator_queue *); +typedef void (elevator_registered_fn) (struct request_queue *); struct elevator_ops { @@ -68,6 +69,7 @@ struct elevator_ops elevator_init_fn *elevator_init_fn; elevator_exit_fn *elevator_exit_fn; + elevator_registered_fn *elevator_registered_fn; }; #define ELV_NAME_MAX (16) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 606563ef8a72..9012f8775208 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -110,7 +110,29 @@ static inline bool is_zero_ether_addr(const u8 *addr) */ static inline bool is_multicast_ether_addr(const u8 *addr) { - return 0x01 & addr[0]; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + u32 a = *(const u32 *)addr; +#else + u16 a = *(const u16 *)addr; +#endif +#ifdef __BIG_ENDIAN + return 0x01 & (a >> ((sizeof(a) * 8) - 8)); +#else + return 0x01 & a; +#endif +} + +static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 +#ifdef __BIG_ENDIAN + return 0x01 & ((*(const u64 *)addr) >> 56); +#else + return 0x01 & (*(const u64 *)addr); +#endif +#else + return is_multicast_ether_addr(addr); +#endif } /** @@ -169,6 +191,24 @@ static inline bool is_valid_ether_addr(const u8 *addr) } /** + * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol + * @proto: Ethertype/length value to be tested + * + * Check that the value from the Ethertype/length field is a valid Ethertype. + * + * Return true if the valid is an 802.3 supported Ethertype. + */ +static inline bool eth_proto_is_802_3(__be16 proto) +{ +#ifndef __BIG_ENDIAN + /* if CPU is little endian mask off bits representing LSB */ + proto &= htons(0xFF00); +#endif + /* cast both to u16 and compare since LSB can be ignored */ + return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); +} + +/** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 36f49c405dfb..b16d929fa75f 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -1,6 +1,9 @@ /* * External connector (extcon) class driver * + * Copyright (C) 2015 Samsung Electronics + * Author: Chanwoo Choi <cw00.choi@samsung.com> + * * Copyright (C) 2012 Samsung Electronics * Author: Donggeun Kim <dg77.kim@samsung.com> * Author: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -27,50 +30,35 @@ #include <linux/notifier.h> #include <linux/sysfs.h> -#define SUPPORTED_CABLE_MAX 32 -#define CABLE_NAME_MAX 30 - /* - * The standard cable name is to help support general notifier - * and notifiee device drivers to share the common names. - * Please use standard cable names unless your notifier device has - * a very unique and abnormal cable or - * the cable type is supposed to be used with only one unique - * pair of notifier/notifiee devices. - * - * Please add any other "standard" cables used with extcon dev. - * - * You may add a dot and number to specify version or specification - * of the specific cable if it is required. (e.g., "Fast-charger.18" - * and "Fast-charger.10" for 1.8A and 1.0A chargers) - * However, the notifiee and notifier should be able to handle such - * string and if the notifiee can negotiate the protocol or identify, - * you don't need such convention. This convention is helpful when - * notifier can distinguish but notifiee cannot. + * Define the unique id of supported external connectors */ -enum extcon_cable_name { - EXTCON_USB = 0, - EXTCON_USB_HOST, - EXTCON_TA, /* Travel Adaptor */ - EXTCON_FAST_CHARGER, - EXTCON_SLOW_CHARGER, - EXTCON_CHARGE_DOWNSTREAM, /* Charging an external device */ - EXTCON_HDMI, - EXTCON_MHL, - EXTCON_DVI, - EXTCON_VGA, - EXTCON_DOCK, - EXTCON_LINE_IN, - EXTCON_LINE_OUT, - EXTCON_MIC_IN, - EXTCON_HEADPHONE_OUT, - EXTCON_SPDIF_IN, - EXTCON_SPDIF_OUT, - EXTCON_VIDEO_IN, - EXTCON_VIDEO_OUT, - EXTCON_MECHANICAL, -}; -extern const char extcon_cable_name[][CABLE_NAME_MAX + 1]; +#define EXTCON_NONE 0 + +#define EXTCON_USB 1 /* USB connector */ +#define EXTCON_USB_HOST 2 + +#define EXTCON_TA 3 /* Charger connector */ +#define EXTCON_FAST_CHARGER 4 +#define EXTCON_SLOW_CHARGER 5 +#define EXTCON_CHARGE_DOWNSTREAM 6 + +#define EXTCON_LINE_IN 7 /* Audio/Video connector */ +#define EXTCON_LINE_OUT 8 +#define EXTCON_MICROPHONE 9 +#define EXTCON_HEADPHONE 10 +#define EXTCON_HDMI 11 +#define EXTCON_MHL 12 +#define EXTCON_DVI 13 +#define EXTCON_VGA 14 +#define EXTCON_SPDIF_IN 15 +#define EXTCON_SPDIF_OUT 16 +#define EXTCON_VIDEO_IN 17 +#define EXTCON_VIDEO_OUT 18 + +#define EXTCON_DOCK 19 /* Misc connector */ +#define EXTCON_JIG 20 +#define EXTCON_MECHANICAL 21 struct extcon_cable; @@ -78,7 +66,7 @@ struct extcon_cable; * struct extcon_dev - An extcon device represents one external connector. * @name: The name of this extcon device. Parent device name is * used if NULL. - * @supported_cable: Array of supported cable names ending with NULL. + * @supported_cable: Array of supported cable names ending with EXTCON_NONE. * If supported_cable is NULL, cable name related APIs * are disabled. * @mutually_exclusive: Array of mutually exclusive set of cables that cannot @@ -89,16 +77,14 @@ struct extcon_cable; * be attached simulataneously. {0x7, 0} is equivalent to * {0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there * can be no simultaneous connections. - * @print_name: An optional callback to override the method to print the - * name of the extcon device. * @print_state: An optional callback to override the method to print the * status of the extcon device. * @dev: Device of this extcon. * @state: Attach/detach state of this extcon. Do not provide at * register-time. * @nh: Notifier for the state change events from this extcon - * @entry: To support list of extcon devices so that users can search - * for extcon devices based on the extcon name. + * @entry: To support list of extcon devices so that users can + * search for extcon devices based on the extcon name. * @lock: * @max_supported: Internal value to store the number of cables. * @extcon_dev_type: Device_type struct to provide attribute_groups @@ -113,16 +99,15 @@ struct extcon_cable; struct extcon_dev { /* Optional user initializing data */ const char *name; - const char **supported_cable; + const unsigned int *supported_cable; const u32 *mutually_exclusive; /* Optional callbacks to override class functions */ - ssize_t (*print_name)(struct extcon_dev *edev, char *buf); ssize_t (*print_state)(struct extcon_dev *edev, char *buf); /* Internal data. Please do not set. */ struct device dev; - struct raw_notifier_head nh; + struct raw_notifier_head *nh; struct list_head entry; int max_supported; spinlock_t lock; /* could be called by irq handler */ @@ -161,8 +146,6 @@ struct extcon_cable { /** * struct extcon_specific_cable_nb - An internal data for * extcon_register_interest(). - * @internal_nb: A notifier block bridging extcon notifier - * and cable notifier. * @user_nb: user provided notifier block for events from * a specific cable. * @cable_index: the target cable. @@ -170,7 +153,6 @@ struct extcon_cable { * @previous_value: the saved previous event value. */ struct extcon_specific_cable_nb { - struct notifier_block internal_nb; struct notifier_block *user_nb; int cable_index; struct extcon_dev *edev; @@ -194,10 +176,10 @@ extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); /* * Following APIs control the memory of extcon device. */ -extern struct extcon_dev *extcon_dev_allocate(const char **cables); +extern struct extcon_dev *extcon_dev_allocate(const unsigned int *cable); extern void extcon_dev_free(struct extcon_dev *edev); extern struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const char **cables); + const unsigned int *cable); extern void devm_extcon_dev_free(struct device *dev, struct extcon_dev *edev); /* @@ -216,13 +198,10 @@ extern int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state); /* * get/set_cable_state access each bit of the 32b encoded state value. - * They are used to access the status of each cable based on the cable_name - * or cable_index, which is retrieved by extcon_find_cable_index + * They are used to access the status of each cable based on the cable_name. */ -extern int extcon_find_cable_index(struct extcon_dev *sdev, - const char *cable_name); -extern int extcon_get_cable_state_(struct extcon_dev *edev, int cable_index); -extern int extcon_set_cable_state_(struct extcon_dev *edev, int cable_index, +extern int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id); +extern int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, bool cable_state); extern int extcon_get_cable_state(struct extcon_dev *edev, @@ -249,16 +228,21 @@ extern int extcon_unregister_interest(struct extcon_specific_cable_nb *nb); * we do not recommend to use this for normal 'notifiee' device drivers who * want to be notified by a specific external port of the notifier. */ -extern int extcon_register_notifier(struct extcon_dev *edev, +extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb); +extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); -extern int extcon_unregister_notifier(struct extcon_dev *edev, - struct notifier_block *nb); /* * Following API get the extcon device from devicetree. * This function use phandle of devicetree to get extcon device directly. */ -extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index); +extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, + int index); + +/* Following API to get information of extcon device */ +extern const char *extcon_get_edev_name(struct extcon_dev *edev); + #else /* CONFIG_EXTCON */ static inline int extcon_dev_register(struct extcon_dev *edev) { @@ -276,7 +260,7 @@ static inline int devm_extcon_dev_register(struct device *dev, static inline void devm_extcon_dev_unregister(struct device *dev, struct extcon_dev *edev) { } -static inline struct extcon_dev *extcon_dev_allocate(const char **cables) +static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -284,7 +268,7 @@ static inline struct extcon_dev *extcon_dev_allocate(const char **cables) static inline void extcon_dev_free(struct extcon_dev *edev) { } static inline struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const char **cables) + const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -307,20 +291,14 @@ static inline int extcon_update_state(struct extcon_dev *edev, u32 mask, return 0; } -static inline int extcon_find_cable_index(struct extcon_dev *edev, - const char *cable_name) -{ - return 0; -} - static inline int extcon_get_cable_state_(struct extcon_dev *edev, - int cable_index) + unsigned int id) { return 0; } static inline int extcon_set_cable_state_(struct extcon_dev *edev, - int cable_index, bool cable_state) + unsigned int id, bool cable_state) { return 0; } @@ -343,13 +321,15 @@ static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) } static inline int extcon_register_notifier(struct extcon_dev *edev, - struct notifier_block *nb) + unsigned int id, + struct notifier_block *nb) { return 0; } static inline int extcon_unregister_notifier(struct extcon_dev *edev, - struct notifier_block *nb) + unsigned int id, + struct notifier_block *nb) { return 0; } diff --git a/include/linux/extcon/extcon-adc-jack.h b/include/linux/extcon/extcon-adc-jack.h index 9ca958c4e94c..53c60806bcfb 100644 --- a/include/linux/extcon/extcon-adc-jack.h +++ b/include/linux/extcon/extcon-adc-jack.h @@ -44,7 +44,7 @@ struct adc_jack_cond { * @consumer_channel: Unique name to identify the channel on the consumer * side. This typically describes the channels used within * the consumer. E.g. 'battery_voltage' - * @cable_names: array of cable names ending with null. + * @cable_names: array of extcon id for supported cables. * @adc_contitions: array of struct adc_jack_cond conditions ending * with .state = 0 entry. This describes how to decode * adc values into extcon state. @@ -58,8 +58,7 @@ struct adc_jack_pdata { const char *name; const char *consumer_channel; - /* The last entry should be NULL */ - const char **cable_names; + const enum extcon *cable_names; /* The last entry's state should be 0 */ struct adc_jack_cond *adc_conditions; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 591f8c3ef410..920408a21ffd 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -50,6 +50,8 @@ #define MAX_ACTIVE_NODE_LOGS 8 #define MAX_ACTIVE_DATA_LOGS 8 +#define VERSION_LEN 256 + /* * For superblock */ @@ -86,6 +88,12 @@ struct f2fs_super_block { __le32 extension_count; /* # of extensions below */ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ __le32 cp_payload; + __u8 version[VERSION_LEN]; /* the kernel version */ + __u8 init_version[VERSION_LEN]; /* the initial kernel version */ + __le32 feature; /* defined features */ + __u8 encryption_level; /* versioning level for encryption */ + __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ + __u8 reserved[871]; /* valid reserved region */ } __packed; /* diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 230f87bdf5ad..fbb88740634a 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -47,6 +47,9 @@ struct files_struct { * read mostly part */ atomic_t count; + bool resize_in_progress; + wait_queue_head_t resize_wait; + struct fdtable __rcu *fdt; struct fdtable fdtab; /* diff --git a/include/linux/filter.h b/include/linux/filter.h index fa11b3a367be..17724f6ea983 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -207,6 +207,16 @@ struct bpf_prog_aux; .off = OFF, \ .imm = 0 }) +/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ + +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ @@ -267,6 +277,14 @@ struct bpf_prog_aux; .off = 0, \ .imm = 0 }) +/* Internal classic blocks for direct assignment */ + +#define __BPF_STMT(CODE, K) \ + ((struct sock_filter) BPF_STMT(CODE, K)) + +#define __BPF_JUMP(CODE, K, JT, JF) \ + ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) + #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ @@ -360,12 +378,9 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) int sk_filter(struct sock *sk, struct sk_buff *skb); -void bpf_prog_select_runtime(struct bpf_prog *fp); +int bpf_prog_select_runtime(struct bpf_prog *fp); void bpf_prog_free(struct bpf_prog *fp); -int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_insn *new_prog, int *new_len); - struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); @@ -377,14 +392,17 @@ static inline void bpf_prog_unlock_free(struct bpf_prog *fp) __bpf_prog_free(fp); } +typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, + unsigned int flen); + int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); +int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, + bpf_aux_classic_check_t trans); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); - -int bpf_check_classic(const struct sock_filter *filter, unsigned int flen); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 8293262401de..e65ef959546c 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -6,16 +6,16 @@ #include <linux/bitops.h> struct frontswap_ops { - void (*init)(unsigned); - int (*store)(unsigned, pgoff_t, struct page *); - int (*load)(unsigned, pgoff_t, struct page *); - void (*invalidate_page)(unsigned, pgoff_t); - void (*invalidate_area)(unsigned); + void (*init)(unsigned); /* this swap type was just swapon'ed */ + int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ + int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ + void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ + void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ + struct frontswap_ops *next; /* private pointer to next ops */ }; extern bool frontswap_enabled; -extern struct frontswap_ops * - frontswap_register_ops(struct frontswap_ops *ops); +extern void frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); extern void frontswap_writethrough(bool); diff --git a/include/linux/fs.h b/include/linux/fs.h index 35ec87e490b1..84b783f277f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,10 +35,10 @@ #include <uapi/linux/fs.h> struct backing_dev_info; +struct bdi_writeback; struct export_operations; struct hd_geometry; struct iovec; -struct nameidata; struct kiocb; struct kobject; struct pipe_inode_info; @@ -55,7 +55,8 @@ struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); @@ -70,6 +71,7 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); +typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 @@ -635,6 +637,14 @@ struct inode { struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *i_wb; /* the associated cgroup wb */ + + /* foreign inode detection, see wbc_detach_inode() */ + int i_wb_frn_winner; + u16 i_wb_frn_avg_time; + u16 i_wb_frn_history; +#endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; union { @@ -656,6 +666,7 @@ struct inode { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; + char *i_link; }; __u32 i_generation; @@ -1036,12 +1047,12 @@ extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int posix_lock_file_wait(struct file *, struct file_lock *); +extern int posix_lock_inode_wait(struct inode *, struct file_lock *); extern int posix_unblock_lock(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); +extern int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); @@ -1127,7 +1138,8 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl, return -ENOLCK; } -static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +static inline int posix_lock_inode_wait(struct inode *inode, + struct file_lock *fl) { return -ENOLCK; } @@ -1153,8 +1165,8 @@ static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) return 0; } -static inline int flock_lock_file_wait(struct file *filp, - struct file_lock *request) +static inline int flock_lock_inode_wait(struct inode *inode, + struct file_lock *request) { return -ENOLCK; } @@ -1192,6 +1204,20 @@ static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} #endif /* !CONFIG_FILE_LOCKING */ +static inline struct inode *file_inode(const struct file *f) +{ + return f->f_inode; +} + +static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return posix_lock_inode_wait(file_inode(filp), fl); +} + +static inline int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return flock_lock_inode_wait(file_inode(filp), fl); +} struct fasync_struct { spinlock_t fa_lock; @@ -1232,6 +1258,8 @@ struct mm_struct; #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ +/* sb->s_iflags */ +#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ /* Possible states of 'frozen' field */ enum { @@ -1270,6 +1298,7 @@ struct super_block { const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; + unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; @@ -1607,12 +1636,12 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - void * (*follow_link) (struct dentry *, struct nameidata *); + const char * (*follow_link) (struct dentry *, void **); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct dentry *, struct nameidata *, void *); + void (*put_link) (struct inode *, void *); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); @@ -1641,7 +1670,6 @@ struct inode_operations { int (*set_acl)(struct inode *, struct posix_acl *, int); /* WARNING: probably going away soon, do not use! */ - int (*dentry_open)(struct dentry *, struct file *, const struct cred *); } ____cacheline_aligned; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, @@ -1806,6 +1834,11 @@ struct super_operations { * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab mapping->tree_lock. See + * inode_switch_wb_work_fn() for details. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1825,6 +1858,7 @@ struct super_operations { #define I_DIRTY_TIME (1 << 11) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) +#define I_WB_SWITCH (1 << 13) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -1879,6 +1913,7 @@ enum file_time_flags { S_VERSION = 8, }; +extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); static inline void file_accessed(struct file *file) { @@ -1897,6 +1932,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_USERNS_VISIBLE 32 /* FS must already be visible */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); @@ -1984,7 +2020,6 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); -extern bool fs_fully_visible(struct file_system_type *); extern int current_umask(void); @@ -1992,11 +2027,6 @@ extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec *, int); -static inline struct inode *file_inode(const struct file *f) -{ - return f->f_inode; -} - /* /sys/fs */ extern struct kobject *fs_kobj; @@ -2193,7 +2223,6 @@ extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); -extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); @@ -2217,7 +2246,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; @@ -2240,7 +2269,13 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); -extern int sb_is_blkdev_sb(struct super_block *sb); + +extern struct super_block *blockdev_superblock; + +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return sb == blockdev_superblock; +} #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } @@ -2279,6 +2314,9 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); +extern int __blkdev_reread_part(struct block_device *bdev); +extern int blkdev_reread_part(struct block_device *bdev); + #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); extern void bd_unlink_disk_holder(struct block_device *bdev, @@ -2501,6 +2539,8 @@ extern struct file * open_exec(const char *); extern int is_subdir(struct dentry *, struct dentry *); extern int path_is_under(struct path *, struct path *); +extern char *file_path(struct file *, char *, int); + #include <linux/err.h> /* needed for stackable file system support */ @@ -2552,7 +2592,12 @@ extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); -extern int file_remove_suid(struct file *); +extern int file_remove_privs(struct file *); +extern int dentry_needs_remove_privs(struct dentry *dentry); +static inline int file_needs_remove_privs(struct file *file) +{ + return dentry_needs_remove_privs(file->f_path.dentry); +} extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) @@ -2627,9 +2672,13 @@ ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, int dax_clear_blocks(struct inode *, sector_t block, long size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); -int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); +int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); -#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) +#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod) +#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod) #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, @@ -2704,13 +2753,14 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern void *page_follow_link_light(struct dentry *, struct nameidata *); -extern void page_put_link(struct dentry *, struct nameidata *, void *); +extern const char *page_follow_link_light(struct dentry *, void **); +extern void page_put_link(struct inode *, void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern void kfree_put_link(struct dentry *, struct nameidata *, void *); +extern void kfree_put_link(struct inode *, void *); +extern void free_page_put_link(struct inode *, void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); @@ -2721,6 +2771,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); +const char *simple_follow_link(struct dentry *, void **); +extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); @@ -2780,6 +2832,8 @@ extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned in extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; +extern void make_empty_dir_inode(struct inode *inode); +extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 771484993ca7..604e1526cd00 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -74,6 +74,7 @@ extern wait_queue_head_t fscache_cache_cleared_wq; */ typedef void (*fscache_operation_release_t)(struct fscache_operation *op); typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); +typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); enum fscache_operation_state { FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ @@ -109,6 +110,9 @@ struct fscache_operation { * the op in a non-pool thread */ fscache_operation_processor_t processor; + /* Operation cancellation cleanup (optional) */ + fscache_operation_cancel_t cancel; + /* operation releaser */ fscache_operation_release_t release; }; @@ -119,33 +123,17 @@ extern void fscache_op_work_func(struct work_struct *work); extern void fscache_enqueue_operation(struct fscache_operation *); extern void fscache_op_complete(struct fscache_operation *, bool); extern void fscache_put_operation(struct fscache_operation *); - -/** - * fscache_operation_init - Do basic initialisation of an operation - * @op: The operation to initialise - * @release: The release function to assign - * - * Do basic initialisation of an operation. The caller must still set flags, - * object and processor if needed. - */ -static inline void fscache_operation_init(struct fscache_operation *op, - fscache_operation_processor_t processor, - fscache_operation_release_t release) -{ - INIT_WORK(&op->work, fscache_op_work_func); - atomic_set(&op->usage, 1); - op->state = FSCACHE_OP_ST_INITIALISED; - op->debug_id = atomic_inc_return(&fscache_op_debug_id); - op->processor = processor; - op->release = release; - INIT_LIST_HEAD(&op->pend_link); -} +extern void fscache_operation_init(struct fscache_operation *, + fscache_operation_processor_t, + fscache_operation_cancel_t, + fscache_operation_release_t); /* * data read operation */ struct fscache_retrieval { struct fscache_operation op; + struct fscache_cookie *cookie; /* The netfs cookie */ struct address_space *mapping; /* netfs pages */ fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ void *context; /* netfs read context (pinned) */ @@ -371,6 +359,7 @@ struct fscache_object { #define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ #define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ #define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ +#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ struct list_head cache_link; /* link in cache->object_list */ struct hlist_node cookie_link; /* link in cookie->backing_objects */ @@ -410,17 +399,16 @@ static inline bool fscache_object_is_available(struct fscache_object *object) return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); } -static inline bool fscache_object_is_active(struct fscache_object *object) +static inline bool fscache_cache_is_broken(struct fscache_object *object) { - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !test_bit(FSCACHE_IOERROR, &object->cache->flags); + return test_bit(FSCACHE_IOERROR, &object->cache->flags); } -static inline bool fscache_object_is_dead(struct fscache_object *object) +static inline bool fscache_object_is_active(struct fscache_object *object) { - return fscache_object_is_dying(object) && - test_bit(FSCACHE_IOERROR, &object->cache->flags); + return fscache_object_is_available(object) && + fscache_object_is_live(object) && + !fscache_cache_is_broken(object); } /** @@ -551,4 +539,15 @@ extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, const void *data, uint16_t datalen); +extern void fscache_object_retrying_stale(struct fscache_object *object); + +enum fscache_why_object_killed { + FSCACHE_OBJECT_IS_STALE, + FSCACHE_OBJECT_NO_SPACE, + FSCACHE_OBJECT_WAS_RETIRED, + FSCACHE_OBJECT_WAS_CULLED, +}; +extern void fscache_object_mark_killed(struct fscache_object *object, + enum fscache_why_object_killed why); + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index a82296af413f..2a2f56b292c1 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -24,6 +24,7 @@ #define FSL_USB_VER_1_6 1 #define FSL_USB_VER_2_2 2 #define FSL_USB_VER_2_4 3 +#define FSL_USB_VER_2_5 4 #include <linux/types.h> diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0f313f93c586..65a517dd32f7 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -84,8 +84,6 @@ struct fsnotify_fname; * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * - * should_send_event - given a group, inode, and mask this function determines - * if the group is interested in this event. * handle_event - main call for a group to handle an fs event * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1da602982cf9..6cd8c0ee4b6f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -116,6 +116,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * SAVE_REGS. If another ops with this flag set is already registered * for any of the functions that this ops will be registered for, then * this ops will fail to register or set_filter_ip. + * PID - Is affected by set_ftrace_pid (allows filtering on those pids) */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -132,6 +133,7 @@ enum { FTRACE_OPS_FL_MODIFYING = 1 << 11, FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 12, FTRACE_OPS_FL_IPMODIFY = 1 << 13, + FTRACE_OPS_FL_PID = 1 << 14, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -159,6 +161,7 @@ struct ftrace_ops { struct ftrace_ops *next; unsigned long flags; void *private; + ftrace_func_t saved_func; int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE int nr_trampolines; diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 1ccaab44abcc..5383bb1394a1 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -119,16 +119,16 @@ extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid); -extern struct gen_pool *dev_get_gen_pool(struct device *dev); +extern struct gen_pool *gen_pool_get(struct device *dev); bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF -extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, +extern struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index); #else -static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np, +static inline struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index) { return NULL; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 97a9373e61e8..ad35f300b9a4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,6 +30,7 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u +#define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -87,6 +88,7 @@ struct vm_area_struct; #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ +#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) @@ -366,6 +368,11 @@ extern void free_pages(unsigned long addr, unsigned int order); extern void free_hot_cold_page(struct page *page, bool cold); extern void free_hot_cold_page_list(struct list_head *list, bool cold); +struct page_frag_cache; +extern void *__alloc_page_frag(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask); +extern void __free_page_frag(void *addr); + extern void __free_kmem_pages(struct page *page, unsigned int order); extern void free_kmem_pages(unsigned long addr, unsigned int order); @@ -377,6 +384,14 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +void page_alloc_init_late(void); +#else +static inline void page_alloc_init_late(void) +{ +} +#endif + /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 569236e6b2bc..93e080b39cf6 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -3,13 +3,24 @@ /* Helpers for Goldfish virtual platform */ -static inline void gf_write64(unsigned long data, - void __iomem *portl, void __iomem *porth) +static inline void gf_write_ptr(const void *ptr, void __iomem *portl, + void __iomem *porth) { - writel((u32)data, portl); + writel((u32)(unsigned long)ptr, portl); #ifdef CONFIG_64BIT - writel(data>>32, porth); + writel((unsigned long)ptr >> 32, porth); #endif } +static inline void gf_write_dma_addr(const dma_addr_t addr, + void __iomem *portl, + void __iomem *porth) +{ + writel((u32)addr, portl); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + writel(addr >> 32, porth); +#endif +} + + #endif /* __LINUX_GOLDFISH_H */ diff --git a/include/linux/gpio.h b/include/linux/gpio.h index ab81339a8590..d12b5d566e4b 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -196,13 +196,6 @@ static inline int gpio_export_link(struct device *dev, const char *name, return -EINVAL; } -static inline int gpio_sysfs_set_active_low(unsigned gpio, int value) -{ - /* GPIO can never have been requested */ - WARN_ON(1); - return -EINVAL; -} - static inline void gpio_unexport(unsigned gpio) { /* GPIO can never have been exported */ diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 3a7c9ffd5ab9..adac255aee86 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -100,24 +100,25 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); void gpiod_set_value(struct gpio_desc *desc, int value); -void gpiod_set_array(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); +void gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, int *value_array); int gpiod_get_raw_value(const struct gpio_desc *desc); void gpiod_set_raw_value(struct gpio_desc *desc, int value); -void gpiod_set_raw_array(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); +void gpiod_set_raw_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_array_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array); +void gpiod_set_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_raw_array_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array); +void gpiod_set_raw_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); @@ -304,9 +305,9 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array) +static inline void gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); @@ -322,9 +323,9 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array(unsigned int array_size, - struct gpio_desc **desc_array, - int *value_array) +static inline void gpiod_set_raw_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + int *value_array) { /* GPIO can never have been requested */ WARN_ON(1); @@ -341,7 +342,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_cansleep(unsigned int array_size, +static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { @@ -360,7 +361,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_raw_array_cansleep(unsigned int array_size, +static inline void gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, int *value_array) { @@ -406,6 +407,21 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) return -EINVAL; } +/* Child properties interface */ +struct fwnode_handle; + +static inline struct gpio_desc *fwnode_get_named_gpiod( + struct fwnode_handle *fwnode, const char *propname) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct gpio_desc *devm_get_gpiod_from_child( + struct device *dev, const char *con_id, struct fwnode_handle *child) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB */ /* @@ -449,7 +465,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) int gpiod_export(struct gpio_desc *desc, bool direction_may_change); int gpiod_export_link(struct device *dev, const char *name, struct gpio_desc *desc); -int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value); void gpiod_unexport(struct gpio_desc *desc); #else /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ @@ -466,11 +481,6 @@ static inline int gpiod_export_link(struct device *dev, const char *name, return -ENOSYS; } -static inline int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value) -{ - return -ENOSYS; -} - static inline void gpiod_unexport(struct gpio_desc *desc) { } diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f1b36593ec9f..c8393cd4d44f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -20,6 +20,7 @@ struct seq_file; * struct gpio_chip - abstract a GPIO controller * @label: for diagnostics * @dev: optional device providing the GPIOs + * @cdev: class device used by sysfs interface (may be NULL) * @owner: helps prevent removal of modules exporting active GPIOs * @list: links gpio_chips together for traversal * @request: optional hook for chip-specific activation, such as @@ -41,8 +42,12 @@ struct seq_file; * @dbg_show: optional routine to show contents in debugfs; default code * will be used when this is omitted, but custom code can show extra * state (such as pullup/pulldown configuration). - * @base: identifies the first GPIO number handled by this chip; or, if - * negative during registration, requests dynamic ID allocation. + * @base: identifies the first GPIO number handled by this chip; + * or, if negative during registration, requests dynamic ID allocation. + * DEPRECATION: providing anything non-negative and nailing the base + * offset of GPIO chips is deprecated. Please pass -1 as base to + * let gpiolib select the chip base in all possible cases. We want to + * get rid of the static GPIO number space in the long run. * @ngpio: the number of GPIOs handled by this controller; the last GPIO * handled is (base + ngpio - 1). * @desc: array of ngpio descriptors. Private. @@ -57,7 +62,6 @@ struct seq_file; * implies that if the chip supports IRQs, these IRQs need to be threaded * as the chip access may sleep when e.g. reading out the IRQ status * registers. - * @exported: flags if the gpiochip is exported for use from sysfs. Private. * @irq_not_threaded: flag must be set if @can_sleep is set but the * IRQs don't need to be threaded * @@ -74,6 +78,7 @@ struct seq_file; struct gpio_chip { const char *label; struct device *dev; + struct device *cdev; struct module *owner; struct list_head list; @@ -109,7 +114,6 @@ struct gpio_chip { const char *const *names; bool can_sleep; bool irq_not_threaded; - bool exported; #ifdef CONFIG_GPIOLIB_IRQCHIP /* @@ -121,6 +125,7 @@ struct gpio_chip { unsigned int irq_base; irq_flow_handler_t irq_handler; unsigned int irq_default_type; + int irq_parent; #endif #if defined(CONFIG_OF_GPIO) diff --git a/include/linux/gsmmux.h b/include/linux/gsmmux.h deleted file mode 100644 index c25e9477f7c3..000000000000 --- a/include/linux/gsmmux.h +++ /dev/null @@ -1,36 +0,0 @@ -#ifndef _LINUX_GSMMUX_H -#define _LINUX_GSMMUX_H - -struct gsm_config -{ - unsigned int adaption; - unsigned int encapsulation; - unsigned int initiator; - unsigned int t1; - unsigned int t2; - unsigned int t3; - unsigned int n2; - unsigned int mru; - unsigned int mtu; - unsigned int k; - unsigned int i; - unsigned int unused[8]; /* Padding for expansion without - breaking stuff */ -}; - -#define GSMIOC_GETCONF _IOR('G', 0, struct gsm_config) -#define GSMIOC_SETCONF _IOW('G', 1, struct gsm_config) - -struct gsm_netconfig { - unsigned int adaption; /* Adaption to use in network mode */ - unsigned short protocol;/* Protocol to use - only ETH_P_IP supported */ - unsigned short unused2; - char if_name[IFNAMSIZ]; /* interface name format string */ - __u8 unused[28]; /* For future use */ -}; - -#define GSMIOC_ENABLE_NET _IOW('G', 2, struct gsm_netconfig) -#define GSMIOC_DISABLE_NET _IO('G', 3) - - -#endif diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f4af03404b97..dfd59d6bc6f0 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -1,7 +1,7 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H -#include <linux/preempt_mask.h> +#include <linux/preempt.h> #include <linux/lockdep.h> #include <linux/ftrace_irq.h> #include <linux/vtime.h> diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 0408421d885f..c02b5ce6c5cd 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -74,7 +74,7 @@ struct sensor_hub_pending { * @usage: Usage id for this hub device instance. * @start_collection_index: Starting index for a phy type collection * @end_collection_index: Last index for a phy type collection - * @mutex: synchronizing mutex. + * @mutex_ptr: synchronizing mutex pointer. * @pending: Holds information of pending sync read request. */ struct hid_sensor_hub_device { @@ -84,7 +84,7 @@ struct hid_sensor_hub_device { u32 usage; int start_collection_index; int end_collection_index; - struct mutex mutex; + struct mutex *mutex_ptr; struct sensor_hub_pending pending; }; @@ -230,6 +230,7 @@ struct hid_sensor_common { struct platform_device *pdev; unsigned usage_id; atomic_t data_ready; + atomic_t user_requested_state; struct iio_trigger *trigger; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; diff --git a/include/linux/hid.h b/include/linux/hid.h index 176b43670e5d..f17980de2662 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -815,6 +815,8 @@ void hid_disconnect(struct hid_device *hid); const struct hid_device_id *hid_match_id(struct hid_device *hdev, const struct hid_device_id *id); s32 hid_snto32(__u32 value, unsigned n); +__u32 hid_field_extract(const struct hid_device *hid, __u8 *report, + unsigned offset, unsigned n); /** * hid_device_io_start - enable HID input during probe, remove diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 9286a46b7d69..6aefcd0031a6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -65,6 +65,7 @@ static inline void kunmap(struct page *page) static inline void *kmap_atomic(struct page *page) { + preempt_disable(); pagefault_disable(); return page_address(page); } @@ -73,6 +74,7 @@ static inline void *kmap_atomic(struct page *page) static inline void __kunmap_atomic(void *addr) { pagefault_enable(); + preempt_enable(); } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 05f6df1fdf5b..76dd4f0da5ca 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -53,34 +53,25 @@ enum hrtimer_restart { * * 0x00 inactive * 0x01 enqueued into rbtree - * 0x02 callback function running - * 0x04 timer is migrated to another cpu * - * Special cases: - * 0x03 callback function running and enqueued - * (was requeued on another CPU) - * 0x05 timer was migrated on CPU hotunplug + * The callback state is not part of the timer->state because clearing it would + * mean touching the timer after the callback, this makes it impossible to free + * the timer from the callback function. * - * The "callback function running and enqueued" status is only possible on - * SMP. It happens for example when a posix timer expired and the callback + * Therefore we track the callback state in: + * + * timer->base->cpu_base->running == timer + * + * On SMP it is possible to have a "callback function running and enqueued" + * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the - * signal and rearm the timer. We have to preserve the callback running state, - * as otherwise the timer could be removed before the softirq code finishes the - * the handling of the timer. - * - * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state - * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This - * also affects HRTIMER_STATE_MIGRATE where the preservation is not - * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is - * enqueued on the new cpu. + * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 -#define HRTIMER_STATE_CALLBACK 0x02 -#define HRTIMER_STATE_MIGRATE 0x04 /** * struct hrtimer - the basic hrtimer structure @@ -130,6 +121,12 @@ struct hrtimer_sleeper { struct task_struct *task; }; +#ifdef CONFIG_64BIT +# define HRTIMER_CLOCK_BASE_ALIGN 64 +#else +# define HRTIMER_CLOCK_BASE_ALIGN 32 +#endif + /** * struct hrtimer_clock_base - the timer base for a specific clock * @cpu_base: per cpu clock base @@ -137,9 +134,7 @@ struct hrtimer_sleeper { * timer to a base on another cpu. * @clockid: clock id for per_cpu support * @active: red black tree root node for the active timers - * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock - * @softirq_time: the time when running the hrtimer queue in the softirq * @offset: offset of this clock to the monotonic base */ struct hrtimer_clock_base { @@ -147,11 +142,9 @@ struct hrtimer_clock_base { int index; clockid_t clockid; struct timerqueue_head active; - ktime_t resolution; ktime_t (*get_time)(void); - ktime_t softirq_time; ktime_t offset; -}; +} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN))); enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, @@ -165,11 +158,16 @@ enum hrtimer_base_type { * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers + * @seq: seqcount around __run_hrtimer + * @running: pointer to the currently running hrtimer * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers - * @clock_was_set: Indicates that clock was set from irq context. + * @clock_was_set_seq: Sequence counter of clock was set events + * @migration_enabled: The migration of hrtimers to other cpus is enabled + * @nohz_active: The nohz functionality is enabled * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @next_timer: Pointer to the first expiring timer * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang @@ -178,27 +176,38 @@ enum hrtimer_base_type { * @nr_hangs: Total number of hrtimer interrupt hangs * @max_hang_time: Maximum time spent in hrtimer_interrupt * @clock_base: array of clock bases for this cpu + * + * Note: next_timer is just an optimization for __remove_hrtimer(). + * Do not dereference the pointer because it is not reliable on + * cross cpu removals. */ struct hrtimer_cpu_base { raw_spinlock_t lock; + seqcount_t seq; + struct hrtimer *running; unsigned int cpu; unsigned int active_bases; - unsigned int clock_was_set; + unsigned int clock_was_set_seq; + bool migration_enabled; + bool nohz_active; #ifdef CONFIG_HIGH_RES_TIMERS + unsigned int in_hrtirq : 1, + hres_active : 1, + hang_detected : 1; ktime_t expires_next; - int in_hrtirq; - int hres_active; - int hang_detected; - unsigned long nr_events; - unsigned long nr_retries; - unsigned long nr_hangs; - ktime_t max_hang_time; + struct hrtimer *next_timer; + unsigned int nr_events; + unsigned int nr_retries; + unsigned int nr_hangs; + unsigned int max_hang_time; #endif struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; -}; +} ____cacheline_aligned; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { + BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN); + timer->node.expires = time; timer->_softexpires = time; } @@ -262,19 +271,16 @@ static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) return ktime_sub(timer->node.expires, timer->base->get_time()); } -#ifdef CONFIG_HIGH_RES_TIMERS -struct clock_event_device; - -extern void hrtimer_interrupt(struct clock_event_device *dev); - -/* - * In high resolution mode the time reference must be read accurate - */ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } +#ifdef CONFIG_HIGH_RES_TIMERS +struct clock_event_device; + +extern void hrtimer_interrupt(struct clock_event_device *dev); + static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return timer->base->cpu_base->hres_active; @@ -295,21 +301,16 @@ extern void hrtimer_peek_ahead_timers(void); extern void clock_was_set_delayed(void); +extern unsigned int hrtimer_resolution; + #else # define MONOTONIC_RES_NSEC LOW_RES_NSEC # define KTIME_MONOTONIC_RES KTIME_LOW_RES -static inline void hrtimer_peek_ahead_timers(void) { } +#define hrtimer_resolution (unsigned int)LOW_RES_NSEC -/* - * In non high resolution mode the time reference is taken from - * the base softirq time variable. - */ -static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) -{ - return timer->base->softirq_time; -} +static inline void hrtimer_peek_ahead_timers(void) { } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { @@ -353,49 +354,47 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ -extern int hrtimer_start(struct hrtimer *timer, ktime_t tim, - const enum hrtimer_mode mode); -extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, +extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long range_ns, const enum hrtimer_mode mode); -extern int -__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, - const enum hrtimer_mode mode, int wakeup); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL) + */ +static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ + hrtimer_start_range_ns(timer, tim, 0, mode); +} extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); -static inline int hrtimer_start_expires(struct hrtimer *timer, - enum hrtimer_mode mode) +static inline void hrtimer_start_expires(struct hrtimer *timer, + enum hrtimer_mode mode) { unsigned long delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); - return hrtimer_start_range_ns(timer, soft, delta, mode); + hrtimer_start_range_ns(timer, soft, delta, mode); } -static inline int hrtimer_restart(struct hrtimer *timer) +static inline void hrtimer_restart(struct hrtimer *timer) { - return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); -extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); -extern ktime_t hrtimer_get_next_event(void); +extern u64 hrtimer_get_next_event(void); -/* - * A timer is active, when it is enqueued into the rbtree or the - * callback function is running or it's in the state of being migrated - * to another cpu. - */ -static inline int hrtimer_active(const struct hrtimer *timer) -{ - return timer->state != HRTIMER_STATE_INACTIVE; -} +extern bool hrtimer_active(const struct hrtimer *timer); /* * Helper function to check, whether the timer is on one of the queues @@ -411,14 +410,29 @@ static inline int hrtimer_is_queued(struct hrtimer *timer) */ static inline int hrtimer_callback_running(struct hrtimer *timer) { - return timer->state & HRTIMER_STATE_CALLBACK; + return timer->base->cpu_base->running == timer; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); -/* Forward a hrtimer so it expires after the hrtimer's current now */ +/** + * hrtimer_forward_now - forward the timer expiry so it expires after now + * @timer: hrtimer to forward + * @interval: the interval to forward + * + * Forward the timer expiry so it will expire after the current time + * of the hrtimer clock base. Returns the number of overruns. + * + * Can be safely called from the callback function of @timer. If + * called from other contexts @timer must neither be enqueued nor + * running the callback and the caller needs to take care of + * serialization. + * + * Note: This only updates the timer expiry value and does not requeue + * the timer. + */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { @@ -443,7 +457,6 @@ extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); -extern void hrtimer_run_pending(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); diff --git a/include/linux/htirq.h b/include/linux/htirq.h index 70a1dbbf2093..d4a527e58434 100644 --- a/include/linux/htirq.h +++ b/include/linux/htirq.h @@ -1,24 +1,38 @@ #ifndef LINUX_HTIRQ_H #define LINUX_HTIRQ_H +struct pci_dev; +struct irq_data; + struct ht_irq_msg { u32 address_lo; /* low 32 bits of the ht irq message */ u32 address_hi; /* high 32 bits of the it irq message */ }; +typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq, + struct ht_irq_msg *msg); + +struct ht_irq_cfg { + struct pci_dev *dev; + /* Update callback used to cope with buggy hardware */ + ht_irq_update_t *update; + unsigned pos; + unsigned idx; + struct ht_irq_msg msg; +}; + /* Helper functions.. */ void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg); -struct irq_data; void mask_ht_irq(struct irq_data *data); void unmask_ht_irq(struct irq_data *data); /* The arch hook for getting things started */ -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev); +int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, + ht_irq_update_t *update); +void arch_teardown_ht_irq(unsigned int irq); /* For drivers of buggy hardware */ -typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq, - struct ht_irq_msg *msg); int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update); #endif /* LINUX_HTIRQ_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 205026175c42..d891f949466a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -460,15 +460,14 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } -static inline bool hugepages_supported(void) -{ - /* - * Some platform decide whether they support huge pages at boot - * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when - * there is no such support - */ - return HPAGE_SHIFT != 0; -} +#ifndef hugepages_supported +/* + * Some platform decide whether they support huge pages at boot + * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 + * when there is no such support + */ +#define hugepages_supported() (HPAGE_SHIFT != 0) +#endif #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 3343298e40e8..859d673d98c8 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -26,6 +26,7 @@ #define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ struct device; +struct device_node; struct hwspinlock; struct hwspinlock_device; struct hwspinlock_ops; @@ -66,6 +67,7 @@ int hwspin_lock_unregister(struct hwspinlock_device *bank); struct hwspinlock *hwspin_lock_request(void); struct hwspinlock *hwspin_lock_request_specific(unsigned int id); int hwspin_lock_free(struct hwspinlock *hwlock); +int of_hwspin_lock_get_id(struct device_node *np, int index); int hwspin_lock_get_id(struct hwspinlock *hwlock); int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, unsigned long *); @@ -120,6 +122,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) { } +static inline int of_hwspin_lock_get_id(struct device_node *np, int index) +{ + return 0; +} + static inline int hwspin_lock_get_id(struct hwspinlock *hwlock) { return 0; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 902c37aef67e..30d3a1f79450 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -160,16 +160,18 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, * 1 . 1 (Windows 7) * 2 . 4 (Windows 8) * 3 . 0 (Windows 8 R2) + * 4 . 0 (Windows 10) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) #define VERSION_WIN8_1 ((3 << 16) | (0)) +#define VERSION_WIN10 ((4 << 16) | (0)) #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN8_1 +#define VERSION_CURRENT VERSION_WIN10 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -389,10 +391,7 @@ enum vmbus_channel_message_type { CHANNELMSG_INITIATE_CONTACT = 14, CHANNELMSG_VERSION_RESPONSE = 15, CHANNELMSG_UNLOAD = 16, -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD - CHANNELMSG_VIEWRANGE_ADD = 17, - CHANNELMSG_VIEWRANGE_REMOVE = 18, -#endif + CHANNELMSG_UNLOAD_RESPONSE = 17, CHANNELMSG_COUNT }; @@ -549,21 +548,6 @@ struct vmbus_channel_gpadl_torndown { u32 gpadl; } __packed; -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD -struct vmbus_channel_view_range_add { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u64 viewrange_length; - u32 child_relid; -} __packed; - -struct vmbus_channel_view_range_remove { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u32 child_relid; -} __packed; -#endif - struct vmbus_channel_relid_released { struct vmbus_channel_message_header header; u32 child_relid; @@ -713,6 +697,11 @@ struct vmbus_channel { /* The corresponding CPUID in the guest */ u32 target_cpu; /* + * State to manage the CPU affiliation of channels. + */ + struct cpumask alloced_cpus_in_node; + int numa_node; + /* * Support for sub-channels. For high performance devices, * it will be useful to have multiple sub-channels to support * a scalable communication infrastructure with the host. @@ -745,6 +734,15 @@ struct vmbus_channel { */ struct list_head sc_list; /* + * Current number of sub-channels. + */ + int num_sc; + /* + * Number of a sub-channel (position within sc_list) which is supposed + * to be used as the next outgoing channel. + */ + int next_oc; + /* * The primary channel this sub-channel belongs to. * This will be NULL for the primary channel. */ @@ -758,9 +756,6 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; - - int num_sc; - int next_oc; }; static inline void set_channel_read_state(struct vmbus_channel *c, bool state) @@ -1236,13 +1231,6 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -int hv_kvp_init(struct hv_util_service *); -void hv_kvp_deinit(void); -void hv_kvp_onchannelcallback(void *); - -int hv_vss_init(struct hv_util_service *); -void hv_vss_deinit(void); -void hv_vss_onchannelcallback(void *); void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); extern struct resource hyperv_mmio; diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index 0bc03f100d04..9ad7828d9d34 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -675,6 +675,7 @@ struct twl4030_power_data { struct twl4030_resconfig *board_config; #define TWL4030_RESCONFIG_UNDEF ((u8)-1) bool use_poweroff; /* Board is wired for TWL poweroff */ + bool ac_charger_quirk; /* Disable AC charger on board */ }; extern int twl4030_remove_script(u8 flags); diff --git a/include/linux/ide.h b/include/linux/ide.h index 93b5ca754b5b..a633898f36ac 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -39,6 +39,19 @@ struct device; +/* IDE-specific values for req->cmd_type */ +enum ata_cmd_type_bits { + REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1, + REQ_TYPE_ATA_PC, + REQ_TYPE_ATA_SENSE, /* sense request */ + REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */ + REQ_TYPE_ATA_PM_RESUME, /* resume request */ +}; + +#define ata_pm_request(rq) \ + ((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME) + /* Error codes returned in rq->errors to the higher part of the driver. */ enum { IDE_DRV_ERROR_GENERAL = 101, @@ -1314,6 +1327,19 @@ struct ide_port_info { u8 udma_mask; }; +/* + * State information carried for REQ_TYPE_ATA_PM_SUSPEND and REQ_TYPE_ATA_PM_RESUME + * requests. + */ +struct ide_pm_state { + /* PM state machine step value, currently driver specific */ + int pm_step; + /* requested PM state value (S1, S2, S3, S4, ...) */ + u32 pm_state; + void* data; /* for driver use */ +}; + + int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *); int ide_pci_init_two(struct pci_dev *, struct pci_dev *, const struct ide_port_info *, void *); @@ -1551,4 +1577,5 @@ static inline void ide_set_drivedata(ide_drive_t *drive, void *data) #define ide_host_for_each_port(i, port, host) \ for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++) + #endif /* _IDE_H */ diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 8872ca103d06..1dc1f4ed4001 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -225,15 +225,13 @@ static inline bool ieee802154_is_valid_psdu_len(const u8 len) * ieee802154_is_valid_psdu_len - check if extended addr is valid * @addr: extended addr to check */ -static inline bool ieee802154_is_valid_extended_addr(const __le64 addr) +static inline bool ieee802154_is_valid_extended_unicast_addr(const __le64 addr) { - /* These EUI-64 addresses are reserved by IEEE. 0xffffffffffffffff - * is used internally as extended to short address broadcast mapping. - * This is currently a workaround because neighbor discovery can't - * deal with short addresses types right now. + /* Bail out if the address is all zero, or if the group + * address bit is set. */ return ((addr != cpu_to_le64(0x0000000000000000ULL)) && - (addr != cpu_to_le64(0xffffffffffffffffULL))); + !(addr & cpu_to_le64(0x0100000000000000ULL))); } /** @@ -244,9 +242,9 @@ static inline void ieee802154_random_extended_addr(__le64 *addr) { get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN); - /* toggle some bit if we hit an invalid extended addr */ - if (!ieee802154_is_valid_extended_addr(*addr)) - ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] ^= 0x01; + /* clear the group bit, and set the locally administered bit */ + ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] &= ~0x01; + ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] |= 0x02; } #endif /* LINUX_IEEE802154_H */ diff --git a/include/linux/if_link.h b/include/linux/if_link.h index da4929927f69..ae5d0d22955d 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -5,6 +5,15 @@ /* We don't want this structure exposed to user space */ +struct ifla_vf_stats { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 broadcast; + __u64 multicast; +}; + struct ifla_vf_info { __u32 vf; __u8 mac[32]; diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 6f6929ea8a0c..a4ccc3122f93 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -29,7 +29,7 @@ struct macvtap_queue; * Maximum times a macvtap device can be opened. This can be used to * configure the number of receive queue, e.g. for multiqueue virtio. */ -#define MAX_MACVTAP_QUEUES 16 +#define MAX_MACVTAP_QUEUES 256 #define MACVLAN_MC_FILTER_BITS 8 #define MACVLAN_MC_FILTER_SZ (1 << MACVLAN_MC_FILTER_BITS) diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 66a7d7600f43..b49cf923becc 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -74,7 +74,7 @@ static inline struct sock *sk_pppox(struct pppox_sock *po) struct module; struct pppox_proto { - int (*create)(struct net *net, struct socket *sock); + int (*create)(struct net *net, struct socket *sock, int kern); int (*ioctl)(struct socket *sock, unsigned int cmd, unsigned long arg); struct module *owner; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 920e4457ce6e..67ce5bd3b56a 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -416,7 +416,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not of VLAN type */ @@ -435,7 +435,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if @skb->vlan_tci is not set correctly */ @@ -456,7 +456,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query - * @vlan_tci: buffer to store vlaue + * @vlan_tci: buffer to store value * * Returns error if the skb is not VLAN tagged */ @@ -539,7 +539,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, */ proto = vhdr->h_vlan_encapsulated_proto; - if (ntohs(proto) >= ETH_P_802_3_MIN) { + if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } @@ -628,4 +628,24 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, return features; } +/** + * compare_vlan_header - Compare two vlan headers + * @h1: Pointer to vlan header + * @h2: Pointer to vlan header + * + * Compare two vlan headers, returns 0 if equal. + * + * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. + */ +static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, + const struct vlan_hdr *h2) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return *(u32 *)h1 ^ *(u32 *)h2; +#else + return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | + ((__force u32)h1->h_vlan_encapsulated_proto ^ + (__force u32)h2->h_vlan_encapsulated_proto); +#endif +} #endif /* !(_LINUX_IF_VLAN_H_) */ diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 2c677afeea47..193ad488d3e2 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -130,5 +130,6 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); +int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed); #endif diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index eb8622b78ec9..1600c55828e0 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -29,6 +29,7 @@ struct iio_buffer; * @set_length: set number of datums in buffer * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @modes: Supported operating modes by this buffer type * * The purpose of this structure is to make the buffer element * modular as event for a given driver, different usecases may require @@ -51,6 +52,8 @@ struct iio_buffer_access_funcs { int (*set_length)(struct iio_buffer *buffer, int length); void (*release)(struct iio_buffer *buffer); + + unsigned int modes; }; /** diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index d86b753e9b30..f79148261d16 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -32,6 +32,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW, IIO_CHAN_INFO_AVERAGE_RAW, IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY, + IIO_CHAN_INFO_HIGH_PASS_FILTER_3DB_FREQUENCY, IIO_CHAN_INFO_SAMP_FREQ, IIO_CHAN_INFO_FREQUENCY, IIO_CHAN_INFO_PHASE, @@ -43,6 +44,8 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_CALIBWEIGHT, IIO_CHAN_INFO_DEBOUNCE_COUNT, IIO_CHAN_INFO_DEBOUNCE_TIME, + IIO_CHAN_INFO_CALIBEMISSIVITY, + IIO_CHAN_INFO_OVERSAMPLING_RATIO, }; enum iio_shared_by { diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 942b6de68e2f..32b579525004 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -17,6 +17,8 @@ enum iio_event_info { IIO_EV_INFO_VALUE, IIO_EV_INFO_HYSTERESIS, IIO_EV_INFO_PERIOD, + IIO_EV_INFO_HIGH_PASS_FILTER_3DB, + IIO_EV_INFO_LOW_PASS_FILTER_3DB, }; #define IIO_VAL_INT 1 diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index ac48b10c9395..0e707f0c1a3e 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -24,6 +24,7 @@ struct inet_diag_handler { struct inet_diag_msg *r, void *info); __u16 idiag_type; + __u16 idiag_info_size; }; struct inet_connection_sock; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 0a21fbefdfbe..a4328cea376a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -120,6 +120,9 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) +#define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ + IN_DEV_CONF_GET((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) + #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_ORCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) diff --git a/include/linux/init.h b/include/linux/init.h index 21b6d768edd7..b449f378f995 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -91,14 +91,6 @@ #define __exit __section(.exit.text) __exitused __cold notrace -/* temporary, until all users are removed */ -#define __cpuinit -#define __cpuinitdata -#define __cpuinitconst -#define __cpuexit -#define __cpuexitdata -#define __cpuexitconst - /* Used for MEMORY_HOTPLUG */ #define __meminit __section(.meminit.text) __cold notrace #define __meminitdata __section(.meminit.data) @@ -116,9 +108,6 @@ #define __INITRODATA .section ".init.rodata","a",%progbits #define __FINITDATA .previous -/* temporary, until all users are removed */ -#define __CPUINIT - #define __MEMINIT .section ".meminit.text", "ax" #define __MEMINITDATA .section ".meminit.data", "aw" #define __MEMINITRODATA .section ".meminit.rodata", "a" @@ -293,68 +282,8 @@ void __init parse_early_param(void); void __init parse_early_options(char *cmdline); #endif /* __ASSEMBLY__ */ -/** - * module_init() - driver initialization entry point - * @x: function to be run at kernel boot time or module insertion - * - * module_init() will either be called during do_initcalls() (if - * builtin) or at module insertion time (if a module). There can only - * be one per module. - */ -#define module_init(x) __initcall(x); - -/** - * module_exit() - driver exit entry point - * @x: function to be run when driver is removed - * - * module_exit() will wrap the driver clean-up code - * with cleanup_module() when used with rmmod when - * the driver is a module. If the driver is statically - * compiled into the kernel, module_exit() has no effect. - * There can only be one per module. - */ -#define module_exit(x) __exitcall(x); - #else /* MODULE */ -/* - * In most cases loadable modules do not need custom - * initcall levels. There are still some valid cases where - * a driver may be needed early if built in, and does not - * matter when built as a loadable module. Like bus - * snooping debug drivers. - */ -#define early_initcall(fn) module_init(fn) -#define core_initcall(fn) module_init(fn) -#define core_initcall_sync(fn) module_init(fn) -#define postcore_initcall(fn) module_init(fn) -#define postcore_initcall_sync(fn) module_init(fn) -#define arch_initcall(fn) module_init(fn) -#define subsys_initcall(fn) module_init(fn) -#define subsys_initcall_sync(fn) module_init(fn) -#define fs_initcall(fn) module_init(fn) -#define fs_initcall_sync(fn) module_init(fn) -#define rootfs_initcall(fn) module_init(fn) -#define device_initcall(fn) module_init(fn) -#define device_initcall_sync(fn) module_init(fn) -#define late_initcall(fn) module_init(fn) -#define late_initcall_sync(fn) module_init(fn) - -#define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) - -/* Each module must use one module_init(). */ -#define module_init(initfn) \ - static inline initcall_t __inittest(void) \ - { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); - -/* This is only required if you want to be unloadable. */ -#define module_exit(exitfn) \ - static inline exitcall_t __exittest(void) \ - { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); - #define __setup_param(str, unique_id, fn) /* nothing */ #define __setup(str, func) /* nothing */ #endif @@ -362,24 +291,6 @@ void __init parse_early_options(char *cmdline); /* Data marked not to be saved by software suspend */ #define __nosavedata __section(.data..nosave) -/* This means "can be init if no module support, otherwise module load - may call it." */ -#ifdef CONFIG_MODULES -#define __init_or_module -#define __initdata_or_module -#define __initconst_or_module -#define __INIT_OR_MODULE .text -#define __INITDATA_OR_MODULE .data -#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits -#else -#define __init_or_module __init -#define __initdata_or_module __initdata -#define __initconst_or_module __initconst -#define __INIT_OR_MODULE __INIT -#define __INITDATA_OR_MODULE __INITDATA -#define __INITRODATA_OR_MODULE __INITRODATA -#endif /*CONFIG_MODULES*/ - #ifdef MODULE #define __exit_p(x) x #else diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 696d22312b31..e8493fee8160 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,13 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; -#ifdef CONFIG_CGROUPS -#define INIT_GROUP_RWSEM(sig) \ - .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), -#else -#define INIT_GROUP_RWSEM(sig) -#endif - #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -50,13 +43,11 @@ extern struct fs_struct init_fs; .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ .cputimer = { \ - .cputime = INIT_CPUTIME, \ - .running = 0, \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = 0, \ }, \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ - INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/input/touchscreen.h b/include/linux/input/touchscreen.h index 08a5ef6e8f25..eecc9ea6cd58 100644 --- a/include/linux/input/touchscreen.h +++ b/include/linux/input/touchscreen.h @@ -12,9 +12,10 @@ #include <linux/input.h> #ifdef CONFIG_OF -void touchscreen_parse_of_params(struct input_dev *dev); +void touchscreen_parse_of_params(struct input_dev *dev, bool multitouch); #else -static inline void touchscreen_parse_of_params(struct input_dev *dev) +static inline void touchscreen_parse_of_params(struct input_dev *dev, + bool multitouch) { } #endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 796ef9645827..d9a366d24e3b 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -87,6 +87,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* * Decoding Capability Register */ +#define cap_pi_support(c) (((c) >> 59) & 1) #define cap_read_drain(c) (((c) >> 55) & 1) #define cap_write_drain(c) (((c) >> 54) & 1) #define cap_max_amask_val(c) (((c) >> 48) & 0x3f) @@ -115,13 +116,14 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) * Extended Capability Register */ +#define ecap_pasid(e) ((e >> 40) & 0x1) #define ecap_pss(e) ((e >> 35) & 0x1f) #define ecap_eafs(e) ((e >> 34) & 0x1) #define ecap_nwfs(e) ((e >> 33) & 0x1) #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) -#define ecap_pasid(e) ((e >> 28) & 0x1) +/* PASID support used to be on bit 28 */ #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) @@ -295,9 +297,12 @@ struct q_inval { /* 1MB - maximum possible interrupt remapping table size */ #define INTR_REMAP_PAGE_ORDER 8 #define INTR_REMAP_TABLE_REG_SIZE 0xf +#define INTR_REMAP_TABLE_REG_SIZE_MASK 0xf #define INTR_REMAP_TABLE_ENTRIES 65536 +struct irq_domain; + struct ir_table { struct irte *base; unsigned long *bitmap; @@ -319,6 +324,9 @@ enum { MAX_SR_DMAR_REGS }; +#define VTD_FLAG_TRANS_PRE_ENABLED (1 << 0) +#define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -347,9 +355,12 @@ struct intel_iommu { #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ + struct irq_domain *ir_domain; + struct irq_domain *ir_msi_domain; #endif struct device *iommu_dev; /* IOMMU-sysfs device */ int node; + u32 flags; /* Software defined flags */ }; static inline void __iommu_flush_cache( diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 950ae4501826..be7e75c945e9 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -413,7 +413,8 @@ enum BLOCK_IOPOLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, - HRTIMER_SOFTIRQ, + HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the + numbering. Sigh! */ RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS @@ -592,10 +593,10 @@ tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, clockid_t which_clock, enum hrtimer_mode mode); static inline -int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) +void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, + const enum hrtimer_mode mode) { - return hrtimer_start(&ttimer->timer, time, mode); + hrtimer_start(&ttimer->timer, time, mode); } static inline diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 657fab4efab3..c27dde7215b5 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -141,6 +141,7 @@ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { + preempt_disable(); pagefault_disable(); return ((char __force __iomem *) mapping) + offset; } @@ -149,6 +150,7 @@ static inline void io_mapping_unmap_atomic(void __iomem *vaddr) { pagefault_enable(); + preempt_enable(); } /* Non-atomic map/unmap */ diff --git a/include/linux/io.h b/include/linux/io.h index 986f2bffea1e..fb5a99800e77 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -19,6 +19,7 @@ #define _LINUX_IO_H #include <linux/types.h> +#include <linux/init.h> #include <asm/io.h> #include <asm/page.h> @@ -111,6 +112,13 @@ static inline void arch_phys_wc_del(int handle) } #define arch_phys_wc_add arch_phys_wc_add +#ifndef arch_phys_wc_index +static inline int arch_phys_wc_index(int handle) +{ + return -1; +} +#define arch_phys_wc_index arch_phys_wc_index +#endif #endif #endif /* _LINUX_IO_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0546b8710ce3..f9c1b6d0f2e4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -114,6 +114,20 @@ enum iommu_attr { DOMAIN_ATTR_MAX, }; +/** + * struct iommu_dm_region - descriptor for a direct mapped memory region + * @list: Linked list pointers + * @start: System physical start address of the region + * @length: Length of the region in bytes + * @prot: IOMMU Protection flags (READ/WRITE/...) + */ +struct iommu_dm_region { + struct list_head list; + phys_addr_t start; + size_t length; + int prot; +}; + #ifdef CONFIG_IOMMU_API /** @@ -159,6 +173,10 @@ struct iommu_ops { int (*domain_set_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); + /* Request/Free a list of direct mapping requirements for a device */ + void (*get_dm_regions)(struct device *dev, struct list_head *list); + void (*put_dm_regions)(struct device *dev, struct list_head *list); + /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); @@ -193,6 +211,7 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); +extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, @@ -204,6 +223,10 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); +extern void iommu_get_dm_regions(struct device *dev, struct list_head *list); +extern void iommu_put_dm_regions(struct device *dev, struct list_head *list); +extern int iommu_request_dm_for_dev(struct device *dev); + extern int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group); extern void iommu_detach_group(struct iommu_domain *domain, @@ -227,6 +250,7 @@ extern int iommu_group_unregister_notifier(struct iommu_group *group, struct notifier_block *nb); extern int iommu_group_id(struct iommu_group *group); extern struct iommu_group *iommu_group_get_for_dev(struct device *dev); +extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, void *data); @@ -234,7 +258,7 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, void *data); struct device *iommu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, - const char *fmt, ...); + const char *fmt, ...) __printf(4, 5); void iommu_device_destroy(struct device *dev); int iommu_device_link(struct device *dev, struct device *link); void iommu_device_unlink(struct device *dev, struct device *link); @@ -332,6 +356,11 @@ static inline void iommu_detach_device(struct iommu_domain *domain, { } +static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) +{ + return NULL; +} + static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, int gfp_order, int prot) { @@ -373,6 +402,21 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } +static inline void iommu_get_dm_regions(struct device *dev, + struct list_head *list) +{ +} + +static inline void iommu_put_dm_regions(struct device *dev, + struct list_head *list) +{ +} + +static inline int iommu_request_dm_for_dev(struct device *dev) +{ + return -ENODEV; +} + static inline int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { diff --git a/include/linux/irq.h b/include/linux/irq.h index 62c6901cab55..92188b0225bb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -126,13 +126,21 @@ struct msi_desc; struct irq_domain; /** - * struct irq_data - per irq and irq chip data passed down to chip functions + * struct irq_common_data - per irq data shared by all irqchips + * @state_use_accessors: status information for irq chip functions. + * Use accessor functions to deal with it + */ +struct irq_common_data { + unsigned int state_use_accessors; +}; + +/** + * struct irq_data - per irq chip data passed down to chip functions * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain * @node: node index useful for balancing - * @state_use_accessors: status information for irq chip functions. - * Use accessor functions to deal with it + * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping * between hwirq number and linux irq number. @@ -153,7 +161,7 @@ struct irq_data { unsigned int irq; unsigned long hwirq; unsigned int node; - unsigned int state_use_accessors; + struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY @@ -166,7 +174,7 @@ struct irq_data { }; /* - * Bit masks for irq_data.state + * Bit masks for irq_common_data.state_use_accessors * * IRQD_TRIGGER_MASK - Mask for the trigger type bits * IRQD_SETAFFINITY_PENDING - Affinity setting is pending @@ -198,34 +206,36 @@ enum { IRQD_WAKEUP_ARMED = (1 << 19), }; +#define __irqd_to_state(d) ((d)->common->state_use_accessors) + static inline bool irqd_is_setaffinity_pending(struct irq_data *d) { - return d->state_use_accessors & IRQD_SETAFFINITY_PENDING; + return __irqd_to_state(d) & IRQD_SETAFFINITY_PENDING; } static inline bool irqd_is_per_cpu(struct irq_data *d) { - return d->state_use_accessors & IRQD_PER_CPU; + return __irqd_to_state(d) & IRQD_PER_CPU; } static inline bool irqd_can_balance(struct irq_data *d) { - return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING)); + return !(__irqd_to_state(d) & (IRQD_PER_CPU | IRQD_NO_BALANCING)); } static inline bool irqd_affinity_was_set(struct irq_data *d) { - return d->state_use_accessors & IRQD_AFFINITY_SET; + return __irqd_to_state(d) & IRQD_AFFINITY_SET; } static inline void irqd_mark_affinity_was_set(struct irq_data *d) { - d->state_use_accessors |= IRQD_AFFINITY_SET; + __irqd_to_state(d) |= IRQD_AFFINITY_SET; } static inline u32 irqd_get_trigger_type(struct irq_data *d) { - return d->state_use_accessors & IRQD_TRIGGER_MASK; + return __irqd_to_state(d) & IRQD_TRIGGER_MASK; } /* @@ -233,43 +243,43 @@ static inline u32 irqd_get_trigger_type(struct irq_data *d) */ static inline void irqd_set_trigger_type(struct irq_data *d, u32 type) { - d->state_use_accessors &= ~IRQD_TRIGGER_MASK; - d->state_use_accessors |= type & IRQD_TRIGGER_MASK; + __irqd_to_state(d) &= ~IRQD_TRIGGER_MASK; + __irqd_to_state(d) |= type & IRQD_TRIGGER_MASK; } static inline bool irqd_is_level_type(struct irq_data *d) { - return d->state_use_accessors & IRQD_LEVEL; + return __irqd_to_state(d) & IRQD_LEVEL; } static inline bool irqd_is_wakeup_set(struct irq_data *d) { - return d->state_use_accessors & IRQD_WAKEUP_STATE; + return __irqd_to_state(d) & IRQD_WAKEUP_STATE; } static inline bool irqd_can_move_in_process_context(struct irq_data *d) { - return d->state_use_accessors & IRQD_MOVE_PCNTXT; + return __irqd_to_state(d) & IRQD_MOVE_PCNTXT; } static inline bool irqd_irq_disabled(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_DISABLED; + return __irqd_to_state(d) & IRQD_IRQ_DISABLED; } static inline bool irqd_irq_masked(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_MASKED; + return __irqd_to_state(d) & IRQD_IRQ_MASKED; } static inline bool irqd_irq_inprogress(struct irq_data *d) { - return d->state_use_accessors & IRQD_IRQ_INPROGRESS; + return __irqd_to_state(d) & IRQD_IRQ_INPROGRESS; } static inline bool irqd_is_wakeup_armed(struct irq_data *d) { - return d->state_use_accessors & IRQD_WAKEUP_ARMED; + return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } @@ -280,12 +290,12 @@ static inline bool irqd_is_wakeup_armed(struct irq_data *d) */ static inline void irqd_set_chained_irq_inprogress(struct irq_data *d) { - d->state_use_accessors |= IRQD_IRQ_INPROGRESS; + __irqd_to_state(d) |= IRQD_IRQ_INPROGRESS; } static inline void irqd_clr_chained_irq_inprogress(struct irq_data *d) { - d->state_use_accessors &= ~IRQD_IRQ_INPROGRESS; + __irqd_to_state(d) &= ~IRQD_IRQ_INPROGRESS; } static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) @@ -327,6 +337,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_write_msi_msg: optional to write message content for MSI * @irq_get_irqchip_state: return the internal state of an interrupt * @irq_set_irqchip_state: set the internal state of a interrupt + * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine * @flags: chip specific flags */ struct irq_chip { @@ -369,6 +380,8 @@ struct irq_chip { int (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state); int (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state); + int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info); + unsigned long flags; }; @@ -394,7 +407,6 @@ enum { IRQCHIP_EOI_THREADED = (1 << 6), }; -/* This include will go away once we isolated irq_desc usage to core code */ #include <linux/irqdesc.h> /* @@ -422,6 +434,7 @@ extern void irq_cpu_online(void); extern void irq_cpu_offline(void); extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); +extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) void irq_move_irq(struct irq_data *data); @@ -458,6 +471,8 @@ extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern void irq_chip_enable_parent(struct irq_data *data); +extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); extern int irq_chip_retrigger_hierarchy(struct irq_data *data); extern void irq_chip_mask_parent(struct irq_data *data); @@ -467,6 +482,8 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data, const struct cpumask *dest, bool force); extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on); +extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, + void *vcpu_info); #endif /* Handling of unhandled and spurious interrupts: */ @@ -517,6 +534,15 @@ irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle) __irq_set_handler(irq, handle, 1, NULL); } +/* + * Set a highlevel chained flow handler and its data for a given IRQ. + * (a chained handler is automatically enabled and set to + * IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD) + */ +void +irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, + void *data); + void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set); static inline void irq_set_status_flags(unsigned int irq, unsigned long set) @@ -624,6 +650,23 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } +static inline int irq_data_get_node(struct irq_data *d) +{ + return d->node; +} + +static inline struct cpumask *irq_get_affinity_mask(int irq) +{ + struct irq_data *d = irq_get_irq_data(irq); + + return d ? d->affinity : NULL; +} + +static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) +{ + return d->affinity; +} + unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 14d79131f53d..638887376e58 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -11,6 +11,20 @@ #ifndef _LINUX_IRQCHIP_H #define _LINUX_IRQCHIP_H +#include <linux/of.h> + +/* + * This macro must be used by the different irqchip drivers to declare + * the association between their DT compatible string and their + * initialization function. + * + * @name: name that must be unique accross all IRQCHIP_DECLARE of the + * same file. + * @compstr: compatible string of the irqchip driver + * @fn: initialization function + */ +#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) + #ifdef CONFIG_IRQCHIP void irqchip_init(void); #else diff --git a/include/linux/irqchip/ingenic.h b/include/linux/irqchip/ingenic.h new file mode 100644 index 000000000000..0ee319a4029d --- /dev/null +++ b/include/linux/irqchip/ingenic.h @@ -0,0 +1,23 @@ +/* + * Copyright (C) 2010, Lars-Peter Clausen <lars@metafoo.de> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __LINUX_IRQCHIP_INGENIC_H__ +#define __LINUX_IRQCHIP_INGENIC_H__ + +#include <linux/irq.h> + +extern void ingenic_intc_irq_suspend(struct irq_data *data); +extern void ingenic_intc_irq_resume(struct irq_data *data); + +#endif diff --git a/include/linux/irqchip/irq-sa11x0.h b/include/linux/irqchip/irq-sa11x0.h new file mode 100644 index 000000000000..15db6829c1e4 --- /dev/null +++ b/include/linux/irqchip/irq-sa11x0.h @@ -0,0 +1,17 @@ +/* + * Generic IRQ handling for the SA11x0. + * + * Copyright (C) 2015 Dmitry Eremin-Solenikov + * Copyright (C) 1999-2001 Nicolas Pitre + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_SA11x0_H +#define __INCLUDE_LINUX_IRQCHIP_IRQ_SA11x0_H + +void __init sa11x0_init_irq_nodt(int irq_start, resource_size_t io_start); + +#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index dd1109fb241e..fcea4e48e21f 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -3,9 +3,6 @@ /* * Core internal functions to deal with irq descriptors - * - * This include will move to kernel/irq once we cleaned up the tree. - * For now it's included from <linux/irq.h> */ struct irq_affinity_notify; @@ -17,7 +14,7 @@ struct pt_regs; /** * struct irq_desc - interrupt descriptor - * @irq_data: per irq and chip data passed down to chip functions + * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu * @handle_irq: highlevel irq-events handler * @preflow_handler: handler called before the flow handler (currently used by sparc) @@ -47,6 +44,7 @@ struct pt_regs; * @name: flow handler name for /proc/interrupts output */ struct irq_desc { + struct irq_common_data irq_common_data; struct irq_data irq_data; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; @@ -89,10 +87,29 @@ struct irq_desc { const char *name; } ____cacheline_internodealigned_in_smp; -#ifndef CONFIG_SPARSE_IRQ +#ifdef CONFIG_SPARSE_IRQ +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } extern struct irq_desc irq_desc[NR_IRQS]; #endif +static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) +{ +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + return irq_to_desc(data->irq); +#else + return container_of(data, struct irq_desc, irq_data); +#endif +} + +static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) +{ + return desc->irq_data.irq; +} + static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc) { return &desc->irq_data; @@ -178,6 +195,47 @@ __irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip, desc->name = name; } +/** + * irq_set_handler_locked - Set irq handler from a locked region + * @data: Pointer to the irq_data structure which identifies the irq + * @handler: Flow control handler function for this interrupt + * + * Sets the handler in the irq descriptor associated to @data. + * + * Must be called with irq_desc locked and valid parameters. Typical + * call site is the irq_set_type() callback. + */ +static inline void irq_set_handler_locked(struct irq_data *data, + irq_flow_handler_t handler) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + desc->handle_irq = handler; +} + +/** + * irq_set_chip_handler_name_locked - Set chip, handler and name from a locked region + * @data: Pointer to the irq_data structure for which the chip is set + * @chip: Pointer to the new irq chip + * @handler: Flow control handler function for this interrupt + * @name: Name of the interrupt + * + * Replace the irq chip at the proper hierarchy level in @data and + * sets the handler and name in the associated irq descriptor. + * + * Must be called with irq_desc locked and valid parameters. + */ +static inline void +irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip, + irq_flow_handler_t handler, const char *name) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + desc->handle_irq = handler; + desc->name = name; + data->chip = chip; +} + static inline int irq_balancing_disabled(unsigned int irq) { struct irq_desc *desc; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 676d7306a360..744ac0ec98eb 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -258,6 +258,10 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr, /* V2 interfaces to support hierarchy IRQ domains. */ extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); +extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, @@ -281,10 +285,6 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data); -extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, - void *chip_data, irq_flow_handler_t handler, - void *handler_data, const char *handler_name); extern void irq_domain_reset_irq_data(struct irq_data *irq_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index fdd5cc16c9c4..9669bf9d4f48 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -23,12 +23,6 @@ unsigned int irq_get_next_irq(unsigned int offset); ; \ else -#ifdef CONFIG_SMP -#define irq_node(irq) (irq_get_irq_data(irq)->node) -#else -#define irq_node(irq) 0 -#endif - # define for_each_active_irq(irq) \ for (irq = irq_get_next_irq(0); irq < nr_irqs; \ irq = irq_get_next_irq(irq + 1)) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 20e7f78041c8..edb640ae9a94 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1035,7 +1035,7 @@ struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); -void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ @@ -1157,7 +1157,7 @@ extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); -extern void jbd2_journal_update_sb_log_tail (journal_t *, tid_t, +extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); extern void __jbd2_journal_abort_hard (journal_t *); extern void jbd2_journal_abort (journal_t *, int); diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index c367cbdf73ab..535fd3bb1ba8 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -7,6 +7,7 @@ #include <linux/time.h> #include <linux/timex.h> #include <asm/param.h> /* for HZ */ +#include <generated/timeconst.h> /* * The following defines establish the engineering parameters of the PLL @@ -288,8 +289,133 @@ static inline u64 jiffies_to_nsecs(const unsigned long j) return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } -extern unsigned long msecs_to_jiffies(const unsigned int m); -extern unsigned long usecs_to_jiffies(const unsigned int u); +extern unsigned long __msecs_to_jiffies(const unsigned int m); +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) +/* + * HZ is equal to or smaller than 1000, and 1000 is a nice round + * multiple of HZ, divide with the factor between them, but round + * upwards: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); +} +#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) +/* + * HZ is larger than 1000, and HZ is a nice round multiple of 1000 - + * simply multiply with the factor between them. + * + * But first make sure the multiplication result cannot overflow: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + return m * (HZ / MSEC_PER_SEC); +} +#else +/* + * Generic case - multiply, round and divide. But first check that if + * we are doing a net multiplication, that we wouldn't overflow: + */ +static inline unsigned long _msecs_to_jiffies(const unsigned int m) +{ + if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + + return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32; +} +#endif +/** + * msecs_to_jiffies: - convert milliseconds to jiffies + * @m: time in milliseconds + * + * conversion is done as follows: + * + * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) + * + * - 'too large' values [that would result in larger than + * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. + * + * - all other values are converted to jiffies by either multiplying + * the input value by a factor or dividing it with a factor and + * handling any 32-bit overflows. + * for the details see __msecs_to_jiffies() + * + * msecs_to_jiffies() checks for the passed in value being a constant + * via __builtin_constant_p() allowing gcc to eliminate most of the + * code, __msecs_to_jiffies() is called if the value passed does not + * allow constant folding and the actual conversion must be done at + * runtime. + * the HZ range specific helpers _msecs_to_jiffies() are called both + * directly here and from __msecs_to_jiffies() in the case where + * constant folding is not possible. + */ +static inline unsigned long msecs_to_jiffies(const unsigned int m) +{ + if (__builtin_constant_p(m)) { + if ((int)m < 0) + return MAX_JIFFY_OFFSET; + return _msecs_to_jiffies(m); + } else { + return __msecs_to_jiffies(m); + } +} + +extern unsigned long __usecs_to_jiffies(const unsigned int u); +#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ + return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); +} +#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ + return u * (HZ / USEC_PER_SEC); +} +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ +#else +static inline unsigned long _usecs_to_jiffies(const unsigned int u) +{ + return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) + >> USEC_TO_HZ_SHR32; +} +#endif + +/** + * usecs_to_jiffies: - convert microseconds to jiffies + * @u: time in microseconds + * + * conversion is done as follows: + * + * - 'too large' values [that would result in larger than + * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. + * + * - all other values are converted to jiffies by either multiplying + * the input value by a factor or dividing it with a factor and + * handling any 32-bit overflows as for msecs_to_jiffies. + * + * usecs_to_jiffies() checks for the passed in value being a constant + * via __builtin_constant_p() allowing gcc to eliminate most of the + * code, __usecs_to_jiffies() is called if the value passed does not + * allow constant folding and the actual conversion must be done at + * runtime. + * the HZ range specific helpers _usecs_to_jiffies() are called both + * directly here and from __msecs_to_jiffies() in the case where + * constant folding is not possible. + */ +static inline unsigned long usecs_to_jiffies(const unsigned int u) +{ + if (__builtin_constant_p(u)) { + if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) + return MAX_JIFFY_OFFSET; + return _usecs_to_jiffies(u); + } else { + return __usecs_to_jiffies(u); + } +} + extern unsigned long timespec_to_jiffies(const struct timespec *value); extern void jiffies_to_timespec(const unsigned long jiffies, struct timespec *value); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3a5b48e52a9e..5582410727cb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -244,7 +244,8 @@ static inline u32 reciprocal_scale(u32 val, u32 ep_ro) #if defined(CONFIG_MMU) && \ (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) -void might_fault(void); +#define might_fault() __might_fault(__FILE__, __LINE__) +void __might_fault(const char *file, int line); #else static inline void might_fault(void) { } #endif @@ -410,7 +411,8 @@ extern __printf(3, 0) int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); extern __printf(2, 3) char *kasprintf(gfp_t gfp, const char *fmt, ...); -extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); +extern __printf(2, 0) +char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); extern __scanf(2, 3) int sscanf(const char *, const char *, ...); @@ -438,6 +440,9 @@ extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. @@ -532,12 +537,6 @@ bool mac_pton(const char *s, u8 *mac); * * Most likely, you want to use tracing_on/tracing_off. */ -#ifdef CONFIG_RING_BUFFER -/* trace_off_permanent stops recording with no way to bring it back */ -void tracing_off_permanent(void); -#else -static inline void tracing_off_permanent(void) { } -#endif enum ftrace_dump_mode { DUMP_NONE, @@ -681,10 +680,10 @@ do { \ __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ } while (0) -extern int +extern __printf(2, 0) int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); -extern int +extern __printf(2, 0) int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); @@ -704,7 +703,7 @@ int trace_printk(const char *fmt, ...) { return 0; } -static inline int +static __printf(1, 0) inline int ftrace_vprintk(const char *fmt, va_list ap) { return 0; @@ -818,13 +817,15 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */ -#define VERIFY_OCTAL_PERMISSIONS(perms) \ - (BUILD_BUG_ON_ZERO((perms) < 0) + \ - BUILD_BUG_ON_ZERO((perms) > 0777) + \ - /* User perms >= group perms >= other perms */ \ - BUILD_BUG_ON_ZERO(((perms) >> 6) < (((perms) >> 3) & 7)) + \ - BUILD_BUG_ON_ZERO((((perms) >> 3) & 7) < ((perms) & 7)) + \ - /* Other writable? Generally considered a bad idea. */ \ - BUILD_BUG_ON_ZERO((perms) & 2) + \ +#define VERIFY_OCTAL_PERMISSIONS(perms) \ + (BUILD_BUG_ON_ZERO((perms) < 0) + \ + BUILD_BUG_ON_ZERO((perms) > 0777) + \ + /* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \ + BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \ + /* USER_WRITABLE >= GROUP_WRITABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \ + /* OTHER_WRITABLE? Generally considered a bad idea. */ \ + BUILD_BUG_ON_ZERO((perms) & 2) + \ (perms)) #endif diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 71ecdab1671b..123be25ea15a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -45,6 +45,7 @@ enum kernfs_node_flag { KERNFS_LOCKDEP = 0x0100, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, + KERNFS_EMPTY_DIR = 0x1000, }; /* @flags for kernfs_create_root() */ @@ -277,6 +278,7 @@ void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); +struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); @@ -285,6 +287,8 @@ void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, void *priv, const void *ns); +struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, + const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, @@ -352,6 +356,10 @@ static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } +static inline struct inode * +kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) +{ return NULL; } + static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index e705467ddb47..d0a1f99e24e3 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -28,7 +28,8 @@ extern void kmemleak_init(void) __ref; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; -extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref; +extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, + gfp_t gfp) __ref; extern void kmemleak_free(const void *ptr) __ref; extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; @@ -71,7 +72,8 @@ static inline void kmemleak_alloc_recursive(const void *ptr, size_t size, gfp_t gfp) { } -static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) +static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, + gfp_t gfp) { } static inline void kmemleak_free(const void *ptr) diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 2d61b909f414..637f67002c5a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -80,8 +80,9 @@ struct kobject { extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +extern __printf(2, 0) +int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, + va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 5fc3d1083071..2b6a204bd8d4 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -166,19 +166,34 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) } #if BITS_PER_LONG < 64 -extern u64 __ktime_divns(const ktime_t kt, s64 div); -static inline u64 ktime_divns(const ktime_t kt, s64 div) +extern s64 __ktime_divns(const ktime_t kt, s64 div); +static inline s64 ktime_divns(const ktime_t kt, s64 div) { + /* + * Negative divisors could cause an inf loop, + * so bug out here. + */ + BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { - u64 ns = kt.tv64; - do_div(ns, div); - return ns; + s64 ns = kt.tv64; + u64 tmp = ns < 0 ? -ns : ns; + + do_div(tmp, div); + return ns < 0 ? -tmp : tmp; } else { return __ktime_divns(kt, div); } } #else /* BITS_PER_LONG < 64 */ -# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) +static inline s64 ktime_divns(const ktime_t kt, s64 div) +{ + /* + * 32-bit implementation cannot handle negative divisors, + * so catch them on 64bit as well. + */ + WARN_ON(div < 0); + return kt.tv64 / div; +} #endif static inline s64 ktime_to_us(const ktime_t kt) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ad45054309a0..05e99b8ef465 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -44,6 +44,10 @@ /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 +#ifndef KVM_ADDRESS_SPACE_NUM +#define KVM_ADDRESS_SPACE_NUM 1 +#endif + /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, @@ -134,6 +138,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_ENABLE_IBS 23 #define KVM_REQ_DISABLE_IBS 24 #define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_SMI 26 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -230,6 +235,7 @@ struct kvm_vcpu { int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; + unsigned char fpu_counter; wait_queue_head_t wq; struct pid *pid; int sigset_active; @@ -329,6 +335,13 @@ struct kvm_kernel_irq_routing_entry { #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif +#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif + /* * Note: * memslots are not sorted by id anymore, please use id_to_memslot() @@ -347,7 +360,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots; + struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; struct srcu_struct srcu; struct srcu_struct irq_srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE @@ -462,13 +475,25 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots, + return rcu_dereference_check(kvm->memslots[as_id], srcu_read_lock_held(&kvm->srcu) || lockdep_is_held(&kvm->slots_lock)); } +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return __kvm_memslots(kvm, 0); +} + +static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) +{ + int as_id = kvm_arch_vcpu_memslots_id(vcpu); + + return __kvm_memslots(vcpu->kvm, as_id); +} + static inline struct kvm_memory_slot * id_to_memslot(struct kvm_memslots *slots, int id) { @@ -500,21 +525,22 @@ enum kvm_mr_change { }; int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages); -void kvm_arch_memslots_updated(struct kvm *kvm); +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); @@ -524,8 +550,8 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages); +int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); @@ -538,13 +564,13 @@ void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); @@ -573,6 +599,25 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, + int len); +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, + unsigned long len); +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, + int offset, int len); +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len); +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); + void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); @@ -689,6 +734,24 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) return false; } #endif +#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE +void kvm_arch_start_assignment(struct kvm *kvm); +void kvm_arch_end_assignment(struct kvm *kvm); +bool kvm_arch_has_assigned_device(struct kvm *kvm); +#else +static inline void kvm_arch_start_assignment(struct kvm *kvm) +{ +} + +static inline void kvm_arch_end_assignment(struct kvm *kvm) +{ +} + +static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return false; +} +#endif static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { @@ -762,16 +825,10 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, } #endif -static inline void kvm_guest_enter(void) +/* must be called with irqs disabled */ +static inline void __kvm_guest_enter(void) { - unsigned long flags; - - BUG_ON(preemptible()); - - local_irq_save(flags); guest_enter(); - local_irq_restore(flags); - /* KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In @@ -783,12 +840,27 @@ static inline void kvm_guest_enter(void) rcu_virt_note_context_switch(smp_processor_id()); } +/* must be called with irqs disabled */ +static inline void __kvm_guest_exit(void) +{ + guest_exit(); +} + +static inline void kvm_guest_enter(void) +{ + unsigned long flags; + + local_irq_save(flags); + __kvm_guest_enter(); + local_irq_restore(flags); +} + static inline void kvm_guest_exit(void) { unsigned long flags; local_irq_save(flags); - guest_exit(); + __kvm_guest_exit(); local_irq_restore(flags); } diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 931da7e917cf..1b47a185c2f0 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -28,6 +28,7 @@ struct kvm_run; struct kvm_userspace_memory_region; struct kvm_vcpu; struct kvm_vcpu_init; +struct kvm_memslots; enum kvm_mr_change; diff --git a/include/linux/leds.h b/include/linux/leds.h index 9a2b000094cf..b122eeafb5dc 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -12,6 +12,7 @@ #ifndef __LINUX_LEDS_H_INCLUDED #define __LINUX_LEDS_H_INCLUDED +#include <linux/device.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> @@ -222,6 +223,11 @@ struct led_trigger { struct list_head next_trig; }; +ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count); +ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, + char *buf); + /* Registration functions for complex triggers */ extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); @@ -238,6 +244,16 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger, unsigned long *delay_on, unsigned long *delay_off, int invert); +extern void led_trigger_set_default(struct led_classdev *led_cdev); +extern void led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger); +extern void led_trigger_remove(struct led_classdev *led_cdev); + +static inline void *led_get_trigger_data(struct led_classdev *led_cdev) +{ + return led_cdev->trigger_data; +} + /** * led_trigger_rename_static - rename a trigger * @name: the new trigger name @@ -267,6 +283,15 @@ static inline void led_trigger_register_simple(const char *name, static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} static inline void led_trigger_event(struct led_trigger *trigger, enum led_brightness event) {} +static inline void led_trigger_set_default(struct led_classdev *led_cdev) {} +static inline void led_trigger_set(struct led_classdev *led_cdev, + struct led_trigger *trigger) {} +static inline void led_trigger_remove(struct led_classdev *led_cdev) {} +static inline void *led_get_trigger_data(struct led_classdev *led_cdev) +{ + return NULL; +} + #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific functions */ diff --git a/include/linux/lglock.h b/include/linux/lglock.h index 0081f000e34b..c92ebd100d9b 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -52,10 +52,15 @@ struct lglock { static struct lglock name = { .lock = &name ## _lock } void lg_lock_init(struct lglock *lg, char *name); + void lg_local_lock(struct lglock *lg); void lg_local_unlock(struct lglock *lg); void lg_local_lock_cpu(struct lglock *lg, int cpu); void lg_local_unlock_cpu(struct lglock *lg, int cpu); + +void lg_double_lock(struct lglock *lg, int cpu1, int cpu2); +void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2); + void lg_global_lock(struct lglock *lg); void lg_global_unlock(struct lglock *lg); diff --git a/include/linux/libata.h b/include/linux/libata.h index 8dad4a307bb8..c9cfbcdb8d14 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -134,7 +134,6 @@ enum { ATA_ALL_DEVICES = (1 << ATA_MAX_DEVICES) - 1, ATA_SHT_EMULATED = 1, - ATA_SHT_CMD_PER_LUN = 1, ATA_SHT_THIS_ID = -1, ATA_SHT_USE_CLUSTERING = 1, @@ -205,6 +204,7 @@ enum { ATA_LFLAG_SW_ACTIVITY = (1 << 7), /* keep activity stats */ ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ + ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -309,6 +309,12 @@ enum { */ ATA_TMOUT_PMP_SRST_WAIT = 5000, + /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might + * be a spurious PHY event, so ignore the first PHY event that + * occurs within 10s after the policy change. + */ + ATA_TMOUT_SPURIOUS_PHY = 10000, + /* ATA bus states */ BUS_UNKNOWN = 0, BUS_DMA = 1, @@ -424,6 +430,9 @@ enum { ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ + ATA_HORKAGE_NO_NCQ_LOG = (1 << 23), /* don't use NCQ for log read */ + ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ + ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ @@ -788,6 +797,8 @@ struct ata_link { struct ata_eh_context eh_context; struct ata_device device[ATA_MAX_DEVICES]; + + unsigned long last_lpm_change; /* when last LPM change happened */ }; #define ATA_LINK_CLEAR_BEGIN offsetof(struct ata_link, active_tag) #define ATA_LINK_CLEAR_END offsetof(struct ata_link, device[0]) @@ -1201,6 +1212,7 @@ extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q); +extern bool sata_lpm_ignore_phy_events(struct ata_link *link); extern int ata_cable_40wire(struct ata_port *ap); extern int ata_cable_80wire(struct ata_port *ap); @@ -1354,7 +1366,6 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ - .cmd_per_lun = ATA_SHT_CMD_PER_LUN, \ .emulated = ATA_SHT_EMULATED, \ .use_clustering = ATA_SHT_USE_CLUSTERING, \ .proc_name = drv_name, \ diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index 01508c7b8c81..2a663c6bb428 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -5,6 +5,10 @@ #include <asm/byteorder.h> +typedef __be16 fdt16_t; +typedef __be32 fdt32_t; +typedef __be64 fdt64_t; + #define fdt32_to_cpu(x) be32_to_cpu(x) #define cpu_to_fdt32(x) cpu_to_be32(x) #define fdt64_to_cpu(x) be64_to_cpu(x) diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h new file mode 100644 index 000000000000..75e3af01ee32 --- /dev/null +++ b/include/linux/libnvdimm.h @@ -0,0 +1,151 @@ +/* + * libnvdimm - Non-volatile-memory Devices Subsystem + * + * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __LIBNVDIMM_H__ +#define __LIBNVDIMM_H__ +#include <linux/kernel.h> +#include <linux/sizes.h> +#include <linux/types.h> + +enum { + /* when a dimm supports both PMEM and BLK access a label is required */ + NDD_ALIASING = 1 << 0, + /* unarmed memory devices may not persist writes */ + NDD_UNARMED = 1 << 1, + + /* need to set a limit somewhere, but yes, this is likely overkill */ + ND_IOCTL_MAX_BUFLEN = SZ_4M, + ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ENVELOPE = 16, + ND_CMD_ARS_STATUS_MAX = SZ_4K, + ND_MAX_MAPPINGS = 32, + + /* mark newly adjusted resources as requiring a label update */ + DPA_RESOURCE_ADJUSTED = 1 << 0, +}; + +extern struct attribute_group nvdimm_bus_attribute_group; +extern struct attribute_group nvdimm_attribute_group; +extern struct attribute_group nd_device_attribute_group; +extern struct attribute_group nd_numa_attribute_group; +extern struct attribute_group nd_region_attribute_group; +extern struct attribute_group nd_mapping_attribute_group; + +struct nvdimm; +struct nvdimm_bus_descriptor; +typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, + struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len); + +struct nd_namespace_label; +struct nvdimm_drvdata; +struct nd_mapping { + struct nvdimm *nvdimm; + struct nd_namespace_label **labels; + u64 start; + u64 size; + /* + * @ndd is for private use at region enable / disable time for + * get_ndd() + put_ndd(), all other nd_mapping to ndd + * conversions use to_ndd() which respects enabled state of the + * nvdimm. + */ + struct nvdimm_drvdata *ndd; +}; + +struct nvdimm_bus_descriptor { + const struct attribute_group **attr_groups; + unsigned long dsm_mask; + char *provider_name; + ndctl_fn ndctl; +}; + +struct nd_cmd_desc { + int in_num; + int out_num; + u32 in_sizes[ND_CMD_MAX_ELEM]; + int out_sizes[ND_CMD_MAX_ELEM]; +}; + +struct nd_interleave_set { + u64 cookie; +}; + +struct nd_region_desc { + struct resource *res; + struct nd_mapping *nd_mapping; + u16 num_mappings; + const struct attribute_group **attr_groups; + struct nd_interleave_set *nd_set; + void *provider_data; + int num_lanes; + int numa_node; +}; + +struct nvdimm_bus; +struct module; +struct device; +struct nd_blk_region; +struct nd_blk_region_desc { + int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + void (*disable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); + int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, + void *iobuf, u64 len, int rw); + struct nd_region_desc ndr_desc; +}; + +static inline struct nd_blk_region_desc *to_blk_region_desc( + struct nd_region_desc *ndr_desc) +{ + return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); + +} + +struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, + struct nvdimm_bus_descriptor *nfit_desc, struct module *module); +#define nvdimm_bus_register(parent, desc) \ + __nvdimm_bus_register(parent, desc, THIS_MODULE) +void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus); +struct nvdimm_bus *to_nvdimm_bus(struct device *dev); +struct nvdimm *to_nvdimm(struct device *dev); +struct nd_region *to_nd_region(struct device *dev); +struct nd_blk_region *to_nd_blk_region(struct device *dev); +struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); +const char *nvdimm_name(struct nvdimm *nvdimm); +void *nvdimm_provider_data(struct nvdimm *nvdimm); +struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, + const struct attribute_group **groups, unsigned long flags, + unsigned long *dsm_mask); +const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); +const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); +u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, void *buf); +u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, + const struct nd_cmd_desc *desc, int idx, const u32 *in_field, + const u32 *out_field); +int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count); +struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, + struct nd_region_desc *ndr_desc); +void *nd_region_provider_data(struct nd_region *nd_region); +void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); +void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); +struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); +unsigned int nd_region_acquire_lane(struct nd_region *nd_region); +void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); +u64 nd_fletcher64(void *addr, size_t len, bool le); +#endif /* __LIBNVDIMM_H__ */ diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index ee6dbb39a809..31db7a05dd36 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -99,7 +99,7 @@ struct klp_object { struct klp_func *funcs; /* internal */ - struct kobject *kobj; + struct kobject kobj; struct module *mod; enum klp_state state; }; @@ -123,6 +123,12 @@ struct klp_patch { enum klp_state state; }; +#define klp_for_each_object(patch, obj) \ + for (obj = patch->objs; obj->funcs; obj++) + +#define klp_for_each_func(obj, func) \ + for (func = obj->funcs; func->old_name; func++) + int klp_register_patch(struct klp_patch *); int klp_unregister_patch(struct klp_patch *); int klp_enable_patch(struct klp_patch *); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 066ba4157541..70400dc7660f 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -130,8 +130,8 @@ enum bounce_type { }; struct lock_class_stats { - unsigned long contention_point[4]; - unsigned long contending_point[4]; + unsigned long contention_point[LOCKSTAT_POINTS]; + unsigned long contending_point[LOCKSTAT_POINTS]; struct lock_time read_waittime; struct lock_time write_waittime; struct lock_time read_holdtime; @@ -255,6 +255,7 @@ struct held_lock { unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ + unsigned int pin_count; }; /* @@ -354,6 +355,9 @@ extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); extern void lockdep_clear_current_reclaim_state(void); extern void lockdep_trace_alloc(gfp_t mask); +extern void lock_pin_lock(struct lockdep_map *lock); +extern void lock_unpin_lock(struct lockdep_map *lock); + # define INIT_LOCKDEP .lockdep_recursion = 0, .lockdep_reclaim_gfp = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -368,6 +372,9 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) +#define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) +#define lockdep_unpin_lock(l) lock_unpin_lock(&(l)->dep_map) + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_off(void) @@ -420,6 +427,9 @@ struct lock_class_key { }; #define lockdep_recursing(tsk) (0) +#define lockdep_pin_lock(l) do { (void)(l); } while (0) +#define lockdep_unpin_lock(l) do { (void)(l); } while (0) + #endif /* !LOCKDEP */ #ifdef CONFIG_LOCK_STAT diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h new file mode 100644 index 000000000000..9429f054c323 --- /dev/null +++ b/include/linux/lsm_hooks.h @@ -0,0 +1,1888 @@ +/* + * Linux Security Module interfaces + * + * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> + * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> + * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> + * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) + * Copyright (C) 2015 Intel Corporation. + * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Due to this file being licensed under the GPL there is controversy over + * whether this permits you to write a module that #includes this file + * without placing your module under the GPL. Please consult a lawyer for + * advice before doing this. + * + */ + +#ifndef __LINUX_LSM_HOOKS_H +#define __LINUX_LSM_HOOKS_H + +#include <linux/security.h> +#include <linux/init.h> +#include <linux/rculist.h> + +/** + * Security hooks for program execution operations. + * + * @bprm_set_creds: + * Save security information in the bprm->security field, typically based + * on information about the bprm->file, for later use by the apply_creds + * hook. This hook may also optionally check permissions (e.g. for + * transitions between security domains). + * This hook may be called multiple times during a single execve, e.g. for + * interpreters. The hook can tell whether it has already been called by + * checking to see if @bprm->security is non-NULL. If so, then the hook + * may decide either to retain the security information saved earlier or + * to replace it. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. + * @bprm_check_security: + * This hook mediates the point when a search for a binary handler will + * begin. It allows a check the @bprm->security value which is set in the + * preceding set_creds call. The primary difference from set_creds is + * that the argv list and envp list are reliably available in @bprm. This + * hook may be called multiple times during a single execve; and in each + * pass set_creds is called first. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. + * @bprm_committing_creds: + * Prepare to install the new security attributes of a process being + * transformed by an execve operation, based on the old credentials + * pointed to by @current->cred and the information set in @bprm->cred by + * the bprm_set_creds hook. @bprm points to the linux_binprm structure. + * This hook is a good place to perform state changes on the process such + * as closing open file descriptors to which access will no longer be + * granted when the attributes are changed. This is called immediately + * before commit_creds(). + * @bprm_committed_creds: + * Tidy up after the installation of the new security attributes of a + * process being transformed by an execve operation. The new credentials + * have, by this point, been set to @current->cred. @bprm points to the + * linux_binprm structure. This hook is a good place to perform state + * changes on the process such as clearing out non-inheritable signal + * state. This is called immediately after commit_creds(). + * @bprm_secureexec: + * Return a boolean value (0 or 1) indicating whether a "secure exec" + * is required. The flag is passed in the auxiliary table + * on the initial stack to the ELF interpreter to indicate whether libc + * should enable secure mode. + * @bprm contains the linux_binprm structure. + * + * Security hooks for filesystem operations. + * + * @sb_alloc_security: + * Allocate and attach a security structure to the sb->s_security field. + * The s_security field is initialized to NULL when the structure is + * allocated. + * @sb contains the super_block structure to be modified. + * Return 0 if operation was successful. + * @sb_free_security: + * Deallocate and clear the sb->s_security field. + * @sb contains the super_block structure to be modified. + * @sb_statfs: + * Check permission before obtaining filesystem statistics for the @mnt + * mountpoint. + * @dentry is a handle on the superblock for the filesystem. + * Return 0 if permission is granted. + * @sb_mount: + * Check permission before an object specified by @dev_name is mounted on + * the mount point named by @nd. For an ordinary mount, @dev_name + * identifies a device if the file system type requires a device. For a + * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a + * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the + * pathname of the object being mounted. + * @dev_name contains the name for object being mounted. + * @path contains the path for mount point object. + * @type contains the filesystem type. + * @flags contains the mount flags. + * @data contains the filesystem-specific data. + * Return 0 if permission is granted. + * @sb_copy_data: + * Allow mount option data to be copied prior to parsing by the filesystem, + * so that the security module can extract security-specific mount + * options cleanly (a filesystem may modify the data e.g. with strsep()). + * This also allows the original mount data to be stripped of security- + * specific options to avoid having to make filesystems aware of them. + * @type the type of filesystem being mounted. + * @orig the original mount data copied from userspace. + * @copy copied data which will be passed to the security module. + * Returns 0 if the copy was successful. + * @sb_remount: + * Extracts security system specific mount options and verifies no changes + * are being made to those options. + * @sb superblock being remounted + * @data contains the filesystem-specific data. + * Return 0 if permission is granted. + * @sb_umount: + * Check permission before the @mnt file system is unmounted. + * @mnt contains the mounted file system. + * @flags contains the unmount flags, e.g. MNT_FORCE. + * Return 0 if permission is granted. + * @sb_pivotroot: + * Check permission before pivoting the root filesystem. + * @old_path contains the path for the new location of the + * current root (put_old). + * @new_path contains the path for the new root (new_root). + * Return 0 if permission is granted. + * @sb_set_mnt_opts: + * Set the security relevant mount options used for a superblock + * @sb the superblock to set security mount options for + * @opts binary data structure containing all lsm mount data + * @sb_clone_mnt_opts: + * Copy all security options from a given superblock to another + * @oldsb old superblock which contain information to clone + * @newsb new superblock which needs filled in + * @sb_parse_opts_str: + * Parse a string of security data filling in the opts structure + * @options string containing all mount options known by the LSM + * @opts binary data structure usable by the LSM + * @dentry_init_security: + * Compute a context for a dentry as the inode is not yet available + * since NFSv4 has no label backed by an EA anyway. + * @dentry dentry to use in calculating the context. + * @mode mode used to determine resource type. + * @name name of the last path component used to create file + * @ctx pointer to place the pointer to the resulting context in. + * @ctxlen point to place the length of the resulting context. + * + * + * Security hooks for inode operations. + * + * @inode_alloc_security: + * Allocate and attach a security structure to @inode->i_security. The + * i_security field is initialized to NULL when the inode structure is + * allocated. + * @inode contains the inode structure. + * Return 0 if operation was successful. + * @inode_free_security: + * @inode contains the inode structure. + * Deallocate the inode security structure and set @inode->i_security to + * NULL. + * @inode_init_security: + * Obtain the security attribute name suffix and value to set on a newly + * created inode and set up the incore security field for the new inode. + * This hook is called by the fs code as part of the inode creation + * transaction and provides for atomic labeling of the inode, unlike + * the post_create/mkdir/... hooks called by the VFS. The hook function + * is expected to allocate the name and value via kmalloc, with the caller + * being responsible for calling kfree after using them. + * If the security module does not use security attributes or does + * not wish to put a security attribute on this particular inode, + * then it should return -EOPNOTSUPP to skip this processing. + * @inode contains the inode structure of the newly created inode. + * @dir contains the inode structure of the parent directory. + * @qstr contains the last path component of the new object + * @name will be set to the allocated name suffix (e.g. selinux). + * @value will be set to the allocated attribute value. + * @len will be set to the length of the value. + * Returns 0 if @name and @value have been successfully set, + * -EOPNOTSUPP if no security attribute is needed, or + * -ENOMEM on memory allocation failure. + * @inode_create: + * Check permission to create a regular file. + * @dir contains inode structure of the parent of the new file. + * @dentry contains the dentry structure for the file to be created. + * @mode contains the file mode of the file to be created. + * Return 0 if permission is granted. + * @inode_link: + * Check permission before creating a new hard link to a file. + * @old_dentry contains the dentry structure for an existing + * link to the file. + * @dir contains the inode structure of the parent directory + * of the new link. + * @new_dentry contains the dentry structure for the new link. + * Return 0 if permission is granted. + * @path_link: + * Check permission before creating a new hard link to a file. + * @old_dentry contains the dentry structure for an existing link + * to the file. + * @new_dir contains the path structure of the parent directory of + * the new link. + * @new_dentry contains the dentry structure for the new link. + * Return 0 if permission is granted. + * @inode_unlink: + * Check the permission to remove a hard link to a file. + * @dir contains the inode structure of parent directory of the file. + * @dentry contains the dentry structure for file to be unlinked. + * Return 0 if permission is granted. + * @path_unlink: + * Check the permission to remove a hard link to a file. + * @dir contains the path structure of parent directory of the file. + * @dentry contains the dentry structure for file to be unlinked. + * Return 0 if permission is granted. + * @inode_symlink: + * Check the permission to create a symbolic link to a file. + * @dir contains the inode structure of parent directory of + * the symbolic link. + * @dentry contains the dentry structure of the symbolic link. + * @old_name contains the pathname of file. + * Return 0 if permission is granted. + * @path_symlink: + * Check the permission to create a symbolic link to a file. + * @dir contains the path structure of parent directory of + * the symbolic link. + * @dentry contains the dentry structure of the symbolic link. + * @old_name contains the pathname of file. + * Return 0 if permission is granted. + * @inode_mkdir: + * Check permissions to create a new directory in the existing directory + * associated with inode structure @dir. + * @dir contains the inode structure of parent of the directory + * to be created. + * @dentry contains the dentry structure of new directory. + * @mode contains the mode of new directory. + * Return 0 if permission is granted. + * @path_mkdir: + * Check permissions to create a new directory in the existing directory + * associated with path structure @path. + * @dir contains the path structure of parent of the directory + * to be created. + * @dentry contains the dentry structure of new directory. + * @mode contains the mode of new directory. + * Return 0 if permission is granted. + * @inode_rmdir: + * Check the permission to remove a directory. + * @dir contains the inode structure of parent of the directory + * to be removed. + * @dentry contains the dentry structure of directory to be removed. + * Return 0 if permission is granted. + * @path_rmdir: + * Check the permission to remove a directory. + * @dir contains the path structure of parent of the directory to be + * removed. + * @dentry contains the dentry structure of directory to be removed. + * Return 0 if permission is granted. + * @inode_mknod: + * Check permissions when creating a special file (or a socket or a fifo + * file created via the mknod system call). Note that if mknod operation + * is being done for a regular file, then the create hook will be called + * and not this hook. + * @dir contains the inode structure of parent of the new file. + * @dentry contains the dentry structure of the new file. + * @mode contains the mode of the new file. + * @dev contains the device number. + * Return 0 if permission is granted. + * @path_mknod: + * Check permissions when creating a file. Note that this hook is called + * even if mknod operation is being done for a regular file. + * @dir contains the path structure of parent of the new file. + * @dentry contains the dentry structure of the new file. + * @mode contains the mode of the new file. + * @dev contains the undecoded device number. Use new_decode_dev() to get + * the decoded device number. + * Return 0 if permission is granted. + * @inode_rename: + * Check for permission to rename a file or directory. + * @old_dir contains the inode structure for parent of the old link. + * @old_dentry contains the dentry structure of the old link. + * @new_dir contains the inode structure for parent of the new link. + * @new_dentry contains the dentry structure of the new link. + * Return 0 if permission is granted. + * @path_rename: + * Check for permission to rename a file or directory. + * @old_dir contains the path structure for parent of the old link. + * @old_dentry contains the dentry structure of the old link. + * @new_dir contains the path structure for parent of the new link. + * @new_dentry contains the dentry structure of the new link. + * Return 0 if permission is granted. + * @path_chmod: + * Check for permission to change DAC's permission of a file or directory. + * @dentry contains the dentry structure. + * @mnt contains the vfsmnt structure. + * @mode contains DAC's mode. + * Return 0 if permission is granted. + * @path_chown: + * Check for permission to change owner/group of a file or directory. + * @path contains the path structure. + * @uid contains new owner's ID. + * @gid contains new group's ID. + * Return 0 if permission is granted. + * @path_chroot: + * Check for permission to change root directory. + * @path contains the path structure. + * Return 0 if permission is granted. + * @inode_readlink: + * Check the permission to read the symbolic link. + * @dentry contains the dentry structure for the file link. + * Return 0 if permission is granted. + * @inode_follow_link: + * Check permission to follow a symbolic link when looking up a pathname. + * @dentry contains the dentry structure for the link. + * @inode contains the inode, which itself is not stable in RCU-walk + * @rcu indicates whether we are in RCU-walk mode. + * Return 0 if permission is granted. + * @inode_permission: + * Check permission before accessing an inode. This hook is called by the + * existing Linux permission function, so a security module can use it to + * provide additional checking for existing Linux permission checks. + * Notice that this hook is called when a file is opened (as well as many + * other operations), whereas the file_security_ops permission hook is + * called when the actual read/write operations are performed. + * @inode contains the inode structure to check. + * @mask contains the permission mask. + * Return 0 if permission is granted. + * @inode_setattr: + * Check permission before setting file attributes. Note that the kernel + * call to notify_change is performed from several locations, whenever + * file attributes change (such as when a file is truncated, chown/chmod + * operations, transferring disk quotas, etc). + * @dentry contains the dentry structure for the file. + * @attr is the iattr structure containing the new file attributes. + * Return 0 if permission is granted. + * @path_truncate: + * Check permission before truncating a file. + * @path contains the path structure for the file. + * Return 0 if permission is granted. + * @inode_getattr: + * Check permission before obtaining file attributes. + * @mnt is the vfsmount where the dentry was looked up + * @dentry contains the dentry structure for the file. + * Return 0 if permission is granted. + * @inode_setxattr: + * Check permission before setting the extended attributes + * @value identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_post_setxattr: + * Update inode security field after successful setxattr operation. + * @value identified by @name for @dentry. + * @inode_getxattr: + * Check permission before obtaining the extended attributes + * identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_listxattr: + * Check permission before obtaining the list of extended attribute + * names for @dentry. + * Return 0 if permission is granted. + * @inode_removexattr: + * Check permission before removing the extended attribute + * identified by @name for @dentry. + * Return 0 if permission is granted. + * @inode_getsecurity: + * Retrieve a copy of the extended attribute representation of the + * security label associated with @name for @inode via @buffer. Note that + * @name is the remainder of the attribute name after the security prefix + * has been removed. @alloc is used to specify of the call should return a + * value via the buffer or just the value length Return size of buffer on + * success. + * @inode_setsecurity: + * Set the security label associated with @name for @inode from the + * extended attribute value @value. @size indicates the size of the + * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. + * Note that @name is the remainder of the attribute name after the + * security. prefix has been removed. + * Return 0 on success. + * @inode_listsecurity: + * Copy the extended attribute names for the security labels + * associated with @inode into @buffer. The maximum size of @buffer + * is specified by @buffer_size. @buffer may be NULL to request + * the size of the buffer required. + * Returns number of bytes used/required on success. + * @inode_need_killpriv: + * Called when an inode has been changed. + * @dentry is the dentry being changed. + * Return <0 on error to abort the inode change operation. + * Return 0 if inode_killpriv does not need to be called. + * Return >0 if inode_killpriv does need to be called. + * @inode_killpriv: + * The setuid bit is being removed. Remove similar security labels. + * Called with the dentry->d_inode->i_mutex held. + * @dentry is the dentry being changed. + * Return 0 on success. If error is returned, then the operation + * causing setuid bit removal is failed. + * @inode_getsecid: + * Get the secid associated with the node. + * @inode contains a pointer to the inode. + * @secid contains a pointer to the location where result will be saved. + * In case of failure, @secid will be set to zero. + * + * Security hooks for file operations + * + * @file_permission: + * Check file permissions before accessing an open file. This hook is + * called by various operations that read or write files. A security + * module can use this hook to perform additional checking on these + * operations, e.g. to revalidate permissions on use to support privilege + * bracketing or policy changes. Notice that this hook is used when the + * actual read/write operations are performed, whereas the + * inode_security_ops hook is called when a file is opened (as well as + * many other operations). + * Caveat: Although this hook can be used to revalidate permissions for + * various system call operations that read or write files, it does not + * address the revalidation of permissions for memory-mapped files. + * Security modules must handle this separately if they need such + * revalidation. + * @file contains the file structure being accessed. + * @mask contains the requested permissions. + * Return 0 if permission is granted. + * @file_alloc_security: + * Allocate and attach a security structure to the file->f_security field. + * The security field is initialized to NULL when the structure is first + * created. + * @file contains the file structure to secure. + * Return 0 if the hook is successful and permission is granted. + * @file_free_security: + * Deallocate and free any security structures stored in file->f_security. + * @file contains the file structure being modified. + * @file_ioctl: + * @file contains the file structure. + * @cmd contains the operation to perform. + * @arg contains the operational arguments. + * Check permission for an ioctl operation on @file. Note that @arg + * sometimes represents a user space pointer; in other cases, it may be a + * simple integer value. When @arg represents a user space pointer, it + * should never be used by the security module. + * Return 0 if permission is granted. + * @mmap_addr : + * Check permissions for a mmap operation at @addr. + * @addr contains virtual address that will be used for the operation. + * Return 0 if permission is granted. + * @mmap_file : + * Check permissions for a mmap operation. The @file may be NULL, e.g. + * if mapping anonymous memory. + * @file contains the file structure for file to map (may be NULL). + * @reqprot contains the protection requested by the application. + * @prot contains the protection that will be applied by the kernel. + * @flags contains the operational flags. + * Return 0 if permission is granted. + * @file_mprotect: + * Check permissions before changing memory access permissions. + * @vma contains the memory region to modify. + * @reqprot contains the protection requested by the application. + * @prot contains the protection that will be applied by the kernel. + * Return 0 if permission is granted. + * @file_lock: + * Check permission before performing file locking operations. + * Note: this hook mediates both flock and fcntl style locks. + * @file contains the file structure. + * @cmd contains the posix-translated lock operation to perform + * (e.g. F_RDLCK, F_WRLCK). + * Return 0 if permission is granted. + * @file_fcntl: + * Check permission before allowing the file operation specified by @cmd + * from being performed on the file @file. Note that @arg sometimes + * represents a user space pointer; in other cases, it may be a simple + * integer value. When @arg represents a user space pointer, it should + * never be used by the security module. + * @file contains the file structure. + * @cmd contains the operation to be performed. + * @arg contains the operational arguments. + * Return 0 if permission is granted. + * @file_set_fowner: + * Save owner security information (typically from current->security) in + * file->f_security for later use by the send_sigiotask hook. + * @file contains the file structure to update. + * Return 0 on success. + * @file_send_sigiotask: + * Check permission for the file owner @fown to send SIGIO or SIGURG to the + * process @tsk. Note that this hook is sometimes called from interrupt. + * Note that the fown_struct, @fown, is never outside the context of a + * struct file, so the file structure (and associated security information) + * can always be obtained: + * container_of(fown, struct file, f_owner) + * @tsk contains the structure of task receiving signal. + * @fown contains the file owner information. + * @sig is the signal that will be sent. When 0, kernel sends SIGIO. + * Return 0 if permission is granted. + * @file_receive: + * This hook allows security modules to control the ability of a process + * to receive an open file descriptor via socket IPC. + * @file contains the file structure being received. + * Return 0 if permission is granted. + * @file_open + * Save open-time permission checking state for later use upon + * file_permission, and recheck access if anything has changed + * since inode_permission. + * + * Security hooks for task operations. + * + * @task_create: + * Check permission before creating a child process. See the clone(2) + * manual page for definitions of the @clone_flags. + * @clone_flags contains the flags indicating what should be shared. + * Return 0 if permission is granted. + * @task_free: + * @task task being freed + * Handle release of task-related resources. (Note that this can be called + * from interrupt context.) + * @cred_alloc_blank: + * @cred points to the credentials. + * @gfp indicates the atomicity of any memory allocations. + * Only allocate sufficient memory and attach to @cred such that + * cred_transfer() will not get ENOMEM. + * @cred_free: + * @cred points to the credentials. + * Deallocate and clear the cred->security field in a set of credentials. + * @cred_prepare: + * @new points to the new credentials. + * @old points to the original credentials. + * @gfp indicates the atomicity of any memory allocations. + * Prepare a new set of credentials by copying the data from the old set. + * @cred_transfer: + * @new points to the new credentials. + * @old points to the original credentials. + * Transfer data from original creds to new creds + * @kernel_act_as: + * Set the credentials for a kernel service to act as (subjective context). + * @new points to the credentials to be modified. + * @secid specifies the security ID to be set + * The current task must be the one that nominated @secid. + * Return 0 if successful. + * @kernel_create_files_as: + * Set the file creation context in a set of credentials to be the same as + * the objective context of the specified inode. + * @new points to the credentials to be modified. + * @inode points to the inode to use as a reference. + * The current task must be the one that nominated @inode. + * Return 0 if successful. + * @kernel_fw_from_file: + * Load firmware from userspace (not called for built-in firmware). + * @file contains the file structure pointing to the file containing + * the firmware to load. This argument will be NULL if the firmware + * was loaded via the uevent-triggered blob-based interface exposed + * by CONFIG_FW_LOADER_USER_HELPER. + * @buf pointer to buffer containing firmware contents. + * @size length of the firmware contents. + * Return 0 if permission is granted. + * @kernel_module_request: + * Ability to trigger the kernel to automatically upcall to userspace for + * userspace to load a kernel module with the given name. + * @kmod_name name of the module requested by the kernel + * Return 0 if successful. + * @kernel_module_from_file: + * Load a kernel module from userspace. + * @file contains the file structure pointing to the file containing + * the kernel module to load. If the module is being loaded from a blob, + * this argument will be NULL. + * Return 0 if permission is granted. + * @task_fix_setuid: + * Update the module's state after setting one or more of the user + * identity attributes of the current process. The @flags parameter + * indicates which of the set*uid system calls invoked this hook. If + * @new is the set of credentials that will be installed. Modifications + * should be made to this rather than to @current->cred. + * @old is the set of credentials that are being replaces + * @flags contains one of the LSM_SETID_* values. + * Return 0 on success. + * @task_setpgid: + * Check permission before setting the process group identifier of the + * process @p to @pgid. + * @p contains the task_struct for process being modified. + * @pgid contains the new pgid. + * Return 0 if permission is granted. + * @task_getpgid: + * Check permission before getting the process group identifier of the + * process @p. + * @p contains the task_struct for the process. + * Return 0 if permission is granted. + * @task_getsid: + * Check permission before getting the session identifier of the process + * @p. + * @p contains the task_struct for the process. + * Return 0 if permission is granted. + * @task_getsecid: + * Retrieve the security identifier of the process @p. + * @p contains the task_struct for the process and place is into @secid. + * In case of failure, @secid will be set to zero. + * + * @task_setnice: + * Check permission before setting the nice value of @p to @nice. + * @p contains the task_struct of process. + * @nice contains the new nice value. + * Return 0 if permission is granted. + * @task_setioprio + * Check permission before setting the ioprio value of @p to @ioprio. + * @p contains the task_struct of process. + * @ioprio contains the new ioprio value + * Return 0 if permission is granted. + * @task_getioprio + * Check permission before getting the ioprio value of @p. + * @p contains the task_struct of process. + * Return 0 if permission is granted. + * @task_setrlimit: + * Check permission before setting the resource limits of the current + * process for @resource to @new_rlim. The old resource limit values can + * be examined by dereferencing (current->signal->rlim + resource). + * @resource contains the resource whose limit is being set. + * @new_rlim contains the new limits for @resource. + * Return 0 if permission is granted. + * @task_setscheduler: + * Check permission before setting scheduling policy and/or parameters of + * process @p based on @policy and @lp. + * @p contains the task_struct for process. + * @policy contains the scheduling policy. + * @lp contains the scheduling parameters. + * Return 0 if permission is granted. + * @task_getscheduler: + * Check permission before obtaining scheduling information for process + * @p. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_movememory + * Check permission before moving memory owned by process @p. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_kill: + * Check permission before sending signal @sig to @p. @info can be NULL, + * the constant 1, or a pointer to a siginfo structure. If @info is 1 or + * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming + * from the kernel and should typically be permitted. + * SIGIO signals are handled separately by the send_sigiotask hook in + * file_security_ops. + * @p contains the task_struct for process. + * @info contains the signal information. + * @sig contains the signal value. + * @secid contains the sid of the process where the signal originated + * Return 0 if permission is granted. + * @task_wait: + * Check permission before allowing a process to reap a child process @p + * and collect its status information. + * @p contains the task_struct for process. + * Return 0 if permission is granted. + * @task_prctl: + * Check permission before performing a process control operation on the + * current process. + * @option contains the operation. + * @arg2 contains a argument. + * @arg3 contains a argument. + * @arg4 contains a argument. + * @arg5 contains a argument. + * Return -ENOSYS if no-one wanted to handle this op, any other value to + * cause prctl() to return immediately with that value. + * @task_to_inode: + * Set the security attributes for an inode based on an associated task's + * security attributes, e.g. for /proc/pid inodes. + * @p contains the task_struct for the task. + * @inode contains the inode structure for the inode. + * + * Security hooks for Netlink messaging. + * + * @netlink_send: + * Save security information for a netlink message so that permission + * checking can be performed when the message is processed. The security + * information can be saved using the eff_cap field of the + * netlink_skb_parms structure. Also may be used to provide fine + * grained control over message transmission. + * @sk associated sock of task sending the message. + * @skb contains the sk_buff structure for the netlink message. + * Return 0 if the information was successfully saved and message + * is allowed to be transmitted. + * + * Security hooks for Unix domain networking. + * + * @unix_stream_connect: + * Check permissions before establishing a Unix domain stream connection + * between @sock and @other. + * @sock contains the sock structure. + * @other contains the peer sock structure. + * @newsk contains the new sock structure. + * Return 0 if permission is granted. + * @unix_may_send: + * Check permissions before connecting or sending datagrams from @sock to + * @other. + * @sock contains the socket structure. + * @other contains the peer socket structure. + * Return 0 if permission is granted. + * + * The @unix_stream_connect and @unix_may_send hooks were necessary because + * Linux provides an alternative to the conventional file name space for Unix + * domain sockets. Whereas binding and connecting to sockets in the file name + * space is mediated by the typical file permissions (and caught by the mknod + * and permission hooks in inode_security_ops), binding and connecting to + * sockets in the abstract name space is completely unmediated. Sufficient + * control of Unix domain sockets in the abstract name space isn't possible + * using only the socket layer hooks, since we need to know the actual target + * socket, which is not looked up until we are inside the af_unix code. + * + * Security hooks for socket operations. + * + * @socket_create: + * Check permissions prior to creating a new socket. + * @family contains the requested protocol family. + * @type contains the requested communications type. + * @protocol contains the requested protocol. + * @kern set to 1 if a kernel socket. + * Return 0 if permission is granted. + * @socket_post_create: + * This hook allows a module to update or allocate a per-socket security + * structure. Note that the security field was not added directly to the + * socket structure, but rather, the socket security information is stored + * in the associated inode. Typically, the inode alloc_security hook will + * allocate and and attach security information to + * sock->inode->i_security. This hook may be used to update the + * sock->inode->i_security field with additional information that wasn't + * available when the inode was allocated. + * @sock contains the newly created socket structure. + * @family contains the requested protocol family. + * @type contains the requested communications type. + * @protocol contains the requested protocol. + * @kern set to 1 if a kernel socket. + * @socket_bind: + * Check permission before socket protocol layer bind operation is + * performed and the socket @sock is bound to the address specified in the + * @address parameter. + * @sock contains the socket structure. + * @address contains the address to bind to. + * @addrlen contains the length of address. + * Return 0 if permission is granted. + * @socket_connect: + * Check permission before socket protocol layer connect operation + * attempts to connect socket @sock to a remote address, @address. + * @sock contains the socket structure. + * @address contains the address of remote endpoint. + * @addrlen contains the length of address. + * Return 0 if permission is granted. + * @socket_listen: + * Check permission before socket protocol layer listen operation. + * @sock contains the socket structure. + * @backlog contains the maximum length for the pending connection queue. + * Return 0 if permission is granted. + * @socket_accept: + * Check permission before accepting a new connection. Note that the new + * socket, @newsock, has been created and some information copied to it, + * but the accept operation has not actually been performed. + * @sock contains the listening socket structure. + * @newsock contains the newly created server socket for connection. + * Return 0 if permission is granted. + * @socket_sendmsg: + * Check permission before transmitting a message to another socket. + * @sock contains the socket structure. + * @msg contains the message to be transmitted. + * @size contains the size of message. + * Return 0 if permission is granted. + * @socket_recvmsg: + * Check permission before receiving a message from a socket. + * @sock contains the socket structure. + * @msg contains the message structure. + * @size contains the size of message structure. + * @flags contains the operational flags. + * Return 0 if permission is granted. + * @socket_getsockname: + * Check permission before the local address (name) of the socket object + * @sock is retrieved. + * @sock contains the socket structure. + * Return 0 if permission is granted. + * @socket_getpeername: + * Check permission before the remote address (name) of a socket object + * @sock is retrieved. + * @sock contains the socket structure. + * Return 0 if permission is granted. + * @socket_getsockopt: + * Check permissions before retrieving the options associated with socket + * @sock. + * @sock contains the socket structure. + * @level contains the protocol level to retrieve option from. + * @optname contains the name of option to retrieve. + * Return 0 if permission is granted. + * @socket_setsockopt: + * Check permissions before setting the options associated with socket + * @sock. + * @sock contains the socket structure. + * @level contains the protocol level to set options for. + * @optname contains the name of the option to set. + * Return 0 if permission is granted. + * @socket_shutdown: + * Checks permission before all or part of a connection on the socket + * @sock is shut down. + * @sock contains the socket structure. + * @how contains the flag indicating how future sends and receives + * are handled. + * Return 0 if permission is granted. + * @socket_sock_rcv_skb: + * Check permissions on incoming network packets. This hook is distinct + * from Netfilter's IP input hooks since it is the first time that the + * incoming sk_buff @skb has been associated with a particular socket, @sk. + * Must not sleep inside this hook because some callers hold spinlocks. + * @sk contains the sock (not socket) associated with the incoming sk_buff. + * @skb contains the incoming network data. + * @socket_getpeersec_stream: + * This hook allows the security module to provide peer socket security + * state for unix or connected tcp sockets to userspace via getsockopt + * SO_GETPEERSEC. For tcp sockets this can be meaningful if the + * socket is associated with an ipsec SA. + * @sock is the local socket. + * @optval userspace memory where the security state is to be copied. + * @optlen userspace int where the module should copy the actual length + * of the security state. + * @len as input is the maximum length to copy to userspace provided + * by the caller. + * Return 0 if all is well, otherwise, typical getsockopt return + * values. + * @socket_getpeersec_dgram: + * This hook allows the security module to provide peer socket security + * state for udp sockets on a per-packet basis to userspace via + * getsockopt SO_GETPEERSEC. The application must first have indicated + * the IP_PASSSEC option via getsockopt. It can then retrieve the + * security state returned by this hook for a packet via the SCM_SECURITY + * ancillary message type. + * @skb is the skbuff for the packet being queried + * @secdata is a pointer to a buffer in which to copy the security data + * @seclen is the maximum length for @secdata + * Return 0 on success, error on failure. + * @sk_alloc_security: + * Allocate and attach a security structure to the sk->sk_security field, + * which is used to copy security attributes between local stream sockets. + * @sk_free_security: + * Deallocate security structure. + * @sk_clone_security: + * Clone/copy security structure. + * @sk_getsecid: + * Retrieve the LSM-specific secid for the sock to enable caching + * of network authorizations. + * @sock_graft: + * Sets the socket's isec sid to the sock's sid. + * @inet_conn_request: + * Sets the openreq's sid to socket's sid with MLS portion taken + * from peer sid. + * @inet_csk_clone: + * Sets the new child socket's sid to the openreq sid. + * @inet_conn_established: + * Sets the connection's peersid to the secmark on skb. + * @secmark_relabel_packet: + * check if the process should be allowed to relabel packets to + * the given secid + * @security_secmark_refcount_inc + * tells the LSM to increment the number of secmark labeling rules loaded + * @security_secmark_refcount_dec + * tells the LSM to decrement the number of secmark labeling rules loaded + * @req_classify_flow: + * Sets the flow's sid to the openreq sid. + * @tun_dev_alloc_security: + * This hook allows a module to allocate a security structure for a TUN + * device. + * @security pointer to a security structure pointer. + * Returns a zero on success, negative values on failure. + * @tun_dev_free_security: + * This hook allows a module to free the security structure for a TUN + * device. + * @security pointer to the TUN device's security structure + * @tun_dev_create: + * Check permissions prior to creating a new TUN device. + * @tun_dev_attach_queue: + * Check permissions prior to attaching to a TUN device queue. + * @security pointer to the TUN device's security structure. + * @tun_dev_attach: + * This hook can be used by the module to update any security state + * associated with the TUN device's sock structure. + * @sk contains the existing sock structure. + * @security pointer to the TUN device's security structure. + * @tun_dev_open: + * This hook can be used by the module to update any security state + * associated with the TUN device's security structure. + * @security pointer to the TUN devices's security structure. + * + * Security hooks for XFRM operations. + * + * @xfrm_policy_alloc_security: + * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy + * Database used by the XFRM system. + * @sec_ctx contains the security context information being provided by + * the user-level policy update program (e.g., setkey). + * Allocate a security structure to the xp->security field; the security + * field is initialized to NULL when the xfrm_policy is allocated. + * Return 0 if operation was successful (memory to allocate, legal context) + * @gfp is to specify the context for the allocation + * @xfrm_policy_clone_security: + * @old_ctx contains an existing xfrm_sec_ctx. + * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. + * Allocate a security structure in new_ctxp that contains the + * information from the old_ctx structure. + * Return 0 if operation was successful (memory to allocate). + * @xfrm_policy_free_security: + * @ctx contains the xfrm_sec_ctx + * Deallocate xp->security. + * @xfrm_policy_delete_security: + * @ctx contains the xfrm_sec_ctx. + * Authorize deletion of xp->security. + * @xfrm_state_alloc: + * @x contains the xfrm_state being added to the Security Association + * Database by the XFRM system. + * @sec_ctx contains the security context information being provided by + * the user-level SA generation program (e.g., setkey or racoon). + * Allocate a security structure to the x->security field; the security + * field is initialized to NULL when the xfrm_state is allocated. Set the + * context to correspond to sec_ctx. Return 0 if operation was successful + * (memory to allocate, legal context). + * @xfrm_state_alloc_acquire: + * @x contains the xfrm_state being added to the Security Association + * Database by the XFRM system. + * @polsec contains the policy's security context. + * @secid contains the secid from which to take the mls portion of the + * context. + * Allocate a security structure to the x->security field; the security + * field is initialized to NULL when the xfrm_state is allocated. Set the + * context to correspond to secid. Return 0 if operation was successful + * (memory to allocate, legal context). + * @xfrm_state_free_security: + * @x contains the xfrm_state. + * Deallocate x->security. + * @xfrm_state_delete_security: + * @x contains the xfrm_state. + * Authorize deletion of x->security. + * @xfrm_policy_lookup: + * @ctx contains the xfrm_sec_ctx for which the access control is being + * checked. + * @fl_secid contains the flow security label that is used to authorize + * access to the policy xp. + * @dir contains the direction of the flow (input or output). + * Check permission when a flow selects a xfrm_policy for processing + * XFRMs on a packet. The hook is called when selecting either a + * per-socket policy or a generic xfrm policy. + * Return 0 if permission is granted, -ESRCH otherwise, or -errno + * on other errors. + * @xfrm_state_pol_flow_match: + * @x contains the state to match. + * @xp contains the policy to check for a match. + * @fl contains the flow to check for a match. + * Return 1 if there is a match. + * @xfrm_decode_session: + * @skb points to skb to decode. + * @secid points to the flow key secid to set. + * @ckall says if all xfrms used should be checked for same secid. + * Return 0 if ckall is zero or all xfrms used have the same secid. + * + * Security hooks affecting all Key Management operations + * + * @key_alloc: + * Permit allocation of a key and assign security data. Note that key does + * not have a serial number assigned at this point. + * @key points to the key. + * @flags is the allocation flags + * Return 0 if permission is granted, -ve error otherwise. + * @key_free: + * Notification of destruction; free security data. + * @key points to the key. + * No return value. + * @key_permission: + * See whether a specific operational right is granted to a process on a + * key. + * @key_ref refers to the key (key pointer + possession attribute bit). + * @cred points to the credentials to provide the context against which to + * evaluate the security data on the key. + * @perm describes the combination of permissions required of this key. + * Return 0 if permission is granted, -ve error otherwise. + * @key_getsecurity: + * Get a textual representation of the security context attached to a key + * for the purposes of honouring KEYCTL_GETSECURITY. This function + * allocates the storage for the NUL-terminated string and the caller + * should free it. + * @key points to the key to be queried. + * @_buffer points to a pointer that should be set to point to the + * resulting string (if no label or an error occurs). + * Return the length of the string (including terminating NUL) or -ve if + * an error. + * May also return 0 (and a NULL buffer pointer) if there is no label. + * + * Security hooks affecting all System V IPC operations. + * + * @ipc_permission: + * Check permissions for access to IPC + * @ipcp contains the kernel IPC permission structure + * @flag contains the desired (requested) permission set + * Return 0 if permission is granted. + * @ipc_getsecid: + * Get the secid associated with the ipc object. + * @ipcp contains the kernel IPC permission structure. + * @secid contains a pointer to the location where result will be saved. + * In case of failure, @secid will be set to zero. + * + * Security hooks for individual messages held in System V IPC message queues + * @msg_msg_alloc_security: + * Allocate and attach a security structure to the msg->security field. + * The security field is initialized to NULL when the structure is first + * created. + * @msg contains the message structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @msg_msg_free_security: + * Deallocate the security structure for this message. + * @msg contains the message structure to be modified. + * + * Security hooks for System V IPC Message Queues + * + * @msg_queue_alloc_security: + * Allocate and attach a security structure to the + * msq->q_perm.security field. The security field is initialized to + * NULL when the structure is first created. + * @msq contains the message queue structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @msg_queue_free_security: + * Deallocate security structure for this message queue. + * @msq contains the message queue structure to be modified. + * @msg_queue_associate: + * Check permission when a message queue is requested through the + * msgget system call. This hook is only called when returning the + * message queue identifier for an existing message queue, not when a + * new message queue is created. + * @msq contains the message queue to act upon. + * @msqflg contains the operation control flags. + * Return 0 if permission is granted. + * @msg_queue_msgctl: + * Check permission when a message control operation specified by @cmd + * is to be performed on the message queue @msq. + * The @msq may be NULL, e.g. for IPC_INFO or MSG_INFO. + * @msq contains the message queue to act upon. May be NULL. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @msg_queue_msgsnd: + * Check permission before a message, @msg, is enqueued on the message + * queue, @msq. + * @msq contains the message queue to send message to. + * @msg contains the message to be enqueued. + * @msqflg contains operational flags. + * Return 0 if permission is granted. + * @msg_queue_msgrcv: + * Check permission before a message, @msg, is removed from the message + * queue, @msq. The @target task structure contains a pointer to the + * process that will be receiving the message (not equal to the current + * process when inline receives are being performed). + * @msq contains the message queue to retrieve message from. + * @msg contains the message destination. + * @target contains the task structure for recipient process. + * @type contains the type of message requested. + * @mode contains the operational flags. + * Return 0 if permission is granted. + * + * Security hooks for System V Shared Memory Segments + * + * @shm_alloc_security: + * Allocate and attach a security structure to the shp->shm_perm.security + * field. The security field is initialized to NULL when the structure is + * first created. + * @shp contains the shared memory structure to be modified. + * Return 0 if operation was successful and permission is granted. + * @shm_free_security: + * Deallocate the security struct for this memory segment. + * @shp contains the shared memory structure to be modified. + * @shm_associate: + * Check permission when a shared memory region is requested through the + * shmget system call. This hook is only called when returning the shared + * memory region identifier for an existing region, not when a new shared + * memory region is created. + * @shp contains the shared memory structure to be modified. + * @shmflg contains the operation control flags. + * Return 0 if permission is granted. + * @shm_shmctl: + * Check permission when a shared memory control operation specified by + * @cmd is to be performed on the shared memory region @shp. + * The @shp may be NULL, e.g. for IPC_INFO or SHM_INFO. + * @shp contains shared memory structure to be modified. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @shm_shmat: + * Check permissions prior to allowing the shmat system call to attach the + * shared memory segment @shp to the data segment of the calling process. + * The attaching address is specified by @shmaddr. + * @shp contains the shared memory structure to be modified. + * @shmaddr contains the address to attach memory region to. + * @shmflg contains the operational flags. + * Return 0 if permission is granted. + * + * Security hooks for System V Semaphores + * + * @sem_alloc_security: + * Allocate and attach a security structure to the sma->sem_perm.security + * field. The security field is initialized to NULL when the structure is + * first created. + * @sma contains the semaphore structure + * Return 0 if operation was successful and permission is granted. + * @sem_free_security: + * deallocate security struct for this semaphore + * @sma contains the semaphore structure. + * @sem_associate: + * Check permission when a semaphore is requested through the semget + * system call. This hook is only called when returning the semaphore + * identifier for an existing semaphore, not when a new one must be + * created. + * @sma contains the semaphore structure. + * @semflg contains the operation control flags. + * Return 0 if permission is granted. + * @sem_semctl: + * Check permission when a semaphore operation specified by @cmd is to be + * performed on the semaphore @sma. The @sma may be NULL, e.g. for + * IPC_INFO or SEM_INFO. + * @sma contains the semaphore structure. May be NULL. + * @cmd contains the operation to be performed. + * Return 0 if permission is granted. + * @sem_semop + * Check permissions before performing operations on members of the + * semaphore set @sma. If the @alter flag is nonzero, the semaphore set + * may be modified. + * @sma contains the semaphore structure. + * @sops contains the operations to perform. + * @nsops contains the number of operations to perform. + * @alter contains the flag indicating whether changes are to be made. + * Return 0 if permission is granted. + * + * @binder_set_context_mgr + * Check whether @mgr is allowed to be the binder context manager. + * @mgr contains the task_struct for the task being registered. + * Return 0 if permission is granted. + * @binder_transaction + * Check whether @from is allowed to invoke a binder transaction call + * to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_binder + * Check whether @from is allowed to transfer a binder reference to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_file + * Check whether @from is allowed to transfer @file to @to. + * @from contains the task_struct for the sending task. + * @file contains the struct file being transferred. + * @to contains the task_struct for the receiving task. + * + * @ptrace_access_check: + * Check permission before allowing the current process to trace the + * @child process. + * Security modules may also want to perform a process tracing check + * during an execve in the set_security or apply_creds hooks of + * tracing check during an execve in the bprm_set_creds hook of + * binprm_security_ops if the process is being traced and its security + * attributes would be changed by the execve. + * @child contains the task_struct structure for the target process. + * @mode contains the PTRACE_MODE flags indicating the form of access. + * Return 0 if permission is granted. + * @ptrace_traceme: + * Check that the @parent process has sufficient permission to trace the + * current process before allowing the current process to present itself + * to the @parent process for tracing. + * @parent contains the task_struct structure for debugger process. + * Return 0 if permission is granted. + * @capget: + * Get the @effective, @inheritable, and @permitted capability sets for + * the @target process. The hook may also perform permission checking to + * determine if the current process is allowed to see the capability sets + * of the @target process. + * @target contains the task_struct structure for target process. + * @effective contains the effective capability set. + * @inheritable contains the inheritable capability set. + * @permitted contains the permitted capability set. + * Return 0 if the capability sets were successfully obtained. + * @capset: + * Set the @effective, @inheritable, and @permitted capability sets for + * the current process. + * @new contains the new credentials structure for target process. + * @old contains the current credentials structure for target process. + * @effective contains the effective capability set. + * @inheritable contains the inheritable capability set. + * @permitted contains the permitted capability set. + * Return 0 and update @new if permission is granted. + * @capable: + * Check whether the @tsk process has the @cap capability in the indicated + * credentials. + * @cred contains the credentials to use. + * @ns contains the user namespace we want the capability in + * @cap contains the capability <include/linux/capability.h>. + * @audit: Whether to write an audit message or not + * Return 0 if the capability is granted for @tsk. + * @syslog: + * Check permission before accessing the kernel message ring or changing + * logging to the console. + * See the syslog(2) manual page for an explanation of the @type values. + * @type contains the type of action. + * @from_file indicates the context of action (if it came from /proc). + * Return 0 if permission is granted. + * @settime: + * Check permission to change the system time. + * struct timespec and timezone are defined in include/linux/time.h + * @ts contains new time + * @tz contains new timezone + * Return 0 if permission is granted. + * @vm_enough_memory: + * Check permissions for allocating a new virtual mapping. + * @mm contains the mm struct it is being added to. + * @pages contains the number of pages. + * Return 0 if permission is granted. + * + * @ismaclabel: + * Check if the extended attribute specified by @name + * represents a MAC label. Returns 1 if name is a MAC + * attribute otherwise returns 0. + * @name full extended attribute name to check against + * LSM as a MAC label. + * + * @secid_to_secctx: + * Convert secid to security context. If secdata is NULL the length of + * the result will be returned in seclen, but no secdata will be returned. + * This does mean that the length could change between calls to check the + * length and the next call which actually allocates and returns the + * secdata. + * @secid contains the security ID. + * @secdata contains the pointer that stores the converted security + * context. + * @seclen pointer which contains the length of the data + * @secctx_to_secid: + * Convert security context to secid. + * @secid contains the pointer to the generated security ID. + * @secdata contains the security context. + * + * @release_secctx: + * Release the security context. + * @secdata contains the security context. + * @seclen contains the length of the security context. + * + * Security hooks for Audit + * + * @audit_rule_init: + * Allocate and initialize an LSM audit rule structure. + * @field contains the required Audit action. + * Fields flags are defined in include/linux/audit.h + * @op contains the operator the rule uses. + * @rulestr contains the context where the rule will be applied to. + * @lsmrule contains a pointer to receive the result. + * Return 0 if @lsmrule has been successfully set, + * -EINVAL in case of an invalid rule. + * + * @audit_rule_known: + * Specifies whether given @rule contains any fields related to + * current LSM. + * @rule contains the audit rule of interest. + * Return 1 in case of relation found, 0 otherwise. + * + * @audit_rule_match: + * Determine if given @secid matches a rule previously approved + * by @audit_rule_known. + * @secid contains the security id in question. + * @field contains the field which relates to current LSM. + * @op contains the operator that will be used for matching. + * @rule points to the audit rule that will be checked against. + * @actx points to the audit context associated with the check. + * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. + * + * @audit_rule_free: + * Deallocate the LSM audit rule structure previously allocated by + * audit_rule_init. + * @rule contains the allocated rule + * + * @inode_notifysecctx: + * Notify the security module of what the security context of an inode + * should be. Initializes the incore security context managed by the + * security module for this inode. Example usage: NFS client invokes + * this hook to initialize the security context in its incore inode to the + * value provided by the server for the file when the server returned the + * file's attributes to the client. + * + * Must be called with inode->i_mutex locked. + * + * @inode we wish to set the security context of. + * @ctx contains the string which we wish to set in the inode. + * @ctxlen contains the length of @ctx. + * + * @inode_setsecctx: + * Change the security context of an inode. Updates the + * incore security context managed by the security module and invokes the + * fs code as needed (via __vfs_setxattr_noperm) to update any backing + * xattrs that represent the context. Example usage: NFS server invokes + * this hook to change the security context in its incore inode and on the + * backing filesystem to a value provided by the client on a SETATTR + * operation. + * + * Must be called with inode->i_mutex locked. + * + * @dentry contains the inode we wish to set the security context of. + * @ctx contains the string which we wish to set in the inode. + * @ctxlen contains the length of @ctx. + * + * @inode_getsecctx: + * On success, returns 0 and fills out @ctx and @ctxlen with the security + * context for the given @inode. + * + * @inode we wish to get the security context of. + * @ctx is a pointer in which to place the allocated security context. + * @ctxlen points to the place to put the length of @ctx. + * This is the main security structure. + */ + +union security_list_options { + int (*binder_set_context_mgr)(struct task_struct *mgr); + int (*binder_transaction)(struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_binder)(struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_file)(struct task_struct *from, + struct task_struct *to, + struct file *file); + + int (*ptrace_access_check)(struct task_struct *child, + unsigned int mode); + int (*ptrace_traceme)(struct task_struct *parent); + int (*capget)(struct task_struct *target, kernel_cap_t *effective, + kernel_cap_t *inheritable, kernel_cap_t *permitted); + int (*capset)(struct cred *new, const struct cred *old, + const kernel_cap_t *effective, + const kernel_cap_t *inheritable, + const kernel_cap_t *permitted); + int (*capable)(const struct cred *cred, struct user_namespace *ns, + int cap, int audit); + int (*quotactl)(int cmds, int type, int id, struct super_block *sb); + int (*quota_on)(struct dentry *dentry); + int (*syslog)(int type); + int (*settime)(const struct timespec *ts, const struct timezone *tz); + int (*vm_enough_memory)(struct mm_struct *mm, long pages); + + int (*bprm_set_creds)(struct linux_binprm *bprm); + int (*bprm_check_security)(struct linux_binprm *bprm); + int (*bprm_secureexec)(struct linux_binprm *bprm); + void (*bprm_committing_creds)(struct linux_binprm *bprm); + void (*bprm_committed_creds)(struct linux_binprm *bprm); + + int (*sb_alloc_security)(struct super_block *sb); + void (*sb_free_security)(struct super_block *sb); + int (*sb_copy_data)(char *orig, char *copy); + int (*sb_remount)(struct super_block *sb, void *data); + int (*sb_kern_mount)(struct super_block *sb, int flags, void *data); + int (*sb_show_options)(struct seq_file *m, struct super_block *sb); + int (*sb_statfs)(struct dentry *dentry); + int (*sb_mount)(const char *dev_name, struct path *path, + const char *type, unsigned long flags, void *data); + int (*sb_umount)(struct vfsmount *mnt, int flags); + int (*sb_pivotroot)(struct path *old_path, struct path *new_path); + int (*sb_set_mnt_opts)(struct super_block *sb, + struct security_mnt_opts *opts, + unsigned long kern_flags, + unsigned long *set_kern_flags); + int (*sb_clone_mnt_opts)(const struct super_block *oldsb, + struct super_block *newsb); + int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); + int (*dentry_init_security)(struct dentry *dentry, int mode, + struct qstr *name, void **ctx, + u32 *ctxlen); + + +#ifdef CONFIG_SECURITY_PATH + int (*path_unlink)(struct path *dir, struct dentry *dentry); + int (*path_mkdir)(struct path *dir, struct dentry *dentry, + umode_t mode); + int (*path_rmdir)(struct path *dir, struct dentry *dentry); + int (*path_mknod)(struct path *dir, struct dentry *dentry, + umode_t mode, unsigned int dev); + int (*path_truncate)(struct path *path); + int (*path_symlink)(struct path *dir, struct dentry *dentry, + const char *old_name); + int (*path_link)(struct dentry *old_dentry, struct path *new_dir, + struct dentry *new_dentry); + int (*path_rename)(struct path *old_dir, struct dentry *old_dentry, + struct path *new_dir, + struct dentry *new_dentry); + int (*path_chmod)(struct path *path, umode_t mode); + int (*path_chown)(struct path *path, kuid_t uid, kgid_t gid); + int (*path_chroot)(struct path *path); +#endif + + int (*inode_alloc_security)(struct inode *inode); + void (*inode_free_security)(struct inode *inode); + int (*inode_init_security)(struct inode *inode, struct inode *dir, + const struct qstr *qstr, + const char **name, void **value, + size_t *len); + int (*inode_create)(struct inode *dir, struct dentry *dentry, + umode_t mode); + int (*inode_link)(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry); + int (*inode_unlink)(struct inode *dir, struct dentry *dentry); + int (*inode_symlink)(struct inode *dir, struct dentry *dentry, + const char *old_name); + int (*inode_mkdir)(struct inode *dir, struct dentry *dentry, + umode_t mode); + int (*inode_rmdir)(struct inode *dir, struct dentry *dentry); + int (*inode_mknod)(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t dev); + int (*inode_rename)(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry); + int (*inode_readlink)(struct dentry *dentry); + int (*inode_follow_link)(struct dentry *dentry, struct inode *inode, + bool rcu); + int (*inode_permission)(struct inode *inode, int mask); + int (*inode_setattr)(struct dentry *dentry, struct iattr *attr); + int (*inode_getattr)(const struct path *path); + int (*inode_setxattr)(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); + void (*inode_post_setxattr)(struct dentry *dentry, const char *name, + const void *value, size_t size, + int flags); + int (*inode_getxattr)(struct dentry *dentry, const char *name); + int (*inode_listxattr)(struct dentry *dentry); + int (*inode_removexattr)(struct dentry *dentry, const char *name); + int (*inode_need_killpriv)(struct dentry *dentry); + int (*inode_killpriv)(struct dentry *dentry); + int (*inode_getsecurity)(const struct inode *inode, const char *name, + void **buffer, bool alloc); + int (*inode_setsecurity)(struct inode *inode, const char *name, + const void *value, size_t size, + int flags); + int (*inode_listsecurity)(struct inode *inode, char *buffer, + size_t buffer_size); + void (*inode_getsecid)(const struct inode *inode, u32 *secid); + + int (*file_permission)(struct file *file, int mask); + int (*file_alloc_security)(struct file *file); + void (*file_free_security)(struct file *file); + int (*file_ioctl)(struct file *file, unsigned int cmd, + unsigned long arg); + int (*mmap_addr)(unsigned long addr); + int (*mmap_file)(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); + int (*file_mprotect)(struct vm_area_struct *vma, unsigned long reqprot, + unsigned long prot); + int (*file_lock)(struct file *file, unsigned int cmd); + int (*file_fcntl)(struct file *file, unsigned int cmd, + unsigned long arg); + void (*file_set_fowner)(struct file *file); + int (*file_send_sigiotask)(struct task_struct *tsk, + struct fown_struct *fown, int sig); + int (*file_receive)(struct file *file); + int (*file_open)(struct file *file, const struct cred *cred); + + int (*task_create)(unsigned long clone_flags); + void (*task_free)(struct task_struct *task); + int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); + void (*cred_free)(struct cred *cred); + int (*cred_prepare)(struct cred *new, const struct cred *old, + gfp_t gfp); + void (*cred_transfer)(struct cred *new, const struct cred *old); + int (*kernel_act_as)(struct cred *new, u32 secid); + int (*kernel_create_files_as)(struct cred *new, struct inode *inode); + int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); + int (*kernel_module_request)(char *kmod_name); + int (*kernel_module_from_file)(struct file *file); + int (*task_fix_setuid)(struct cred *new, const struct cred *old, + int flags); + int (*task_setpgid)(struct task_struct *p, pid_t pgid); + int (*task_getpgid)(struct task_struct *p); + int (*task_getsid)(struct task_struct *p); + void (*task_getsecid)(struct task_struct *p, u32 *secid); + int (*task_setnice)(struct task_struct *p, int nice); + int (*task_setioprio)(struct task_struct *p, int ioprio); + int (*task_getioprio)(struct task_struct *p); + int (*task_setrlimit)(struct task_struct *p, unsigned int resource, + struct rlimit *new_rlim); + int (*task_setscheduler)(struct task_struct *p); + int (*task_getscheduler)(struct task_struct *p); + int (*task_movememory)(struct task_struct *p); + int (*task_kill)(struct task_struct *p, struct siginfo *info, + int sig, u32 secid); + int (*task_wait)(struct task_struct *p); + int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); + void (*task_to_inode)(struct task_struct *p, struct inode *inode); + + int (*ipc_permission)(struct kern_ipc_perm *ipcp, short flag); + void (*ipc_getsecid)(struct kern_ipc_perm *ipcp, u32 *secid); + + int (*msg_msg_alloc_security)(struct msg_msg *msg); + void (*msg_msg_free_security)(struct msg_msg *msg); + + int (*msg_queue_alloc_security)(struct msg_queue *msq); + void (*msg_queue_free_security)(struct msg_queue *msq); + int (*msg_queue_associate)(struct msg_queue *msq, int msqflg); + int (*msg_queue_msgctl)(struct msg_queue *msq, int cmd); + int (*msg_queue_msgsnd)(struct msg_queue *msq, struct msg_msg *msg, + int msqflg); + int (*msg_queue_msgrcv)(struct msg_queue *msq, struct msg_msg *msg, + struct task_struct *target, long type, + int mode); + + int (*shm_alloc_security)(struct shmid_kernel *shp); + void (*shm_free_security)(struct shmid_kernel *shp); + int (*shm_associate)(struct shmid_kernel *shp, int shmflg); + int (*shm_shmctl)(struct shmid_kernel *shp, int cmd); + int (*shm_shmat)(struct shmid_kernel *shp, char __user *shmaddr, + int shmflg); + + int (*sem_alloc_security)(struct sem_array *sma); + void (*sem_free_security)(struct sem_array *sma); + int (*sem_associate)(struct sem_array *sma, int semflg); + int (*sem_semctl)(struct sem_array *sma, int cmd); + int (*sem_semop)(struct sem_array *sma, struct sembuf *sops, + unsigned nsops, int alter); + + int (*netlink_send)(struct sock *sk, struct sk_buff *skb); + + void (*d_instantiate)(struct dentry *dentry, struct inode *inode); + + int (*getprocattr)(struct task_struct *p, char *name, char **value); + int (*setprocattr)(struct task_struct *p, char *name, void *value, + size_t size); + int (*ismaclabel)(const char *name); + int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen); + int (*secctx_to_secid)(const char *secdata, u32 seclen, u32 *secid); + void (*release_secctx)(char *secdata, u32 seclen); + + int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen); + int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen); + int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); + +#ifdef CONFIG_SECURITY_NETWORK + int (*unix_stream_connect)(struct sock *sock, struct sock *other, + struct sock *newsk); + int (*unix_may_send)(struct socket *sock, struct socket *other); + + int (*socket_create)(int family, int type, int protocol, int kern); + int (*socket_post_create)(struct socket *sock, int family, int type, + int protocol, int kern); + int (*socket_bind)(struct socket *sock, struct sockaddr *address, + int addrlen); + int (*socket_connect)(struct socket *sock, struct sockaddr *address, + int addrlen); + int (*socket_listen)(struct socket *sock, int backlog); + int (*socket_accept)(struct socket *sock, struct socket *newsock); + int (*socket_sendmsg)(struct socket *sock, struct msghdr *msg, + int size); + int (*socket_recvmsg)(struct socket *sock, struct msghdr *msg, + int size, int flags); + int (*socket_getsockname)(struct socket *sock); + int (*socket_getpeername)(struct socket *sock); + int (*socket_getsockopt)(struct socket *sock, int level, int optname); + int (*socket_setsockopt)(struct socket *sock, int level, int optname); + int (*socket_shutdown)(struct socket *sock, int how); + int (*socket_sock_rcv_skb)(struct sock *sk, struct sk_buff *skb); + int (*socket_getpeersec_stream)(struct socket *sock, + char __user *optval, + int __user *optlen, unsigned len); + int (*socket_getpeersec_dgram)(struct socket *sock, + struct sk_buff *skb, u32 *secid); + int (*sk_alloc_security)(struct sock *sk, int family, gfp_t priority); + void (*sk_free_security)(struct sock *sk); + void (*sk_clone_security)(const struct sock *sk, struct sock *newsk); + void (*sk_getsecid)(struct sock *sk, u32 *secid); + void (*sock_graft)(struct sock *sk, struct socket *parent); + int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + void (*inet_csk_clone)(struct sock *newsk, + const struct request_sock *req); + void (*inet_conn_established)(struct sock *sk, struct sk_buff *skb); + int (*secmark_relabel_packet)(u32 secid); + void (*secmark_refcount_inc)(void); + void (*secmark_refcount_dec)(void); + void (*req_classify_flow)(const struct request_sock *req, + struct flowi *fl); + int (*tun_dev_alloc_security)(void **security); + void (*tun_dev_free_security)(void *security); + int (*tun_dev_create)(void); + int (*tun_dev_attach_queue)(void *security); + int (*tun_dev_attach)(struct sock *sk, void *security); + int (*tun_dev_open)(void *security); +#endif /* CONFIG_SECURITY_NETWORK */ + +#ifdef CONFIG_SECURITY_NETWORK_XFRM + int (*xfrm_policy_alloc_security)(struct xfrm_sec_ctx **ctxp, + struct xfrm_user_sec_ctx *sec_ctx, + gfp_t gfp); + int (*xfrm_policy_clone_security)(struct xfrm_sec_ctx *old_ctx, + struct xfrm_sec_ctx **new_ctx); + void (*xfrm_policy_free_security)(struct xfrm_sec_ctx *ctx); + int (*xfrm_policy_delete_security)(struct xfrm_sec_ctx *ctx); + int (*xfrm_state_alloc)(struct xfrm_state *x, + struct xfrm_user_sec_ctx *sec_ctx); + int (*xfrm_state_alloc_acquire)(struct xfrm_state *x, + struct xfrm_sec_ctx *polsec, + u32 secid); + void (*xfrm_state_free_security)(struct xfrm_state *x); + int (*xfrm_state_delete_security)(struct xfrm_state *x); + int (*xfrm_policy_lookup)(struct xfrm_sec_ctx *ctx, u32 fl_secid, + u8 dir); + int (*xfrm_state_pol_flow_match)(struct xfrm_state *x, + struct xfrm_policy *xp, + const struct flowi *fl); + int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall); +#endif /* CONFIG_SECURITY_NETWORK_XFRM */ + + /* key management security hooks */ +#ifdef CONFIG_KEYS + int (*key_alloc)(struct key *key, const struct cred *cred, + unsigned long flags); + void (*key_free)(struct key *key); + int (*key_permission)(key_ref_t key_ref, const struct cred *cred, + unsigned perm); + int (*key_getsecurity)(struct key *key, char **_buffer); +#endif /* CONFIG_KEYS */ + +#ifdef CONFIG_AUDIT + int (*audit_rule_init)(u32 field, u32 op, char *rulestr, + void **lsmrule); + int (*audit_rule_known)(struct audit_krule *krule); + int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule, + struct audit_context *actx); + void (*audit_rule_free)(void *lsmrule); +#endif /* CONFIG_AUDIT */ +}; + +struct security_hook_heads { + struct list_head binder_set_context_mgr; + struct list_head binder_transaction; + struct list_head binder_transfer_binder; + struct list_head binder_transfer_file; + struct list_head ptrace_access_check; + struct list_head ptrace_traceme; + struct list_head capget; + struct list_head capset; + struct list_head capable; + struct list_head quotactl; + struct list_head quota_on; + struct list_head syslog; + struct list_head settime; + struct list_head vm_enough_memory; + struct list_head bprm_set_creds; + struct list_head bprm_check_security; + struct list_head bprm_secureexec; + struct list_head bprm_committing_creds; + struct list_head bprm_committed_creds; + struct list_head sb_alloc_security; + struct list_head sb_free_security; + struct list_head sb_copy_data; + struct list_head sb_remount; + struct list_head sb_kern_mount; + struct list_head sb_show_options; + struct list_head sb_statfs; + struct list_head sb_mount; + struct list_head sb_umount; + struct list_head sb_pivotroot; + struct list_head sb_set_mnt_opts; + struct list_head sb_clone_mnt_opts; + struct list_head sb_parse_opts_str; + struct list_head dentry_init_security; +#ifdef CONFIG_SECURITY_PATH + struct list_head path_unlink; + struct list_head path_mkdir; + struct list_head path_rmdir; + struct list_head path_mknod; + struct list_head path_truncate; + struct list_head path_symlink; + struct list_head path_link; + struct list_head path_rename; + struct list_head path_chmod; + struct list_head path_chown; + struct list_head path_chroot; +#endif + struct list_head inode_alloc_security; + struct list_head inode_free_security; + struct list_head inode_init_security; + struct list_head inode_create; + struct list_head inode_link; + struct list_head inode_unlink; + struct list_head inode_symlink; + struct list_head inode_mkdir; + struct list_head inode_rmdir; + struct list_head inode_mknod; + struct list_head inode_rename; + struct list_head inode_readlink; + struct list_head inode_follow_link; + struct list_head inode_permission; + struct list_head inode_setattr; + struct list_head inode_getattr; + struct list_head inode_setxattr; + struct list_head inode_post_setxattr; + struct list_head inode_getxattr; + struct list_head inode_listxattr; + struct list_head inode_removexattr; + struct list_head inode_need_killpriv; + struct list_head inode_killpriv; + struct list_head inode_getsecurity; + struct list_head inode_setsecurity; + struct list_head inode_listsecurity; + struct list_head inode_getsecid; + struct list_head file_permission; + struct list_head file_alloc_security; + struct list_head file_free_security; + struct list_head file_ioctl; + struct list_head mmap_addr; + struct list_head mmap_file; + struct list_head file_mprotect; + struct list_head file_lock; + struct list_head file_fcntl; + struct list_head file_set_fowner; + struct list_head file_send_sigiotask; + struct list_head file_receive; + struct list_head file_open; + struct list_head task_create; + struct list_head task_free; + struct list_head cred_alloc_blank; + struct list_head cred_free; + struct list_head cred_prepare; + struct list_head cred_transfer; + struct list_head kernel_act_as; + struct list_head kernel_create_files_as; + struct list_head kernel_fw_from_file; + struct list_head kernel_module_request; + struct list_head kernel_module_from_file; + struct list_head task_fix_setuid; + struct list_head task_setpgid; + struct list_head task_getpgid; + struct list_head task_getsid; + struct list_head task_getsecid; + struct list_head task_setnice; + struct list_head task_setioprio; + struct list_head task_getioprio; + struct list_head task_setrlimit; + struct list_head task_setscheduler; + struct list_head task_getscheduler; + struct list_head task_movememory; + struct list_head task_kill; + struct list_head task_wait; + struct list_head task_prctl; + struct list_head task_to_inode; + struct list_head ipc_permission; + struct list_head ipc_getsecid; + struct list_head msg_msg_alloc_security; + struct list_head msg_msg_free_security; + struct list_head msg_queue_alloc_security; + struct list_head msg_queue_free_security; + struct list_head msg_queue_associate; + struct list_head msg_queue_msgctl; + struct list_head msg_queue_msgsnd; + struct list_head msg_queue_msgrcv; + struct list_head shm_alloc_security; + struct list_head shm_free_security; + struct list_head shm_associate; + struct list_head shm_shmctl; + struct list_head shm_shmat; + struct list_head sem_alloc_security; + struct list_head sem_free_security; + struct list_head sem_associate; + struct list_head sem_semctl; + struct list_head sem_semop; + struct list_head netlink_send; + struct list_head d_instantiate; + struct list_head getprocattr; + struct list_head setprocattr; + struct list_head ismaclabel; + struct list_head secid_to_secctx; + struct list_head secctx_to_secid; + struct list_head release_secctx; + struct list_head inode_notifysecctx; + struct list_head inode_setsecctx; + struct list_head inode_getsecctx; +#ifdef CONFIG_SECURITY_NETWORK + struct list_head unix_stream_connect; + struct list_head unix_may_send; + struct list_head socket_create; + struct list_head socket_post_create; + struct list_head socket_bind; + struct list_head socket_connect; + struct list_head socket_listen; + struct list_head socket_accept; + struct list_head socket_sendmsg; + struct list_head socket_recvmsg; + struct list_head socket_getsockname; + struct list_head socket_getpeername; + struct list_head socket_getsockopt; + struct list_head socket_setsockopt; + struct list_head socket_shutdown; + struct list_head socket_sock_rcv_skb; + struct list_head socket_getpeersec_stream; + struct list_head socket_getpeersec_dgram; + struct list_head sk_alloc_security; + struct list_head sk_free_security; + struct list_head sk_clone_security; + struct list_head sk_getsecid; + struct list_head sock_graft; + struct list_head inet_conn_request; + struct list_head inet_csk_clone; + struct list_head inet_conn_established; + struct list_head secmark_relabel_packet; + struct list_head secmark_refcount_inc; + struct list_head secmark_refcount_dec; + struct list_head req_classify_flow; + struct list_head tun_dev_alloc_security; + struct list_head tun_dev_free_security; + struct list_head tun_dev_create; + struct list_head tun_dev_attach_queue; + struct list_head tun_dev_attach; + struct list_head tun_dev_open; + struct list_head skb_owned_by; +#endif /* CONFIG_SECURITY_NETWORK */ +#ifdef CONFIG_SECURITY_NETWORK_XFRM + struct list_head xfrm_policy_alloc_security; + struct list_head xfrm_policy_clone_security; + struct list_head xfrm_policy_free_security; + struct list_head xfrm_policy_delete_security; + struct list_head xfrm_state_alloc; + struct list_head xfrm_state_alloc_acquire; + struct list_head xfrm_state_free_security; + struct list_head xfrm_state_delete_security; + struct list_head xfrm_policy_lookup; + struct list_head xfrm_state_pol_flow_match; + struct list_head xfrm_decode_session; +#endif /* CONFIG_SECURITY_NETWORK_XFRM */ +#ifdef CONFIG_KEYS + struct list_head key_alloc; + struct list_head key_free; + struct list_head key_permission; + struct list_head key_getsecurity; +#endif /* CONFIG_KEYS */ +#ifdef CONFIG_AUDIT + struct list_head audit_rule_init; + struct list_head audit_rule_known; + struct list_head audit_rule_match; + struct list_head audit_rule_free; +#endif /* CONFIG_AUDIT */ +}; + +/* + * Security module hook list structure. + * For use with generic list macros for common operations. + */ +struct security_hook_list { + struct list_head list; + struct list_head *head; + union security_list_options hook; +}; + +/* + * Initializing a security_hook_list structure takes + * up a lot of space in a source file. This macro takes + * care of the common case and reduces the amount of + * text involved. + */ +#define LSM_HOOK_INIT(HEAD, HOOK) \ + { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } + +extern struct security_hook_heads security_hook_heads; + +static inline void security_add_hooks(struct security_hook_list *hooks, + int count) +{ + int i; + + for (i = 0; i < count; i++) + list_add_tail_rcu(&hooks[i].list, hooks[i].head); +} + +#ifdef CONFIG_SECURITY_SELINUX_DISABLE +/* + * Assuring the safety of deleting a security module is up to + * the security module involved. This may entail ordering the + * module's hook list in a particular way, refusing to disable + * the module once a policy is loaded or any number of other + * actions better imagined than described. + * + * The name of the configuration option reflects the only module + * that currently uses the mechanism. Any developer who thinks + * disabling their module is a good idea needs to be at least as + * careful as the SELinux team. + */ +static inline void security_delete_hooks(struct security_hook_list *hooks, + int count) +{ + int i; + + for (i = 0; i < count; i++) + list_del_rcu(&hooks[i].list); +} +#endif /* CONFIG_SECURITY_SELINUX_DISABLE */ + +extern int __init security_module_enable(const char *module); +extern void __init capability_add_hooks(void); +#ifdef CONFIG_SECURITY_YAMA_STACKED +void __init yama_add_hooks(void); +#endif + +#endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index 1726ccbd8009..44348710953f 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -40,6 +40,8 @@ struct mbox_client { void (*tx_done)(struct mbox_client *cl, void *mssg, int r); }; +struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, + const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); int mbox_send_message(struct mbox_chan *chan, void *mssg); void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */ diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index d4cf96f07cfc..68c42454439b 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -72,7 +72,7 @@ struct mbox_chan_ops { */ struct mbox_controller { struct device *dev; - struct mbox_chan_ops *ops; + const struct mbox_chan_ops *ops; struct mbox_chan *chans; int num_chans; bool txdone_irq; diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 611b69fa8594..1f7bc630d225 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -54,11 +54,16 @@ struct mbus_dram_target_info */ #ifdef CONFIG_PLAT_ORION extern const struct mbus_dram_target_info *mv_mbus_dram_info(void); +extern const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void); #else static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) { return NULL; } +static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void) +{ + return NULL; +} #endif int mvebu_mbus_save_cpu_target(u32 *store_addr); diff --git a/include/linux/mdio-gpio.h b/include/linux/mdio-gpio.h index 66c30a763b10..11f00cdabe3d 100644 --- a/include/linux/mdio-gpio.h +++ b/include/linux/mdio-gpio.h @@ -23,7 +23,8 @@ struct mdio_gpio_platform_data { bool mdio_active_low; bool mdo_active_low; - unsigned int phy_mask; + u32 phy_mask; + u32 phy_ignore_ta_mask; int irqs[PHY_MAX_ADDR]; /* reset callback */ int (*reset)(struct mii_bus *bus); diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 0819d36a3a74..a16b1f9c1aca 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -7,6 +7,42 @@ struct mei_cl_device; +typedef void (*mei_cl_event_cb_t)(struct mei_cl_device *device, + u32 events, void *context); + +/** + * struct mei_cl_device - MEI device handle + * An mei_cl_device pointer is returned from mei_add_device() + * and links MEI bus clients to their actual ME host client pointer. + * Drivers for MEI devices will get an mei_cl_device pointer + * when being probed and shall use it for doing ME bus I/O. + * + * @dev: linux driver model device pointer + * @me_cl: me client + * @cl: mei client + * @name: device name + * @event_work: async work to execute event callback + * @event_cb: Drivers register this callback to get asynchronous ME + * events (e.g. Rx buffer pending) notifications. + * @event_context: event callback run context + * @events: Events bitmask sent to the driver. + * @priv_data: client private data + */ +struct mei_cl_device { + struct device dev; + + struct mei_me_client *me_cl; + struct mei_cl *cl; + char name[MEI_CL_NAME_SIZE]; + + struct work_struct event_work; + mei_cl_event_cb_t event_cb; + void *event_context; + unsigned long events; + + void *priv_data; +}; + struct mei_cl_driver { struct device_driver driver; const char *name; @@ -28,8 +64,6 @@ void mei_cl_driver_unregister(struct mei_cl_driver *driver); ssize_t mei_cl_send(struct mei_cl_device *device, u8 *buf, size_t length); ssize_t mei_cl_recv(struct mei_cl_device *device, u8 *buf, size_t length); -typedef void (*mei_cl_event_cb_t)(struct mei_cl_device *device, - u32 events, void *context); int mei_cl_register_event_cb(struct mei_cl_device *device, mei_cl_event_cb_t read_cb, void *context); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9497ec7c77ea..cc4b01972060 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -21,7 +21,11 @@ #define INIT_PHYSMEM_REGIONS 4 /* Definition of memblock flags. */ -#define MEMBLOCK_HOTPLUG 0x1 /* hotpluggable region */ +enum { + MEMBLOCK_NONE = 0x0, /* No special request */ + MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ + MEMBLOCK_MIRROR = 0x2, /* mirrored region */ +}; struct memblock_region { phys_addr_t base; @@ -61,7 +65,7 @@ extern bool movable_node_enabled; phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, - int nid); + int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); @@ -75,6 +79,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); +int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); +ulong choose_memblock_flags(void); /* Low level functions */ int memblock_add_range(struct memblock_type *type, @@ -85,14 +91,19 @@ int memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size); -void __next_mem_range(u64 *idx, int nid, struct memblock_type *type_a, +void __next_mem_range(u64 *idx, int nid, ulong flags, + struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, +void __next_mem_range_rev(u64 *idx, int nid, ulong flags, + struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); +void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, + phys_addr_t *out_end); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. @@ -100,16 +111,17 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, * @type_a: ptr to memblock_type to iterate * @type_b: ptr to memblock_type which excludes from the iteration * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range(i, type_a, type_b, nid, \ +#define for_each_mem_range(i, type_a, type_b, nid, flags, \ p_start, p_end, p_nid) \ - for (i = 0, __next_mem_range(&i, nid, type_a, type_b, \ + for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ - __next_mem_range(&i, nid, type_a, type_b, \ + __next_mem_range(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) /** @@ -119,19 +131,35 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a, * @type_a: ptr to memblock_type to iterate * @type_b: ptr to memblock_type which excludes from the iteration * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL */ -#define for_each_mem_range_rev(i, type_a, type_b, nid, \ +#define for_each_mem_range_rev(i, type_a, type_b, nid, flags, \ p_start, p_end, p_nid) \ for (i = (u64)ULLONG_MAX, \ - __next_mem_range_rev(&i, nid, type_a, type_b, \ + __next_mem_range_rev(&i, nid, flags, type_a, type_b,\ p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ - __next_mem_range_rev(&i, nid, type_a, type_b, \ + __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) +/** + * for_each_reserved_mem_region - iterate over all reserved memblock areas + * @i: u64 used as loop variable + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * + * Walks over reserved areas of memblock. Available as soon as memblock + * is initialized. + */ +#define for_each_reserved_mem_region(i, p_start, p_end) \ + for (i = 0UL, \ + __next_reserved_mem_region(&i, p_start, p_end); \ + i != (u64)ULLONG_MAX; \ + __next_reserved_mem_region(&i, p_start, p_end)) + #ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { @@ -153,6 +181,11 @@ static inline bool movable_node_is_enabled(void) } #endif +static inline bool memblock_is_mirror(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_MIRROR; +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); @@ -181,13 +214,14 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL + * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock. Available as * soon as memblock is initialized. */ -#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \ +#define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid) \ for_each_mem_range(i, &memblock.memory, &memblock.reserved, \ - nid, p_start, p_end, p_nid) + nid, flags, p_start, p_end, p_nid) /** * for_each_free_mem_range_reverse - rev-iterate through free memblock areas @@ -196,13 +230,15 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL + * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock in reverse * order. Available as soon as memblock is initialized. */ -#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \ +#define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end, \ + p_nid) \ for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ - nid, p_start, p_end, p_nid) + nid, flags, p_start, p_end, p_nid) static inline void memblock_set_region_flags(struct memblock_region *r, unsigned long flags) @@ -273,7 +309,8 @@ static inline bool memblock_bottom_up(void) { return false; } #define MEMBLOCK_ALLOC_ACCESSIBLE 0 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, - phys_addr_t start, phys_addr_t end); + phys_addr_t start, phys_addr_t end, + ulong flags); phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 72dff5fb0d0c..73b02b0a8f60 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -41,6 +41,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */ MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, @@ -67,6 +68,8 @@ enum mem_cgroup_events_index { }; #ifdef CONFIG_MEMCG +extern struct cgroup_subsys_state *mem_cgroup_root_css; + void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr); @@ -112,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, } extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); +extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, @@ -195,6 +199,8 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; +#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) + static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr) @@ -382,6 +388,29 @@ enum { OVER_LIMIT, }; +#ifdef CONFIG_CGROUP_WRITEBACK + +struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, + unsigned long *pdirty, unsigned long *pwriteback); + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + return NULL; +} + +static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, + unsigned long *pavail, + unsigned long *pdirty, + unsigned long *pwriteback) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + struct sock; #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk); @@ -463,6 +492,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) if (!memcg_kmem_enabled()) return true; + if (gfp & __GFP_NOACCOUNT) + return true; /* * __GFP_NOFAIL allocations will move on even if charging is not * possible. Therefore we don't even try, and have this allocation @@ -522,6 +553,8 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { if (!memcg_kmem_enabled()) return cachep; + if (gfp & __GFP_NOACCOUNT) + return cachep; if (gfp & __GFP_NOFAIL) return cachep; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h index 16a498f48169..2f434f4f79a1 100644 --- a/include/linux/mfd/arizona/core.h +++ b/include/linux/mfd/arizona/core.h @@ -117,6 +117,7 @@ struct arizona { int num_core_supplies; struct regulator_bulk_data core_supplies[ARIZONA_MAX_CORE_SUPPLIES]; struct regulator *dcvdd; + bool has_fully_powered_off; struct arizona_pdata pdata; @@ -153,7 +154,15 @@ int arizona_request_irq(struct arizona *arizona, int irq, char *name, void arizona_free_irq(struct arizona *arizona, int irq, void *data); int arizona_set_irq_wake(struct arizona *arizona, int irq, int on); +#ifdef CONFIG_MFD_WM5102 int wm5102_patch(struct arizona *arizona); +#else +static inline int wm5102_patch(struct arizona *arizona) +{ + return 0; +} +#endif + int wm5110_patch(struct arizona *arizona); int wm8997_patch(struct arizona *arizona); diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 1789cb0f4f17..43db4faad143 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -121,6 +121,9 @@ struct arizona_pdata { /** GPIO used for mic isolation with HPDET */ int hpdet_id_gpio; + /** Channel to use for headphone detection */ + unsigned int hpdet_channel; + /** Extra debounce timeout used during initial mic detection (ms) */ int micd_detect_debounce; @@ -156,7 +159,10 @@ struct arizona_pdata { /** MICBIAS configurations */ struct arizona_micbias micbias[ARIZONA_MAX_MICBIAS]; - /** Mode of input structures */ + /** + * Mode of input structures + * One of the ARIZONA_INMODE_xxx values + */ int inmode[ARIZONA_MAX_INPUT]; /** Mode for outputs */ diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index aacc10d7789c..3499d36e6067 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -2515,9 +2515,12 @@ #define ARIZONA_IN1_DMIC_SUP_MASK 0x1800 /* IN1_DMIC_SUP - [12:11] */ #define ARIZONA_IN1_DMIC_SUP_SHIFT 11 /* IN1_DMIC_SUP - [12:11] */ #define ARIZONA_IN1_DMIC_SUP_WIDTH 2 /* IN1_DMIC_SUP - [12:11] */ -#define ARIZONA_IN1_MODE_MASK 0x0600 /* IN1_MODE - [10:9] */ -#define ARIZONA_IN1_MODE_SHIFT 9 /* IN1_MODE - [10:9] */ -#define ARIZONA_IN1_MODE_WIDTH 2 /* IN1_MODE - [10:9] */ +#define ARIZONA_IN1_MODE_MASK 0x0400 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_MODE_SHIFT 10 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_MODE_WIDTH 1 /* IN1_MODE - [10] */ +#define ARIZONA_IN1_SINGLE_ENDED_MASK 0x0200 /* IN1_MODE - [9] */ +#define ARIZONA_IN1_SINGLE_ENDED_SHIFT 9 /* IN1_MODE - [9] */ +#define ARIZONA_IN1_SINGLE_ENDED_WIDTH 1 /* IN1_MODE - [9] */ #define ARIZONA_IN1L_PGA_VOL_MASK 0x00FE /* IN1L_PGA_VOL - [7:1] */ #define ARIZONA_IN1L_PGA_VOL_SHIFT 1 /* IN1L_PGA_VOL - [7:1] */ #define ARIZONA_IN1L_PGA_VOL_WIDTH 7 /* IN1L_PGA_VOL - [7:1] */ @@ -2588,9 +2591,12 @@ #define ARIZONA_IN2_DMIC_SUP_MASK 0x1800 /* IN2_DMIC_SUP - [12:11] */ #define ARIZONA_IN2_DMIC_SUP_SHIFT 11 /* IN2_DMIC_SUP - [12:11] */ #define ARIZONA_IN2_DMIC_SUP_WIDTH 2 /* IN2_DMIC_SUP - [12:11] */ -#define ARIZONA_IN2_MODE_MASK 0x0600 /* IN2_MODE - [10:9] */ -#define ARIZONA_IN2_MODE_SHIFT 9 /* IN2_MODE - [10:9] */ -#define ARIZONA_IN2_MODE_WIDTH 2 /* IN2_MODE - [10:9] */ +#define ARIZONA_IN2_MODE_MASK 0x0400 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_MODE_SHIFT 10 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_MODE_WIDTH 1 /* IN2_MODE - [10] */ +#define ARIZONA_IN2_SINGLE_ENDED_MASK 0x0200 /* IN2_MODE - [9] */ +#define ARIZONA_IN2_SINGLE_ENDED_SHIFT 9 /* IN2_MODE - [9] */ +#define ARIZONA_IN2_SINGLE_ENDED_WIDTH 1 /* IN2_MODE - [9] */ #define ARIZONA_IN2L_PGA_VOL_MASK 0x00FE /* IN2L_PGA_VOL - [7:1] */ #define ARIZONA_IN2L_PGA_VOL_SHIFT 1 /* IN2L_PGA_VOL - [7:1] */ #define ARIZONA_IN2L_PGA_VOL_WIDTH 7 /* IN2L_PGA_VOL - [7:1] */ @@ -2661,9 +2667,12 @@ #define ARIZONA_IN3_DMIC_SUP_MASK 0x1800 /* IN3_DMIC_SUP - [12:11] */ #define ARIZONA_IN3_DMIC_SUP_SHIFT 11 /* IN3_DMIC_SUP - [12:11] */ #define ARIZONA_IN3_DMIC_SUP_WIDTH 2 /* IN3_DMIC_SUP - [12:11] */ -#define ARIZONA_IN3_MODE_MASK 0x0600 /* IN3_MODE - [10:9] */ -#define ARIZONA_IN3_MODE_SHIFT 9 /* IN3_MODE - [10:9] */ -#define ARIZONA_IN3_MODE_WIDTH 2 /* IN3_MODE - [10:9] */ +#define ARIZONA_IN3_MODE_MASK 0x0400 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_MODE_SHIFT 10 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_MODE_WIDTH 1 /* IN3_MODE - [10] */ +#define ARIZONA_IN3_SINGLE_ENDED_MASK 0x0200 /* IN3_MODE - [9] */ +#define ARIZONA_IN3_SINGLE_ENDED_SHIFT 9 /* IN3_MODE - [9] */ +#define ARIZONA_IN3_SINGLE_ENDED_WIDTH 1 /* IN3_MODE - [9] */ #define ARIZONA_IN3L_PGA_VOL_MASK 0x00FE /* IN3L_PGA_VOL - [7:1] */ #define ARIZONA_IN3L_PGA_VOL_SHIFT 1 /* IN3L_PGA_VOL - [7:1] */ #define ARIZONA_IN3L_PGA_VOL_WIDTH 7 /* IN3L_PGA_VOL - [7:1] */ diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index dfabd6db7ddf..c2aa853fb412 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -14,6 +14,7 @@ enum { AXP202_ID = 0, AXP209_ID, + AXP221_ID, AXP288_ID, NR_AXP20X_VARIANTS, }; @@ -45,6 +46,28 @@ enum { #define AXP20X_V_LTF_DISCHRG 0x3c #define AXP20X_V_HTF_DISCHRG 0x3d +#define AXP22X_PWR_OUT_CTRL1 0x10 +#define AXP22X_PWR_OUT_CTRL2 0x12 +#define AXP22X_PWR_OUT_CTRL3 0x13 +#define AXP22X_DLDO1_V_OUT 0x15 +#define AXP22X_DLDO2_V_OUT 0x16 +#define AXP22X_DLDO3_V_OUT 0x17 +#define AXP22X_DLDO4_V_OUT 0x18 +#define AXP22X_ELDO1_V_OUT 0x19 +#define AXP22X_ELDO2_V_OUT 0x1a +#define AXP22X_ELDO3_V_OUT 0x1b +#define AXP22X_DC5LDO_V_OUT 0x1c +#define AXP22X_DCDC1_V_OUT 0x21 +#define AXP22X_DCDC2_V_OUT 0x22 +#define AXP22X_DCDC3_V_OUT 0x23 +#define AXP22X_DCDC4_V_OUT 0x24 +#define AXP22X_DCDC5_V_OUT 0x25 +#define AXP22X_DCDC23_V_RAMP_CTRL 0x27 +#define AXP22X_ALDO1_V_OUT 0x28 +#define AXP22X_ALDO2_V_OUT 0x29 +#define AXP22X_ALDO3_V_OUT 0x2a +#define AXP22X_CHRG_CTRL3 0x35 + /* Interrupt */ #define AXP20X_IRQ1_EN 0x40 #define AXP20X_IRQ2_EN 0x41 @@ -100,6 +123,9 @@ enum { #define AXP20X_VBUS_MON 0x8b #define AXP20X_OVER_TMP 0x8f +#define AXP22X_PWREN_CTRL1 0x8c +#define AXP22X_PWREN_CTRL2 0x8d + /* GPIO */ #define AXP20X_GPIO0_CTRL 0x90 #define AXP20X_LDO5_V_OUT 0x91 @@ -108,6 +134,11 @@ enum { #define AXP20X_GPIO20_SS 0x94 #define AXP20X_GPIO3_CTRL 0x95 +#define AXP22X_LDO_IO0_V_OUT 0x91 +#define AXP22X_LDO_IO1_V_OUT 0x93 +#define AXP22X_GPIO_STATE 0x94 +#define AXP22X_GPIO_PULL_DOWN 0x95 + /* Battery */ #define AXP20X_CHRG_CC_31_24 0xb0 #define AXP20X_CHRG_CC_23_16 0xb1 @@ -120,6 +151,9 @@ enum { #define AXP20X_CC_CTRL 0xb8 #define AXP20X_FG_RES 0xb9 +/* AXP22X specific registers */ +#define AXP22X_BATLOW_THRES1 0xe6 + /* AXP288 specific registers */ #define AXP288_PMIC_ADC_H 0x56 #define AXP288_PMIC_ADC_L 0x57 @@ -158,6 +192,30 @@ enum { AXP20X_REG_ID_MAX, }; +enum { + AXP22X_DCDC1 = 0, + AXP22X_DCDC2, + AXP22X_DCDC3, + AXP22X_DCDC4, + AXP22X_DCDC5, + AXP22X_DC1SW, + AXP22X_DC5LDO, + AXP22X_ALDO1, + AXP22X_ALDO2, + AXP22X_ALDO3, + AXP22X_ELDO1, + AXP22X_ELDO2, + AXP22X_ELDO3, + AXP22X_DLDO1, + AXP22X_DLDO2, + AXP22X_DLDO3, + AXP22X_DLDO4, + AXP22X_RTC_LDO, + AXP22X_LDO_IO0, + AXP22X_LDO_IO1, + AXP22X_REG_ID_MAX, +}; + /* IRQs */ enum { AXP20X_IRQ_ACIN_OVER_V = 1, @@ -199,6 +257,34 @@ enum { AXP20X_IRQ_GPIO0_INPUT, }; +enum axp22x_irqs { + AXP22X_IRQ_ACIN_OVER_V = 1, + AXP22X_IRQ_ACIN_PLUGIN, + AXP22X_IRQ_ACIN_REMOVAL, + AXP22X_IRQ_VBUS_OVER_V, + AXP22X_IRQ_VBUS_PLUGIN, + AXP22X_IRQ_VBUS_REMOVAL, + AXP22X_IRQ_VBUS_V_LOW, + AXP22X_IRQ_BATT_PLUGIN, + AXP22X_IRQ_BATT_REMOVAL, + AXP22X_IRQ_BATT_ENT_ACT_MODE, + AXP22X_IRQ_BATT_EXIT_ACT_MODE, + AXP22X_IRQ_CHARG, + AXP22X_IRQ_CHARG_DONE, + AXP22X_IRQ_BATT_TEMP_HIGH, + AXP22X_IRQ_BATT_TEMP_LOW, + AXP22X_IRQ_DIE_TEMP_HIGH, + AXP22X_IRQ_PEK_SHORT, + AXP22X_IRQ_PEK_LONG, + AXP22X_IRQ_LOW_PWR_LVL1, + AXP22X_IRQ_LOW_PWR_LVL2, + AXP22X_IRQ_TIMER, + AXP22X_IRQ_PEK_RIS_EDGE, + AXP22X_IRQ_PEK_FAL_EDGE, + AXP22X_IRQ_GPIO1_INPUT, + AXP22X_IRQ_GPIO0_INPUT, +}; + enum axp288_irqs { AXP288_IRQ_VBUS_FALL = 2, AXP288_IRQ_VBUS_RISE, @@ -275,4 +361,16 @@ struct axp20x_fg_pdata { int thermistor_curve[MAX_THERM_CURVE_SIZE][2]; }; +struct axp20x_chrg_pdata { + int max_cc; + int max_cv; + int def_cc; + int def_cv; +}; + +struct axp288_extcon_pdata { + /* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */ + struct gpio_desc *gpio_mux_cntl; +}; + #endif /* __LINUX_MFD_AXP20X_H */ diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 324a34683971..da72671a42fa 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -17,10 +17,29 @@ #define __LINUX_MFD_CROS_EC_H #include <linux/cdev.h> +#include <linux/device.h> #include <linux/notifier.h> #include <linux/mfd/cros_ec_commands.h> #include <linux/mutex.h> +#define CROS_EC_DEV_NAME "cros_ec" +#define CROS_EC_DEV_PD_NAME "cros_pd" + +/* + * The EC is unresponsive for a time after a reboot command. Add a + * simple delay to make sure that the bus stays locked. + */ +#define EC_REBOOT_DELAY_MS 50 + +/* + * Max bus-specific overhead incurred by request/responses. + * I2C requires 1 additional byte for requests. + * I2C requires 2 additional bytes for responses. + * */ +#define EC_PROTO_VERSION_UNKNOWN 0 +#define EC_MAX_REQUEST_OVERHEAD 1 +#define EC_MAX_RESPONSE_OVERHEAD 2 + /* * Command interface between EC and AP, for LPC, I2C and SPI interfaces. */ @@ -42,8 +61,7 @@ enum { * @outsize: Outgoing length in bytes * @insize: Max number of bytes to accept from EC * @result: EC's response to the command (separate from communication failure) - * @outdata: Outgoing data to EC - * @indata: Where to put the incoming data from EC + * @data: Where to put the incoming data from EC and outgoing data to EC */ struct cros_ec_command { uint32_t version; @@ -51,18 +69,14 @@ struct cros_ec_command { uint32_t outsize; uint32_t insize; uint32_t result; - uint8_t outdata[EC_PROTO2_MAX_PARAM_SIZE]; - uint8_t indata[EC_PROTO2_MAX_PARAM_SIZE]; + uint8_t data[0]; }; /** * struct cros_ec_device - Information about a ChromeOS EC device * - * @ec_name: name of EC device (e.g. 'chromeos-ec') * @phys_name: name of physical comms layer (e.g. 'i2c-4') * @dev: Device pointer for physical comms device - * @vdev: Device pointer for virtual comms device - * @cdev: Character device structure for virtual comms device * @was_wake_device: true if this device was set to wake the system from * sleep at the last suspend * @cmd_readmem: direct read of the EC memory-mapped region, if supported @@ -74,6 +88,7 @@ struct cros_ec_command { * * @priv: Private data * @irq: Interrupt to use + * @id: Device id * @din: input buffer (for data from EC) * @dout: output buffer (for data to EC) * \note @@ -85,41 +100,72 @@ struct cros_ec_command { * to using dword. * @din_size: size of din buffer to allocate (zero to use static din) * @dout_size: size of dout buffer to allocate (zero to use static dout) - * @parent: pointer to parent device (e.g. i2c or spi device) * @wake_enabled: true if this device can wake the system from sleep * @cmd_xfer: send command to EC and get response * Returns the number of bytes received if the communication succeeded, but * that doesn't mean the EC was happy with the command. The caller * should check msg.result for the EC's result code. + * @pkt_xfer: send packet to EC and get response * @lock: one transaction at a time */ struct cros_ec_device { /* These are used by other drivers that want to talk to the EC */ - const char *ec_name; const char *phys_name; struct device *dev; - struct device *vdev; - struct cdev cdev; bool was_wake_device; struct class *cros_class; int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset, unsigned int bytes, void *dest); /* These are used to implement the platform-specific interface */ + u16 max_request; + u16 max_response; + u16 max_passthru; + u16 proto_version; void *priv; int irq; - uint8_t *din; - uint8_t *dout; + u8 *din; + u8 *dout; int din_size; int dout_size; - struct device *parent; bool wake_enabled; int (*cmd_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); + int (*pkt_xfer)(struct cros_ec_device *ec, + struct cros_ec_command *msg); struct mutex lock; }; +/* struct cros_ec_platform - ChromeOS EC platform information + * + * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) + * used in /dev/ and sysfs. + * @cmd_offset: offset to apply for each command. Set when + * registering a devicde behind another one. + */ +struct cros_ec_platform { + const char *ec_name; + u16 cmd_offset; +}; + +/* + * struct cros_ec_dev - ChromeOS EC device entry point + * + * @class_dev: Device structure used in sysfs + * @cdev: Character device structure in /dev + * @ec_dev: cros_ec_device structure to talk to the physical device + * @dev: pointer to the platform device + * @cmd_offset: offset to apply for each command. + */ +struct cros_ec_dev { + struct device class_dev; + struct cdev cdev; + struct cros_ec_device *ec_dev; + struct device *dev; + u16 cmd_offset; +}; + /** * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device * @@ -198,4 +244,16 @@ int cros_ec_remove(struct cros_ec_device *ec_dev); */ int cros_ec_register(struct cros_ec_device *ec_dev); +/** + * cros_ec_register - Query the protocol version supported by the ChromeOS EC + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_query_all(struct cros_ec_device *ec_dev); + +/* sysfs stuff */ +extern struct attribute_group cros_ec_attr_group; +extern struct attribute_group cros_ec_lightbar_attr_group; + #endif /* __LINUX_MFD_CROS_EC_H */ diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index a49cd41feea7..13b630c10d4c 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -515,7 +515,7 @@ struct ec_host_response { /* * Notes on commands: * - * Each command is an 8-byte command value. Commands which take params or + * Each command is an 16-bit command value. Commands which take params or * return response data specify structs for that data. If no struct is * specified, the command does not input or output data, respectively. * Parameter/response length is implicit in the structs. Some underlying @@ -966,7 +966,7 @@ struct rgb_s { /* List of tweakable parameters. NOTE: It's __packed so it can be sent in a * host command, but the alignment is the same regardless. Keep it that way. */ -struct lightbar_params { +struct lightbar_params_v0 { /* Timing */ int32_t google_ramp_up; int32_t google_ramp_down; @@ -1000,32 +1000,81 @@ struct lightbar_params { struct rgb_s color[8]; /* 0-3 are Google colors */ } __packed; +struct lightbar_params_v1 { + /* Timing */ + int32_t google_ramp_up; + int32_t google_ramp_down; + int32_t s3s0_ramp_up; + int32_t s0_tick_delay[2]; /* AC=0/1 */ + int32_t s0a_tick_delay[2]; /* AC=0/1 */ + int32_t s0s3_ramp_down; + int32_t s3_sleep_for; + int32_t s3_ramp_up; + int32_t s3_ramp_down; + int32_t tap_tick_delay; + int32_t tap_display_time; + + /* Tap-for-battery params */ + uint8_t tap_pct_red; + uint8_t tap_pct_green; + uint8_t tap_seg_min_on; + uint8_t tap_seg_max_on; + uint8_t tap_seg_osc; + uint8_t tap_idx[3]; + + /* Oscillation */ + uint8_t osc_min[2]; /* AC=0/1 */ + uint8_t osc_max[2]; /* AC=0/1 */ + uint8_t w_ofs[2]; /* AC=0/1 */ + + /* Brightness limits based on the backlight and AC. */ + uint8_t bright_bl_off_fixed[2]; /* AC=0/1 */ + uint8_t bright_bl_on_min[2]; /* AC=0/1 */ + uint8_t bright_bl_on_max[2]; /* AC=0/1 */ + + /* Battery level thresholds */ + uint8_t battery_threshold[LB_BATTERY_LEVELS - 1]; + + /* Map [AC][battery_level] to color index */ + uint8_t s0_idx[2][LB_BATTERY_LEVELS]; /* AP is running */ + uint8_t s3_idx[2][LB_BATTERY_LEVELS]; /* AP is sleeping */ + + /* Color palette */ + struct rgb_s color[8]; /* 0-3 are Google colors */ +} __packed; + struct ec_params_lightbar { uint8_t cmd; /* Command (see enum lightbar_command) */ union { struct { /* no args */ - } dump, off, on, init, get_seq, get_params, version; + } dump, off, on, init, get_seq, get_params_v0, get_params_v1, + version, get_brightness, get_demo; - struct num { + struct { uint8_t num; - } brightness, seq, demo; + } set_brightness, seq, demo; - struct reg { + struct { uint8_t ctrl, reg, value; } reg; - struct rgb { + struct { uint8_t led, red, green, blue; - } rgb; + } set_rgb; + + struct { + uint8_t led; + } get_rgb; - struct lightbar_params set_params; + struct lightbar_params_v0 set_params_v0; + struct lightbar_params_v1 set_params_v1; }; } __packed; struct ec_response_lightbar { union { - struct dump { + struct { struct { uint8_t reg; uint8_t ic0; @@ -1033,20 +1082,26 @@ struct ec_response_lightbar { } vals[23]; } dump; - struct get_seq { + struct { uint8_t num; - } get_seq; + } get_seq, get_brightness, get_demo; - struct lightbar_params get_params; + struct lightbar_params_v0 get_params_v0; + struct lightbar_params_v1 get_params_v1; - struct version { + struct { uint32_t num; uint32_t flags; } version; struct { + uint8_t red, green, blue; + } get_rgb; + + struct { /* no return params */ - } off, on, init, brightness, seq, reg, rgb, demo, set_params; + } off, on, init, set_brightness, seq, reg, set_rgb, + demo, set_params_v0, set_params_v1; }; } __packed; @@ -1056,15 +1111,20 @@ enum lightbar_command { LIGHTBAR_CMD_OFF = 1, LIGHTBAR_CMD_ON = 2, LIGHTBAR_CMD_INIT = 3, - LIGHTBAR_CMD_BRIGHTNESS = 4, + LIGHTBAR_CMD_SET_BRIGHTNESS = 4, LIGHTBAR_CMD_SEQ = 5, LIGHTBAR_CMD_REG = 6, - LIGHTBAR_CMD_RGB = 7, + LIGHTBAR_CMD_SET_RGB = 7, LIGHTBAR_CMD_GET_SEQ = 8, LIGHTBAR_CMD_DEMO = 9, - LIGHTBAR_CMD_GET_PARAMS = 10, - LIGHTBAR_CMD_SET_PARAMS = 11, + LIGHTBAR_CMD_GET_PARAMS_V0 = 10, + LIGHTBAR_CMD_SET_PARAMS_V0 = 11, LIGHTBAR_CMD_VERSION = 12, + LIGHTBAR_CMD_GET_BRIGHTNESS = 13, + LIGHTBAR_CMD_GET_RGB = 14, + LIGHTBAR_CMD_GET_DEMO = 15, + LIGHTBAR_CMD_GET_PARAMS_V1 = 16, + LIGHTBAR_CMD_SET_PARAMS_V1 = 17, LIGHTBAR_NUM_CMDS }; @@ -1421,8 +1481,40 @@ struct ec_response_rtc { /*****************************************************************************/ /* Port80 log access */ +/* Maximum entries that can be read/written in a single command */ +#define EC_PORT80_SIZE_MAX 32 + /* Get last port80 code from previous boot */ #define EC_CMD_PORT80_LAST_BOOT 0x48 +#define EC_CMD_PORT80_READ 0x48 + +enum ec_port80_subcmd { + EC_PORT80_GET_INFO = 0, + EC_PORT80_READ_BUFFER, +}; + +struct ec_params_port80_read { + uint16_t subcmd; + union { + struct { + uint32_t offset; + uint32_t num_entries; + } read_buffer; + }; +} __packed; + +struct ec_response_port80_read { + union { + struct { + uint32_t writes; + uint32_t history_size; + uint32_t last_boot; + } get_info; + struct { + uint16_t codes[EC_PORT80_SIZE_MAX]; + } data; + }; +} __packed; struct ec_response_port80_last_boot { uint16_t code; @@ -1782,6 +1874,7 @@ struct ec_params_gpio_set { /* Get GPIO value */ #define EC_CMD_GPIO_GET 0x93 +/* Version 0 of input params and response */ struct ec_params_gpio_get { char name[32]; } __packed; @@ -1789,6 +1882,38 @@ struct ec_response_gpio_get { uint8_t val; } __packed; +/* Version 1 of input params and response */ +struct ec_params_gpio_get_v1 { + uint8_t subcmd; + union { + struct { + char name[32]; + } get_value_by_name; + struct { + uint8_t index; + } get_info; + }; +} __packed; + +struct ec_response_gpio_get_v1 { + union { + struct { + uint8_t val; + } get_value_by_name, get_count; + struct { + uint8_t val; + char name[32]; + uint32_t flags; + } get_info; + }; +} __packed; + +enum gpio_get_subcmd { + EC_GPIO_GET_BY_NAME = 0, + EC_GPIO_GET_COUNT = 1, + EC_GPIO_GET_INFO = 2, +}; + /*****************************************************************************/ /* I2C commands. Only available when flash write protect is unlocked. */ @@ -1857,13 +1982,21 @@ struct ec_params_charge_control { /*****************************************************************************/ /* - * Cut off battery power output if the battery supports. + * Cut off battery power immediately or after the host has shut down. * - * For unsupported battery, just don't implement this command and lets EC - * return EC_RES_INVALID_COMMAND. + * return EC_RES_INVALID_COMMAND if unsupported by a board/battery. + * EC_RES_SUCCESS if the command was successful. + * EC_RES_ERROR if the cut off command failed. */ + #define EC_CMD_BATTERY_CUT_OFF 0x99 +#define EC_BATTERY_CUTOFF_FLAG_AT_SHUTDOWN (1 << 0) + +struct ec_params_battery_cutoff { + uint8_t flags; +} __packed; + /*****************************************************************************/ /* USB port mux control. */ @@ -2142,6 +2275,32 @@ struct ec_params_sb_wr_block { } __packed; /*****************************************************************************/ +/* Battery vendor parameters + * + * Get or set vendor-specific parameters in the battery. Implementations may + * differ between boards or batteries. On a set operation, the response + * contains the actual value set, which may be rounded or clipped from the + * requested value. + */ + +#define EC_CMD_BATTERY_VENDOR_PARAM 0xb4 + +enum ec_battery_vendor_param_mode { + BATTERY_VENDOR_PARAM_MODE_GET = 0, + BATTERY_VENDOR_PARAM_MODE_SET, +}; + +struct ec_params_battery_vendor_param { + uint32_t param; + uint32_t value; + uint8_t mode; +} __packed; + +struct ec_response_battery_vendor_param { + uint32_t value; +} __packed; + +/*****************************************************************************/ /* System commands */ /* @@ -2338,6 +2497,80 @@ struct ec_params_reboot_ec { /*****************************************************************************/ /* + * PD commands + * + * These commands are for PD MCU communication. + */ + +/* EC to PD MCU exchange status command */ +#define EC_CMD_PD_EXCHANGE_STATUS 0x100 + +/* Status of EC being sent to PD */ +struct ec_params_pd_status { + int8_t batt_soc; /* battery state of charge */ +} __packed; + +/* Status of PD being sent back to EC */ +struct ec_response_pd_status { + int8_t status; /* PD MCU status */ + uint32_t curr_lim_ma; /* input current limit */ +} __packed; + +/* Set USB type-C port role and muxes */ +#define EC_CMD_USB_PD_CONTROL 0x101 + +enum usb_pd_control_role { + USB_PD_CTRL_ROLE_NO_CHANGE = 0, + USB_PD_CTRL_ROLE_TOGGLE_ON = 1, /* == AUTO */ + USB_PD_CTRL_ROLE_TOGGLE_OFF = 2, + USB_PD_CTRL_ROLE_FORCE_SINK = 3, + USB_PD_CTRL_ROLE_FORCE_SOURCE = 4, +}; + +enum usb_pd_control_mux { + USB_PD_CTRL_MUX_NO_CHANGE = 0, + USB_PD_CTRL_MUX_NONE = 1, + USB_PD_CTRL_MUX_USB = 2, + USB_PD_CTRL_MUX_DP = 3, + USB_PD_CTRL_MUX_DOCK = 4, + USB_PD_CTRL_MUX_AUTO = 5, +}; + +struct ec_params_usb_pd_control { + uint8_t port; + uint8_t role; + uint8_t mux; +} __packed; + +/*****************************************************************************/ +/* + * Passthru commands + * + * Some platforms have sub-processors chained to each other. For example. + * + * AP <--> EC <--> PD MCU + * + * The top 2 bits of the command number are used to indicate which device the + * command is intended for. Device 0 is always the device receiving the + * command; other device mapping is board-specific. + * + * When a device receives a command to be passed to a sub-processor, it passes + * it on with the device number set back to 0. This allows the sub-processor + * to remain blissfully unaware of whether the command originated on the next + * device up the chain, or was passed through from the AP. + * + * In the above example, if the AP wants to send command 0x0002 to the PD MCU, + * AP sends command 0x4002 to the EC + * EC sends command 0x0002 to the PD MCU + * EC forwards PD MCU response back to the AP + */ + +/* Offset and max command number for sub-device n */ +#define EC_CMD_PASSTHRU_OFFSET(n) (0x4000 * (n)) +#define EC_CMD_PASSTHRU_MAX(n) (EC_CMD_PASSTHRU_OFFSET(n) + 0x3fff) + +/*****************************************************************************/ +/* * Deprecated constants. These constants have been renamed for clarity. The * meaning and size has not changed. Programs that use the old names should * switch to the new names soon, as the old names may not be carried forward diff --git a/include/linux/mfd/da9055/core.h b/include/linux/mfd/da9055/core.h index 956afa445998..5dc743fd63a6 100644 --- a/include/linux/mfd/da9055/core.h +++ b/include/linux/mfd/da9055/core.h @@ -89,6 +89,6 @@ static inline int da9055_reg_update(struct da9055 *da9055, unsigned char reg, int da9055_device_init(struct da9055 *da9055); void da9055_device_exit(struct da9055 *da9055); -extern struct regmap_config da9055_regmap_config; +extern const struct regmap_config da9055_regmap_config; #endif /* __DA9055_CORE_H */ diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 95c8742215a7..612383bd80ae 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -103,6 +103,7 @@ struct da9063; struct da9063_pdata { int (*init)(struct da9063 *da9063); int irq_base; + bool key_power; unsigned flags; struct da9063_regulators_pdata *regulators_pdata; struct led_platform_data *leds_pdata; diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h index bb995ab9a575..d4b72d519115 100644 --- a/include/linux/mfd/max77686.h +++ b/include/linux/mfd/max77686.h @@ -125,9 +125,4 @@ enum max77686_opmode { MAX77686_OPMODE_STANDBY, }; -struct max77686_opmode_data { - int id; - int mode; -}; - #endif /* __LINUX_MFD_MAX77686_H */ diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index c9d869027300..cb83883918a7 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -118,47 +118,6 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) /** - * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform - * data - * @sample_time: ADC converstion time in number of clock. - * (0 -> 36 clocks, 1 -> 44 clocks, 2 -> 56 clocks, 3 -> 64 clocks, - * 4 -> 80 clocks, 5 -> 96 clocks, 6 -> 144 clocks), - * recommended is 4. - * @mod_12b: ADC Bit mode (0 -> 10bit ADC, 1 -> 12bit ADC) - * @ref_sel: ADC reference source - * (0 -> internal reference, 1 -> external reference) - * @adc_freq: ADC Clock speed - * (0 -> 1.625 MHz, 1 -> 3.25 MHz, 2 || 3 -> 6.5 MHz) - * @ave_ctrl: Sample average control - * (0 -> 1 sample, 1 -> 2 samples, 2 -> 4 samples, 3 -> 8 samples) - * @touch_det_delay: Touch detect interrupt delay - * (0 -> 10 us, 1 -> 50 us, 2 -> 100 us, 3 -> 500 us, - * 4-> 1 ms, 5 -> 5 ms, 6 -> 10 ms, 7 -> 50 ms) - * recommended is 3 - * @settling: Panel driver settling time - * (0 -> 10 us, 1 -> 100 us, 2 -> 500 us, 3 -> 1 ms, - * 4 -> 5 ms, 5 -> 10 ms, 6 for 50 ms, 7 -> 100 ms) - * recommended is 2 - * @fraction_z: Length of the fractional part in z - * (fraction_z ([0..7]) = Count of the fractional part) - * recommended is 7 - * @i_drive: current limit value of the touchscreen drivers - * (0 -> 20 mA typical 35 mA max, 1 -> 50 mA typical 80 mA max) - * - * */ -struct stmpe_ts_platform_data { - u8 sample_time; - u8 mod_12b; - u8 ref_sel; - u8 adc_freq; - u8 ave_ctrl; - u8 touch_det_delay; - u8 settling; - u8 fraction_z; - u8 i_drive; -}; - -/** * struct stmpe_platform_data - STMPE platform data * @id: device id to distinguish between multiple STMPEs on the same board * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*) @@ -168,7 +127,6 @@ struct stmpe_ts_platform_data { * @irq_over_gpio: true if gpio is used to get irq * @irq_gpio: gpio number over which irq will be requested (significant only if * irq_over_gpio is true) - * @ts: touchscreen-specific platform data */ struct stmpe_platform_data { int id; @@ -178,8 +136,6 @@ struct stmpe_platform_data { bool irq_over_gpio; int irq_gpio; int autosleep_timeout; - - struct stmpe_ts_platform_data *ts; }; #endif diff --git a/include/linux/mfd/syscon/atmel-mc.h b/include/linux/mfd/syscon/atmel-mc.h new file mode 100644 index 000000000000..afd9b8f1e363 --- /dev/null +++ b/include/linux/mfd/syscon/atmel-mc.h @@ -0,0 +1,144 @@ +/* + * Copyright (C) 2005 Ivan Kokshaysky + * Copyright (C) SAN People + * + * Memory Controllers (MC, EBI, SMC, SDRAMC, BFC) - System peripherals + * registers. + * Based on AT91RM9200 datasheet revision E. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _LINUX_MFD_SYSCON_ATMEL_MC_H_ +#define _LINUX_MFD_SYSCON_ATMEL_MC_H_ + +/* Memory Controller */ +#define AT91_MC_RCR 0x00 +#define AT91_MC_RCB BIT(0) + +#define AT91_MC_ASR 0x04 +#define AT91_MC_UNADD BIT(0) +#define AT91_MC_MISADD BIT(1) +#define AT91_MC_ABTSZ GENMASK(9, 8) +#define AT91_MC_ABTSZ_BYTE (0 << 8) +#define AT91_MC_ABTSZ_HALFWORD (1 << 8) +#define AT91_MC_ABTSZ_WORD (2 << 8) +#define AT91_MC_ABTTYP GENMASK(11, 10) +#define AT91_MC_ABTTYP_DATAREAD (0 << 10) +#define AT91_MC_ABTTYP_DATAWRITE (1 << 10) +#define AT91_MC_ABTTYP_FETCH (2 << 10) +#define AT91_MC_MST(n) BIT(16 + (n)) +#define AT91_MC_SVMST(n) BIT(24 + (n)) + +#define AT91_MC_AASR 0x08 + +#define AT91_MC_MPR 0x0c +#define AT91_MPR_MSTP(n) GENMASK(2 + ((x) * 4), ((x) * 4)) + +/* External Bus Interface (EBI) registers */ +#define AT91_MC_EBI_CSA 0x60 +#define AT91_MC_EBI_CS(n) BIT(x) +#define AT91_MC_EBI_NUM_CS 8 + +#define AT91_MC_EBI_CFGR 0x64 +#define AT91_MC_EBI_DBPUC BIT(0) + +/* Static Memory Controller (SMC) registers */ +#define AT91_MC_SMC_CSR(n) (0x70 + ((n) * 4)) +#define AT91_MC_SMC_NWS GENMASK(6, 0) +#define AT91_MC_SMC_NWS_(x) ((x) << 0) +#define AT91_MC_SMC_WSEN BIT(7) +#define AT91_MC_SMC_TDF GENMASK(11, 8) +#define AT91_MC_SMC_TDF_(x) ((x) << 8) +#define AT91_MC_SMC_TDF_MAX 0xf +#define AT91_MC_SMC_BAT BIT(12) +#define AT91_MC_SMC_DBW GENMASK(14, 13) +#define AT91_MC_SMC_DBW_16 (1 << 13) +#define AT91_MC_SMC_DBW_8 (2 << 13) +#define AT91_MC_SMC_DPR BIT(15) +#define AT91_MC_SMC_ACSS GENMASK(17, 16) +#define AT91_MC_SMC_ACSS_(x) ((x) << 16) +#define AT91_MC_SMC_ACSS_MAX 3 +#define AT91_MC_SMC_RWSETUP GENMASK(26, 24) +#define AT91_MC_SMC_RWSETUP_(x) ((x) << 24) +#define AT91_MC_SMC_RWHOLD GENMASK(30, 28) +#define AT91_MC_SMC_RWHOLD_(x) ((x) << 28) +#define AT91_MC_SMC_RWHOLDSETUP_MAX 7 + +/* SDRAM Controller registers */ +#define AT91_MC_SDRAMC_MR 0x90 +#define AT91_MC_SDRAMC_MODE GENMASK(3, 0) +#define AT91_MC_SDRAMC_MODE_NORMAL (0 << 0) +#define AT91_MC_SDRAMC_MODE_NOP (1 << 0) +#define AT91_MC_SDRAMC_MODE_PRECHARGE (2 << 0) +#define AT91_MC_SDRAMC_MODE_LMR (3 << 0) +#define AT91_MC_SDRAMC_MODE_REFRESH (4 << 0) +#define AT91_MC_SDRAMC_DBW_16 BIT(4) + +#define AT91_MC_SDRAMC_TR 0x94 +#define AT91_MC_SDRAMC_COUNT GENMASK(11, 0) + +#define AT91_MC_SDRAMC_CR 0x98 +#define AT91_MC_SDRAMC_NC GENMASK(1, 0) +#define AT91_MC_SDRAMC_NC_8 (0 << 0) +#define AT91_MC_SDRAMC_NC_9 (1 << 0) +#define AT91_MC_SDRAMC_NC_10 (2 << 0) +#define AT91_MC_SDRAMC_NC_11 (3 << 0) +#define AT91_MC_SDRAMC_NR GENMASK(3, 2) +#define AT91_MC_SDRAMC_NR_11 (0 << 2) +#define AT91_MC_SDRAMC_NR_12 (1 << 2) +#define AT91_MC_SDRAMC_NR_13 (2 << 2) +#define AT91_MC_SDRAMC_NB BIT(4) +#define AT91_MC_SDRAMC_NB_2 (0 << 4) +#define AT91_MC_SDRAMC_NB_4 (1 << 4) +#define AT91_MC_SDRAMC_CAS GENMASK(6, 5) +#define AT91_MC_SDRAMC_CAS_2 (2 << 5) +#define AT91_MC_SDRAMC_TWR GENMASK(10, 7) +#define AT91_MC_SDRAMC_TRC GENMASK(14, 11) +#define AT91_MC_SDRAMC_TRP GENMASK(18, 15) +#define AT91_MC_SDRAMC_TRCD GENMASK(22, 19) +#define AT91_MC_SDRAMC_TRAS GENMASK(26, 23) +#define AT91_MC_SDRAMC_TXSR GENMASK(30, 27) + +#define AT91_MC_SDRAMC_SRR 0x9c +#define AT91_MC_SDRAMC_SRCB BIT(0) + +#define AT91_MC_SDRAMC_LPR 0xa0 +#define AT91_MC_SDRAMC_LPCB BIT(0) + +#define AT91_MC_SDRAMC_IER 0xa4 +#define AT91_MC_SDRAMC_IDR 0xa8 +#define AT91_MC_SDRAMC_IMR 0xac +#define AT91_MC_SDRAMC_ISR 0xb0 +#define AT91_MC_SDRAMC_RES BIT(0) + +/* Burst Flash Controller register */ +#define AT91_MC_BFC_MR 0xc0 +#define AT91_MC_BFC_BFCOM GENMASK(1, 0) +#define AT91_MC_BFC_BFCOM_DISABLED (0 << 0) +#define AT91_MC_BFC_BFCOM_ASYNC (1 << 0) +#define AT91_MC_BFC_BFCOM_BURST (2 << 0) +#define AT91_MC_BFC_BFCC GENMASK(3, 2) +#define AT91_MC_BFC_BFCC_MCK (1 << 2) +#define AT91_MC_BFC_BFCC_DIV2 (2 << 2) +#define AT91_MC_BFC_BFCC_DIV4 (3 << 2) +#define AT91_MC_BFC_AVL GENMASK(7, 4) +#define AT91_MC_BFC_PAGES GENMASK(10, 8) +#define AT91_MC_BFC_PAGES_NO_PAGE (0 << 8) +#define AT91_MC_BFC_PAGES_16 (1 << 8) +#define AT91_MC_BFC_PAGES_32 (2 << 8) +#define AT91_MC_BFC_PAGES_64 (3 << 8) +#define AT91_MC_BFC_PAGES_128 (4 << 8) +#define AT91_MC_BFC_PAGES_256 (5 << 8) +#define AT91_MC_BFC_PAGES_512 (6 << 8) +#define AT91_MC_BFC_PAGES_1024 (7 << 8) +#define AT91_MC_BFC_OEL GENMASK(13, 12) +#define AT91_MC_BFC_BAAEN BIT(16) +#define AT91_MC_BFC_BFOEH BIT(17) +#define AT91_MC_BFC_MUXEN BIT(18) +#define AT91_MC_BFC_RDYEN BIT(19) + +#endif /* _LINUX_MFD_SYSCON_ATMEL_MC_H_ */ diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index f62e7cf227c6..58391f2e0414 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -35,6 +35,8 @@ #include <linux/dma-mapping.h> #include <linux/if_link.h> +#include <linux/mlx4/device.h> +#include <linux/netdevice.h> enum { /* initialization and general commands */ @@ -300,6 +302,10 @@ static inline int mlx4_cmd_imm(struct mlx4_dev *dev, u64 in_param, u64 *out_para struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev); void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox); +int mlx4_get_counter_stats(struct mlx4_dev *dev, int counter_index, + struct mlx4_counter *counter_stats, int reset); +int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, + struct ifla_vf_stats *vf_stats); u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 83e80ab94500..fd13c1ce3b4a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -46,8 +46,9 @@ #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 -#define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 +#define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \ + (dev_cap).num_ports * MIN_MSIX_P_PORT) #define MLX4_MAX_100M_UNITS_VAL 255 /* * work around: can't set values @@ -528,7 +529,6 @@ struct mlx4_caps { int num_eqs; int reserved_eqs; int num_comp_vectors; - int comp_pool; int num_mpts; int max_fmr_maps; int num_mtts; @@ -771,6 +771,14 @@ union mlx4_ext_av { struct mlx4_eth_av eth; }; +/* Counters should be saturate once they reach their maximum value */ +#define ASSIGN_32BIT_COUNTER(counter, value) do { \ + if ((value) > U32_MAX) \ + counter = cpu_to_be32(U32_MAX); \ + else \ + counter = cpu_to_be32(value); \ +} while (0) + struct mlx4_counter { u8 reserved1[3]; u8 counter_mode; @@ -829,6 +837,12 @@ struct mlx4_dev { struct mlx4_vf_dev *dev_vfs; }; +struct mlx4_clock_params { + u64 offset; + u8 bar; + u8 size; +}; + struct mlx4_eqe { u8 reserved1; u8 type; @@ -957,6 +971,7 @@ struct mlx4_mad_ifc { ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)) #define MLX4_INVALID_SLAVE_ID 0xFF +#define MLX4_SINK_COUNTER_INDEX(dev) (dev->caps.max_counters - 1) void handle_port_mgmt_change_event(struct work_struct *work); @@ -1332,10 +1347,13 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); -int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector); +u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port); +bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector); +struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port); +int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector); int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec); int mlx4_get_phys_port_id(struct mlx4_dev *dev); @@ -1344,6 +1362,7 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); +int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port); void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port); @@ -1485,4 +1504,7 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev, enum mlx4_access_reg_method method, struct mlx4_ptys_reg *ptys_reg); +int mlx4_get_internal_clock_params(struct mlx4_dev *dev, + struct mlx4_clock_params *params); + #endif /* MLX4_DEVICE_H */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 2695ced222df..abc4767695e4 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -169,6 +169,9 @@ int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_query_cq_mbox_out *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, struct mlx5_modify_cq_mbox_in *in, int in_sz); +int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, + struct mlx5_core_cq *cq, u16 cq_period, + u16 cq_max_count); int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index abf65c790421..b943cd9e2097 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -35,6 +35,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> +#include <linux/mlx5/mlx5_ifc.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -58,6 +59,8 @@ #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8) #define MLX5_ST_SZ_BYTES(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 8) #define MLX5_ST_SZ_DW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 32) +#define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) +#define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) #define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld)) @@ -70,6 +73,14 @@ << __mlx5_dw_bit_off(typ, fld))); \ } while (0) +#define MLX5_SET_TO_ONES(typ, p, fld) do { \ + BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32); \ + *((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \ + cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \ + (~__mlx5_dw_mask(typ, fld))) | ((__mlx5_mask(typ, fld)) \ + << __mlx5_dw_bit_off(typ, fld))); \ +} while (0) + #define MLX5_GET(typ, p, fld) ((be32_to_cpu(*((__be32 *)(p) +\ __mlx5_dw_off(typ, fld))) >> __mlx5_dw_bit_off(typ, fld)) & \ __mlx5_mask(typ, fld)) @@ -88,6 +99,12 @@ __mlx5_mask(typ, fld)) #define MLX5_GET64(typ, p, fld) be64_to_cpu(*((__be64 *)(p) + __mlx5_64_off(typ, fld))) +#define MLX5_GET64_PR(typ, p, fld) ({ \ + u64 ___t = MLX5_GET64(typ, p, fld); \ + pr_debug(#fld " = 0x%llx\n", ___t); \ + ___t; \ +}) + enum { MLX5_MAX_COMMANDS = 32, MLX5_CMD_DATA_BLOCK_SIZE = 512, @@ -115,6 +132,10 @@ enum { }; enum { + MLX5_HW_START_PADDING = MLX5_INLINE_SEG, +}; + +enum { MLX5_MIN_PKEY_TABLE_SIZE = 128, MLX5_MAX_LOG_PKEY_TABLE = 5, }; @@ -264,6 +285,7 @@ enum { MLX5_OPCODE_RDMA_WRITE_IMM = 0x09, MLX5_OPCODE_SEND = 0x0a, MLX5_OPCODE_SEND_IMM = 0x0b, + MLX5_OPCODE_LSO = 0x0e, MLX5_OPCODE_RDMA_READ = 0x10, MLX5_OPCODE_ATOMIC_CS = 0x11, MLX5_OPCODE_ATOMIC_FA = 0x12, @@ -312,13 +334,6 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; -enum { - HCA_CAP_OPMOD_GET_MAX = 0, - HCA_CAP_OPMOD_GET_CUR = 1, - HCA_CAP_OPMOD_GET_ODP_MAX = 4, - HCA_CAP_OPMOD_GET_ODP_CUR = 5 -}; - struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; @@ -541,6 +556,10 @@ struct mlx5_cmd_prot_block { u8 sig; }; +enum { + MLX5_CQE_SYND_FLUSHED_IN_ERROR = 5, +}; + struct mlx5_err_cqe { u8 rsvd0[32]; __be32 srqn; @@ -554,13 +573,22 @@ struct mlx5_err_cqe { }; struct mlx5_cqe64 { - u8 rsvd0[17]; + u8 rsvd0[4]; + u8 lro_tcppsh_abort_dupack; + u8 lro_min_ttl; + __be16 lro_tcp_win; + __be32 lro_ack_seq_num; + __be32 rss_hash_result; + u8 rss_hash_type; u8 ml_path; - u8 rsvd20[4]; + u8 rsvd20[2]; + __be16 check_sum; __be16 slid; __be32 flags_rqpn; - u8 rsvd28[4]; - __be32 srqn; + u8 hds_ip_ext; + u8 l4_hdr_type_etc; + __be16 vlan_info; + __be32 srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */ __be32 imm_inval_pkey; u8 rsvd40[4]; __be32 byte_cnt; @@ -571,6 +599,40 @@ struct mlx5_cqe64 { u8 op_own; }; +static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) +{ + return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; +} + +static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) +{ + return (cqe->l4_hdr_type_etc >> 4) & 0x7; +} + +static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) +{ + return !!(cqe->l4_hdr_type_etc & 0x1); +} + +enum { + CQE_L4_HDR_TYPE_NONE = 0x0, + CQE_L4_HDR_TYPE_TCP_NO_ACK = 0x1, + CQE_L4_HDR_TYPE_UDP = 0x2, + CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA = 0x3, + CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA = 0x4, +}; + +enum { + CQE_RSS_HTYPE_IP = 0x3 << 6, + CQE_RSS_HTYPE_L4 = 0x3 << 2, +}; + +enum { + CQE_L2_OK = 1 << 0, + CQE_L3_OK = 1 << 1, + CQE_L4_OK = 1 << 2, +}; + struct mlx5_sig_err_cqe { u8 rsvd0[16]; __be32 expected_trans_sig; @@ -996,4 +1058,135 @@ struct mlx5_destroy_psv_out { u8 rsvd[8]; }; +#define MLX5_CMD_OP_MAX 0x920 + +enum { + VPORT_STATE_DOWN = 0x0, + VPORT_STATE_UP = 0x1, +}; + +enum { + MLX5_L3_PROT_TYPE_IPV4 = 0, + MLX5_L3_PROT_TYPE_IPV6 = 1, +}; + +enum { + MLX5_L4_PROT_TYPE_TCP = 0, + MLX5_L4_PROT_TYPE_UDP = 1, +}; + +enum { + MLX5_HASH_FIELD_SEL_SRC_IP = 1 << 0, + MLX5_HASH_FIELD_SEL_DST_IP = 1 << 1, + MLX5_HASH_FIELD_SEL_L4_SPORT = 1 << 2, + MLX5_HASH_FIELD_SEL_L4_DPORT = 1 << 3, + MLX5_HASH_FIELD_SEL_IPSEC_SPI = 1 << 4, +}; + +enum { + MLX5_MATCH_OUTER_HEADERS = 1 << 0, + MLX5_MATCH_MISC_PARAMETERS = 1 << 1, + MLX5_MATCH_INNER_HEADERS = 1 << 2, + +}; + +enum { + MLX5_FLOW_TABLE_TYPE_NIC_RCV = 0, + MLX5_FLOW_TABLE_TYPE_ESWITCH = 4, +}; + +enum { + MLX5_FLOW_CONTEXT_DEST_TYPE_VPORT = 0, + MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE = 1, + MLX5_FLOW_CONTEXT_DEST_TYPE_TIR = 2, +}; + +enum { + MLX5_RQC_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, +}; + +/* MLX5 DEV CAPs */ + +/* TODO: EAT.ME */ +enum mlx5_cap_mode { + HCA_CAP_OPMOD_GET_MAX = 0, + HCA_CAP_OPMOD_GET_CUR = 1, +}; + +enum mlx5_cap_type { + MLX5_CAP_GENERAL = 0, + MLX5_CAP_ETHERNET_OFFLOADS, + MLX5_CAP_ODP, + MLX5_CAP_ATOMIC, + MLX5_CAP_ROCE, + MLX5_CAP_IPOIB_OFFLOADS, + MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_FLOW_TABLE, + /* NUM OF CAP Types */ + MLX5_CAP_NUM +}; + +/* GET Dev Caps macros */ +#define MLX5_CAP_GEN(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_cur[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_GEN_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap, mdev->hca_caps_max[MLX5_CAP_GENERAL], cap) + +#define MLX5_CAP_ETH(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ETH_MAX(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->hca_caps_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) + +#define MLX5_CAP_ROCE(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_cur[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ROCE_MAX(mdev, cap) \ + MLX5_GET(roce_cap, mdev->hca_caps_max[MLX5_CAP_ROCE], cap) + +#define MLX5_CAP_ATOMIC(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_cur[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_ATOMIC_MAX(mdev, cap) \ + MLX5_GET(atomic_caps, mdev->hca_caps_max[MLX5_CAP_ATOMIC], cap) + +#define MLX5_CAP_FLOWTABLE(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_cur[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ + MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap) + +#define MLX5_CAP_ODP(mdev, cap)\ + MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) + +enum { + MLX5_CMD_STAT_OK = 0x0, + MLX5_CMD_STAT_INT_ERR = 0x1, + MLX5_CMD_STAT_BAD_OP_ERR = 0x2, + MLX5_CMD_STAT_BAD_PARAM_ERR = 0x3, + MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, + MLX5_CMD_STAT_BAD_RES_ERR = 0x5, + MLX5_CMD_STAT_RES_BUSY = 0x6, + MLX5_CMD_STAT_LIM_ERR = 0x8, + MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, + MLX5_CMD_STAT_IX_ERR = 0xa, + MLX5_CMD_STAT_NO_RES_ERR = 0xf, + MLX5_CMD_STAT_BAD_INP_LEN_ERR = 0x50, + MLX5_CMD_STAT_BAD_OUTP_LEN_ERR = 0x51, + MLX5_CMD_STAT_BAD_QP_STATE_ERR = 0x10, + MLX5_CMD_STAT_BAD_PKT_ERR = 0x30, + MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40, +}; + +static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) +{ + if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) + return 0; + return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; +} + #endif /* MLX5_DEVICE_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9a90e7523dc2..5722d88c2429 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -44,7 +44,6 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> -#include <linux/mlx5/mlx5_ifc.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -85,7 +84,7 @@ enum { }; enum { - MLX5_MAX_EQ_NAME = 32 + MLX5_MAX_IRQ_NAME = 32 }; enum { @@ -108,6 +107,7 @@ enum { MLX5_REG_PUDE = 0x5009, MLX5_REG_PMPE = 0x5010, MLX5_REG_PELC = 0x500e, + MLX5_REG_PVLC = 0x500f, MLX5_REG_PMLP = 0, /* TBD */ MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, @@ -150,6 +150,11 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_CLIENT_REREG, }; +enum mlx5_port_status { + MLX5_PORT_UP = 1 << 1, + MLX5_PORT_DOWN = 1 << 2, +}; + struct mlx5_uuar_info { struct mlx5_uar *uars; int num_uars; @@ -269,56 +274,7 @@ struct mlx5_cmd { struct mlx5_port_caps { int gid_table_len; int pkey_table_len; -}; - -struct mlx5_general_caps { - u8 log_max_eq; - u8 log_max_cq; - u8 log_max_qp; - u8 log_max_mkey; - u8 log_max_pd; - u8 log_max_srq; - u8 log_max_strq; - u8 log_max_mrw_sz; - u8 log_max_bsf_list_size; - u8 log_max_klm_list_size; - u32 max_cqes; - int max_wqes; - u32 max_eqes; - u32 max_indirection; - int max_sq_desc_sz; - int max_rq_desc_sz; - int max_dc_sq_desc_sz; - u64 flags; - u16 stat_rate_support; - int log_max_msg; - int num_ports; - u8 log_max_ra_res_qp; - u8 log_max_ra_req_qp; - int max_srq_wqes; - int bf_reg_size; - int bf_regs_per_page; - struct mlx5_port_caps port[MLX5_MAX_PORTS]; - u8 ext_port_cap[MLX5_MAX_PORTS]; - int max_vf; - u32 reserved_lkey; - u8 local_ca_ack_delay; - u8 log_max_mcg; - u32 max_qp_mcg; - int min_page_sz; - int pd_cap; - u32 max_qp_counters; - u32 pkey_table_size; - u8 log_max_ra_req_dc; - u8 log_max_ra_res_dc; - u32 uar_sz; - u8 min_log_pg_sz; - u8 log_max_xrcd; - u16 log_uar_page_sz; -}; - -struct mlx5_caps { - struct mlx5_general_caps gen; + u8 ext_port_cap; }; struct mlx5_cmd_mailbox { @@ -334,8 +290,6 @@ struct mlx5_buf_list { struct mlx5_buf { struct mlx5_buf_list direct; - struct mlx5_buf_list *page_list; - int nbufs; int npages; int size; u8 page_shift; @@ -351,7 +305,6 @@ struct mlx5_eq { u8 eqn; int nent; u64 mask; - char name[MLX5_MAX_EQ_NAME]; struct list_head list; int index; struct mlx5_rsc_debug *dbg; @@ -387,6 +340,8 @@ struct mlx5_core_mr { enum mlx5_res_type { MLX5_RES_QP, + MLX5_RES_SRQ, + MLX5_RES_XSRQ, }; struct mlx5_core_rsc_common { @@ -396,6 +351,7 @@ struct mlx5_core_rsc_common { }; struct mlx5_core_srq { + struct mlx5_core_rsc_common common; /* must be first */ u32 srqn; int max; int max_gs; @@ -414,7 +370,6 @@ struct mlx5_eq_table { struct mlx5_eq pages_eq; struct mlx5_eq async_eq; struct mlx5_eq cmd_eq; - struct msix_entry *msix_arr; int num_comp_vectors; /* protect EQs list */ @@ -467,9 +422,16 @@ struct mlx5_mr_table { struct radix_tree_root tree; }; +struct mlx5_irq_info { + cpumask_var_t mask; + char name[MLX5_MAX_IRQ_NAME]; +}; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; + struct msix_entry *msix_arr; + struct mlx5_irq_info *irq_info; struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); @@ -520,7 +482,9 @@ struct mlx5_core_dev { u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; - struct mlx5_caps caps; + struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; + u32 hca_caps_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; + u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; void (*event) (struct mlx5_core_dev *dev, @@ -529,6 +493,7 @@ struct mlx5_core_dev { struct mlx5_priv priv; struct mlx5_profile *profile; atomic_t num_qps; + u32 issi; }; struct mlx5_db { @@ -549,6 +514,11 @@ enum { MLX5_COMP_EQ_SIZE = 1024, }; +enum { + MLX5_PTYS_IB = 1 << 0, + MLX5_PTYS_EN = 1 << 2, +}; + struct mlx5_db_pgdir { struct list_head list; DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE); @@ -584,13 +554,44 @@ struct mlx5_pas { u8 log_sz; }; +enum port_state_policy { + MLX5_AAA_000 +}; + +enum phy_port_state { + MLX5_AAA_111 +}; + +struct mlx5_hca_vport_context { + u32 field_select; + bool sm_virt_aware; + bool has_smi; + bool has_raw; + enum port_state_policy policy; + enum phy_port_state phys_state; + enum ib_port_state vport_state; + u8 port_physical_state; + u64 sys_image_guid; + u64 port_guid; + u64 node_guid; + u32 cap_mask1; + u32 cap_mask1_perm; + u32 cap_mask2; + u32 cap_mask2_perm; + u16 lid; + u8 init_type_reply; /* bitmask: see ib spec 14.2.5.6 InitTypeReply */ + u8 lmc; + u8 subnet_timeout; + u16 sm_lid; + u8 sm_sl; + u16 qkey_violation_counter; + u16 pkey_violation_counter; + bool grh_required; +}; + static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) { - if (likely(BITS_PER_LONG == 64 || buf->nbufs == 1)) return buf->direct.buf + offset; - else - return buf->page_list[offset >> PAGE_SHIFT].buf + - (offset & (PAGE_SIZE - 1)); } extern struct workqueue_struct *mlx5_core_wq; @@ -654,8 +655,8 @@ void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr); int mlx5_cmd_status_to_err_v2(void *ptr); -int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps, - u16 opmod); +int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, + enum mlx5_cap_mode cap_mode); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, @@ -665,19 +666,21 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(void); void __init mlx5_health_init(void); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, int max_direct, - struct mlx5_buf *buf); +int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_create_srq_mbox_in *in, int inlen); + struct mlx5_create_srq_mbox_in *in, int inlen, + int is_xrc); int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq); int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, struct mlx5_query_srq_mbox_out *out); @@ -696,7 +699,7 @@ int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr, u32 *mkey); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, void *inb, void *outb, +int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); void mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); @@ -734,7 +737,32 @@ void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); + int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask, u8 local_port); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, + u8 *link_width_oper, u8 local_port); +int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, + u8 *proto_oper, int proto_mask, + u8 local_port); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, + u8 port); + +int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, + u8 *vl_hw_cap, u8 local_port); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); @@ -799,6 +827,7 @@ struct mlx5_interface { void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); +int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); struct mlx5_profile { u64 mask; @@ -809,4 +838,14 @@ struct mlx5_profile { } mr_cache[MAX_MR_CACHE_ENTRIES]; }; +static inline int mlx5_get_gid_table_len(u16 param) +{ + if (param > 4) { + pr_warn("gid table length is zero\n"); + return 0; + } + + return 8 * (1 << param); +} + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/flow_table.h b/include/linux/mlx5/flow_table.h new file mode 100644 index 000000000000..5f922c6d4fc2 --- /dev/null +++ b/include/linux/mlx5/flow_table.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef MLX5_FLOW_TABLE_H +#define MLX5_FLOW_TABLE_H + +#include <linux/mlx5/driver.h> + +struct mlx5_flow_table_group { + u8 log_sz; + u8 match_criteria_enable; + u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; +}; + +void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, + u16 num_groups, + struct mlx5_flow_table_group *group); +void mlx5_destroy_flow_table(void *flow_table); +int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, + void *match_criteria, void *flow_context, + u32 *flow_index); +void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index); +u32 mlx5_get_flow_table_id(void *flow_table); + +#endif /* MLX5_FLOW_TABLE_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cb3ad17edd1f..6d2f6fee041c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -28,12 +28,45 @@ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. - */ - +*/ #ifndef MLX5_IFC_H #define MLX5_IFC_H enum { + MLX5_EVENT_TYPE_CODING_COMPLETION_EVENTS = 0x0, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATED_SUCCEEDED = 0x1, + MLX5_EVENT_TYPE_CODING_COMMUNICATION_ESTABLISHED = 0x2, + MLX5_EVENT_TYPE_CODING_SEND_QUEUE_DRAINED = 0x3, + MLX5_EVENT_TYPE_CODING_LAST_WQE_REACHED = 0x13, + MLX5_EVENT_TYPE_CODING_SRQ_LIMIT = 0x14, + MLX5_EVENT_TYPE_CODING_DCT_ALL_CONNECTIONS_CLOSED = 0x1c, + MLX5_EVENT_TYPE_CODING_DCT_ACCESS_KEY_VIOLATION = 0x1d, + MLX5_EVENT_TYPE_CODING_CQ_ERROR = 0x4, + MLX5_EVENT_TYPE_CODING_LOCAL_WQ_CATASTROPHIC_ERROR = 0x5, + MLX5_EVENT_TYPE_CODING_PATH_MIGRATION_FAILED = 0x7, + MLX5_EVENT_TYPE_CODING_PAGE_FAULT_EVENT = 0xc, + MLX5_EVENT_TYPE_CODING_INVALID_REQUEST_LOCAL_WQ_ERROR = 0x10, + MLX5_EVENT_TYPE_CODING_LOCAL_ACCESS_VIOLATION_WQ_ERROR = 0x11, + MLX5_EVENT_TYPE_CODING_LOCAL_SRQ_CATASTROPHIC_ERROR = 0x12, + MLX5_EVENT_TYPE_CODING_INTERNAL_ERROR = 0x8, + MLX5_EVENT_TYPE_CODING_PORT_STATE_CHANGE = 0x9, + MLX5_EVENT_TYPE_CODING_GPIO_EVENT = 0x15, + MLX5_EVENT_TYPE_CODING_REMOTE_CONFIGURATION_PROTOCOL_EVENT = 0x19, + MLX5_EVENT_TYPE_CODING_DOORBELL_BLUEFLAME_CONGESTION_EVENT = 0x1a, + MLX5_EVENT_TYPE_CODING_STALL_VL_EVENT = 0x1b, + MLX5_EVENT_TYPE_CODING_DROPPED_PACKET_LOGGED_EVENT = 0x1f, + MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION = 0xa, + MLX5_EVENT_TYPE_CODING_PAGE_REQUEST = 0xb +}; + +enum { + MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, + MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, + MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, + MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 +}; + +enum { MLX5_CMD_OP_QUERY_HCA_CAP = 0x100, MLX5_CMD_OP_QUERY_ADAPTER = 0x101, MLX5_CMD_OP_INIT_HCA = 0x102, @@ -43,6 +76,8 @@ enum { MLX5_CMD_OP_QUERY_PAGES = 0x107, MLX5_CMD_OP_MANAGE_PAGES = 0x108, MLX5_CMD_OP_SET_HCA_CAP = 0x109, + MLX5_CMD_OP_QUERY_ISSI = 0x10a, + MLX5_CMD_OP_SET_ISSI = 0x10b, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -66,6 +101,7 @@ enum { MLX5_CMD_OP_2ERR_QP = 0x507, MLX5_CMD_OP_2RST_QP = 0x50a, MLX5_CMD_OP_QUERY_QP = 0x50b, + MLX5_CMD_OP_SQD_RTS_QP = 0x50c, MLX5_CMD_OP_INIT2INIT_QP = 0x50e, MLX5_CMD_OP_CREATE_PSV = 0x600, MLX5_CMD_OP_DESTROY_PSV = 0x601, @@ -73,7 +109,10 @@ enum { MLX5_CMD_OP_DESTROY_SRQ = 0x701, MLX5_CMD_OP_QUERY_SRQ = 0x702, MLX5_CMD_OP_ARM_RQ = 0x703, - MLX5_CMD_OP_RESIZE_SRQ = 0x704, + MLX5_CMD_OP_CREATE_XRC_SRQ = 0x705, + MLX5_CMD_OP_DESTROY_XRC_SRQ = 0x706, + MLX5_CMD_OP_QUERY_XRC_SRQ = 0x707, + MLX5_CMD_OP_ARM_XRC_SRQ = 0x708, MLX5_CMD_OP_CREATE_DCT = 0x710, MLX5_CMD_OP_DESTROY_DCT = 0x711, MLX5_CMD_OP_DRAIN_DCT = 0x712, @@ -85,8 +124,12 @@ enum { MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT = 0x753, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT = 0x754, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT = 0x755, - MLX5_CMD_OP_QUERY_RCOE_ADDRESS = 0x760, + MLX5_CMD_OP_QUERY_ROCE_ADDRESS = 0x760, MLX5_CMD_OP_SET_ROCE_ADDRESS = 0x761, + MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT = 0x762, + MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT = 0x763, + MLX5_CMD_OP_QUERY_HCA_VPORT_GID = 0x764, + MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY = 0x765, MLX5_CMD_OP_QUERY_VPORT_COUNTER = 0x770, MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, @@ -98,7 +141,7 @@ enum { MLX5_CMD_OP_CONFIG_INT_MODERATION = 0x804, MLX5_CMD_OP_ACCESS_REG = 0x805, MLX5_CMD_OP_ATTACH_TO_MCG = 0x806, - MLX5_CMD_OP_DETACH_FROM_MCG = 0x807, + MLX5_CMD_OP_DETTACH_FROM_MCG = 0x807, MLX5_CMD_OP_GET_DROPPED_PACKET_LOG = 0x80a, MLX5_CMD_OP_MAD_IFC = 0x50d, MLX5_CMD_OP_QUERY_MAD_DEMUX = 0x80b, @@ -106,23 +149,22 @@ enum { MLX5_CMD_OP_NOP = 0x80d, MLX5_CMD_OP_ALLOC_XRCD = 0x80e, MLX5_CMD_OP_DEALLOC_XRCD = 0x80f, - MLX5_CMD_OP_SET_BURST_SIZE = 0x812, - MLX5_CMD_OP_QUERY_BURST_SZIE = 0x813, - MLX5_CMD_OP_ACTIVATE_TRACER = 0x814, - MLX5_CMD_OP_DEACTIVATE_TRACER = 0x815, - MLX5_CMD_OP_CREATE_SNIFFER_RULE = 0x820, - MLX5_CMD_OP_DESTROY_SNIFFER_RULE = 0x821, - MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x822, - MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x823, - MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x824, + MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN = 0x816, + MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN = 0x817, + MLX5_CMD_OP_QUERY_CONG_STATUS = 0x822, + MLX5_CMD_OP_MODIFY_CONG_STATUS = 0x823, + MLX5_CMD_OP_QUERY_CONG_PARAMS = 0x824, + MLX5_CMD_OP_MODIFY_CONG_PARAMS = 0x825, + MLX5_CMD_OP_QUERY_CONG_STATISTICS = 0x826, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT = 0x827, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT = 0x828, + MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, + MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, + MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, MLX5_CMD_OP_QUERY_TIR = 0x903, - MLX5_CMD_OP_CREATE_TIS = 0x912, - MLX5_CMD_OP_MODIFY_TIS = 0x913, - MLX5_CMD_OP_DESTROY_TIS = 0x914, - MLX5_CMD_OP_QUERY_TIS = 0x915, MLX5_CMD_OP_CREATE_SQ = 0x904, MLX5_CMD_OP_MODIFY_SQ = 0x905, MLX5_CMD_OP_DESTROY_SQ = 0x906, @@ -135,9 +177,430 @@ enum { MLX5_CMD_OP_MODIFY_RMP = 0x90d, MLX5_CMD_OP_DESTROY_RMP = 0x90e, MLX5_CMD_OP_QUERY_RMP = 0x90f, - MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x910, - MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x911, - MLX5_CMD_OP_MAX = 0x911 + MLX5_CMD_OP_CREATE_TIS = 0x912, + MLX5_CMD_OP_MODIFY_TIS = 0x913, + MLX5_CMD_OP_DESTROY_TIS = 0x914, + MLX5_CMD_OP_QUERY_TIS = 0x915, + MLX5_CMD_OP_CREATE_RQT = 0x916, + MLX5_CMD_OP_MODIFY_RQT = 0x917, + MLX5_CMD_OP_DESTROY_RQT = 0x918, + MLX5_CMD_OP_QUERY_RQT = 0x919, + MLX5_CMD_OP_CREATE_FLOW_TABLE = 0x930, + MLX5_CMD_OP_DESTROY_FLOW_TABLE = 0x931, + MLX5_CMD_OP_QUERY_FLOW_TABLE = 0x932, + MLX5_CMD_OP_CREATE_FLOW_GROUP = 0x933, + MLX5_CMD_OP_DESTROY_FLOW_GROUP = 0x934, + MLX5_CMD_OP_QUERY_FLOW_GROUP = 0x935, + MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x936, + MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x937, + MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY = 0x938 +}; + +struct mlx5_ifc_flow_table_fields_supported_bits { + u8 outer_dmac[0x1]; + u8 outer_smac[0x1]; + u8 outer_ether_type[0x1]; + u8 reserved_0[0x1]; + u8 outer_first_prio[0x1]; + u8 outer_first_cfi[0x1]; + u8 outer_first_vid[0x1]; + u8 reserved_1[0x1]; + u8 outer_second_prio[0x1]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0x1]; + u8 reserved_2[0x1]; + u8 outer_sip[0x1]; + u8 outer_dip[0x1]; + u8 outer_frag[0x1]; + u8 outer_ip_protocol[0x1]; + u8 outer_ip_ecn[0x1]; + u8 outer_ip_dscp[0x1]; + u8 outer_udp_sport[0x1]; + u8 outer_udp_dport[0x1]; + u8 outer_tcp_sport[0x1]; + u8 outer_tcp_dport[0x1]; + u8 outer_tcp_flags[0x1]; + u8 outer_gre_protocol[0x1]; + u8 outer_gre_key[0x1]; + u8 outer_vxlan_vni[0x1]; + u8 reserved_3[0x5]; + u8 source_eswitch_port[0x1]; + + u8 inner_dmac[0x1]; + u8 inner_smac[0x1]; + u8 inner_ether_type[0x1]; + u8 reserved_4[0x1]; + u8 inner_first_prio[0x1]; + u8 inner_first_cfi[0x1]; + u8 inner_first_vid[0x1]; + u8 reserved_5[0x1]; + u8 inner_second_prio[0x1]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0x1]; + u8 reserved_6[0x1]; + u8 inner_sip[0x1]; + u8 inner_dip[0x1]; + u8 inner_frag[0x1]; + u8 inner_ip_protocol[0x1]; + u8 inner_ip_ecn[0x1]; + u8 inner_ip_dscp[0x1]; + u8 inner_udp_sport[0x1]; + u8 inner_udp_dport[0x1]; + u8 inner_tcp_sport[0x1]; + u8 inner_tcp_dport[0x1]; + u8 inner_tcp_flags[0x1]; + u8 reserved_7[0x9]; + + u8 reserved_8[0x40]; +}; + +struct mlx5_ifc_flow_table_prop_layout_bits { + u8 ft_support[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x2]; + u8 log_max_ft_size[0x6]; + u8 reserved_2[0x10]; + u8 max_ft_level[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x18]; + u8 log_max_ft_num[0x8]; + + u8 reserved_5[0x18]; + u8 log_max_destination[0x8]; + + u8 reserved_6[0x18]; + u8 log_max_flow[0x8]; + + u8 reserved_7[0x40]; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; + + struct mlx5_ifc_flow_table_fields_supported_bits ft_field_bitmask_support; +}; + +struct mlx5_ifc_odp_per_transport_service_cap_bits { + u8 send[0x1]; + u8 receive[0x1]; + u8 write[0x1]; + u8 read[0x1]; + u8 reserved_0[0x1]; + u8 srq_receive[0x1]; + u8 reserved_1[0x1a]; +}; + +struct mlx5_ifc_fte_match_set_lyr_2_4_bits { + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 ethertype[0x10]; + + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 first_prio[0x3]; + u8 first_cfi[0x1]; + u8 first_vid[0xc]; + + u8 ip_protocol[0x8]; + u8 ip_dscp[0x6]; + u8 ip_ecn[0x2]; + u8 vlan_tag[0x1]; + u8 reserved_0[0x1]; + u8 frag[0x1]; + u8 reserved_1[0x4]; + u8 tcp_flags[0x9]; + + u8 tcp_sport[0x10]; + u8 tcp_dport[0x10]; + + u8 reserved_2[0x20]; + + u8 udp_sport[0x10]; + u8 udp_dport[0x10]; + + u8 src_ip[4][0x20]; + + u8 dst_ip[4][0x20]; +}; + +struct mlx5_ifc_fte_match_set_misc_bits { + u8 reserved_0[0x20]; + + u8 reserved_1[0x10]; + u8 source_port[0x10]; + + u8 outer_second_prio[0x3]; + u8 outer_second_cfi[0x1]; + u8 outer_second_vid[0xc]; + u8 inner_second_prio[0x3]; + u8 inner_second_cfi[0x1]; + u8 inner_second_vid[0xc]; + + u8 outer_second_vlan_tag[0x1]; + u8 inner_second_vlan_tag[0x1]; + u8 reserved_2[0xe]; + u8 gre_protocol[0x10]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 vxlan_vni[0x18]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0xc]; + u8 outer_ipv6_flow_label[0x14]; + + u8 reserved_6[0xc]; + u8 inner_ipv6_flow_label[0x14]; + + u8 reserved_7[0xe0]; +}; + +struct mlx5_ifc_cmd_pas_bits { + u8 pa_h[0x20]; + + u8 pa_l[0x14]; + u8 reserved_0[0xc]; +}; + +struct mlx5_ifc_uint64_bits { + u8 hi[0x20]; + + u8 lo[0x20]; +}; + +enum { + MLX5_ADS_STAT_RATE_NO_LIMIT = 0x0, + MLX5_ADS_STAT_RATE_2_5GBPS = 0x7, + MLX5_ADS_STAT_RATE_10GBPS = 0x8, + MLX5_ADS_STAT_RATE_30GBPS = 0x9, + MLX5_ADS_STAT_RATE_5GBPS = 0xa, + MLX5_ADS_STAT_RATE_20GBPS = 0xb, + MLX5_ADS_STAT_RATE_40GBPS = 0xc, + MLX5_ADS_STAT_RATE_60GBPS = 0xd, + MLX5_ADS_STAT_RATE_80GBPS = 0xe, + MLX5_ADS_STAT_RATE_120GBPS = 0xf, +}; + +struct mlx5_ifc_ads_bits { + u8 fl[0x1]; + u8 free_ar[0x1]; + u8 reserved_0[0xe]; + u8 pkey_index[0x10]; + + u8 reserved_1[0x8]; + u8 grh[0x1]; + u8 mlid[0x7]; + u8 rlid[0x10]; + + u8 ack_timeout[0x5]; + u8 reserved_2[0x3]; + u8 src_addr_index[0x8]; + u8 reserved_3[0x4]; + u8 stat_rate[0x4]; + u8 hop_limit[0x8]; + + u8 reserved_4[0x4]; + u8 tclass[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; + + u8 reserved_5[0x4]; + u8 f_dscp[0x1]; + u8 f_ecn[0x1]; + u8 reserved_6[0x1]; + u8 f_eth_prio[0x1]; + u8 ecn[0x2]; + u8 dscp[0x6]; + u8 udp_sport[0x10]; + + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 sl[0x4]; + u8 port[0x8]; + u8 rmac_47_32[0x10]; + + u8 rmac_31_0[0x20]; +}; + +struct mlx5_ifc_flow_table_nic_cap_bits { + u8 reserved_0[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; + + u8 reserved_1[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit; + + u8 reserved_2[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; + + u8 reserved_3[0x7200]; +}; + +struct mlx5_ifc_per_protocol_networking_offload_caps_bits { + u8 csum_cap[0x1]; + u8 vlan_cap[0x1]; + u8 lro_cap[0x1]; + u8 lro_psh_flag[0x1]; + u8 lro_time_stamp[0x1]; + u8 reserved_0[0x6]; + u8 max_lso_cap[0x5]; + u8 reserved_1[0x4]; + u8 rss_ind_tbl_cap[0x4]; + u8 reserved_2[0x3]; + u8 tunnel_lso_const_out_ip_id[0x1]; + u8 reserved_3[0x2]; + u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_vxlan[0x1]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x10]; + u8 lro_min_mss_size[0x10]; + + u8 reserved_6[0x120]; + + u8 lro_timer_supported_periods[4][0x20]; + + u8 reserved_7[0x600]; +}; + +struct mlx5_ifc_roce_cap_bits { + u8 roce_apm[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; + + u8 reserved_2[0xc]; + u8 l3_type[0x4]; + u8 reserved_3[0x8]; + u8 roce_version[0x8]; + + u8 reserved_4[0x10]; + u8 r_roce_dest_udp_port[0x10]; + + u8 r_roce_max_src_udp_port[0x10]; + u8 r_roce_min_src_udp_port[0x10]; + + u8 reserved_5[0x10]; + u8 roce_address_table_size[0x10]; + + u8 reserved_6[0x700]; +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_256_BYTES = 0x100, +}; + +enum { + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_1_BYTE = 0x1, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_2_BYTES = 0x2, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_4_BYTES = 0x4, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_8_BYTES = 0x8, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_16_BYTES = 0x10, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_32_BYTES = 0x20, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_64_BYTES = 0x40, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_128_BYTES = 0x80, + MLX5_ATOMIC_CAPS_ATOMIC_SIZE_DC_256_BYTES = 0x100, +}; + +struct mlx5_ifc_atomic_caps_bits { + u8 reserved_0[0x40]; + + u8 atomic_req_endianness[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 atomic_operations[0x10]; + + u8 reserved_4[0x10]; + u8 atomic_size_qp[0x10]; + + u8 reserved_5[0x10]; + u8 atomic_size_dc[0x10]; + + u8 reserved_6[0x720]; +}; + +struct mlx5_ifc_odp_cap_bits { + u8 reserved_0[0x40]; + + u8 sig[0x1]; + u8 reserved_1[0x1f]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits uc_odp_caps; + + struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; + + u8 reserved_3[0x720]; +}; + +enum { + MLX5_WQ_TYPE_LINKED_LIST = 0x0, + MLX5_WQ_TYPE_CYCLIC = 0x1, + MLX5_WQ_TYPE_STRQ = 0x2, +}; + +enum { + MLX5_WQ_END_PAD_MODE_NONE = 0x0, + MLX5_WQ_END_PAD_MODE_ALIGN = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_8_GID_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_16_GID_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_32_GID_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_64_GID_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_GID_TABLE_SIZE_128_GID_ENTRIES = 0x4, +}; + +enum { + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_128_ENTRIES = 0x0, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_256_ENTRIES = 0x1, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_512_ENTRIES = 0x2, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_1K_ENTRIES = 0x3, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_2K_ENTRIES = 0x4, + MLX5_CMD_HCA_CAP_PKEY_TABLE_SIZE_4K_ENTRIES = 0x5, +}; + +enum { + MLX5_CMD_HCA_CAP_PORT_TYPE_IB = 0x0, + MLX5_CMD_HCA_CAP_PORT_TYPE_ETHERNET = 0x1, +}; + +enum { + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_DISABLED = 0x0, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_INITIAL_STATE = 0x1, + MLX5_CMD_HCA_CAP_CMDIF_CHECKSUM_ENABLED = 0x3, +}; + +enum { + MLX5_CAP_PORT_TYPE_IB = 0x0, + MLX5_CAP_PORT_TYPE_ETH = 0x1, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -148,9 +611,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_1[0xb]; u8 log_max_qp[0x5]; - u8 log_max_strq_sz[0x8]; - u8 reserved_2[0x3]; - u8 log_max_srqs[0x5]; + u8 reserved_2[0xb]; + u8 log_max_srq[0x5]; u8 reserved_3[0x10]; u8 reserved_4[0x8]; @@ -185,123 +647,2112 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pad_cap[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_15[0x1d]; + u8 reserved_15[0xd]; + u8 gid_table_size[0x10]; - u8 reserved_16[0x6]; + u8 out_of_seq_cnt[0x1]; + u8 vport_counters[0x1]; + u8 reserved_16[0x4]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; - u8 eswitch_owner[0x1]; - u8 reserved_17[0xa]; + u8 vport_group_manager[0x1]; + u8 vhca_group_manager[0x1]; + u8 ib_virt[0x1]; + u8 eth_virt[0x1]; + u8 reserved_17[0x1]; + u8 ets[0x1]; + u8 nic_flow_table[0x1]; + u8 reserved_18[0x4]; u8 local_ca_ack_delay[0x5]; - u8 reserved_18[0x8]; + u8 reserved_19[0x6]; + u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_19[0x3]; + u8 reserved_20[0x3]; u8 log_max_msg[0x5]; - u8 reserved_20[0x18]; + u8 reserved_21[0x18]; u8 stat_rate_support[0x10]; - u8 reserved_21[0x10]; + u8 reserved_22[0xc]; + u8 cqe_version[0x4]; - u8 reserved_22[0x10]; + u8 compact_address_vector[0x1]; + u8 reserved_23[0xe]; + u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; - u8 reserved_23[0x1]; + u8 reserved_24[0x1]; u8 wq_signature[0x1]; u8 sctr_data_cqe[0x1]; - u8 reserved_24[0x1]; + u8 reserved_25[0x1]; u8 sho[0x1]; u8 tph[0x1]; u8 rf[0x1]; - u8 dc[0x1]; - u8 reserved_25[0x2]; + u8 dct[0x1]; + u8 reserved_26[0x1]; + u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; - u8 rsz_srq[0x1]; + u8 reserved_27[0x1]; u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 sniffer_rule_flow[0x1]; - u8 sniffer_rule_vport[0x1]; - u8 sniffer_rule_phy[0x1]; - u8 reserved_26[0x1]; + u8 reserved_28[0x3]; + u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; - u8 reserved_27[0x3]; + u8 reserved_29[0x1]; + u8 scqe_break_moderation[0x1]; + u8 reserved_30[0x1]; u8 cd[0x1]; - u8 reserved_28[0x1]; + u8 reserved_31[0x1]; u8 apm[0x1]; - u8 reserved_29[0x7]; + u8 reserved_32[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_30[0x4]; + u8 reserved_33[0x4]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_31[0xa]; + u8 reserved_34[0xa]; u8 uar_sz[0x6]; - u8 reserved_32[0x8]; + u8 reserved_35[0x8]; u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_33[0xa]; + u8 reserved_36[0x1]; + u8 pad_tx_eth_packet[0x1]; + u8 reserved_37[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_34[0x10]; + u8 reserved_38[0x10]; - u8 reserved_35[0x10]; + u8 reserved_39[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_36[0x10]; + u8 reserved_40[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_37[0x10]; + u8 reserved_41[0x10]; u8 max_wqe_sz_sq_dc[0x10]; - u8 reserved_38[0x7]; + u8 reserved_42[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_39[0x18]; + u8 reserved_43[0x18]; u8 log_max_mcg[0x8]; - u8 reserved_40[0xb]; + u8 reserved_44[0x3]; + u8 log_max_transport_domain[0x5]; + u8 reserved_45[0x3]; u8 log_max_pd[0x5]; - u8 reserved_41[0xb]; + u8 reserved_46[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_42[0x20]; + u8 reserved_47[0x20]; - u8 reserved_43[0x3]; + u8 reserved_48[0x3]; u8 log_max_rq[0x5]; - u8 reserved_44[0x3]; + u8 reserved_49[0x3]; u8 log_max_sq[0x5]; - u8 reserved_45[0x3]; + u8 reserved_50[0x3]; u8 log_max_tir[0x5]; - u8 reserved_46[0x3]; + u8 reserved_51[0x3]; u8 log_max_tis[0x5]; - u8 reserved_47[0x13]; - u8 log_max_rq_per_tir[0x5]; - u8 reserved_48[0x3]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_52[0x2]; + u8 log_max_rmp[0x5]; + u8 reserved_53[0x3]; + u8 log_max_rqt[0x5]; + u8 reserved_54[0x3]; + u8 log_max_rqt_size[0x5]; + u8 reserved_55[0x3]; u8 log_max_tis_per_sq[0x5]; - u8 reserved_49[0xe0]; + u8 reserved_56[0x3]; + u8 log_max_stride_sz_rq[0x5]; + u8 reserved_57[0x3]; + u8 log_min_stride_sz_rq[0x5]; + u8 reserved_58[0x3]; + u8 log_max_stride_sz_sq[0x5]; + u8 reserved_59[0x3]; + u8 log_min_stride_sz_sq[0x5]; - u8 reserved_50[0x10]; + u8 reserved_60[0x1b]; + u8 log_max_wq_sz[0x5]; + + u8 reserved_61[0xa0]; + + u8 reserved_62[0x3]; + u8 log_max_l2_table[0x5]; + u8 reserved_63[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_51[0x100]; + u8 reserved_64[0x100]; - u8 reserved_52[0x1f]; + u8 reserved_65[0x1f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_53[0x220]; + u8 reserved_66[0x220]; +}; + +enum { + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_FLOW_TABLE_ = 0x1, + MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_TIR = 0x2, +}; + +struct mlx5_ifc_dest_format_struct_bits { + u8 destination_type[0x8]; + u8 destination_id[0x18]; + + u8 reserved_0[0x20]; +}; + +struct mlx5_ifc_fte_match_param_bits { + struct mlx5_ifc_fte_match_set_lyr_2_4_bits outer_headers; + + struct mlx5_ifc_fte_match_set_misc_bits misc_parameters; + + struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; + + u8 reserved_0[0xa00]; +}; + +enum { + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_SRC_IP = 0x0, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_DST_IP = 0x1, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_SPORT = 0x2, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_L4_DPORT = 0x3, + MLX5_RX_HASH_FIELD_SELECT_SELECTED_FIELDS_IPSEC_SPI = 0x4, +}; + +struct mlx5_ifc_rx_hash_field_select_bits { + u8 l3_prot_type[0x1]; + u8 l4_prot_type[0x1]; + u8 selected_fields[0x1e]; +}; + +enum { + MLX5_WQ_WQ_TYPE_WQ_LINKED_LIST = 0x0, + MLX5_WQ_WQ_TYPE_WQ_CYCLIC = 0x1, +}; + +enum { + MLX5_WQ_END_PADDING_MODE_END_PAD_NONE = 0x0, + MLX5_WQ_END_PADDING_MODE_END_PAD_ALIGN = 0x1, +}; + +struct mlx5_ifc_wq_bits { + u8 wq_type[0x4]; + u8 wq_signature[0x1]; + u8 end_padding_mode[0x2]; + u8 cd_slave[0x1]; + u8 reserved_0[0x18]; + + u8 hds_skip_first_sge[0x1]; + u8 log2_hds_buf_size[0x3]; + u8 reserved_1[0x7]; + u8 page_offset[0x5]; + u8 lwm[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x8]; + u8 uar_page[0x18]; + + u8 dbr_addr[0x40]; + + u8 hw_counter[0x20]; + + u8 sw_counter[0x20]; + + u8 reserved_4[0xc]; + u8 log_wq_stride[0x4]; + u8 reserved_5[0x3]; + u8 log_wq_pg_sz[0x5]; + u8 reserved_6[0x3]; + u8 log_wq_sz[0x5]; + + u8 reserved_7[0x4e0]; + + struct mlx5_ifc_cmd_pas_bits pas[0]; +}; + +struct mlx5_ifc_rq_num_bits { + u8 reserved_0[0x8]; + u8 rq_num[0x18]; +}; + +struct mlx5_ifc_mac_address_layout_bits { + u8 reserved_0[0x10]; + u8 mac_addr_47_32[0x10]; + + u8 mac_addr_31_0[0x20]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { + u8 reserved_0[0xa0]; + + u8 min_time_between_cnps[0x20]; + + u8 reserved_1[0x12]; + u8 cnp_dscp[0x6]; + u8 reserved_2[0x5]; + u8 cnp_802p_prio[0x3]; + + u8 reserved_3[0x720]; +}; + +struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { + u8 reserved_0[0x60]; + + u8 reserved_1[0x4]; + u8 clamp_tgt_rate[0x1]; + u8 reserved_2[0x3]; + u8 clamp_tgt_rate_after_time_inc[0x1]; + u8 reserved_3[0x17]; + + u8 reserved_4[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_5[0xe0]; + + u8 rate_to_set_on_first_cnp[0x20]; + + u8 dce_tcp_g[0x20]; + + u8 dce_tcp_rtt[0x20]; + + u8 rate_reduce_monitor_period[0x20]; + + u8 reserved_6[0x20]; + + u8 initial_alpha_value[0x20]; + + u8 reserved_7[0x4a0]; +}; + +struct mlx5_ifc_cong_control_802_1qau_rp_bits { + u8 reserved_0[0x80]; + + u8 rppp_max_rps[0x20]; + + u8 rpg_time_reset[0x20]; + + u8 rpg_byte_reset[0x20]; + + u8 rpg_threshold[0x20]; + + u8 rpg_max_rate[0x20]; + + u8 rpg_ai_rate[0x20]; + + u8 rpg_hai_rate[0x20]; + + u8 rpg_gd[0x20]; + + u8 rpg_min_dec_fac[0x20]; + + u8 rpg_min_rate[0x20]; + + u8 reserved_1[0x640]; +}; + +enum { + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_CQ_SIZE = 0x1, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_PAGE_OFFSET = 0x2, + MLX5_RESIZE_FIELD_SELECT_RESIZE_FIELD_SELECT_LOG_PAGE_SIZE = 0x4, +}; + +struct mlx5_ifc_resize_field_select_bits { + u8 resize_field_select[0x20]; +}; + +enum { + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_PERIOD = 0x1, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_CQ_MAX_COUNT = 0x2, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_OI = 0x4, + MLX5_MODIFY_FIELD_SELECT_MODIFY_FIELD_SELECT_C_EQN = 0x8, +}; + +struct mlx5_ifc_modify_field_select_bits { + u8 modify_field_select[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_np_bits { + u8 field_select_r_roce_np[0x20]; +}; + +struct mlx5_ifc_field_select_r_roce_rp_bits { + u8 field_select_r_roce_rp[0x20]; +}; + +enum { + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPPP_MAX_RPS = 0x4, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_TIME_RESET = 0x8, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_BYTE_RESET = 0x10, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_THRESHOLD = 0x20, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MAX_RATE = 0x40, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_AI_RATE = 0x80, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_HAI_RATE = 0x100, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_GD = 0x200, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_DEC_FAC = 0x400, + MLX5_FIELD_SELECT_802_1QAU_RP_FIELD_SELECT_8021QAURP_RPG_MIN_RATE = 0x800, +}; + +struct mlx5_ifc_field_select_802_1qau_rp_bits { + u8 field_select_8021qaurp[0x20]; +}; + +struct mlx5_ifc_phys_layer_cntrs_bits { + u8 time_since_last_clear_high[0x20]; + + u8 time_since_last_clear_low[0x20]; + + u8 symbol_errors_high[0x20]; + + u8 symbol_errors_low[0x20]; + + u8 sync_headers_errors_high[0x20]; + + u8 sync_headers_errors_low[0x20]; + + u8 edpl_bip_errors_lane0_high[0x20]; + + u8 edpl_bip_errors_lane0_low[0x20]; + + u8 edpl_bip_errors_lane1_high[0x20]; + + u8 edpl_bip_errors_lane1_low[0x20]; + + u8 edpl_bip_errors_lane2_high[0x20]; + + u8 edpl_bip_errors_lane2_low[0x20]; + + u8 edpl_bip_errors_lane3_high[0x20]; + + u8 edpl_bip_errors_lane3_low[0x20]; + + u8 fc_fec_corrected_blocks_lane0_high[0x20]; + + u8 fc_fec_corrected_blocks_lane0_low[0x20]; + + u8 fc_fec_corrected_blocks_lane1_high[0x20]; + + u8 fc_fec_corrected_blocks_lane1_low[0x20]; + + u8 fc_fec_corrected_blocks_lane2_high[0x20]; + + u8 fc_fec_corrected_blocks_lane2_low[0x20]; + + u8 fc_fec_corrected_blocks_lane3_high[0x20]; + + u8 fc_fec_corrected_blocks_lane3_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane0_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane1_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane2_low[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_high[0x20]; + + u8 fc_fec_uncorrectable_blocks_lane3_low[0x20]; + + u8 rs_fec_corrected_blocks_high[0x20]; + + u8 rs_fec_corrected_blocks_low[0x20]; + + u8 rs_fec_uncorrectable_blocks_high[0x20]; + + u8 rs_fec_uncorrectable_blocks_low[0x20]; + + u8 rs_fec_no_errors_blocks_high[0x20]; + + u8 rs_fec_no_errors_blocks_low[0x20]; + + u8 rs_fec_single_error_blocks_high[0x20]; + + u8 rs_fec_single_error_blocks_low[0x20]; + + u8 rs_fec_corrected_symbols_total_high[0x20]; + + u8 rs_fec_corrected_symbols_total_low[0x20]; + + u8 rs_fec_corrected_symbols_lane0_high[0x20]; + + u8 rs_fec_corrected_symbols_lane0_low[0x20]; + + u8 rs_fec_corrected_symbols_lane1_high[0x20]; + + u8 rs_fec_corrected_symbols_lane1_low[0x20]; + + u8 rs_fec_corrected_symbols_lane2_high[0x20]; + + u8 rs_fec_corrected_symbols_lane2_low[0x20]; + + u8 rs_fec_corrected_symbols_lane3_high[0x20]; + + u8 rs_fec_corrected_symbols_lane3_low[0x20]; + + u8 link_down_events[0x20]; + + u8 successful_recovery_events[0x20]; + + u8 reserved_0[0x180]; +}; + +struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { + u8 transmit_queue_high[0x20]; + + u8 transmit_queue_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { + u8 rx_octets_high[0x20]; + + u8 rx_octets_low[0x20]; + + u8 reserved_0[0xc0]; + + u8 rx_frames_high[0x20]; + + u8 rx_frames_low[0x20]; + + u8 tx_octets_high[0x20]; + + u8 tx_octets_low[0x20]; + + u8 reserved_1[0xc0]; + + u8 tx_frames_high[0x20]; + + u8 tx_frames_low[0x20]; + + u8 rx_pause_high[0x20]; + + u8 rx_pause_low[0x20]; + + u8 rx_pause_duration_high[0x20]; + + u8 rx_pause_duration_low[0x20]; + + u8 tx_pause_high[0x20]; + + u8 tx_pause_low[0x20]; + + u8 tx_pause_duration_high[0x20]; + + u8 tx_pause_duration_low[0x20]; + + u8 rx_pause_transition_high[0x20]; + + u8 rx_pause_transition_low[0x20]; + + u8 reserved_2[0x400]; +}; + +struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { + u8 port_transmit_wait_high[0x20]; + + u8 port_transmit_wait_low[0x20]; + + u8 reserved_0[0x780]; +}; + +struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { + u8 dot3stats_alignment_errors_high[0x20]; + + u8 dot3stats_alignment_errors_low[0x20]; + + u8 dot3stats_fcs_errors_high[0x20]; + + u8 dot3stats_fcs_errors_low[0x20]; + + u8 dot3stats_single_collision_frames_high[0x20]; + + u8 dot3stats_single_collision_frames_low[0x20]; + + u8 dot3stats_multiple_collision_frames_high[0x20]; + + u8 dot3stats_multiple_collision_frames_low[0x20]; + + u8 dot3stats_sqe_test_errors_high[0x20]; + + u8 dot3stats_sqe_test_errors_low[0x20]; + + u8 dot3stats_deferred_transmissions_high[0x20]; + + u8 dot3stats_deferred_transmissions_low[0x20]; + + u8 dot3stats_late_collisions_high[0x20]; + + u8 dot3stats_late_collisions_low[0x20]; + + u8 dot3stats_excessive_collisions_high[0x20]; + + u8 dot3stats_excessive_collisions_low[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_high[0x20]; + + u8 dot3stats_internal_mac_transmit_errors_low[0x20]; + + u8 dot3stats_carrier_sense_errors_high[0x20]; + + u8 dot3stats_carrier_sense_errors_low[0x20]; + + u8 dot3stats_frame_too_longs_high[0x20]; + + u8 dot3stats_frame_too_longs_low[0x20]; + + u8 dot3stats_internal_mac_receive_errors_high[0x20]; + + u8 dot3stats_internal_mac_receive_errors_low[0x20]; + + u8 dot3stats_symbol_errors_high[0x20]; + + u8 dot3stats_symbol_errors_low[0x20]; + + u8 dot3control_in_unknown_opcodes_high[0x20]; + + u8 dot3control_in_unknown_opcodes_low[0x20]; + + u8 dot3in_pause_frames_high[0x20]; + + u8 dot3in_pause_frames_low[0x20]; + + u8 dot3out_pause_frames_high[0x20]; + + u8 dot3out_pause_frames_low[0x20]; + + u8 reserved_0[0x3c0]; +}; + +struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { + u8 ether_stats_drop_events_high[0x20]; + + u8 ether_stats_drop_events_low[0x20]; + + u8 ether_stats_octets_high[0x20]; + + u8 ether_stats_octets_low[0x20]; + + u8 ether_stats_pkts_high[0x20]; + + u8 ether_stats_pkts_low[0x20]; + + u8 ether_stats_broadcast_pkts_high[0x20]; + + u8 ether_stats_broadcast_pkts_low[0x20]; + + u8 ether_stats_multicast_pkts_high[0x20]; + + u8 ether_stats_multicast_pkts_low[0x20]; + + u8 ether_stats_crc_align_errors_high[0x20]; + + u8 ether_stats_crc_align_errors_low[0x20]; + + u8 ether_stats_undersize_pkts_high[0x20]; + + u8 ether_stats_undersize_pkts_low[0x20]; + + u8 ether_stats_oversize_pkts_high[0x20]; + + u8 ether_stats_oversize_pkts_low[0x20]; + + u8 ether_stats_fragments_high[0x20]; + + u8 ether_stats_fragments_low[0x20]; + + u8 ether_stats_jabbers_high[0x20]; + + u8 ether_stats_jabbers_low[0x20]; + + u8 ether_stats_collisions_high[0x20]; + + u8 ether_stats_collisions_low[0x20]; + + u8 ether_stats_pkts64octets_high[0x20]; + + u8 ether_stats_pkts64octets_low[0x20]; + + u8 ether_stats_pkts65to127octets_high[0x20]; + + u8 ether_stats_pkts65to127octets_low[0x20]; + + u8 ether_stats_pkts128to255octets_high[0x20]; + + u8 ether_stats_pkts128to255octets_low[0x20]; + + u8 ether_stats_pkts256to511octets_high[0x20]; + + u8 ether_stats_pkts256to511octets_low[0x20]; + + u8 ether_stats_pkts512to1023octets_high[0x20]; + + u8 ether_stats_pkts512to1023octets_low[0x20]; + + u8 ether_stats_pkts1024to1518octets_high[0x20]; + + u8 ether_stats_pkts1024to1518octets_low[0x20]; + + u8 ether_stats_pkts1519to2047octets_high[0x20]; + + u8 ether_stats_pkts1519to2047octets_low[0x20]; + + u8 ether_stats_pkts2048to4095octets_high[0x20]; + + u8 ether_stats_pkts2048to4095octets_low[0x20]; + + u8 ether_stats_pkts4096to8191octets_high[0x20]; + + u8 ether_stats_pkts4096to8191octets_low[0x20]; + + u8 ether_stats_pkts8192to10239octets_high[0x20]; + + u8 ether_stats_pkts8192to10239octets_low[0x20]; + + u8 reserved_0[0x280]; +}; + +struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { + u8 if_in_octets_high[0x20]; + + u8 if_in_octets_low[0x20]; + + u8 if_in_ucast_pkts_high[0x20]; + + u8 if_in_ucast_pkts_low[0x20]; + + u8 if_in_discards_high[0x20]; + + u8 if_in_discards_low[0x20]; + + u8 if_in_errors_high[0x20]; + + u8 if_in_errors_low[0x20]; + + u8 if_in_unknown_protos_high[0x20]; + + u8 if_in_unknown_protos_low[0x20]; + + u8 if_out_octets_high[0x20]; + + u8 if_out_octets_low[0x20]; + + u8 if_out_ucast_pkts_high[0x20]; + + u8 if_out_ucast_pkts_low[0x20]; + + u8 if_out_discards_high[0x20]; + + u8 if_out_discards_low[0x20]; + + u8 if_out_errors_high[0x20]; + + u8 if_out_errors_low[0x20]; + + u8 if_in_multicast_pkts_high[0x20]; + + u8 if_in_multicast_pkts_low[0x20]; + + u8 if_in_broadcast_pkts_high[0x20]; + + u8 if_in_broadcast_pkts_low[0x20]; + + u8 if_out_multicast_pkts_high[0x20]; + + u8 if_out_multicast_pkts_low[0x20]; + + u8 if_out_broadcast_pkts_high[0x20]; + + u8 if_out_broadcast_pkts_low[0x20]; + + u8 reserved_0[0x480]; +}; + +struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { + u8 a_frames_transmitted_ok_high[0x20]; + + u8 a_frames_transmitted_ok_low[0x20]; + + u8 a_frames_received_ok_high[0x20]; + + u8 a_frames_received_ok_low[0x20]; + + u8 a_frame_check_sequence_errors_high[0x20]; + + u8 a_frame_check_sequence_errors_low[0x20]; + + u8 a_alignment_errors_high[0x20]; + + u8 a_alignment_errors_low[0x20]; + + u8 a_octets_transmitted_ok_high[0x20]; + + u8 a_octets_transmitted_ok_low[0x20]; + + u8 a_octets_received_ok_high[0x20]; + + u8 a_octets_received_ok_low[0x20]; + + u8 a_multicast_frames_xmitted_ok_high[0x20]; + + u8 a_multicast_frames_xmitted_ok_low[0x20]; + + u8 a_broadcast_frames_xmitted_ok_high[0x20]; + + u8 a_broadcast_frames_xmitted_ok_low[0x20]; + + u8 a_multicast_frames_received_ok_high[0x20]; + + u8 a_multicast_frames_received_ok_low[0x20]; + + u8 a_broadcast_frames_received_ok_high[0x20]; + + u8 a_broadcast_frames_received_ok_low[0x20]; + + u8 a_in_range_length_errors_high[0x20]; + + u8 a_in_range_length_errors_low[0x20]; + + u8 a_out_of_range_length_field_high[0x20]; + + u8 a_out_of_range_length_field_low[0x20]; + + u8 a_frame_too_long_errors_high[0x20]; + + u8 a_frame_too_long_errors_low[0x20]; + + u8 a_symbol_error_during_carrier_high[0x20]; + + u8 a_symbol_error_during_carrier_low[0x20]; + + u8 a_mac_control_frames_transmitted_high[0x20]; + + u8 a_mac_control_frames_transmitted_low[0x20]; + + u8 a_mac_control_frames_received_high[0x20]; + + u8 a_mac_control_frames_received_low[0x20]; + + u8 a_unsupported_opcodes_received_high[0x20]; + + u8 a_unsupported_opcodes_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_received_high[0x20]; + + u8 a_pause_mac_ctrl_frames_received_low[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_high[0x20]; + + u8 a_pause_mac_ctrl_frames_transmitted_low[0x20]; + + u8 reserved_0[0x300]; +}; + +struct mlx5_ifc_cmd_inter_comp_event_bits { + u8 command_completion_vector[0x20]; + + u8 reserved_0[0xc0]; +}; + +struct mlx5_ifc_stall_vl_event_bits { + u8 reserved_0[0x18]; + u8 port_num[0x1]; + u8 reserved_1[0x3]; + u8 vl[0x4]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_db_bf_congestion_event_bits { + u8 event_subtype[0x8]; + u8 reserved_0[0x8]; + u8 congestion_level[0x8]; + u8 reserved_1[0x8]; + + u8 reserved_2[0xa0]; +}; + +struct mlx5_ifc_gpio_event_bits { + u8 reserved_0[0x60]; + + u8 gpio_event_hi[0x20]; + + u8 gpio_event_lo[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_port_state_change_event_bits { + u8 reserved_0[0x40]; + + u8 port_num[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_dropped_packet_logged_bits { + u8 reserved_0[0xe0]; +}; + +enum { + MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, + MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, +}; + +struct mlx5_ifc_cq_error_bits { + u8 reserved_0[0x8]; + u8 cqn[0x18]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 syndrome[0x8]; + + u8 reserved_3[0x80]; +}; + +struct mlx5_ifc_rdma_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 r_key[0x20]; + + u8 reserved_0[0x10]; + u8 packet_len[0x10]; + + u8 rdma_op_len[0x20]; + + u8 rdma_va[0x40]; + + u8 reserved_1[0x5]; + u8 rdma[0x1]; + u8 write[0x1]; + u8 requestor[0x1]; + u8 qp_number[0x18]; +}; + +struct mlx5_ifc_wqe_associated_page_fault_event_bits { + u8 bytes_committed[0x20]; + + u8 reserved_0[0x10]; + u8 wqe_index[0x10]; + + u8 reserved_1[0x10]; + u8 len[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x5]; + u8 rdma[0x1]; + u8 write_read[0x1]; + u8 requestor[0x1]; + u8 qpn[0x18]; +}; + +struct mlx5_ifc_qp_events_bits { + u8 reserved_0[0xa0]; + + u8 type[0x8]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 qpn_rqn_sqn[0x18]; +}; + +struct mlx5_ifc_dct_events_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 dct_number[0x18]; +}; + +struct mlx5_ifc_comp_event_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 cq_number[0x18]; +}; + +enum { + MLX5_QPC_STATE_RST = 0x0, + MLX5_QPC_STATE_INIT = 0x1, + MLX5_QPC_STATE_RTR = 0x2, + MLX5_QPC_STATE_RTS = 0x3, + MLX5_QPC_STATE_SQER = 0x4, + MLX5_QPC_STATE_ERR = 0x6, + MLX5_QPC_STATE_SQD = 0x7, + MLX5_QPC_STATE_SUSPENDED = 0x9, +}; + +enum { + MLX5_QPC_ST_RC = 0x0, + MLX5_QPC_ST_UC = 0x1, + MLX5_QPC_ST_UD = 0x2, + MLX5_QPC_ST_XRC = 0x3, + MLX5_QPC_ST_DCI = 0x5, + MLX5_QPC_ST_QP0 = 0x7, + MLX5_QPC_ST_QP1 = 0x8, + MLX5_QPC_ST_RAW_DATAGRAM = 0x9, + MLX5_QPC_ST_REG_UMR = 0xc, +}; + +enum { + MLX5_QPC_PM_STATE_ARMED = 0x0, + MLX5_QPC_PM_STATE_REARM = 0x1, + MLX5_QPC_PM_STATE_RESERVED = 0x2, + MLX5_QPC_PM_STATE_MIGRATED = 0x3, +}; + +enum { + MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, + MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, +}; + +enum { + MLX5_QPC_MTU_256_BYTES = 0x1, + MLX5_QPC_MTU_512_BYTES = 0x2, + MLX5_QPC_MTU_1K_BYTES = 0x3, + MLX5_QPC_MTU_2K_BYTES = 0x4, + MLX5_QPC_MTU_4K_BYTES = 0x5, + MLX5_QPC_MTU_RAW_ETHERNET_QP = 0x7, +}; + +enum { + MLX5_QPC_ATOMIC_MODE_IB_SPEC = 0x1, + MLX5_QPC_ATOMIC_MODE_ONLY_8B = 0x2, + MLX5_QPC_ATOMIC_MODE_UP_TO_8B = 0x3, + MLX5_QPC_ATOMIC_MODE_UP_TO_16B = 0x4, + MLX5_QPC_ATOMIC_MODE_UP_TO_32B = 0x5, + MLX5_QPC_ATOMIC_MODE_UP_TO_64B = 0x6, + MLX5_QPC_ATOMIC_MODE_UP_TO_128B = 0x7, + MLX5_QPC_ATOMIC_MODE_UP_TO_256B = 0x8, +}; + +enum { + MLX5_QPC_CS_REQ_DISABLE = 0x0, + MLX5_QPC_CS_REQ_UP_TO_32B = 0x11, + MLX5_QPC_CS_REQ_UP_TO_64B = 0x22, +}; + +enum { + MLX5_QPC_CS_RES_DISABLE = 0x0, + MLX5_QPC_CS_RES_UP_TO_32B = 0x1, + MLX5_QPC_CS_RES_UP_TO_64B = 0x2, +}; + +struct mlx5_ifc_qpc_bits { + u8 state[0x4]; + u8 reserved_0[0x4]; + u8 st[0x8]; + u8 reserved_1[0x3]; + u8 pm_state[0x2]; + u8 reserved_2[0x7]; + u8 end_padding_mode[0x2]; + u8 reserved_3[0x2]; + + u8 wq_signature[0x1]; + u8 block_lb_mc[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 reserved_4[0x1]; + u8 drain_sigerr[0x1]; + u8 reserved_5[0x2]; + u8 pd[0x18]; + + u8 mtu[0x3]; + u8 log_msg_max[0x5]; + u8 reserved_6[0x1]; + u8 log_rq_size[0x4]; + u8 log_rq_stride[0x3]; + u8 no_sq[0x1]; + u8 log_sq_size[0x4]; + u8 reserved_7[0x6]; + u8 rlky[0x1]; + u8 reserved_8[0x4]; + + u8 counter_set_id[0x8]; + u8 uar_page[0x18]; + + u8 reserved_9[0x8]; + u8 user_index[0x18]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 remote_qpn[0x18]; + + struct mlx5_ifc_ads_bits primary_address_path; + + struct mlx5_ifc_ads_bits secondary_address_path; + + u8 log_ack_req_freq[0x4]; + u8 reserved_11[0x4]; + u8 log_sra_max[0x3]; + u8 reserved_12[0x2]; + u8 retry_count[0x3]; + u8 rnr_retry[0x3]; + u8 reserved_13[0x1]; + u8 fre[0x1]; + u8 cur_rnr_retry[0x3]; + u8 cur_retry_count[0x3]; + u8 reserved_14[0x5]; + + u8 reserved_15[0x20]; + + u8 reserved_16[0x8]; + u8 next_send_psn[0x18]; + + u8 reserved_17[0x8]; + u8 cqn_snd[0x18]; + + u8 reserved_18[0x40]; + + u8 reserved_19[0x8]; + u8 last_acked_psn[0x18]; + + u8 reserved_20[0x8]; + u8 ssn[0x18]; + + u8 reserved_21[0x8]; + u8 log_rra_max[0x3]; + u8 reserved_22[0x1]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 reserved_23[0x1]; + u8 page_offset[0x6]; + u8 reserved_24[0x3]; + u8 cd_slave_receive[0x1]; + u8 cd_slave_send[0x1]; + u8 cd_master[0x1]; + + u8 reserved_25[0x3]; + u8 min_rnr_nak[0x5]; + u8 next_rcv_psn[0x18]; + + u8 reserved_26[0x8]; + u8 xrcd[0x18]; + + u8 reserved_27[0x8]; + u8 cqn_rcv[0x18]; + + u8 dbr_addr[0x40]; + + u8 q_key[0x20]; + + u8 reserved_28[0x5]; + u8 rq_type[0x3]; + u8 srqn_rmpn[0x18]; + + u8 reserved_29[0x8]; + u8 rmsn[0x18]; + + u8 hw_sq_wqebb_counter[0x10]; + u8 sw_sq_wqebb_counter[0x10]; + + u8 hw_rq_counter[0x20]; + + u8 sw_rq_counter[0x20]; + + u8 reserved_30[0x20]; + + u8 reserved_31[0xf]; + u8 cgs[0x1]; + u8 cs_req[0x8]; + u8 cs_res[0x8]; + + u8 dc_access_key[0x40]; + + u8 reserved_32[0xc0]; +}; + +struct mlx5_ifc_roce_addr_layout_bits { + u8 source_l3_address[16][0x8]; + + u8 reserved_0[0x3]; + u8 vlan_valid[0x1]; + u8 vlan_id[0xc]; + u8 source_mac_47_32[0x10]; + + u8 source_mac_31_0[0x20]; + + u8 reserved_1[0x14]; + u8 roce_l3_type[0x4]; + u8 roce_version[0x8]; + + u8 reserved_2[0x20]; +}; + +union mlx5_ifc_hca_cap_union_bits { + struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_odp_cap_bits odp_cap; + struct mlx5_ifc_atomic_caps_bits atomic_caps; + struct mlx5_ifc_roce_cap_bits roce_cap; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; + struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; + u8 reserved_0[0x8000]; +}; + +enum { + MLX5_FLOW_CONTEXT_ACTION_ALLOW = 0x1, + MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, +}; + +struct mlx5_ifc_flow_context_bits { + u8 reserved_0[0x20]; + + u8 group_id[0x20]; + + u8 reserved_1[0x8]; + u8 flow_tag[0x18]; + + u8 reserved_2[0x10]; + u8 action[0x10]; + + u8 reserved_3[0x8]; + u8 destination_list_size[0x18]; + + u8 reserved_4[0x160]; + + struct mlx5_ifc_fte_match_param_bits match_value; + + u8 reserved_5[0x600]; + + struct mlx5_ifc_dest_format_struct_bits destination[0]; +}; + +enum { + MLX5_XRC_SRQC_STATE_GOOD = 0x0, + MLX5_XRC_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_xrc_srqc_bits { + u8 state[0x4]; + u8 log_xrc_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 basic_cyclic_rcv_wqe[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_2[0x2]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; + + u8 user_index_equal_xrc_srqn[0x1]; + u8 reserved_4[0x1]; + u8 log_page_size[0x6]; + u8 user_index[0x18]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_7[0x40]; + + u8 db_record_addr_h[0x20]; + + u8 db_record_addr_l[0x1e]; + u8 reserved_8[0x2]; + + u8 reserved_9[0x80]; +}; + +struct mlx5_ifc_traffic_counter_bits { + u8 packets[0x40]; + + u8 octets[0x40]; +}; + +struct mlx5_ifc_tisc_bits { + u8 reserved_0[0xc]; + u8 prio[0x4]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x100]; + + u8 reserved_3[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_4[0x3c0]; +}; + +enum { + MLX5_TIRC_DISP_TYPE_DIRECT = 0x0, + MLX5_TIRC_DISP_TYPE_INDIRECT = 0x1, +}; + +enum { + MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO = 0x1, + MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO = 0x2, +}; + +enum { + MLX5_TIRC_RX_HASH_FN_HASH_NONE = 0x0, + MLX5_TIRC_RX_HASH_FN_HASH_INVERTED_XOR8 = 0x1, + MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ = 0x2, +}; + +enum { + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, +}; + +struct mlx5_ifc_tirc_bits { + u8 reserved_0[0x20]; + + u8 disp_type[0x4]; + u8 reserved_1[0x1c]; + + u8 reserved_2[0x40]; + + u8 reserved_3[0x4]; + u8 lro_timeout_period_usecs[0x10]; + u8 lro_enable_mask[0x4]; + u8 lro_max_ip_payload_size[0x8]; + + u8 reserved_4[0x40]; + + u8 reserved_5[0x8]; + u8 inline_rqn[0x18]; + + u8 rx_hash_symmetric[0x1]; + u8 reserved_6[0x1]; + u8 tunneled_offload_en[0x1]; + u8 reserved_7[0x5]; + u8 indirect_table[0x18]; + + u8 rx_hash_fn[0x4]; + u8 reserved_8[0x2]; + u8 self_lb_block[0x2]; + u8 transport_domain[0x18]; + + u8 rx_hash_toeplitz_key[10][0x20]; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_outer; + + struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner; + + u8 reserved_9[0x4c0]; +}; + +enum { + MLX5_SRQC_STATE_GOOD = 0x0, + MLX5_SRQC_STATE_ERROR = 0x1, +}; + +struct mlx5_ifc_srqc_bits { + u8 state[0x4]; + u8 log_srq_size[0x4]; + u8 reserved_0[0x18]; + + u8 wq_signature[0x1]; + u8 cont_srq[0x1]; + u8 reserved_1[0x1]; + u8 rlky[0x1]; + u8 reserved_2[0x1]; + u8 log_rq_stride[0x3]; + u8 xrcd[0x18]; + + u8 page_offset[0x6]; + u8 reserved_3[0x2]; + u8 cqn[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x2]; + u8 log_page_size[0x6]; + u8 reserved_6[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x8]; + u8 pd[0x18]; + + u8 lwm[0x10]; + u8 wqe_cnt[0x10]; + + u8 reserved_9[0x40]; + + u8 dbr_addr[0x40]; + + u8 reserved_10[0x80]; +}; + +enum { + MLX5_SQC_STATE_RST = 0x0, + MLX5_SQC_STATE_RDY = 0x1, + MLX5_SQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_sqc_bits { + u8 rlky[0x1]; + u8 cd_master[0x1]; + u8 fre[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 reserved_4[0xa0]; + + u8 tis_lst_sz[0x10]; + u8 reserved_5[0x10]; + + u8 reserved_6[0x40]; + + u8 reserved_7[0x8]; + u8 tis_num_0[0x18]; + + struct mlx5_ifc_wq_bits wq; +}; + +struct mlx5_ifc_rqtc_bits { + u8 reserved_0[0xa0]; + + u8 reserved_1[0x10]; + u8 rqt_max_size[0x10]; + + u8 reserved_2[0x10]; + u8 rqt_actual_size[0x10]; + + u8 reserved_3[0x6a0]; + + struct mlx5_ifc_rq_num_bits rq_num[0]; +}; + +enum { + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, + MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_RMP = 0x1, +}; + +enum { + MLX5_RQC_STATE_RST = 0x0, + MLX5_RQC_STATE_RDY = 0x1, + MLX5_RQC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rqc_bits { + u8 rlky[0x1]; + u8 reserved_0[0x2]; + u8 vsd[0x1]; + u8 mem_rq_type[0x4]; + u8 state[0x4]; + u8 reserved_1[0x1]; + u8 flush_in_error_en[0x1]; + u8 reserved_2[0x12]; + + u8 reserved_3[0x8]; + u8 user_index[0x18]; + + u8 reserved_4[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 reserved_5[0x18]; + + u8 reserved_6[0x8]; + u8 rmpn[0x18]; + + u8 reserved_7[0xe0]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_RMPC_STATE_RDY = 0x1, + MLX5_RMPC_STATE_ERR = 0x3, +}; + +struct mlx5_ifc_rmpc_bits { + u8 reserved_0[0x8]; + u8 state[0x4]; + u8 reserved_1[0x14]; + + u8 basic_cyclic_rcv_wqe[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x140]; + + struct mlx5_ifc_wq_bits wq; +}; + +enum { + MLX5_NIC_VPORT_CONTEXT_ALLOWED_LIST_TYPE_CURRENT_UC_MAC_ADDRESS = 0x0, +}; + +struct mlx5_ifc_nic_vport_context_bits { + u8 reserved_0[0x1f]; + u8 roce_en[0x1]; + + u8 reserved_1[0x760]; + + u8 reserved_2[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_3[0xc]; + u8 allowed_list_size[0xc]; + + struct mlx5_ifc_mac_address_layout_bits permanent_address; + + u8 reserved_4[0x20]; + + u8 current_uc_mac_address[0][0x40]; +}; + +enum { + MLX5_MKC_ACCESS_MODE_PA = 0x0, + MLX5_MKC_ACCESS_MODE_MTT = 0x1, + MLX5_MKC_ACCESS_MODE_KLMS = 0x2, +}; + +struct mlx5_ifc_mkc_bits { + u8 reserved_0[0x1]; + u8 free[0x1]; + u8 reserved_1[0xd]; + u8 small_fence_on_rdma_read_response[0x1]; + u8 umr_en[0x1]; + u8 a[0x1]; + u8 rw[0x1]; + u8 rr[0x1]; + u8 lw[0x1]; + u8 lr[0x1]; + u8 access_mode[0x2]; + u8 reserved_2[0x8]; + + u8 qpn[0x18]; + u8 mkey_7_0[0x8]; + + u8 reserved_3[0x20]; + + u8 length64[0x1]; + u8 bsf_en[0x1]; + u8 sync_umr[0x1]; + u8 reserved_4[0x2]; + u8 expected_sigerr_count[0x1]; + u8 reserved_5[0x1]; + u8 en_rinval[0x1]; + u8 pd[0x18]; + + u8 start_addr[0x40]; + + u8 len[0x40]; + + u8 bsf_octword_size[0x20]; + + u8 reserved_6[0x80]; + + u8 translations_octword_size[0x20]; + + u8 reserved_7[0x1b]; + u8 log_page_size[0x5]; + + u8 reserved_8[0x20]; +}; + +struct mlx5_ifc_pkey_bits { + u8 reserved_0[0x10]; + u8 pkey[0x10]; +}; + +struct mlx5_ifc_array128_auto_bits { + u8 array128_auto[16][0x8]; +}; + +struct mlx5_ifc_hca_vport_context_bits { + u8 field_select[0x20]; + + u8 reserved_0[0xe0]; + + u8 sm_virt_aware[0x1]; + u8 has_smi[0x1]; + u8 has_raw[0x1]; + u8 grh_required[0x1]; + u8 reserved_1[0xc]; + u8 port_physical_state[0x4]; + u8 vport_state_policy[0x4]; + u8 port_state[0x4]; + u8 vport_state[0x4]; + + u8 reserved_2[0x20]; + + u8 system_image_guid[0x40]; + + u8 port_guid[0x40]; + + u8 node_guid[0x40]; + + u8 cap_mask1[0x20]; + + u8 cap_mask1_field_select[0x20]; + + u8 cap_mask2[0x20]; + + u8 cap_mask2_field_select[0x20]; + + u8 reserved_3[0x80]; + + u8 lid[0x10]; + u8 reserved_4[0x4]; + u8 init_type_reply[0x4]; + u8 lmc[0x3]; + u8 subnet_timeout[0x5]; + + u8 sm_lid[0x10]; + u8 sm_sl[0x4]; + u8 reserved_5[0xc]; + + u8 qkey_violation_counter[0x10]; + u8 pkey_violation_counter[0x10]; + + u8 reserved_6[0xca0]; +}; + +enum { + MLX5_EQC_STATUS_OK = 0x0, + MLX5_EQC_STATUS_EQ_WRITE_FAILURE = 0xa, +}; + +enum { + MLX5_EQC_ST_ARMED = 0x9, + MLX5_EQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_eqc_bits { + u8 status[0x4]; + u8 reserved_0[0x9]; + u8 ec[0x1]; + u8 oi[0x1]; + u8 reserved_1[0x5]; + u8 st[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x14]; + u8 page_offset[0x6]; + u8 reserved_5[0x6]; + + u8 reserved_6[0x3]; + u8 log_eq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x18]; + u8 intr[0x8]; + + u8 reserved_9[0x3]; + u8 log_page_size[0x5]; + u8 reserved_10[0x18]; + + u8 reserved_11[0x60]; + + u8 reserved_12[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_13[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_14[0x80]; +}; + +enum { + MLX5_DCTC_STATE_ACTIVE = 0x0, + MLX5_DCTC_STATE_DRAINING = 0x1, + MLX5_DCTC_STATE_DRAINED = 0x2, +}; + +enum { + MLX5_DCTC_CS_RES_DISABLE = 0x0, + MLX5_DCTC_CS_RES_NA = 0x1, + MLX5_DCTC_CS_RES_UP_TO_64B = 0x2, +}; + +enum { + MLX5_DCTC_MTU_256_BYTES = 0x1, + MLX5_DCTC_MTU_512_BYTES = 0x2, + MLX5_DCTC_MTU_1K_BYTES = 0x3, + MLX5_DCTC_MTU_2K_BYTES = 0x4, + MLX5_DCTC_MTU_4K_BYTES = 0x5, +}; + +struct mlx5_ifc_dctc_bits { + u8 reserved_0[0x4]; + u8 state[0x4]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x8]; + u8 user_index[0x18]; + + u8 reserved_3[0x8]; + u8 cqn[0x18]; + + u8 counter_set_id[0x8]; + u8 atomic_mode[0x4]; + u8 rre[0x1]; + u8 rwe[0x1]; + u8 rae[0x1]; + u8 atomic_like_write_en[0x1]; + u8 latency_sensitive[0x1]; + u8 rlky[0x1]; + u8 free_ar[0x1]; + u8 reserved_4[0xd]; + + u8 reserved_5[0x8]; + u8 cs_res[0x8]; + u8 reserved_6[0x3]; + u8 min_rnr_nak[0x5]; + u8 reserved_7[0x8]; + + u8 reserved_8[0x8]; + u8 srqn[0x18]; + + u8 reserved_9[0x8]; + u8 pd[0x18]; + + u8 tclass[0x8]; + u8 reserved_10[0x4]; + u8 flow_label[0x14]; + + u8 dc_access_key[0x40]; + + u8 reserved_11[0x5]; + u8 mtu[0x3]; + u8 port[0x8]; + u8 pkey_index[0x10]; + + u8 reserved_12[0x8]; + u8 my_addr_index[0x8]; + u8 reserved_13[0x8]; + u8 hop_limit[0x8]; + + u8 dc_access_key_violation_count[0x20]; + + u8 reserved_14[0x14]; + u8 dei_cfi[0x1]; + u8 eth_prio[0x3]; + u8 ecn[0x2]; + u8 dscp[0x6]; + + u8 reserved_15[0x40]; +}; + +enum { + MLX5_CQC_STATUS_OK = 0x0, + MLX5_CQC_STATUS_CQ_OVERFLOW = 0x9, + MLX5_CQC_STATUS_CQ_WRITE_FAIL = 0xa, +}; + +enum { + MLX5_CQC_CQE_SZ_64_BYTES = 0x0, + MLX5_CQC_CQE_SZ_128_BYTES = 0x1, +}; + +enum { + MLX5_CQC_ST_SOLICITED_NOTIFICATION_REQUEST_ARMED = 0x6, + MLX5_CQC_ST_NOTIFICATION_REQUEST_ARMED = 0x9, + MLX5_CQC_ST_FIRED = 0xa, +}; + +struct mlx5_ifc_cqc_bits { + u8 status[0x4]; + u8 reserved_0[0x4]; + u8 cqe_sz[0x3]; + u8 cc[0x1]; + u8 reserved_1[0x1]; + u8 scqe_break_moderation_en[0x1]; + u8 oi[0x1]; + u8 reserved_2[0x2]; + u8 cqe_zip_en[0x1]; + u8 mini_cqe_res_format[0x2]; + u8 st[0x4]; + u8 reserved_3[0x8]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x14]; + u8 page_offset[0x6]; + u8 reserved_6[0x6]; + + u8 reserved_7[0x3]; + u8 log_cq_size[0x5]; + u8 uar_page[0x18]; + + u8 reserved_8[0x4]; + u8 cq_period[0xc]; + u8 cq_max_count[0x10]; + + u8 reserved_9[0x18]; + u8 c_eqn[0x8]; + + u8 reserved_10[0x3]; + u8 log_page_size[0x5]; + u8 reserved_11[0x18]; + + u8 reserved_12[0x20]; + + u8 reserved_13[0x8]; + u8 last_notified_index[0x18]; + + u8 reserved_14[0x8]; + u8 last_solicit_index[0x18]; + + u8 reserved_15[0x8]; + u8 consumer_counter[0x18]; + + u8 reserved_16[0x8]; + u8 producer_counter[0x18]; + + u8 reserved_17[0x40]; + + u8 dbr_addr[0x40]; +}; + +union mlx5_ifc_cong_control_roce_ecn_auto_bits { + struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; + struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; + u8 reserved_0[0x800]; +}; + +struct mlx5_ifc_query_adapter_param_block_bits { + u8 reserved_0[0xc0]; + + u8 reserved_1[0x8]; + u8 ieee_vendor_id[0x18]; + + u8 reserved_2[0x10]; + u8 vsd_vendor_id[0x10]; + + u8 vsd[208][0x8]; + + u8 vsd_contd_psid[16][0x8]; +}; + +union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { + struct mlx5_ifc_modify_field_select_bits modify_field_select; + struct mlx5_ifc_resize_field_select_bits resize_field_select; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_field_select_802_1_r_roce_auto_bits { + struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp; + struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp; + struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np; + u8 reserved_0[0x20]; +}; + +union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + u8 reserved_0[0x7c0]; +}; + +union mlx5_ifc_event_auto_bits { + struct mlx5_ifc_comp_event_bits comp_event; + struct mlx5_ifc_dct_events_bits dct_events; + struct mlx5_ifc_qp_events_bits qp_events; + struct mlx5_ifc_wqe_associated_page_fault_event_bits wqe_associated_page_fault_event; + struct mlx5_ifc_rdma_page_fault_event_bits rdma_page_fault_event; + struct mlx5_ifc_cq_error_bits cq_error; + struct mlx5_ifc_dropped_packet_logged_bits dropped_packet_logged; + struct mlx5_ifc_port_state_change_event_bits port_state_change_event; + struct mlx5_ifc_gpio_event_bits gpio_event; + struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event; + struct mlx5_ifc_stall_vl_event_bits stall_vl_event; + struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event; + u8 reserved_0[0xe0]; +}; + +struct mlx5_ifc_health_buffer_bits { + u8 reserved_0[0x100]; + + u8 assert_existptr[0x20]; + + u8 assert_callra[0x20]; + + u8 reserved_1[0x40]; + + u8 fw_version[0x20]; + + u8 hw_id[0x20]; + + u8 reserved_2[0x20]; + + u8 irisc_index[0x8]; + u8 synd[0x8]; + u8 ext_synd[0x10]; +}; + +struct mlx5_ifc_register_loopback_control_bits { + u8 no_lb[0x1]; + u8 reserved_0[0x7]; + u8 port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_teardown_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, + MLX5_TEARDOWN_HCA_IN_PROFILE_PANIC_CLOSE = 0x1, +}; + +struct mlx5_ifc_teardown_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 profile[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_sqerr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqerr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_sqd2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_sqd2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_set_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_set_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_PASS_ALL = 0x0, + MLX5_SET_MAD_DEMUX_IN_DEMUX_MODE_SELECTIVE = 0x2, +}; + +struct mlx5_ifc_set_mad_demux_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x6]; + u8 demux_mode[0x2]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_set_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_6[0xc0]; +}; + +struct mlx5_ifc_set_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_issi_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 current_issi[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_set_hca_cap_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; }; struct mlx5_ifc_set_hca_cap_in_bits { @@ -313,10 +2764,653 @@ struct mlx5_ifc_set_hca_cap_in_bits { u8 reserved_2[0x40]; - struct mlx5_ifc_cmd_hca_cap_bits hca_capability_struct; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_query_hca_cap_in_bits { +struct mlx5_ifc_set_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_rts2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rts2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rtr2rts_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rtr2rts_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_rst2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rst2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_query_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_OUT_STATE_DOWN = 0x0, + MLX5_QUERY_VPORT_STATE_OUT_STATE_UP = 0x1, +}; + +struct mlx5_ifc_query_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 reserved_2[0x18]; + u8 admin_state[0x4]; + u8 state[0x4]; +}; + +enum { + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, +}; + +struct mlx5_ifc_query_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_vport_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_traffic_counter_bits received_errors; + + struct mlx5_ifc_traffic_counter_bits transmit_errors; + + struct mlx5_ifc_traffic_counter_bits received_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_unicast; + + struct mlx5_ifc_traffic_counter_bits received_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_ib_multicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_broadcast; + + struct mlx5_ifc_traffic_counter_bits received_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_unicast; + + struct mlx5_ifc_traffic_counter_bits received_eth_multicast; + + struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast; + + u8 reserved_2[0xa00]; +}; + +enum { + MLX5_QUERY_VPORT_COUNTER_IN_OP_MOD_VPORT_COUNTERS = 0x0, +}; + +struct mlx5_ifc_query_vport_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x60]; + + u8 clear[0x1]; + u8 reserved_4[0x1f]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_query_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_tisc_bits tis_context; +}; + +struct mlx5_ifc_query_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_tirc_bits tir_context; +}; + +struct mlx5_ifc_query_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_sqc_bits sq_context; +}; + +struct mlx5_ifc_query_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 resd_lkey[0x20]; +}; + +struct mlx5_ifc_query_special_contexts_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_query_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rqc_bits rq_context; +}; + +struct mlx5_ifc_query_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_roce_address_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_roce_addr_layout_bits roce_address; +}; + +struct mlx5_ifc_query_roce_address_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 roce_address_index[0x10]; + u8 reserved_2[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xc0]; + + struct mlx5_ifc_rmpc_bits rmp_context; +}; + +struct mlx5_ifc_query_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_2[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_3[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 rx_write_requests[0x20]; + + u8 reserved_2[0x20]; + + u8 rx_read_requests[0x20]; + + u8 reserved_3[0x20]; + + u8 rx_atomic_requests[0x20]; + + u8 reserved_4[0x20]; + + u8 rx_dct_connect[0x20]; + + u8 reserved_5[0x20]; + + u8 out_of_buffer[0x20]; + + u8 reserved_6[0x20]; + + u8 out_of_sequence[0x20]; + + u8 reserved_7[0x620]; +}; + +struct mlx5_ifc_query_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x80]; + + u8 clear[0x1]; + u8 reserved_3[0x1f]; + + u8 reserved_4[0x18]; + u8 counter_set_id[0x8]; +}; + +struct mlx5_ifc_query_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; +}; + +enum { + MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES = 0x1, + MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES = 0x2, + MLX5_QUERY_PAGES_IN_OP_MOD_REGULAR_PAGES = 0x3, +}; + +struct mlx5_ifc_query_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_query_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x5]; + u8 allowed_list_type[0x3]; + u8 reserved_4[0x18]; +}; + +struct mlx5_ifc_query_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_2[0x600]; + + u8 bsf0_klm0_pas_mtt0_1[16][0x8]; + + u8 bsf1_klm1_pas_mtt2_3[16][0x8]; +}; + +struct mlx5_ifc_query_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; +}; + +struct mlx5_ifc_query_mad_demux_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 mad_dumux_parameters_block[0x20]; +}; + +struct mlx5_ifc_query_mad_demux_in_bits { u8 opcode[0x10]; u8 reserved_0[0x10]; @@ -326,6 +3420,146 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 reserved_2[0x40]; }; +struct mlx5_ifc_query_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 reserved_2[0x13]; + u8 vlan_valid[0x1]; + u8 vlan[0xc]; + + struct mlx5_ifc_mac_address_layout_bits mac_address; + + u8 reserved_3[0xc0]; +}; + +struct mlx5_ifc_query_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_query_issi_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x10]; + u8 current_issi[0x10]; + + u8 reserved_2[0xa0]; + + u8 supported_issi_reserved[76][0x8]; + u8 supported_issi_dw0[0x20]; +}; + +struct mlx5_ifc_query_issi_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_hca_vport_pkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_pkey_bits pkey[0]; +}; + +struct mlx5_ifc_query_hca_vport_pkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 pkey_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_gid_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 gids_num[0x10]; + u8 reserved_2[0x10]; + + struct mlx5_ifc_array128_auto_bits gid[0]; +}; + +struct mlx5_ifc_query_hca_vport_gid_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x10]; + u8 gid_index[0x10]; +}; + +struct mlx5_ifc_query_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_query_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + struct mlx5_ifc_query_hca_cap_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -334,16 +3568,3216 @@ struct mlx5_ifc_query_hca_cap_out_bits { u8 reserved_1[0x40]; - u8 capability_struct[256][0x8]; + union mlx5_ifc_hca_cap_union_bits capability; }; -struct mlx5_ifc_set_hca_cap_out_bits { +struct mlx5_ifc_query_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_query_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x80]; + + u8 reserved_2[0x8]; + u8 level[0x8]; + u8 reserved_3[0x8]; + u8 log_size[0x8]; + + u8 reserved_4[0x120]; +}; + +struct mlx5_ifc_query_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_query_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x1c0]; + + struct mlx5_ifc_flow_context_bits flow_context; +}; + +struct mlx5_ifc_query_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +enum { + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_query_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0xa0]; + + u8 start_flow_index[0x20]; + + u8 reserved_2[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_3[0xa0]; + + u8 reserved_4[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_5[0xe00]; +}; + +struct mlx5_ifc_query_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_query_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_2[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_3[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_2[0x180]; +}; + +struct mlx5_ifc_query_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cq_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; u8 syndrome[0x20]; u8 reserved_1[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_2[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_query_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_2[0x1e]; +}; + +struct mlx5_ifc_query_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_statistics_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 cur_flows[0x20]; + + u8 sum_flows[0x20]; + + u8 cnp_ignored_high[0x20]; + + u8 cnp_ignored_low[0x20]; + + u8 cnp_handled_high[0x20]; + + u8 cnp_handled_low[0x20]; + + u8 reserved_2[0x100]; + + u8 time_stamp_high[0x20]; + + u8 time_stamp_low[0x20]; + + u8 accumulators_period[0x20]; + + u8 ecn_marked_roce_packets_high[0x20]; + + u8 ecn_marked_roce_packets_low[0x20]; + + u8 cnps_sent_high[0x20]; + + u8 cnps_sent_low[0x20]; + + u8 reserved_3[0x560]; +}; + +struct mlx5_ifc_query_cong_statistics_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 clear[0x1]; + u8 reserved_2[0x1f]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_query_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_query_adapter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct; +}; + +struct mlx5_ifc_query_adapter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_qp_2rst_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2rst_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_qp_2err_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_qp_2err_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_page_fault_resume_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_page_fault_resume_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 error[0x1]; + u8 reserved_2[0x4]; + u8 rdma[0x1]; + u8 read_write[0x1]; + u8 req_res[0x1]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_nop_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_nop_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_vport_state_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x18]; + u8 admin_state[0x4]; + u8 reserved_4[0x4]; +}; + +struct mlx5_ifc_modify_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_modify_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_modify_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 sq_state[0x4]; + u8 reserved_2[0x4]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_modify_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqtc_bits ctx; +}; + +struct mlx5_ifc_modify_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rq_state[0x4]; + u8 reserved_2[0x4]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; + + u8 modify_bitmask[0x40]; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_modify_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_rmp_bitmask_bits { + u8 reserved[0x20]; + + u8 reserved1[0x1f]; + u8 lwm[0x1]; +}; + +struct mlx5_ifc_modify_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 rmp_state[0x4]; + u8 reserved_2[0x4]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_rmp_bitmask_bits bitmask; + + u8 reserved_4[0x40]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_modify_nic_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_nic_vport_field_select_bits { + u8 reserved_0[0x1c]; + u8 permanent_address[0x1]; + u8 addresses_list[0x1]; + u8 roce_en[0x1]; + u8 reserved_1[0x1]; +}; + +struct mlx5_ifc_modify_nic_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + struct mlx5_ifc_modify_nic_vport_field_select_bits field_select; + + u8 reserved_3[0x780]; + + struct mlx5_ifc_nic_vport_context_bits nic_vport_context; +}; + +struct mlx5_ifc_modify_hca_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_hca_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xb]; + u8 port_num[0x4]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_hca_vport_context_bits hca_vport_context; +}; + +struct mlx5_ifc_modify_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_MODIFY_CQ_IN_OP_MOD_MODIFY_CQ = 0x0, + MLX5_MODIFY_CQ_IN_OP_MOD_RESIZE_CQ = 0x1, +}; + +struct mlx5_ifc_modify_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_modify_cong_status_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_status_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 priority[0x4]; + u8 cong_protocol[0x4]; + + u8 enable[0x1]; + u8 tag_enable[0x1]; + u8 reserved_3[0x1e]; +}; + +struct mlx5_ifc_modify_cong_params_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_cong_params_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x1c]; + u8 cong_protocol[0x4]; + + union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select; + + u8 reserved_3[0x80]; + + union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; +}; + +struct mlx5_ifc_manage_pages_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 output_num_entries[0x20]; + + u8 reserved_1[0x20]; + + u8 pas[0][0x40]; +}; + +enum { + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_FAIL = 0x0, + MLX5_MANAGE_PAGES_IN_OP_MOD_ALLOCATION_SUCCESS = 0x1, + MLX5_MANAGE_PAGES_IN_OP_MOD_HCA_RETURN_PAGES = 0x2, +}; + +struct mlx5_ifc_manage_pages_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 input_num_entries[0x20]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_mad_ifc_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 response_mad_packet[256][0x8]; +}; + +struct mlx5_ifc_mad_ifc_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 remote_lid[0x10]; + u8 reserved_2[0x8]; + u8 port[0x8]; + + u8 reserved_3[0x20]; + + u8 mad[256][0x8]; +}; + +struct mlx5_ifc_init_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2rtr_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_init2init_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_init2init_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 opt_param_mask[0x20]; + + u8 reserved_4[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_get_dropped_packet_log_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 packet_headers_log[128][0x8]; + + u8 packet_syndrome[64][0x8]; +}; + +struct mlx5_ifc_get_dropped_packet_log_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_gen_eqe_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; + + u8 eqe[64][0x8]; +}; + +struct mlx5_ifc_gen_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_enable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_enable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_drain_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_drain_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_disable_hca_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_disable_hca_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_detach_from_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_detach_from_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_destroy_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tisn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 tirn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 sqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqtn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 rmpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 psvn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + +struct mlx5_ifc_destroy_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 group_id[0x20]; + + u8 reserved_5[0x120]; +}; + +struct mlx5_ifc_destroy_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 eq_number[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dctn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_destroy_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_destroy_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 cqn[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_delete_l2_table_entry_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_l2_table_entry_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x8]; + u8 table_index[0x18]; + + u8 reserved_4[0x140]; +}; + +struct mlx5_ifc_delete_fte_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_delete_fte_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x40]; + + u8 flow_index[0x20]; + + u8 reserved_6[0xe0]; +}; + +struct mlx5_ifc_dealloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrcd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 uar[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_dealloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_dealloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_tis_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tisn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tis_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tisc_bits ctx; +}; + +struct mlx5_ifc_create_tir_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 tirn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_tir_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_tirc_bits ctx; +}; + +struct mlx5_ifc_create_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 srqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_srqc_bits srq_context_entry; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_sq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 sqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_sq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_sqc_bits ctx; +}; + +struct mlx5_ifc_create_rqt_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqtn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rqt_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqtc_bits rqt_context; +}; + +struct mlx5_ifc_create_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rqc_bits ctx; +}; + +struct mlx5_ifc_create_rmp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 rmpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_rmp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0xc0]; + + struct mlx5_ifc_rmpc_bits ctx; +}; + +struct mlx5_ifc_create_qp_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 qpn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_qp_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 opt_param_mask[0x20]; + + u8 reserved_3[0x20]; + + struct mlx5_ifc_qpc_bits qpc; + + u8 reserved_4[0x80]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_psv_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 reserved_2[0x8]; + u8 psv0_index[0x18]; + + u8 reserved_3[0x8]; + u8 psv1_index[0x18]; + + u8 reserved_4[0x8]; + u8 psv2_index[0x18]; + + u8 reserved_5[0x8]; + u8 psv3_index[0x18]; +}; + +struct mlx5_ifc_create_psv_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 num_psv[0x4]; + u8 reserved_2[0x4]; + u8 pd[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_create_mkey_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 mkey_index[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_mkey_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 pg_access[0x1]; + u8 reserved_3[0x1f]; + + struct mlx5_ifc_mkc_bits memory_key_mkey_entry; + + u8 reserved_4[0x80]; + + u8 translations_octword_actual_size[0x20]; + + u8 reserved_5[0x560]; + + u8 klm_pas_mtt[0][0x20]; +}; + +struct mlx5_ifc_create_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 table_id[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x20]; + + u8 reserved_5[0x8]; + u8 level[0x8]; + u8 reserved_6[0x8]; + u8 log_size[0x8]; + + u8 reserved_7[0x120]; +}; + +struct mlx5_ifc_create_flow_group_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 group_id[0x18]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, + MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS = 0x2, +}; + +struct mlx5_ifc_create_flow_group_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x20]; + + u8 start_flow_index[0x20]; + + u8 reserved_6[0x20]; + + u8 end_flow_index[0x20]; + + u8 reserved_7[0xa0]; + + u8 reserved_8[0x18]; + u8 match_criteria_enable[0x8]; + + struct mlx5_ifc_fte_match_param_bits match_criteria; + + u8 reserved_9[0xe00]; +}; + +struct mlx5_ifc_create_eq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 eq_number[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_eq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_eqc_bits eq_context_entry; + + u8 reserved_3[0x40]; + + u8 event_bitmask[0x40]; + + u8 reserved_4[0x580]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_create_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 dctn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_dctc_bits dct_context_entry; + + u8 reserved_3[0x180]; +}; + +struct mlx5_ifc_create_cq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 cqn[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_create_cq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + struct mlx5_ifc_cqc_bits cq_context; + + u8 reserved_3[0x600]; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_config_int_moderation_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_2[0x20]; +}; + +enum { + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_WRITE = 0x0, + MLX5_CONFIG_INT_MODERATION_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_config_int_moderation_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x4]; + u8 min_delay[0xc]; + u8 int_vector[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_attach_to_mcg_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_attach_to_mcg_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 qpn[0x18]; + + u8 reserved_3[0x20]; + + u8 multicast_gid[16][0x8]; +}; + +struct mlx5_ifc_arm_xrc_srq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ = 0x1, +}; + +struct mlx5_ifc_arm_xrc_srq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 xrc_srqn[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_rq_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +enum { + MLX5_ARM_RQ_IN_OP_MOD_SRQ_ = 0x1, +}; + +struct mlx5_ifc_arm_rq_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 srq_number[0x18]; + + u8 reserved_3[0x10]; + u8 lwm[0x10]; +}; + +struct mlx5_ifc_arm_dct_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_arm_dct_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x8]; + u8 dct_number[0x18]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 xrcd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_xrcd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_uar_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 uar[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_uar_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_transport_domain_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 transport_domain[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_transport_domain_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_q_counter_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x18]; + u8 counter_set_id[0x8]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_q_counter_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_alloc_pd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x8]; + u8 pd[0x18]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_alloc_pd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_add_vxlan_udp_dport_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 vxlan_udp_port[0x10]; +}; + +struct mlx5_ifc_access_register_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + u8 register_data[0][0x20]; +}; + +enum { + MLX5_ACCESS_REGISTER_IN_OP_MOD_WRITE = 0x0, + MLX5_ACCESS_REGISTER_IN_OP_MOD_READ = 0x1, +}; + +struct mlx5_ifc_access_register_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 register_id[0x10]; + + u8 argument[0x20]; + + u8 register_data[0][0x20]; +}; + +struct mlx5_ifc_sltp_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x7]; + u8 polarity[0x1]; + u8 ob_tap0[0x8]; + u8 ob_tap1[0x8]; + u8 ob_tap2[0x8]; + + u8 reserved_4[0xc]; + u8 ob_preemp_mode[0x4]; + u8 ob_reg[0x8]; + u8 ob_bias[0x8]; + + u8 reserved_5[0x20]; +}; + +struct mlx5_ifc_slrg_reg_bits { + u8 status[0x4]; + u8 version[0x4]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x2]; + u8 lane[0x4]; + u8 reserved_1[0x8]; + + u8 time_to_link_up[0x10]; + u8 reserved_2[0xc]; + u8 grade_lane_speed[0x4]; + + u8 grade_version[0x8]; + u8 grade[0x18]; + + u8 reserved_3[0x4]; + u8 height_grade_type[0x4]; + u8 height_grade[0x18]; + + u8 height_dz[0x10]; + u8 height_dv[0x10]; + + u8 reserved_4[0x10]; + u8 height_sigma[0x10]; + + u8 reserved_5[0x20]; + + u8 reserved_6[0x4]; + u8 phase_grade_type[0x4]; + u8 phase_grade[0x18]; + + u8 reserved_7[0x8]; + u8 phase_eo_pos[0x8]; + u8 reserved_8[0x8]; + u8 phase_eo_neg[0x8]; + + u8 ffe_set_tested[0x10]; + u8 test_errors_per_lane[0x10]; +}; + +struct mlx5_ifc_pvlc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x1c]; + u8 vl_hw_cap[0x4]; + + u8 reserved_3[0x1c]; + u8 vl_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 vl_operational[0x4]; +}; + +struct mlx5_ifc_pude_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_ptys_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 proto_mask[0x3]; + + u8 reserved_2[0x40]; + + u8 eth_proto_capability[0x20]; + + u8 ib_link_width_capability[0x10]; + u8 ib_proto_capability[0x10]; + + u8 reserved_3[0x20]; + + u8 eth_proto_admin[0x20]; + + u8 ib_link_width_admin[0x10]; + u8 ib_proto_admin[0x10]; + + u8 reserved_4[0x20]; + + u8 eth_proto_oper[0x20]; + + u8 ib_link_width_oper[0x10]; + u8 ib_proto_oper[0x10]; + + u8 reserved_5[0x20]; + + u8 eth_proto_lp_advertise[0x20]; + + u8 reserved_6[0x60]; +}; + +struct mlx5_ifc_ptas_reg_bits { + u8 reserved_0[0x20]; + + u8 algorithm_options[0x10]; + u8 reserved_1[0x4]; + u8 repetitions_mode[0x4]; + u8 num_of_repetitions[0x8]; + + u8 grade_version[0x8]; + u8 height_grade_type[0x4]; + u8 phase_grade_type[0x4]; + u8 height_grade_weight[0x8]; + u8 phase_grade_weight[0x8]; + + u8 gisim_measure_bits[0x10]; + u8 adaptive_tap_measure_bits[0x10]; + + u8 ber_bath_high_error_threshold[0x10]; + u8 ber_bath_mid_error_threshold[0x10]; + + u8 ber_bath_low_error_threshold[0x10]; + u8 one_ratio_high_threshold[0x10]; + + u8 one_ratio_high_mid_threshold[0x10]; + u8 one_ratio_low_mid_threshold[0x10]; + + u8 one_ratio_low_threshold[0x10]; + u8 ndeo_error_threshold[0x10]; + + u8 mixer_offset_step_size[0x10]; + u8 reserved_2[0x8]; + u8 mix90_phase_for_voltage_bath[0x8]; + + u8 mixer_offset_start[0x10]; + u8 mixer_offset_end[0x10]; + + u8 reserved_3[0x15]; + u8 ber_test_time[0xb]; +}; + +struct mlx5_ifc_pspa_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 sub_port[0x8]; + u8 reserved_0[0x8]; + + u8 reserved_1[0x20]; +}; + +struct mlx5_ifc_pqdr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x5]; + u8 prio[0x3]; + u8 reserved_2[0x6]; + u8 mode[0x2]; + + u8 reserved_3[0x20]; + + u8 reserved_4[0x10]; + u8 min_threshold[0x10]; + + u8 reserved_5[0x10]; + u8 max_threshold[0x10]; + + u8 reserved_6[0x10]; + u8 mark_probability_denominator[0x10]; + + u8 reserved_7[0x60]; +}; + +struct mlx5_ifc_ppsc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x60]; + + u8 reserved_3[0x1c]; + u8 wrps_admin[0x4]; + + u8 reserved_4[0x1c]; + u8 wrps_status[0x4]; + + u8 reserved_5[0x8]; + u8 up_threshold[0x8]; + u8 reserved_6[0x8]; + u8 down_threshold[0x8]; + + u8 reserved_7[0x20]; + + u8 reserved_8[0x1c]; + u8 srps_admin[0x4]; + + u8 reserved_9[0x1c]; + u8 srps_status[0x4]; + + u8 reserved_10[0x40]; +}; + +struct mlx5_ifc_pplr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x8]; + u8 lb_cap[0x8]; + u8 reserved_3[0x8]; + u8 lb_en[0x8]; +}; + +struct mlx5_ifc_pplm_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x20]; + + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_3[0x8]; + + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; + + u8 reserved_4[0x20]; +}; + +struct mlx5_ifc_ppcnt_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 reserved_0[0x8]; + u8 grp[0x6]; + + u8 clr[0x1]; + u8 reserved_1[0x1c]; + u8 prio_tc[0x3]; + + union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; +}; + +struct mlx5_ifc_ppad_reg_bits { + u8 reserved_0[0x3]; + u8 single_mac[0x1]; + u8 reserved_1[0x4]; + u8 local_port[0x8]; + u8 mac_47_32[0x10]; + + u8 mac_31_0[0x20]; + + u8 reserved_2[0x40]; +}; + +struct mlx5_ifc_pmtu_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 max_mtu[0x10]; + u8 reserved_2[0x10]; + + u8 admin_mtu[0x10]; + u8 reserved_3[0x10]; + + u8 oper_mtu[0x10]; + u8 reserved_4[0x10]; +}; + +struct mlx5_ifc_pmpr_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0x18]; + u8 attenuation_5g[0x8]; + + u8 reserved_3[0x18]; + u8 attenuation_7g[0x8]; + + u8 reserved_4[0x18]; + u8 attenuation_12g[0x8]; +}; + +struct mlx5_ifc_pmpe_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0xc]; + u8 module_status[0x4]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_pmpc_reg_bits { + u8 module_state_updated[32][0x8]; +}; + +struct mlx5_ifc_pmlpn_reg_bits { + u8 reserved_0[0x4]; + u8 mlpn_status[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 e[0x1]; + u8 reserved_2[0x1f]; +}; + +struct mlx5_ifc_pmlp_reg_bits { + u8 rxtx[0x1]; + u8 reserved_0[0x7]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 width[0x8]; + + u8 lane0_module_mapping[0x20]; + + u8 lane1_module_mapping[0x20]; + + u8 lane2_module_mapping[0x20]; + + u8 lane3_module_mapping[0x20]; + + u8 reserved_2[0x160]; +}; + +struct mlx5_ifc_pmaos_reg_bits { + u8 reserved_0[0x8]; + u8 module[0x8]; + u8 reserved_1[0x4]; + u8 admin_status[0x4]; + u8 reserved_2[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_3[0x1c]; + u8 e[0x2]; + + u8 reserved_4[0x40]; +}; + +struct mlx5_ifc_plpc_reg_bits { + u8 reserved_0[0x4]; + u8 profile_id[0xc]; + u8 reserved_1[0x4]; + u8 proto_mask[0x4]; + u8 reserved_2[0x8]; + + u8 reserved_3[0x10]; + u8 lane_speed[0x10]; + + u8 reserved_4[0x17]; + u8 lpbf[0x1]; + u8 fec_mode_policy[0x8]; + + u8 retransmission_capability[0x8]; + u8 fec_mode_capability[0x18]; + + u8 retransmission_support_admin[0x8]; + u8 fec_mode_support_admin[0x18]; + + u8 retransmission_request_admin[0x8]; + u8 fec_mode_request_admin[0x18]; + + u8 reserved_5[0x80]; +}; + +struct mlx5_ifc_plib_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x8]; + u8 ib_port[0x8]; + + u8 reserved_2[0x60]; +}; + +struct mlx5_ifc_plbf_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0xd]; + u8 lbf_mode[0x3]; + + u8 reserved_2[0x20]; +}; + +struct mlx5_ifc_pipg_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 dic[0x1]; + u8 reserved_2[0x19]; + u8 ipg[0x4]; + u8 reserved_3[0x2]; +}; + +struct mlx5_ifc_pifr_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xe0]; + + u8 port_filter[8][0x20]; + + u8 port_filter_update_en[8][0x20]; +}; + +struct mlx5_ifc_pfcc_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 ppan[0x4]; + u8 reserved_2[0x4]; + u8 prio_mask_tx[0x8]; + u8 reserved_3[0x8]; + u8 prio_mask_rx[0x8]; + + u8 pptx[0x1]; + u8 aptx[0x1]; + u8 reserved_4[0x6]; + u8 pfctx[0x8]; + u8 reserved_5[0x10]; + + u8 pprx[0x1]; + u8 aprx[0x1]; + u8 reserved_6[0x6]; + u8 pfcrx[0x8]; + u8 reserved_7[0x10]; + + u8 reserved_8[0x80]; +}; + +struct mlx5_ifc_pelc_reg_bits { + u8 op[0x4]; + u8 reserved_0[0x4]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 op_admin[0x8]; + u8 op_capability[0x8]; + u8 op_request[0x8]; + u8 op_active[0x8]; + + u8 admin[0x40]; + + u8 capability[0x40]; + + u8 request[0x40]; + + u8 active[0x40]; + + u8 reserved_2[0x80]; +}; + +struct mlx5_ifc_peir_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 reserved_2[0xc]; + u8 error_count[0x4]; + u8 reserved_3[0x10]; + + u8 reserved_4[0xc]; + u8 lane[0x4]; + u8 reserved_5[0x8]; + u8 error_type[0x8]; +}; + +struct mlx5_ifc_pcap_reg_bits { + u8 reserved_0[0x8]; + u8 local_port[0x8]; + u8 reserved_1[0x10]; + + u8 port_capability_mask[4][0x20]; +}; + +struct mlx5_ifc_paos_reg_bits { + u8 swid[0x8]; + u8 local_port[0x8]; + u8 reserved_0[0x4]; + u8 admin_status[0x4]; + u8 reserved_1[0x4]; + u8 oper_status[0x4]; + + u8 ase[0x1]; + u8 ee[0x1]; + u8 reserved_2[0x1c]; + u8 e[0x2]; + + u8 reserved_3[0x40]; +}; + +struct mlx5_ifc_pamp_reg_bits { + u8 reserved_0[0x8]; + u8 opamp_group[0x8]; + u8 reserved_1[0xc]; + u8 opamp_group_type[0x4]; + + u8 start_index[0x10]; + u8 reserved_2[0x4]; + u8 num_of_indices[0xc]; + + u8 index_data[18][0x10]; +}; + +struct mlx5_ifc_lane_2_module_mapping_bits { + u8 reserved_0[0x6]; + u8 rx_lane[0x2]; + u8 reserved_1[0x6]; + u8 tx_lane[0x2]; + u8 reserved_2[0x8]; + u8 module[0x8]; +}; + +struct mlx5_ifc_bufferx_reg_bits { + u8 reserved_0[0x6]; + u8 lossy[0x1]; + u8 epsb[0x1]; + u8 reserved_1[0xc]; + u8 size[0xc]; + + u8 xoff_threshold[0x10]; + u8 xon_threshold[0x10]; +}; + +struct mlx5_ifc_set_node_in_bits { + u8 node_description[64][0x8]; +}; + +struct mlx5_ifc_register_power_settings_bits { + u8 reserved_0[0x18]; + u8 power_settings_level[0x8]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_register_host_endianness_bits { + u8 he[0x1]; + u8 reserved_0[0x1f]; + + u8 reserved_1[0x60]; +}; + +struct mlx5_ifc_umr_pointer_desc_argument_bits { + u8 reserved_0[0x20]; + + u8 mkey[0x20]; + + u8 addressh_63_32[0x20]; + + u8 addressl_31_0[0x20]; +}; + +struct mlx5_ifc_ud_adrs_vector_bits { + u8 dc_key[0x40]; + + u8 ext[0x1]; + u8 reserved_0[0x7]; + u8 destination_qp_dct[0x18]; + + u8 static_rate[0x4]; + u8 sl_eth_prio[0x4]; + u8 fl[0x1]; + u8 mlid[0x7]; + u8 rlid_udp_sport[0x10]; + + u8 reserved_1[0x20]; + + u8 rmac_47_16[0x20]; + + u8 rmac_15_0[0x10]; + u8 tclass[0x8]; + u8 hop_limit[0x8]; + + u8 reserved_2[0x1]; + u8 grh[0x1]; + u8 reserved_3[0x2]; + u8 src_addr_index[0x8]; + u8 flow_label[0x14]; + + u8 rgid_rip[16][0x8]; +}; + +struct mlx5_ifc_pages_req_event_bits { + u8 reserved_0[0x10]; + u8 function_id[0x10]; + + u8 num_pages[0x20]; + + u8 reserved_1[0xa0]; +}; + +struct mlx5_ifc_eqe_bits { + u8 reserved_0[0x8]; + u8 event_type[0x8]; + u8 reserved_1[0x8]; + u8 event_sub_type[0x8]; + + u8 reserved_2[0xe0]; + + union mlx5_ifc_event_auto_bits event_data; + + u8 reserved_3[0x10]; + u8 signature[0x8]; + u8 reserved_4[0x7]; + u8 owner[0x1]; +}; + +enum { + MLX5_CMD_QUEUE_ENTRY_TYPE_PCIE_CMD_IF_TRANSPORT = 0x7, +}; + +struct mlx5_ifc_cmd_queue_entry_bits { + u8 type[0x8]; + u8 reserved_0[0x18]; + + u8 input_length[0x20]; + + u8 input_mailbox_pointer_63_32[0x20]; + + u8 input_mailbox_pointer_31_9[0x17]; + u8 reserved_1[0x9]; + + u8 command_input_inline_data[16][0x8]; + + u8 command_output_inline_data[16][0x8]; + + u8 output_mailbox_pointer_63_32[0x20]; + + u8 output_mailbox_pointer_31_9[0x17]; + u8 reserved_2[0x9]; + + u8 output_length[0x20]; + + u8 token[0x8]; + u8 signature[0x8]; + u8 reserved_3[0x8]; + u8 status[0x7]; + u8 ownership[0x1]; +}; + +struct mlx5_ifc_cmd_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 command_output[0x20]; +}; + +struct mlx5_ifc_cmd_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 command[0][0x20]; +}; + +struct mlx5_ifc_cmd_if_box_bits { + u8 mailbox_data[512][0x8]; + + u8 reserved_0[0x180]; + + u8 next_pointer_63_32[0x20]; + + u8 next_pointer_31_10[0x16]; + u8 reserved_1[0xa]; + + u8 block_number[0x20]; + + u8 reserved_2[0x8]; + u8 token[0x8]; + u8 ctrl_signature[0x8]; + u8 signature[0x8]; +}; + +struct mlx5_ifc_mtt_bits { + u8 ptag_63_32[0x20]; + + u8 ptag_31_8[0x18]; + u8 reserved_0[0x6]; + u8 wr_en[0x1]; + u8 rd_en[0x1]; +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_FULL_DRIVER = 0x0, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_DISABLED = 0x1, + MLX5_INITIAL_SEG_NIC_INTERFACE_SUPPORTED_NO_DRAM_NIC = 0x2, +}; + +enum { + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_INTERNAL_ERR = 0x1, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_DEAD_IRISC = 0x7, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HW_FATAL_ERR = 0x8, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FW_CRC_ERR = 0x9, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_FETCH_PCI_ERR = 0xa, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PAGE_ERR = 0xb, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ASYNCHRONOUS_EQ_BUF_OVERRUN = 0xc, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_IN_ERR = 0xd, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV = 0xe, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, +}; + +struct mlx5_ifc_initial_seg_bits { + u8 fw_rev_minor[0x10]; + u8 fw_rev_major[0x10]; + + u8 cmd_interface_rev[0x10]; + u8 fw_rev_subminor[0x10]; + + u8 reserved_0[0x40]; + + u8 cmdq_phy_addr_63_32[0x20]; + + u8 cmdq_phy_addr_31_12[0x14]; + u8 reserved_1[0x2]; + u8 nic_interface[0x2]; + u8 log_cmdq_size[0x4]; + u8 log_cmdq_stride[0x4]; + + u8 command_doorbell_vector[0x20]; + + u8 reserved_2[0xf00]; + + u8 initializing[0x1]; + u8 reserved_3[0x4]; + u8 nic_interface_supported[0x3]; + u8 reserved_4[0x18]; + + struct mlx5_ifc_health_buffer_bits health_buffer; + + u8 no_dram_nic_offset[0x20]; + + u8 reserved_5[0x6e40]; + + u8 reserved_6[0x1f]; + u8 clear_int[0x1]; + + u8 health_syndrome[0x8]; + u8 health_counter[0x18]; + + u8 reserved_7[0x17fc0]; +}; + +union mlx5_ifc_ports_control_registers_document_bits { + struct mlx5_ifc_bufferx_reg_bits bufferx_reg; + struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; + struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout; + struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; + struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; + struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; + struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; + struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_lane_2_module_mapping_bits lane_2_module_mapping; + struct mlx5_ifc_pamp_reg_bits pamp_reg; + struct mlx5_ifc_paos_reg_bits paos_reg; + struct mlx5_ifc_pcap_reg_bits pcap_reg; + struct mlx5_ifc_peir_reg_bits peir_reg; + struct mlx5_ifc_pelc_reg_bits pelc_reg; + struct mlx5_ifc_pfcc_reg_bits pfcc_reg; + struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; + struct mlx5_ifc_pifr_reg_bits pifr_reg; + struct mlx5_ifc_pipg_reg_bits pipg_reg; + struct mlx5_ifc_plbf_reg_bits plbf_reg; + struct mlx5_ifc_plib_reg_bits plib_reg; + struct mlx5_ifc_plpc_reg_bits plpc_reg; + struct mlx5_ifc_pmaos_reg_bits pmaos_reg; + struct mlx5_ifc_pmlp_reg_bits pmlp_reg; + struct mlx5_ifc_pmlpn_reg_bits pmlpn_reg; + struct mlx5_ifc_pmpc_reg_bits pmpc_reg; + struct mlx5_ifc_pmpe_reg_bits pmpe_reg; + struct mlx5_ifc_pmpr_reg_bits pmpr_reg; + struct mlx5_ifc_pmtu_reg_bits pmtu_reg; + struct mlx5_ifc_ppad_reg_bits ppad_reg; + struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg; + struct mlx5_ifc_pplm_reg_bits pplm_reg; + struct mlx5_ifc_pplr_reg_bits pplr_reg; + struct mlx5_ifc_ppsc_reg_bits ppsc_reg; + struct mlx5_ifc_pqdr_reg_bits pqdr_reg; + struct mlx5_ifc_pspa_reg_bits pspa_reg; + struct mlx5_ifc_ptas_reg_bits ptas_reg; + struct mlx5_ifc_ptys_reg_bits ptys_reg; + struct mlx5_ifc_pude_reg_bits pude_reg; + struct mlx5_ifc_pvlc_reg_bits pvlc_reg; + struct mlx5_ifc_slrg_reg_bits slrg_reg; + struct mlx5_ifc_sltp_reg_bits sltp_reg; + u8 reserved_0[0x60e0]; +}; + +union mlx5_ifc_debug_enhancements_document_bits { + struct mlx5_ifc_health_buffer_bits health_buffer; + u8 reserved_0[0x200]; +}; + +union mlx5_ifc_uplink_pci_interface_document_bits { + struct mlx5_ifc_initial_seg_bits initial_seg; + u8 reserved_0[0x20060]; }; #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 310b5f7fd6ae..f079fb1a31f7 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -134,13 +134,21 @@ enum { enum { MLX5_WQE_CTRL_CQ_UPDATE = 2 << 2, + MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE = 3 << 2, MLX5_WQE_CTRL_SOLICITED = 1 << 1, }; enum { + MLX5_SEND_WQE_DS = 16, MLX5_SEND_WQE_BB = 64, }; +#define MLX5_SEND_WQEBB_NUM_DS (MLX5_SEND_WQE_BB / MLX5_SEND_WQE_DS) + +enum { + MLX5_SEND_WQE_MAX_WQEBBS = 16, +}; + enum { MLX5_WQE_FMR_PERM_LOCAL_READ = 1 << 27, MLX5_WQE_FMR_PERM_LOCAL_WRITE = 1 << 28, @@ -200,6 +208,23 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 +enum { + MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, + MLX5_ETH_WQE_L4_INNER_CSUM = 1 << 5, + MLX5_ETH_WQE_L3_CSUM = 1 << 6, + MLX5_ETH_WQE_L4_CSUM = 1 << 7, +}; + +struct mlx5_wqe_eth_seg { + u8 rsvd0[4]; + u8 cs_flags; + u8 rsvd1; + __be16 mss; + __be32 rsvd2; + __be16 inline_hdr_sz; + u8 inline_hdr_start[2]; +}; + struct mlx5_wqe_xrc_seg { __be32 xrc_srqn; u8 rsvd[12]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h new file mode 100644 index 000000000000..967e0fd06e89 --- /dev/null +++ b/include/linux/mlx5/vport.h @@ -0,0 +1,55 @@ +/* + * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_VPORT_H__ +#define __MLX5_VPORT_H__ + +#include <linux/mlx5/driver.h> + +u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); +void mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr); +int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, u16 vf_num, u16 gid_index, + union ib_gid *gid); +int mlx5_query_hca_vport_pkey(struct mlx5_core_dev *dev, u8 other_vport, + u8 port_num, u16 vf_num, u16 pkey_index, + u16 *pkey); +int mlx5_query_hca_vport_context(struct mlx5_core_dev *dev, + u8 other_vport, u8 port_num, + u16 vf_num, + struct mlx5_hca_vport_context *rep); +int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev, + u64 *sys_image_guid); +int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, + u64 *node_guid); + +#endif /* __MLX5_VPORT_H__ */ diff --git a/include/linux/mm-arch-hooks.h b/include/linux/mm-arch-hooks.h new file mode 100644 index 000000000000..4efc3f56e6df --- /dev/null +++ b/include/linux/mm-arch-hooks.h @@ -0,0 +1,25 @@ +/* + * Generic mm no-op hooks. + * + * Copyright (C) 2015, IBM Corporation + * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _LINUX_MM_ARCH_HOOKS_H +#define _LINUX_MM_ARCH_HOOKS_H + +#include <asm/mm-arch-hooks.h> + +#ifndef arch_remap +static inline void arch_remap(struct mm_struct *mm, + unsigned long old_start, unsigned long old_end, + unsigned long new_start, unsigned long new_end) +{ +} +#define arch_remap arch_remap +#endif + +#endif /* _LINUX_MM_ARCH_HOOKS_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 0755b9fd03a7..2e872f92dbac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -27,6 +27,7 @@ struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; +struct bdi_writeback; #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -499,7 +500,7 @@ static inline int page_count(struct page *page) static inline bool __compound_tail_refcounted(struct page *page) { - return !PageSlab(page) && !PageHeadHuge(page); + return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page); } /* @@ -1211,10 +1212,13 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping); -void account_page_cleaned(struct page *page, struct address_space *mapping); +void account_page_dirtied(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg); +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); +void cancel_dirty_page(struct page *page); int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); @@ -1631,6 +1635,8 @@ extern void free_highmem_page(struct page *page); extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); +extern void reserve_bootmem_region(unsigned long start, unsigned long end); + /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { @@ -1720,7 +1726,8 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn) +static inline int __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { return 0; } @@ -1728,7 +1735,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn) /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); /* there is a per-arch backend function. */ -extern int __meminit __early_pfn_to_nid(unsigned long pfn); +extern int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); @@ -2146,12 +2154,47 @@ enum mf_flags { extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); +extern int get_hwpoison_page(struct page *page); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); + +/* + * Error handlers for various types of pages. + */ +enum mf_result { + MF_IGNORED, /* Error: cannot be handled */ + MF_FAILED, /* Error: handling failed */ + MF_DELAYED, /* Will be handled later */ + MF_RECOVERED, /* Successfully recovered */ +}; + +enum mf_action_page_type { + MF_MSG_KERNEL, + MF_MSG_KERNEL_HIGH_ORDER, + MF_MSG_SLAB, + MF_MSG_DIFFERENT_COMPOUND, + MF_MSG_POISONED_HUGE, + MF_MSG_HUGE, + MF_MSG_FREE_HUGE, + MF_MSG_UNMAP_FAILED, + MF_MSG_DIRTY_SWAPCACHE, + MF_MSG_CLEAN_SWAPCACHE, + MF_MSG_DIRTY_MLOCKED_LRU, + MF_MSG_CLEAN_MLOCKED_LRU, + MF_MSG_DIRTY_UNEVICTABLE_LRU, + MF_MSG_CLEAN_UNEVICTABLE_LRU, + MF_MSG_DIRTY_LRU, + MF_MSG_CLEAN_LRU, + MF_MSG_TRUNCATED_LRU, + MF_MSG_BUDDY, + MF_MSG_BUDDY_2ND, + MF_MSG_UNKNOWN, +}; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8d37e26a1007..0038ac7466fd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -226,6 +226,24 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) + +struct page_frag_cache { + void * va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_count every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + typedef unsigned long __nocast vm_flags_t; /* diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 19f0175c0afa..4d3776d25925 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -97,6 +97,7 @@ struct mmc_ext_csd { u8 raw_erased_mem_count; /* 181 */ u8 raw_ext_csd_structure; /* 194 */ u8 raw_card_type; /* 196 */ + u8 raw_driver_strength; /* 197 */ u8 out_of_int_time; /* 198 */ u8 raw_pwr_cl_52_195; /* 200 */ u8 raw_pwr_cl_26_195; /* 201 */ @@ -305,6 +306,7 @@ struct mmc_card { unsigned int sd_bus_speed; /* Bus Speed Mode set for the card */ unsigned int mmc_avail_type; /* supported device type by both host and card */ + unsigned int drive_strength; /* for UHS-I, HS200 or HS400 */ struct dentry *debugfs_root; struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index de722d4e9d61..258daf914c6d 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -121,6 +121,7 @@ struct mmc_data { struct mmc_request *mrq; /* associated request */ unsigned int sg_len; /* size of scatter list */ + int sg_count; /* mapped sg entries */ struct scatterlist *sg; /* I/O scatter list */ s32 host_cookie; /* host private data */ }; diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 12111993a317..5be97676f1fa 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -226,12 +226,6 @@ struct dw_mci_dma_ops { #define DW_MCI_QUIRK_HIGHSPEED BIT(2) /* Unreliable card detection */ #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) -/* No write protect */ -#define DW_MCI_QUIRK_NO_WRITE_PROTECT BIT(4) - -/* Slot level quirks */ -/* This slot has no write protect */ -#define DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT BIT(0) struct dma_pdata; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index b5bedaec6223..1369e54faeb7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -12,6 +12,7 @@ #include <linux/leds.h> #include <linux/mutex.h> +#include <linux/timer.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/fault-inject.h> @@ -131,7 +132,9 @@ struct mmc_host_ops { /* Prepare HS400 target operating frequency depending host driver */ int (*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios); - int (*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv); + int (*select_drive_strength)(struct mmc_card *card, + unsigned int max_dtr, int host_drv, + int card_drv, int *drv_type); void (*hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); @@ -285,6 +288,7 @@ struct mmc_host { MMC_CAP2_HS400_1_2V) #define MMC_CAP2_HSX00_1_2V (MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V) #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17) +#define MMC_CAP2_NO_WRITE_PROTECT (1 << 18) /* No physical write protect pin, assume that card is always read-write */ mmc_pm_flag_t pm_caps; /* supported pm features */ @@ -321,10 +325,18 @@ struct mmc_host { #ifdef CONFIG_MMC_DEBUG unsigned int removed:1; /* host is being removed */ #endif + unsigned int can_retune:1; /* re-tuning can be used */ + unsigned int doing_retune:1; /* re-tuning in progress */ + unsigned int retune_now:1; /* do re-tuning at next req */ int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ + int need_retune; /* re-tuning is needed */ + int hold_retune; /* hold off re-tuning */ + unsigned int retune_period; /* re-tuning period in secs */ + struct timer_list retune_timer; /* for periodic re-tuning */ + bool trigger_card_event; /* card_event necessary */ struct mmc_card *card; /* device attached to this host */ @@ -513,4 +525,18 @@ static inline bool mmc_card_hs400(struct mmc_card *card) return card->host->ios.timing == MMC_TIMING_MMC_HS400; } +void mmc_retune_timer_stop(struct mmc_host *host); + +static inline void mmc_retune_needed(struct mmc_host *host) +{ + if (host->can_retune) + host->need_retune = 1; +} + +static inline void mmc_retune_recheck(struct mmc_host *host) +{ + if (host->hold_retune <= 1) + host->retune_now = 1; +} + #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 124f562118b8..15f2c4a0a62c 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -302,6 +302,7 @@ struct _mmc_csd { #define EXT_CSD_REV 192 /* RO */ #define EXT_CSD_STRUCTURE 194 /* RO */ #define EXT_CSD_CARD_TYPE 196 /* RO */ +#define EXT_CSD_DRIVER_STRENGTH 197 /* RO */ #define EXT_CSD_OUT_OF_INTERRUPT_TIME 198 /* RO */ #define EXT_CSD_PART_SWITCH_TIME 199 /* RO */ #define EXT_CSD_PWR_CL_52_195 200 /* RO */ @@ -390,6 +391,7 @@ struct _mmc_csd { #define EXT_CSD_TIMING_HS 1 /* High speed */ #define EXT_CSD_TIMING_HS200 2 /* HS200 */ #define EXT_CSD_TIMING_HS400 3 /* HS400 */ +#define EXT_CSD_DRV_STR_SHIFT 4 /* Driver Strength shift */ #define EXT_CSD_SEC_ER_EN BIT(0) #define EXT_CSD_SEC_BD_BLK_EN BIT(2) @@ -441,4 +443,6 @@ struct _mmc_csd { #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ +#define mmc_driver_type_mask(n) (1 << (n)) + #endif /* LINUX_MMC_MMC_H */ diff --git a/include/linux/mmc/sdhci-pci-data.h b/include/linux/mmc/sdhci-pci-data.h index 8959604a13d3..fda15b6d4135 100644 --- a/include/linux/mmc/sdhci-pci-data.h +++ b/include/linux/mmc/sdhci-pci-data.h @@ -15,4 +15,6 @@ struct sdhci_pci_data { extern struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno); +extern int sdhci_pci_spt_drive_strength; + #endif diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index c5d52780d6a0..3ba327af055c 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -106,6 +106,6 @@ extern void enable_mmiotrace(void); extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); -extern int mmio_trace_printk(const char *fmt, va_list args); +extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args); #endif /* _LINUX_MMIOTRACE_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 95243d28a0ee..61cd67f4d788 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -324,25 +324,25 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) ___pte; \ }) -#define pmdp_clear_flush_notify(__vma, __haddr, __pmd) \ +#define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pmd_t ___pmd; \ \ - ___pmd = pmdp_clear_flush(__vma, __haddr, __pmd); \ + ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ ___pmd; \ }) -#define pmdp_get_and_clear_notify(__mm, __haddr, __pmd) \ +#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ pmd_t ___pmd; \ \ - ___pmd = pmdp_get_and_clear(__mm, __haddr, __pmd); \ + ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \ mmu_notifier_invalidate_range(__mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ @@ -428,8 +428,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_flush_notify ptep_clear_flush -#define pmdp_clear_flush_notify pmdp_clear_flush -#define pmdp_get_and_clear_notify pmdp_get_and_clear +#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush +#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 54d74f6eb233..754c25966a0a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -762,6 +762,14 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* + * If memory initialisation on large machines is deferred then this + * is the first PFN that needs to be initialised. + */ + unsigned long first_deferred_pfn; +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -1216,11 +1224,16 @@ void sparse_init(void); #define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool early_pfn_in_nid(unsigned long pfn, int nid); -#else -#define early_pfn_in_nid(pfn, nid) (1) -#endif +/* + * During memory init memblocks map pfns to nids. The search is expensive and + * this caches recent lookups. The implementation of __early_pfn_to_nid + * may treat start/end as pfns or sections. + */ +struct mminit_pfnnid_cache { + unsigned long last_start; + unsigned long last_end; + int last_nid; +}; #ifndef early_pfn_valid #define early_pfn_valid(pfn) (1) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 3bfd56778c29..34f25b7bf642 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -189,6 +189,8 @@ struct css_device_id { struct acpi_device_id { __u8 id[ACPI_ID_LEN]; kernel_ulong_t driver_data; + __u32 cls; + __u32 cls_msk; }; #define PNP_ID_LEN 8 @@ -599,9 +601,22 @@ struct ipack_device_id { #define MEI_CL_MODULE_PREFIX "mei:" #define MEI_CL_NAME_SIZE 32 +#define MEI_CL_UUID_FMT "%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x" +#define MEI_CL_UUID_ARGS(_u) \ + _u[0], _u[1], _u[2], _u[3], _u[4], _u[5], _u[6], _u[7], \ + _u[8], _u[9], _u[10], _u[11], _u[12], _u[13], _u[14], _u[15] +/** + * struct mei_cl_device_id - MEI client device identifier + * @name: helper name + * @uuid: client uuid + * @driver_info: information used by the driver. + * + * identifies mei client device by uuid and name + */ struct mei_cl_device_id { char name[MEI_CL_NAME_SIZE]; + uuid_le uuid; kernel_ulong_t driver_info; }; @@ -629,4 +644,10 @@ struct mcb_device_id { kernel_ulong_t driver_data; }; +struct ulpi_device_id { + __u16 vendor; + __u16 product; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index c883b86ea964..3a19c79918e0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -11,12 +11,14 @@ #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> +#include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> +#include <linux/rbtree_latch.h> #include <linux/percpu.h> #include <asm/module.h> @@ -70,6 +72,89 @@ extern struct module_attribute module_uevent; extern int init_module(void); extern void cleanup_module(void); +#ifndef MODULE +/** + * module_init() - driver initialization entry point + * @x: function to be run at kernel boot time or module insertion + * + * module_init() will either be called during do_initcalls() (if + * builtin) or at module insertion time (if a module). There can only + * be one per module. + */ +#define module_init(x) __initcall(x); + +/** + * module_exit() - driver exit entry point + * @x: function to be run when driver is removed + * + * module_exit() will wrap the driver clean-up code + * with cleanup_module() when used with rmmod when + * the driver is a module. If the driver is statically + * compiled into the kernel, module_exit() has no effect. + * There can only be one per module. + */ +#define module_exit(x) __exitcall(x); + +#else /* MODULE */ + +/* + * In most cases loadable modules do not need custom + * initcall levels. There are still some valid cases where + * a driver may be needed early if built in, and does not + * matter when built as a loadable module. Like bus + * snooping debug drivers. + */ +#define early_initcall(fn) module_init(fn) +#define core_initcall(fn) module_init(fn) +#define core_initcall_sync(fn) module_init(fn) +#define postcore_initcall(fn) module_init(fn) +#define postcore_initcall_sync(fn) module_init(fn) +#define arch_initcall(fn) module_init(fn) +#define subsys_initcall(fn) module_init(fn) +#define subsys_initcall_sync(fn) module_init(fn) +#define fs_initcall(fn) module_init(fn) +#define fs_initcall_sync(fn) module_init(fn) +#define rootfs_initcall(fn) module_init(fn) +#define device_initcall(fn) module_init(fn) +#define device_initcall_sync(fn) module_init(fn) +#define late_initcall(fn) module_init(fn) +#define late_initcall_sync(fn) module_init(fn) + +#define console_initcall(fn) module_init(fn) +#define security_initcall(fn) module_init(fn) + +/* Each module must use one module_init(). */ +#define module_init(initfn) \ + static inline initcall_t __inittest(void) \ + { return initfn; } \ + int init_module(void) __attribute__((alias(#initfn))); + +/* This is only required if you want to be unloadable. */ +#define module_exit(exitfn) \ + static inline exitcall_t __exittest(void) \ + { return exitfn; } \ + void cleanup_module(void) __attribute__((alias(#exitfn))); + +#endif + +/* This means "can be init if no module support, otherwise module load + may call it." */ +#ifdef CONFIG_MODULES +#define __init_or_module +#define __initdata_or_module +#define __initconst_or_module +#define __INIT_OR_MODULE .text +#define __INITDATA_OR_MODULE .data +#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits +#else +#define __init_or_module __init +#define __initdata_or_module __initdata +#define __initconst_or_module __initconst +#define __INIT_OR_MODULE __INIT +#define __INITDATA_OR_MODULE __INITDATA +#define __INITRODATA_OR_MODULE __INITRODATA +#endif /*CONFIG_MODULES*/ + /* Archs provide a method of finding the correct exception table. */ struct exception_table_entry; @@ -210,6 +295,13 @@ enum module_state { MODULE_STATE_UNFORMED, /* Still setting it up. */ }; +struct module; + +struct mod_tree_node { + struct module *mod; + struct latch_tree_node node; +}; + struct module { enum module_state state; @@ -232,6 +324,9 @@ struct module { unsigned int num_syms; /* Kernel parameters. */ +#ifdef CONFIG_SYSFS + struct mutex param_lock; +#endif struct kernel_param *kp; unsigned int num_kp; @@ -257,6 +352,8 @@ struct module { bool sig_ok; #endif + bool async_probe_requested; + /* symbols that will be GPL-only in the near future. */ const struct kernel_symbol *gpl_future_syms; const unsigned long *gpl_future_crcs; @@ -269,8 +366,15 @@ struct module { /* Startup function. */ int (*init)(void); - /* If this is non-NULL, vfree after init() returns */ - void *module_init; + /* + * If this is non-NULL, vfree() after init() returns. + * + * Cacheline align here, such that: + * module_init, module_core, init_size, core_size, + * init_text_size, core_text_size and mtn_core::{mod,node[0]} + * are on the same cacheline. + */ + void *module_init ____cacheline_aligned; /* Here is the actual code + data, vfree'd on unload. */ void *module_core; @@ -281,6 +385,16 @@ struct module { /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; +#ifdef CONFIG_MODULES_TREE_LOOKUP + /* + * We want mtn_core::{mod,node[0]} to be in the same cacheline as the + * above entries such that a regular lookup will only touch one + * cacheline. + */ + struct mod_tree_node mtn_core; + struct mod_tree_node mtn_init; +#endif + /* Size of RO sections of the module (text+rodata) */ unsigned int init_ro_size, core_ro_size; @@ -336,7 +450,7 @@ struct module { const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call **trace_events; + struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_enum_map **trace_enums; unsigned int num_trace_enums; @@ -367,7 +481,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -}; +} ____cacheline_aligned; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif @@ -421,14 +535,22 @@ struct symsearch { bool unused; }; -/* Search for an exported symbol by name. */ +/* + * Search for an exported symbol by name. + * + * Must be called with module_mutex held or preemption disabled. + */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, const unsigned long **crc, bool gplok, bool warn); -/* Walk the exported symbol table */ +/* + * Walk the exported symbol table + * + * Must be called with module_mutex held or preemption disabled. + */ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, struct module *owner, void *data), void *data); @@ -508,6 +630,11 @@ int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); +static inline bool module_requested_async_probing(struct module *module) +{ + return module && module->async_probe_requested; +} + #else /* !CONFIG_MODULES... */ /* Given an address, look for it in the exception tables. */ @@ -618,6 +745,12 @@ static inline int unregister_module_notifier(struct notifier_block *nb) static inline void print_modules(void) { } + +static inline bool module_requested_async_probing(struct module *module) +{ + return false; +} + #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -655,4 +788,16 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef CONFIG_MODULE_SIG +static inline bool module_sig_ok(struct module *module) +{ + return module->sig_ok; +} +#else /* !CONFIG_MODULE_SIG */ +static inline bool module_sig_ok(struct module *module) +{ + return true; +} +#endif /* CONFIG_MODULE_SIG */ + #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 1c9effa25e26..c12f2147c350 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -67,8 +67,9 @@ enum { struct kernel_param { const char *name; + struct module *mod; const struct kernel_param_ops *ops; - u16 perm; + const u16 perm; s8 level; u8 flags; union { @@ -108,7 +109,7 @@ struct kparam_array * * @perm is 0 if the the variable is not to appear in sysfs, or 0444 * for world-readable, 0644 for root-writable, etc. Note that if it - * is writable, you may need to use kparam_block_sysfs_write() around + * is writable, you may need to use kernel_param_lock() around * accesses (esp. charp, which can be kfreed when it changes). * * The @type is simply pasted to refer to a param_ops_##type and a @@ -216,16 +217,16 @@ struct kparam_array parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ /* Default value instead of permissions? */ \ - static const char __param_str_##name[] = prefix #name; \ + static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ - = { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm), \ - level, flags, { arg } } + = { __param_str_##name, THIS_MODULE, ops, \ + VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } } /* Obsolete - use module_param_cb() */ #define module_param_call(name, set, get, arg, perm) \ - static struct kernel_param_ops __param_ops_##name = \ + static const struct kernel_param_ops __param_ops_##name = \ { .flags = 0, (void *)set, (void *)get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ name, &__param_ops_##name, arg, \ @@ -238,58 +239,14 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) return 0; } -/** - * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs. - * @name: the name of the parameter - * - * There's no point blocking write on a paramter that isn't writable via sysfs! - */ -#define kparam_block_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_write - allows sysfs to write to a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_unlock(); \ - } while (0) - -/** - * kparam_block_sysfs_read - make sure a parameter isn't read via sysfs. - * @name: the name of the parameter - * - * This also blocks sysfs writes. - */ -#define kparam_block_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_read - allows sysfs to read a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_unlock(); \ - } while (0) - #ifdef CONFIG_SYSFS -extern void __kernel_param_lock(void); -extern void __kernel_param_unlock(void); +extern void kernel_param_lock(struct module *mod); +extern void kernel_param_unlock(struct module *mod); #else -static inline void __kernel_param_lock(void) +static inline void kernel_param_lock(struct module *mod) { } -static inline void __kernel_param_unlock(void) +static inline void kernel_param_unlock(struct module *mod) { } #endif @@ -310,6 +267,15 @@ static inline void __kernel_param_unlock(void) #define core_param(name, var, type, perm) \ param_check_##type(name, &(var)); \ __module_param_call("", name, ¶m_ops_##type, &var, perm, -1, 0) + +/** + * core_param_unsafe - same as core_param but taints kernel + */ +#define core_param_unsafe(name, var, type, perm) \ + param_check_##type(name, &(var)); \ + __module_param_call("", name, ¶m_ops_##type, &var, perm, \ + -1, KERNEL_PARAM_FL_UNSAFE) + #endif /* !MODULE */ /** @@ -357,8 +323,9 @@ extern char *parse_args(const char *name, unsigned num, s16 level_min, s16 level_max, + void *arg, int (*unknown)(char *param, char *val, - const char *doing)); + const char *doing, void *arg)); /* Called by module remove. */ #ifdef CONFIG_SYSFS @@ -376,64 +343,70 @@ static inline void destroy_params(const struct kernel_param *params, #define __param_check(name, p, type) \ static inline type __always_unused *__check_##name(void) { return(p); } -extern struct kernel_param_ops param_ops_byte; +extern const struct kernel_param_ops param_ops_byte; extern int param_set_byte(const char *val, const struct kernel_param *kp); extern int param_get_byte(char *buffer, const struct kernel_param *kp); #define param_check_byte(name, p) __param_check(name, p, unsigned char) -extern struct kernel_param_ops param_ops_short; +extern const struct kernel_param_ops param_ops_short; extern int param_set_short(const char *val, const struct kernel_param *kp); extern int param_get_short(char *buffer, const struct kernel_param *kp); #define param_check_short(name, p) __param_check(name, p, short) -extern struct kernel_param_ops param_ops_ushort; +extern const struct kernel_param_ops param_ops_ushort; extern int param_set_ushort(const char *val, const struct kernel_param *kp); extern int param_get_ushort(char *buffer, const struct kernel_param *kp); #define param_check_ushort(name, p) __param_check(name, p, unsigned short) -extern struct kernel_param_ops param_ops_int; +extern const struct kernel_param_ops param_ops_int; extern int param_set_int(const char *val, const struct kernel_param *kp); extern int param_get_int(char *buffer, const struct kernel_param *kp); #define param_check_int(name, p) __param_check(name, p, int) -extern struct kernel_param_ops param_ops_uint; +extern const struct kernel_param_ops param_ops_uint; extern int param_set_uint(const char *val, const struct kernel_param *kp); extern int param_get_uint(char *buffer, const struct kernel_param *kp); #define param_check_uint(name, p) __param_check(name, p, unsigned int) -extern struct kernel_param_ops param_ops_long; +extern const struct kernel_param_ops param_ops_long; extern int param_set_long(const char *val, const struct kernel_param *kp); extern int param_get_long(char *buffer, const struct kernel_param *kp); #define param_check_long(name, p) __param_check(name, p, long) -extern struct kernel_param_ops param_ops_ulong; +extern const struct kernel_param_ops param_ops_ulong; extern int param_set_ulong(const char *val, const struct kernel_param *kp); extern int param_get_ulong(char *buffer, const struct kernel_param *kp); #define param_check_ulong(name, p) __param_check(name, p, unsigned long) -extern struct kernel_param_ops param_ops_ullong; +extern const struct kernel_param_ops param_ops_ullong; extern int param_set_ullong(const char *val, const struct kernel_param *kp); extern int param_get_ullong(char *buffer, const struct kernel_param *kp); #define param_check_ullong(name, p) __param_check(name, p, unsigned long long) -extern struct kernel_param_ops param_ops_charp; +extern const struct kernel_param_ops param_ops_charp; extern int param_set_charp(const char *val, const struct kernel_param *kp); extern int param_get_charp(char *buffer, const struct kernel_param *kp); #define param_check_charp(name, p) __param_check(name, p, char *) /* We used to allow int as well as bool. We're taking that away! */ -extern struct kernel_param_ops param_ops_bool; +extern const struct kernel_param_ops param_ops_bool; extern int param_set_bool(const char *val, const struct kernel_param *kp); extern int param_get_bool(char *buffer, const struct kernel_param *kp); #define param_check_bool(name, p) __param_check(name, p, bool) -extern struct kernel_param_ops param_ops_invbool; +extern const struct kernel_param_ops param_ops_bool_enable_only; +extern int param_set_bool_enable_only(const char *val, + const struct kernel_param *kp); +/* getter is the same as for the regular bool */ +#define param_check_bool_enable_only param_check_bool + +extern const struct kernel_param_ops param_ops_invbool; extern int param_set_invbool(const char *val, const struct kernel_param *kp); extern int param_get_invbool(char *buffer, const struct kernel_param *kp); #define param_check_invbool(name, p) __param_check(name, p, bool) /* An int, which can only be set like a bool (though it shows as an int). */ -extern struct kernel_param_ops param_ops_bint; +extern const struct kernel_param_ops param_ops_bint; extern int param_set_bint(const char *val, const struct kernel_param *kp); #define param_get_bint param_get_int #define param_check_bint param_check_int @@ -477,9 +450,9 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp); perm, -1, 0); \ __MODULE_PARM_TYPE(name, "array of " #type) -extern struct kernel_param_ops param_array_ops; +extern const struct kernel_param_ops param_array_ops; -extern struct kernel_param_ops param_ops_string; +extern const struct kernel_param_ops param_ops_string; extern int param_set_copystring(const char *val, const struct kernel_param *); extern int param_get_string(char *buffer, const struct kernel_param *kp); diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 5af1b81def49..641b7d6fd096 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -81,6 +81,8 @@ MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); int mpi_fromstr(MPI val, const char *str); u32 mpi_get_keyid(MPI a, u32 *keyid); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); +int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, + int *sign); void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign); @@ -142,4 +144,17 @@ int mpi_rshift(MPI x, MPI a, unsigned n); /*-- mpi-inv.c --*/ int mpi_invm(MPI x, MPI u, MPI v); +/* inline functions */ + +/** + * mpi_get_size() - returns max size required to store the number + * + * @a: A multi precision integer for which we want to allocate a bufer + * + * Return: size required to store the number + */ +static inline unsigned int mpi_get_size(MPI a) +{ + return a->nlimbs * BYTES_PER_MPI_LIMB; +} #endif /*G10_MPI_H */ diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 299d7d31fe53..9b57a9b1b081 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -296,183 +296,19 @@ struct cfi_private { struct flchip chips[0]; /* per-chip data structure for each chip */ }; -/* - * Returns the command address according to the given geometry. - */ -static inline uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, - struct map_info *map, struct cfi_private *cfi) -{ - unsigned bankwidth = map_bankwidth(map); - unsigned interleave = cfi_interleave(cfi); - unsigned type = cfi->device_type; - uint32_t addr; - - addr = (cmd_ofs * type) * interleave; - - /* Modify the unlock address if we are in compatibility mode. - * For 16bit devices on 8 bit busses - * and 32bit devices on 16 bit busses - * set the low bit of the alternating bit sequence of the address. - */ - if (((type * interleave) > bankwidth) && ((cmd_ofs & 0xff) == 0xaa)) - addr |= (type >> 1)*interleave; - - return addr; -} - -/* - * Transforms the CFI command for the given geometry (bus width & interleave). - * It looks too long to be inline, but in the common case it should almost all - * get optimised away. - */ -static inline map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi) -{ - map_word val = { {0} }; - int wordwidth, words_per_bus, chip_mode, chips_per_word; - unsigned long onecmd; - int i; - - /* We do it this way to give the compiler a fighting chance - of optimising away all the crap for 'bankwidth' larger than - an unsigned long, in the common case where that support is - disabled */ - if (map_bankwidth_is_large(map)) { - wordwidth = sizeof(unsigned long); - words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1 - } else { - wordwidth = map_bankwidth(map); - words_per_bus = 1; - } - - chip_mode = map_bankwidth(map) / cfi_interleave(cfi); - chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map); - - /* First, determine what the bit-pattern should be for a single - device, according to chip mode and endianness... */ - switch (chip_mode) { - default: BUG(); - case 1: - onecmd = cmd; - break; - case 2: - onecmd = cpu_to_cfi16(map, cmd); - break; - case 4: - onecmd = cpu_to_cfi32(map, cmd); - break; - } - - /* Now replicate it across the size of an unsigned long, or - just to the bus width as appropriate */ - switch (chips_per_word) { - default: BUG(); -#if BITS_PER_LONG >= 64 - case 8: - onecmd |= (onecmd << (chip_mode * 32)); -#endif - case 4: - onecmd |= (onecmd << (chip_mode * 16)); - case 2: - onecmd |= (onecmd << (chip_mode * 8)); - case 1: - ; - } +uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, + struct map_info *map, struct cfi_private *cfi); - /* And finally, for the multi-word case, replicate it - in all words in the structure */ - for (i=0; i < words_per_bus; i++) { - val.x[i] = onecmd; - } - - return val; -} +map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi); #define CMD(x) cfi_build_cmd((x), map, cfi) - -static inline unsigned long cfi_merge_status(map_word val, struct map_info *map, - struct cfi_private *cfi) -{ - int wordwidth, words_per_bus, chip_mode, chips_per_word; - unsigned long onestat, res = 0; - int i; - - /* We do it this way to give the compiler a fighting chance - of optimising away all the crap for 'bankwidth' larger than - an unsigned long, in the common case where that support is - disabled */ - if (map_bankwidth_is_large(map)) { - wordwidth = sizeof(unsigned long); - words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1 - } else { - wordwidth = map_bankwidth(map); - words_per_bus = 1; - } - - chip_mode = map_bankwidth(map) / cfi_interleave(cfi); - chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map); - - onestat = val.x[0]; - /* Or all status words together */ - for (i=1; i < words_per_bus; i++) { - onestat |= val.x[i]; - } - - res = onestat; - switch(chips_per_word) { - default: BUG(); -#if BITS_PER_LONG >= 64 - case 8: - res |= (onestat >> (chip_mode * 32)); -#endif - case 4: - res |= (onestat >> (chip_mode * 16)); - case 2: - res |= (onestat >> (chip_mode * 8)); - case 1: - ; - } - - /* Last, determine what the bit-pattern should be for a single - device, according to chip mode and endianness... */ - switch (chip_mode) { - case 1: - break; - case 2: - res = cfi16_to_cpu(map, res); - break; - case 4: - res = cfi32_to_cpu(map, res); - break; - default: BUG(); - } - return res; -} - +unsigned long cfi_merge_status(map_word val, struct map_info *map, + struct cfi_private *cfi); #define MERGESTATUS(x) cfi_merge_status((x), map, cfi) - -/* - * Sends a CFI command to a bank of flash for the given geometry. - * - * Returns the offset in flash where the command was written. - * If prev_val is non-null, it will be set to the value at the command address, - * before the command was written. - */ -static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t base, +uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t base, struct map_info *map, struct cfi_private *cfi, - int type, map_word *prev_val) -{ - map_word val; - uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, map, cfi); - val = cfi_build_cmd(cmd, map, cfi); - - if (prev_val) - *prev_val = map_read(map, addr); - - map_write(map, val, addr); - - return addr - base; -} + int type, map_word *prev_val); static inline uint8_t cfi_read_query(struct map_info *map, uint32_t addr) { @@ -506,15 +342,7 @@ static inline uint16_t cfi_read_query16(struct map_info *map, uint32_t addr) } } -static inline void cfi_udelay(int us) -{ - if (us >= 1000) { - msleep((us+999)/1000); - } else { - udelay(us); - cond_resched(); - } -} +void cfi_udelay(int us); int __xipram cfi_qry_present(struct map_info *map, __u32 base, struct cfi_private *cfi); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 3d4ea7eb2b68..272f42952f34 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -26,6 +26,8 @@ struct mtd_info; struct nand_flash_dev; +struct device_node; + /* Scan and identify a NAND device */ extern int nand_scan(struct mtd_info *mtd, int max_chips); /* @@ -176,17 +178,17 @@ typedef enum { /* Chip may not exist, so silence any errors in scan */ #define NAND_SCAN_SILENT_NODEV 0x00040000 /* - * This option could be defined by controller drivers to protect against - * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers - */ -#define NAND_USE_BOUNCE_BUFFER 0x00080000 -/* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode * when calling nand_scan_ident, and update its configuration * before calling nand_scan_tail. */ #define NAND_BUSWIDTH_AUTO 0x00080000 +/* + * This option could be defined by controller drivers to protect against + * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers + */ +#define NAND_USE_BOUNCE_BUFFER 0x00100000 /* Options set by nand scan */ /* Nand scan has allocated controller struct */ @@ -542,6 +544,7 @@ struct nand_buffers { * flash device * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the * flash device. + * @dn: [BOARDSPECIFIC] device node describing this instance * @read_byte: [REPLACEABLE] read one byte from the chip * @read_word: [REPLACEABLE] read one word from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the @@ -644,6 +647,8 @@ struct nand_chip { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + struct device_node *dn; + uint8_t (*read_byte)(struct mtd_info *mtd); u16 (*read_word)(struct mtd_info *mtd); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); @@ -833,7 +838,6 @@ struct nand_manufacturers { extern struct nand_flash_dev nand_flash_ids[]; extern struct nand_manufacturers nand_manuf_ids[]; -extern int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd); extern int nand_default_bbt(struct mtd_info *mtd); extern int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); extern int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); diff --git a/include/linux/namei.h b/include/linux/namei.h index c8990779f0c3..d8c6334cd150 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -1,16 +1,15 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H -#include <linux/dcache.h> -#include <linux/errno.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/path.h> - -struct vfsmount; -struct nameidata; +#include <linux/fcntl.h> +#include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; +#define MAXSYMLINKS 40 + /* * Type of the last component on LOOKUP_PARENT */ @@ -45,13 +44,29 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 -extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) -#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path) -#define user_path_dir(name, path) \ - user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path) +static inline int user_path_at(int dfd, const char __user *name, unsigned flags, + struct path *path) +{ + return user_path_at_empty(dfd, name, flags, path, NULL); +} + +static inline int user_path(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, LOOKUP_FOLLOW, path, NULL); +} + +static inline int user_lpath(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, 0, path, NULL); +} + +static inline int user_path_dir(const char __user *name, struct path *path) +{ + return user_path_at_empty(AT_FDCWD, name, + LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path, NULL); +} extern int kern_path(const char *, unsigned, struct path *); @@ -70,9 +85,7 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); -extern void nd_jump_link(struct nameidata *nd, struct path *path); -extern void nd_set_link(struct nameidata *nd, char *path); -extern char *nd_get_link(struct nameidata *nd); +extern void nd_jump_link(struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { diff --git a/include/linux/nd.h b/include/linux/nd.h new file mode 100644 index 000000000000..507e47c86737 --- /dev/null +++ b/include/linux/nd.h @@ -0,0 +1,151 @@ +/* + * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __LINUX_ND_H__ +#define __LINUX_ND_H__ +#include <linux/fs.h> +#include <linux/ndctl.h> +#include <linux/device.h> + +struct nd_device_driver { + struct device_driver drv; + unsigned long type; + int (*probe)(struct device *dev); + int (*remove)(struct device *dev); +}; + +static inline struct nd_device_driver *to_nd_device_driver( + struct device_driver *drv) +{ + return container_of(drv, struct nd_device_driver, drv); +}; + +/** + * struct nd_namespace_common - core infrastructure of a namespace + * @force_raw: ignore other personalities for the namespace (e.g. btt) + * @dev: device model node + * @claim: when set a another personality has taken ownership of the namespace + * @rw_bytes: access the raw namespace capacity with byte-aligned transfers + */ +struct nd_namespace_common { + int force_raw; + struct device dev; + struct device *claim; + int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset, + void *buf, size_t size, int rw); +}; + +static inline struct nd_namespace_common *to_ndns(struct device *dev) +{ + return container_of(dev, struct nd_namespace_common, dev); +} + +/** + * struct nd_namespace_io - infrastructure for loading an nd_pmem instance + * @dev: namespace device created by the nd region driver + * @res: struct resource conversion of a NFIT SPA table + */ +struct nd_namespace_io { + struct nd_namespace_common common; + struct resource res; +}; + +/** + * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory + * @nsio: device and system physical address range to drive + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + */ +struct nd_namespace_pmem { + struct nd_namespace_io nsio; + char *alt_name; + u8 *uuid; +}; + +/** + * struct nd_namespace_blk - namespace for dimm-bounded persistent memory + * @alt_name: namespace name supplied in the dimm label + * @uuid: namespace name supplied in the dimm label + * @id: ida allocated id + * @lbasize: blk namespaces have a native sector size when btt not present + * @num_resources: number of dpa extents to claim + * @res: discontiguous dpa extents for given dimm + */ +struct nd_namespace_blk { + struct nd_namespace_common common; + char *alt_name; + u8 *uuid; + int id; + unsigned long lbasize; + int num_resources; + struct resource **res; +}; + +static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev) +{ + return container_of(dev, struct nd_namespace_io, common.dev); +} + +static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(dev); + + return container_of(nsio, struct nd_namespace_pmem, nsio); +} + +static inline struct nd_namespace_blk *to_nd_namespace_blk(struct device *dev) +{ + return container_of(dev, struct nd_namespace_blk, common.dev); +} + +/** + * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace + * @ndns: device to read + * @offset: namespace-relative starting offset + * @buf: buffer to fill + * @size: transfer length + * + * @buf is up-to-date upon return from this routine. + */ +static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns, + resource_size_t offset, void *buf, size_t size) +{ + return ndns->rw_bytes(ndns, offset, buf, size, READ); +} + +/** + * nvdimm_write_bytes() - synchronously write bytes to an nvdimm namespace + * @ndns: device to read + * @offset: namespace-relative starting offset + * @buf: buffer to drain + * @size: transfer length + * + * NVDIMM Namepaces disks do not implement sectors internally. Depending on + * the @ndns, the contents of @buf may be in cpu cache, platform buffers, + * or on backing memory media upon return from this routine. Flushing + * to media is handled internal to the @ndns driver, if at all. + */ +static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns, + resource_size_t offset, void *buf, size_t size) +{ + return ndns->rw_bytes(ndns, offset, buf, size, WRITE); +} + +#define MODULE_ALIAS_ND_DEVICE(type) \ + MODULE_ALIAS("nd:t" __stringify(type) "*") +#define ND_DEVICE_MODALIAS_FMT "nd:t%d" + +int __must_check __nd_driver_register(struct nd_device_driver *nd_drv, + struct module *module, const char *mod_name); +#define nd_driver_register(driver) \ + __nd_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +#endif /* __LINUX_ND_H__ */ diff --git a/include/linux/net.h b/include/linux/net.h index 738ea48be889..04aa06852771 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -38,7 +38,6 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define SOCK_EXTERNALLY_ALLOCATED 5 #ifndef ARCH_HAS_SOCKET_TYPES /** @@ -208,7 +207,7 @@ void sock_unregister(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); -int sock_create_kern(int family, int type, int proto, struct socket **res); +int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 7d59dc6ab789..9672781c593d 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -66,7 +66,6 @@ enum { NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ - NETIF_F_HW_SWITCH_OFFLOAD_BIT, /* HW switch offload */ /* * Add your fresh new feature above and remember to update @@ -125,7 +124,6 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) -#define NETIF_F_HW_SWITCH_OFFLOAD __NETIF_F(HW_SWITCH_OFFLOAD) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ @@ -161,8 +159,7 @@ enum { */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ - NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_HW_SWITCH_OFFLOAD) + NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) /* * If one device doesn't support one of these features, then disable it diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1899c74a7127..e20979dfd6a9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -25,7 +25,6 @@ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H -#include <linux/pm_qos.h> #include <linux/timer.h> #include <linux/bug.h> #include <linux/delay.h> @@ -1101,6 +1100,10 @@ struct net_device_ops { struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); + int (*ndo_get_vf_stats)(struct net_device *dev, + int vf, + struct ifla_vf_stats + *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); @@ -1499,8 +1502,6 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * - * @pm_qos_req: Power Management QoS object - * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1567,7 +1568,7 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_SWITCHDEV - const struct swdev_ops *swdev_ops; + const struct switchdev_ops *switchdev_ops; #endif const struct header_ops *header_ops; @@ -1655,7 +1656,14 @@ struct net_device { rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto __rcu *ingress_cl_list; +#endif struct netdev_queue __rcu *ingress_queue; +#ifdef CONFIG_NETFILTER_INGRESS + struct list_head nf_hooks_ingress; +#endif + unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; @@ -1993,6 +2001,7 @@ struct offload_callbacks { struct packet_offload { __be16 type; /* This is really htons(ether_type). */ + u16 priority; struct offload_callbacks callbacks; struct list_head list; }; @@ -2555,10 +2564,6 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { - if (WARN_ON(!dev_queue)) { - pr_info("netif_stop_queue() cannot be called before register_netdev()\n"); - return; - } set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -2574,15 +2579,7 @@ static inline void netif_stop_queue(struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } -static inline void netif_tx_stop_all_queues(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - netif_tx_stop_queue(txq); - } -} +void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -2843,6 +2840,9 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, + unsigned int num_tx_queues); + /* * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used * as a distribution range limit for the returned value. diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 63560d0a8dfe..00050dfd9f23 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -10,7 +10,8 @@ #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> -#include <uapi/linux/netfilter.h> +#include <linux/netfilter_defs.h> + #ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) { @@ -38,9 +39,6 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, int netfilter_init(void); -/* Largest hook number + 1 */ -#define NF_MAX_HOOKS 8 - struct sk_buff; struct nf_hook_ops; @@ -54,10 +52,12 @@ struct nf_hook_state { struct net_device *in; struct net_device *out; struct sock *sk; + struct list_head *hook_list; int (*okfn)(struct sock *, struct sk_buff *); }; static inline void nf_hook_state_init(struct nf_hook_state *p, + struct list_head *hook_list, unsigned int hook, int thresh, u_int8_t pf, struct net_device *indev, @@ -71,6 +71,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->in = indev; p->out = outdev; p->sk = sk; + p->hook_list = hook_list; p->okfn = okfn; } @@ -79,16 +80,17 @@ typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, const struct nf_hook_state *state); struct nf_hook_ops { - struct list_head list; + struct list_head list; /* User fills in from here down. */ - nf_hookfn *hook; - struct module *owner; - void *priv; - u_int8_t pf; - unsigned int hooknum; + nf_hookfn *hook; + struct net_device *dev; + struct module *owner; + void *priv; + u_int8_t pf; + unsigned int hooknum; /* Hooks are ordered in ascending priority. */ - int priority; + int priority; }; struct nf_sockopt_ops { @@ -131,26 +133,33 @@ extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) +static inline bool nf_hook_list_active(struct list_head *nf_hook_list, + u_int8_t pf, unsigned int hook) { if (__builtin_constant_p(pf) && __builtin_constant_p(hook)) return static_key_false(&nf_hooks_needed[pf][hook]); - return !list_empty(&nf_hooks[pf][hook]); + return !list_empty(nf_hook_list); } #else -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) +static inline bool nf_hook_list_active(struct list_head *nf_hook_list, + u_int8_t pf, unsigned int hook) { - return !list_empty(&nf_hooks[pf][hook]); + return !list_empty(nf_hook_list); } #endif +static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) +{ + return nf_hook_list_active(&nf_hooks[pf][hook], pf, hook); +} + int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); /** * nf_hook_thresh - call a netfilter hook - * + * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. @@ -166,8 +175,8 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, if (nf_hooks_active(pf, hook)) { struct nf_hook_state state; - nf_hook_state_init(&state, hook, thresh, pf, - indev, outdev, sk, okfn); + nf_hook_state_init(&state, &nf_hooks[pf][hook], hook, thresh, + pf, indev, outdev, sk, okfn); return nf_hook_slow(skb, &state); } return 1; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34b172301558..48bb01edcf30 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -108,8 +108,13 @@ struct ip_set_counter { atomic64_t packets; }; +struct ip_set_comment_rcu { + struct rcu_head rcu; + char str[0]; +}; + struct ip_set_comment { - char *str; + struct ip_set_comment_rcu __rcu *c; }; struct ip_set_skbinfo { @@ -122,13 +127,13 @@ struct ip_set_skbinfo { struct ip_set; #define ext_timeout(e, s) \ -(unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT]) +((unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])) #define ext_counter(e, s) \ -(struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER]) +((struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])) #define ext_comment(e, s) \ -(struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT]) +((struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT])) #define ext_skbinfo(e, s) \ -(struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO]) +((struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO])) typedef int (*ipset_adtfn)(struct ip_set *set, void *value, const struct ip_set_ext *ext, @@ -176,6 +181,9 @@ struct ip_set_type_variant { /* List elements */ int (*list)(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb); + /* Keep listing private when resizing runs parallel */ + void (*uref)(struct ip_set *set, struct netlink_callback *cb, + bool start); /* Return true if "b" set is the same as "a" * according to the create set parameters */ @@ -223,7 +231,7 @@ struct ip_set { /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ - rwlock_t lock; + spinlock_t lock; /* References to the set */ u32 ref; /* The core set type */ @@ -341,12 +349,11 @@ ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo) cpu_to_be64((u64)skbinfo->skbmark << 32 | skbinfo->skbmarkmask))) || (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, cpu_to_be32(skbinfo->skbprio))) || (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, cpu_to_be16(skbinfo->skbqueue))); - } static inline void @@ -380,12 +387,12 @@ ip_set_init_counter(struct ip_set_counter *counter, /* Netlink CB args */ enum { - IPSET_CB_NET = 0, - IPSET_CB_DUMP, - IPSET_CB_INDEX, - IPSET_CB_ARG0, + IPSET_CB_NET = 0, /* net namespace */ + IPSET_CB_DUMP, /* dump single set/all sets */ + IPSET_CB_INDEX, /* set index */ + IPSET_CB_PRIVATE, /* set private data */ + IPSET_CB_ARG0, /* type specific */ IPSET_CB_ARG1, - IPSET_CB_ARG2, }; /* register and unregister set references */ @@ -533,29 +540,9 @@ bitmap_bytes(u32 a, u32 b) #include <linux/netfilter/ipset/ip_set_timeout.h> #include <linux/netfilter/ipset/ip_set_comment.h> -static inline int +int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, - const void *e, bool active) -{ - if (SET_WITH_TIMEOUT(set)) { - unsigned long *timeout = ext_timeout(e, set); - - if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, - htonl(active ? ip_set_timeout_get(timeout) - : *timeout))) - return -EMSGSIZE; - } - if (SET_WITH_COUNTER(set) && - ip_set_put_counter(skb, ext_counter(e, set))) - return -EMSGSIZE; - if (SET_WITH_COMMENT(set) && - ip_set_put_comment(skb, ext_comment(e, set))) - return -EMSGSIZE; - if (SET_WITH_SKBINFO(set) && - ip_set_put_skbinfo(skb, ext_skbinfo(e, set))) - return -EMSGSIZE; - return 0; -} + const void *e, bool active); #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, \ @@ -565,8 +552,6 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, { .bytes = ULLONG_MAX, .packets = ULLONG_MAX, \ .timeout = (set)->timeout } -#define IP_SET_INIT_CIDR(a, b) ((a) ? (a) : (b)) - #define IPSET_CONCAT(a, b) a##b #define IPSET_TOKEN(a, b) IPSET_CONCAT(a, b) diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 21217ea008d7..8d0248525957 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -16,41 +16,57 @@ ip_set_comment_uget(struct nlattr *tb) return nla_data(tb); } +/* Called from uadd only, protected by the set spinlock. + * The kadt functions don't use the comment extensions in any way. + */ static inline void ip_set_init_comment(struct ip_set_comment *comment, const struct ip_set_ext *ext) { + struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); size_t len = ext->comment ? strlen(ext->comment) : 0; - if (unlikely(comment->str)) { - kfree(comment->str); - comment->str = NULL; + if (unlikely(c)) { + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); } if (!len) return; if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) len = IPSET_MAX_COMMENT_SIZE; - comment->str = kzalloc(len + 1, GFP_ATOMIC); - if (unlikely(!comment->str)) + c = kzalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + if (unlikely(!c)) return; - strlcpy(comment->str, ext->comment, len + 1); + strlcpy(c->str, ext->comment, len + 1); + rcu_assign_pointer(comment->c, c); } +/* Used only when dumping a set, protected by rcu_read_lock_bh() */ static inline int ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment) { - if (!comment->str) + struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + + if (!c) return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, comment->str); + return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); } +/* Called from uadd/udel, flush or the garbage collectors protected + * by the set spinlock. + * Called when the set is destroyed and when there can't be any user + * of the set data anymore. + */ static inline void ip_set_comment_free(struct ip_set_comment *comment) { - if (unlikely(!comment->str)) + struct ip_set_comment_rcu *c; + + c = rcu_dereference_protected(comment->c, 1); + if (unlikely(!c)) return; - kfree(comment->str); - comment->str = NULL; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); } #endif diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 83c2f9e0886c..1d6a935c1ac5 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -40,38 +40,33 @@ ip_set_timeout_uget(struct nlattr *tb) } static inline bool -ip_set_timeout_test(unsigned long timeout) +ip_set_timeout_expired(unsigned long *t) { - return timeout == IPSET_ELEM_PERMANENT || - time_is_after_jiffies(timeout); -} - -static inline bool -ip_set_timeout_expired(unsigned long *timeout) -{ - return *timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(*timeout); + return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); } static inline void -ip_set_timeout_set(unsigned long *timeout, u32 t) +ip_set_timeout_set(unsigned long *timeout, u32 value) { - if (!t) { + unsigned long t; + + if (!value) { *timeout = IPSET_ELEM_PERMANENT; return; } - *timeout = msecs_to_jiffies(t * 1000) + jiffies; - if (*timeout == IPSET_ELEM_PERMANENT) + t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; + if (t == IPSET_ELEM_PERMANENT) /* Bingo! :-) */ - (*timeout)--; + t--; + *timeout = t; } static inline u32 ip_set_timeout_get(unsigned long *timeout) { return *timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(*timeout - jiffies)/1000; + jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; } #endif /* __KERNEL__ */ diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index a3e215bb0241..286098a5667f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -62,6 +62,7 @@ struct xt_mtchk_param { void *matchinfo; unsigned int hook_mask; u_int8_t family; + bool nft_compat; }; /** @@ -92,6 +93,7 @@ struct xt_tgchk_param { void *targinfo; unsigned int hook_mask; u_int8_t family; + bool nft_compat; }; /* Target destructor parameters */ @@ -222,13 +224,10 @@ struct xt_table_info { unsigned int stacksize; unsigned int __percpu *stackptr; void ***jumpstack; - /* ipt_entry tables: one per CPU */ - /* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */ - void *entries[1]; + + unsigned char entries[0] __aligned(8); }; -#define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \ - + nr_cpu_ids * sizeof(char *)) int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); @@ -351,6 +350,57 @@ static inline unsigned long ifname_compare_aligned(const char *_a, return ret; } + +/* On SMP, ip(6)t_entry->counters.pcnt holds address of the + * real (percpu) counter. On !SMP, its just the packet count, + * so nothing needs to be done there. + * + * xt_percpu_counter_alloc returns the address of the percpu + * counter, or 0 on !SMP. We force an alignment of 16 bytes + * so that bytes/packets share a common cache line. + * + * Hence caller must use IS_ERR_VALUE to check for error, this + * allows us to return 0 for single core systems without forcing + * callers to deal with SMP vs. NONSMP issues. + */ +static inline u64 xt_percpu_counter_alloc(void) +{ + if (nr_cpu_ids > 1) { + void __percpu *res = __alloc_percpu(sizeof(struct xt_counters), + sizeof(struct xt_counters)); + + if (res == NULL) + return (u64) -ENOMEM; + + return (u64) (__force unsigned long) res; + } + + return 0; +} +static inline void xt_percpu_counter_free(u64 pcnt) +{ + if (nr_cpu_ids > 1) + free_percpu((void __percpu *) (unsigned long) pcnt); +} + +static inline struct xt_counters * +xt_get_this_cpu_counter(struct xt_counters *cnt) +{ + if (nr_cpu_ids > 1) + return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); + + return cnt; +} + +static inline struct xt_counters * +xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) +{ + if (nr_cpu_ids > 1) + return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); + + return cnt; +} + struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *); void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *); diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index f2fdb5a52070..6d80fc686323 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -20,13 +20,6 @@ enum nf_br_hook_priorities { #define BRNF_BRIDGED_DNAT 0x02 #define BRNF_NF_BRIDGE_PREROUTING 0x08 -static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) -{ - if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE) - return PPPOE_SES_HLEN; - return 0; -} - int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index f1bd3962e6b6..8ca6d6464ea3 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -6,7 +6,7 @@ * * ebtables.c,v 2.0, April, 2002 * - * This code is stongly inspired on the iptables code which is + * This code is strongly inspired by the iptables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling */ #ifndef __LINUX_BRIDGE_EFF_H diff --git a/include/linux/netfilter_defs.h b/include/linux/netfilter_defs.h new file mode 100644 index 000000000000..d3a7f8597e82 --- /dev/null +++ b/include/linux/netfilter_defs.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_NETFILTER_CORE_H_ +#define __LINUX_NETFILTER_CORE_H_ + +#include <uapi/linux/netfilter.h> + +/* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */ +#define NF_MAX_HOOKS 8 + +#endif diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h new file mode 100644 index 000000000000..cb0727fe2b3d --- /dev/null +++ b/include/linux/netfilter_ingress.h @@ -0,0 +1,41 @@ +#ifndef _NETFILTER_INGRESS_H_ +#define _NETFILTER_INGRESS_H_ + +#include <linux/netfilter.h> +#include <linux/netdevice.h> + +#ifdef CONFIG_NETFILTER_INGRESS +static inline int nf_hook_ingress_active(struct sk_buff *skb) +{ + return nf_hook_list_active(&skb->dev->nf_hooks_ingress, + NFPROTO_NETDEV, NF_NETDEV_INGRESS); +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + struct nf_hook_state state; + + nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, + NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL, + skb->dev, NULL, NULL); + return nf_hook_slow(skb, &state); +} + +static inline void nf_hook_ingress_init(struct net_device *dev) +{ + INIT_LIST_HEAD(&dev->nf_hooks_ingress); +} +#else /* CONFIG_NETFILTER_INGRESS */ +static inline int nf_hook_ingress_active(struct sk_buff *skb) +{ + return 0; +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + return 0; +} + +static inline void nf_hook_ingress_init(struct net_device *dev) {} +#endif /* CONFIG_NETFILTER_INGRESS */ +#endif /* _NETFILTER_INGRESS_H_ */ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 64dad1cc1a4b..8b7d28f3aada 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -25,6 +25,9 @@ void ipv6_netfilter_fini(void); struct nf_ipv6_ops { int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); + void (*route_input)(struct sk_buff *skb); + int (*fragment)(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)); }; extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6835c1279df7..9120edb650a0 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -28,6 +28,8 @@ struct netlink_skb_parms { __u32 dst_group; __u32 flags; struct sock *sk; + bool nsid_is_set; + int nsid; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 32201c269890..b8e72aad919c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -500,6 +500,7 @@ enum { NFSPROC4_CLNT_SEEK, NFSPROC4_CLNT_ALLOCATE, NFSPROC4_CLNT_DEALLOCATE, + NFSPROC4_CLNT_LAYOUTSTATS, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b95f914ce083..874b77228fb9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -219,6 +219,7 @@ struct nfs_inode { #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ +#define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { @@ -291,9 +292,12 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR | + NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 5e1273d4de14..20bc8e51b161 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -220,7 +220,7 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) -#define NFS_CAP_CHANGE_ATTR (1U << 5) +/* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ #define NFS_CAP_FILEID (1U << 6) #define NFS_CAP_MODE (1U << 7) #define NFS_CAP_NLINK (1U << 8) @@ -237,5 +237,6 @@ struct nfs_server { #define NFS_CAP_SEEK (1U << 19) #define NFS_CAP_ALLOCATE (1U << 20) #define NFS_CAP_DEALLOCATE (1U << 21) +#define NFS_CAP_LAYOUTSTATS (1U << 22) #endif diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3eb072dbce83..f2f650f136ee 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -67,7 +67,6 @@ struct nfs_rw_ops { const fmode_t rw_mode; struct nfs_pgio_header *(*rw_alloc_header)(void); void (*rw_free_header)(struct nfs_pgio_header *); - void (*rw_release)(struct nfs_pgio_header *); int (*rw_done)(struct rpc_task *, struct nfs_pgio_header *, struct inode *); void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 93ab6071bbe9..7bbe50504211 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -316,6 +316,49 @@ struct nfs4_layoutreturn { int rpc_status; }; +#define PNFS_LAYOUTSTATS_MAXSIZE 256 + +struct nfs42_layoutstat_args; +struct nfs42_layoutstat_devinfo; +typedef void (*layoutstats_encode_t)(struct xdr_stream *, + struct nfs42_layoutstat_args *, + struct nfs42_layoutstat_devinfo *); + +/* Per file per deviceid layoutstats */ +struct nfs42_layoutstat_devinfo { + struct nfs4_deviceid dev_id; + __u64 offset; + __u64 length; + __u64 read_count; + __u64 read_bytes; + __u64 write_count; + __u64 write_bytes; + __u32 layout_type; + layoutstats_encode_t layoutstats_encode; + void *layout_private; +}; + +struct nfs42_layoutstat_args { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + struct inode *inode; + nfs4_stateid stateid; + int num_dev; + struct nfs42_layoutstat_devinfo *devinfo; +}; + +struct nfs42_layoutstat_res { + struct nfs4_sequence_res seq_res; + int num_dev; + int rpc_status; +}; + +struct nfs42_layoutstat_data { + struct inode *inode; + struct nfs42_layoutstat_args args; + struct nfs42_layoutstat_res res; +}; + struct stateowner_id { __u64 create_time; __u32 uniquifier; @@ -984,17 +1027,14 @@ struct nfs4_readlink_res { struct nfs4_sequence_res seq_res; }; -#define NFS4_SETCLIENTID_NAMELEN (127) struct nfs4_setclientid { const nfs4_verifier * sc_verifier; - unsigned int sc_name_len; - char sc_name[NFS4_SETCLIENTID_NAMELEN + 1]; u32 sc_prog; unsigned int sc_netid_len; char sc_netid[RPCBIND_MAXNETIDLEN + 1]; unsigned int sc_uaddr_len; char sc_uaddr[RPCBIND_MAXUADDRLEN + 1]; - u32 sc_cb_ident; + struct nfs_client *sc_clnt; struct rpc_cred *sc_cred; }; @@ -1142,12 +1182,9 @@ struct nfs41_state_protection { struct nfs4_op_map allow; }; -#define NFS4_EXCHANGE_ID_LEN (48) struct nfs41_exchange_id_args { struct nfs_client *client; nfs4_verifier *verifier; - unsigned int id_len; - char id[NFS4_EXCHANGE_ID_LEN]; u32 flags; struct nfs41_state_protection state_protect; }; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 3d46fb4708e0..f94da0e65dea 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -67,6 +67,7 @@ extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; +extern unsigned long *watchdog_cpumask_bits; extern int sysctl_softlockup_all_cpu_backtrace; struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , @@ -77,6 +78,8 @@ extern int proc_soft_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); +extern int proc_watchdog_cpumask(struct ctl_table *, int, + void __user *, size_t *, loff_t *); #endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 9ac1a62fc6f5..b02f72bb8e32 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -4,15 +4,20 @@ * * GPL LICENSE SUMMARY * - * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * * BSD LICENSE * - * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -40,49 +45,940 @@ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * - * Intel PCIe NTB Linux driver + * PCIe NTB Linux driver * * Contact Information: - * Jon Mason <jon.mason@intel.com> + * Allen Hubbe <Allen.Hubbe@emc.com> */ -struct ntb_transport_qp; +#ifndef _NTB_H_ +#define _NTB_H_ -struct ntb_client { - struct device_driver driver; - int (*probe)(struct pci_dev *pdev); - void (*remove)(struct pci_dev *pdev); +#include <linux/completion.h> +#include <linux/device.h> + +struct ntb_client; +struct ntb_dev; +struct pci_dev; + +/** + * enum ntb_topo - NTB connection topology + * @NTB_TOPO_NONE: Topology is unknown or invalid. + * @NTB_TOPO_PRI: On primary side of local ntb. + * @NTB_TOPO_SEC: On secondary side of remote ntb. + * @NTB_TOPO_B2B_USD: On primary side of local ntb upstream of remote ntb. + * @NTB_TOPO_B2B_DSD: On primary side of local ntb downstream of remote ntb. + */ +enum ntb_topo { + NTB_TOPO_NONE = -1, + NTB_TOPO_PRI, + NTB_TOPO_SEC, + NTB_TOPO_B2B_USD, + NTB_TOPO_B2B_DSD, +}; + +static inline int ntb_topo_is_b2b(enum ntb_topo topo) +{ + switch ((int)topo) { + case NTB_TOPO_B2B_USD: + case NTB_TOPO_B2B_DSD: + return 1; + } + return 0; +} + +static inline char *ntb_topo_string(enum ntb_topo topo) +{ + switch (topo) { + case NTB_TOPO_NONE: return "NTB_TOPO_NONE"; + case NTB_TOPO_PRI: return "NTB_TOPO_PRI"; + case NTB_TOPO_SEC: return "NTB_TOPO_SEC"; + case NTB_TOPO_B2B_USD: return "NTB_TOPO_B2B_USD"; + case NTB_TOPO_B2B_DSD: return "NTB_TOPO_B2B_DSD"; + } + return "NTB_TOPO_INVALID"; +} + +/** + * enum ntb_speed - NTB link training speed + * @NTB_SPEED_AUTO: Request the max supported speed. + * @NTB_SPEED_NONE: Link is not trained to any speed. + * @NTB_SPEED_GEN1: Link is trained to gen1 speed. + * @NTB_SPEED_GEN2: Link is trained to gen2 speed. + * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + */ +enum ntb_speed { + NTB_SPEED_AUTO = -1, + NTB_SPEED_NONE = 0, + NTB_SPEED_GEN1 = 1, + NTB_SPEED_GEN2 = 2, + NTB_SPEED_GEN3 = 3, +}; + +/** + * enum ntb_width - NTB link training width + * @NTB_WIDTH_AUTO: Request the max supported width. + * @NTB_WIDTH_NONE: Link is not trained to any width. + * @NTB_WIDTH_1: Link is trained to 1 lane width. + * @NTB_WIDTH_2: Link is trained to 2 lane width. + * @NTB_WIDTH_4: Link is trained to 4 lane width. + * @NTB_WIDTH_8: Link is trained to 8 lane width. + * @NTB_WIDTH_12: Link is trained to 12 lane width. + * @NTB_WIDTH_16: Link is trained to 16 lane width. + * @NTB_WIDTH_32: Link is trained to 32 lane width. + */ +enum ntb_width { + NTB_WIDTH_AUTO = -1, + NTB_WIDTH_NONE = 0, + NTB_WIDTH_1 = 1, + NTB_WIDTH_2 = 2, + NTB_WIDTH_4 = 4, + NTB_WIDTH_8 = 8, + NTB_WIDTH_12 = 12, + NTB_WIDTH_16 = 16, + NTB_WIDTH_32 = 32, +}; + +/** + * struct ntb_client_ops - ntb client operations + * @probe: Notify client of a new device. + * @remove: Notify client to remove a device. + */ +struct ntb_client_ops { + int (*probe)(struct ntb_client *client, struct ntb_dev *ntb); + void (*remove)(struct ntb_client *client, struct ntb_dev *ntb); +}; + +static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) +{ + /* commented callbacks are not required: */ + return + ops->probe && + ops->remove && + 1; +} + +/** + * struct ntb_ctx_ops - ntb driver context operations + * @link_event: See ntb_link_event(). + * @db_event: See ntb_db_event(). + */ +struct ntb_ctx_ops { + void (*link_event)(void *ctx); + void (*db_event)(void *ctx, int db_vector); +}; + +static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) +{ + /* commented callbacks are not required: */ + return + /* ops->link_event && */ + /* ops->db_event && */ + 1; +} + +/** + * struct ntb_ctx_ops - ntb device operations + * @mw_count: See ntb_mw_count(). + * @mw_get_range: See ntb_mw_get_range(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @link_is_up: See ntb_link_is_up(). + * @link_enable: See ntb_link_enable(). + * @link_disable: See ntb_link_disable(). + * @db_is_unsafe: See ntb_db_is_unsafe(). + * @db_valid_mask: See ntb_db_valid_mask(). + * @db_vector_count: See ntb_db_vector_count(). + * @db_vector_mask: See ntb_db_vector_mask(). + * @db_read: See ntb_db_read(). + * @db_set: See ntb_db_set(). + * @db_clear: See ntb_db_clear(). + * @db_read_mask: See ntb_db_read_mask(). + * @db_set_mask: See ntb_db_set_mask(). + * @db_clear_mask: See ntb_db_clear_mask(). + * @peer_db_addr: See ntb_peer_db_addr(). + * @peer_db_read: See ntb_peer_db_read(). + * @peer_db_set: See ntb_peer_db_set(). + * @peer_db_clear: See ntb_peer_db_clear(). + * @peer_db_read_mask: See ntb_peer_db_read_mask(). + * @peer_db_set_mask: See ntb_peer_db_set_mask(). + * @peer_db_clear_mask: See ntb_peer_db_clear_mask(). + * @spad_is_unsafe: See ntb_spad_is_unsafe(). + * @spad_count: See ntb_spad_count(). + * @spad_read: See ntb_spad_read(). + * @spad_write: See ntb_spad_write(). + * @peer_spad_addr: See ntb_peer_spad_addr(). + * @peer_spad_read: See ntb_peer_spad_read(). + * @peer_spad_write: See ntb_peer_spad_write(). + */ +struct ntb_dev_ops { + int (*mw_count)(struct ntb_dev *ntb); + int (*mw_get_range)(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size, + resource_size_t *align, resource_size_t *align_size); + int (*mw_set_trans)(struct ntb_dev *ntb, int idx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + + int (*link_is_up)(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width); + int (*link_enable)(struct ntb_dev *ntb, + enum ntb_speed max_speed, enum ntb_width max_width); + int (*link_disable)(struct ntb_dev *ntb); + + int (*db_is_unsafe)(struct ntb_dev *ntb); + u64 (*db_valid_mask)(struct ntb_dev *ntb); + int (*db_vector_count)(struct ntb_dev *ntb); + u64 (*db_vector_mask)(struct ntb_dev *ntb, int db_vector); + + u64 (*db_read)(struct ntb_dev *ntb); + int (*db_set)(struct ntb_dev *ntb, u64 db_bits); + int (*db_clear)(struct ntb_dev *ntb, u64 db_bits); + + u64 (*db_read_mask)(struct ntb_dev *ntb); + int (*db_set_mask)(struct ntb_dev *ntb, u64 db_bits); + int (*db_clear_mask)(struct ntb_dev *ntb, u64 db_bits); + + int (*peer_db_addr)(struct ntb_dev *ntb, + phys_addr_t *db_addr, resource_size_t *db_size); + u64 (*peer_db_read)(struct ntb_dev *ntb); + int (*peer_db_set)(struct ntb_dev *ntb, u64 db_bits); + int (*peer_db_clear)(struct ntb_dev *ntb, u64 db_bits); + + u64 (*peer_db_read_mask)(struct ntb_dev *ntb); + int (*peer_db_set_mask)(struct ntb_dev *ntb, u64 db_bits); + int (*peer_db_clear_mask)(struct ntb_dev *ntb, u64 db_bits); + + int (*spad_is_unsafe)(struct ntb_dev *ntb); + int (*spad_count)(struct ntb_dev *ntb); + + u32 (*spad_read)(struct ntb_dev *ntb, int idx); + int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + + int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + phys_addr_t *spad_addr); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); + int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); }; -enum { - NTB_LINK_DOWN = 0, - NTB_LINK_UP, +static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) +{ + /* commented callbacks are not required: */ + return + ops->mw_count && + ops->mw_get_range && + ops->mw_set_trans && + /* ops->mw_clear_trans && */ + ops->link_is_up && + ops->link_enable && + ops->link_disable && + /* ops->db_is_unsafe && */ + ops->db_valid_mask && + + /* both set, or both unset */ + (!ops->db_vector_count == !ops->db_vector_mask) && + + ops->db_read && + /* ops->db_set && */ + ops->db_clear && + /* ops->db_read_mask && */ + ops->db_set_mask && + ops->db_clear_mask && + ops->peer_db_addr && + /* ops->peer_db_read && */ + ops->peer_db_set && + /* ops->peer_db_clear && */ + /* ops->peer_db_read_mask && */ + /* ops->peer_db_set_mask && */ + /* ops->peer_db_clear_mask && */ + /* ops->spad_is_unsafe && */ + ops->spad_count && + ops->spad_read && + ops->spad_write && + ops->peer_spad_addr && + /* ops->peer_spad_read && */ + ops->peer_spad_write && + 1; +} + +/** + * struct ntb_client - client interested in ntb devices + * @drv: Linux driver object. + * @ops: See &ntb_client_ops. + */ +struct ntb_client { + struct device_driver drv; + const struct ntb_client_ops ops; }; -int ntb_register_client(struct ntb_client *drvr); -void ntb_unregister_client(struct ntb_client *drvr); -int ntb_register_client_dev(char *device_name); -void ntb_unregister_client_dev(char *device_name); - -struct ntb_queue_handlers { - void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data, - void *data, int len); - void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data, - void *data, int len); - void (*event_handler)(void *data, int status); +#define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) + +/** + * struct ntb_device - ntb device + * @dev: Linux device object. + * @pdev: Pci device entry of the ntb. + * @topo: Detected topology of the ntb. + * @ops: See &ntb_dev_ops. + * @ctx: See &ntb_ctx_ops. + * @ctx_ops: See &ntb_ctx_ops. + */ +struct ntb_dev { + struct device dev; + struct pci_dev *pdev; + enum ntb_topo topo; + const struct ntb_dev_ops *ops; + void *ctx; + const struct ntb_ctx_ops *ctx_ops; + + /* private: */ + + /* synchronize setting, clearing, and calling ctx_ops */ + spinlock_t ctx_lock; + /* block unregister until device is fully released */ + struct completion released; }; -unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp); -unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp); -struct ntb_transport_qp * -ntb_transport_create_queue(void *data, struct pci_dev *pdev, - const struct ntb_queue_handlers *handlers); -void ntb_transport_free_queue(struct ntb_transport_qp *qp); -int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, - unsigned int len); -int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, - unsigned int len); -void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); -void ntb_transport_link_up(struct ntb_transport_qp *qp); -void ntb_transport_link_down(struct ntb_transport_qp *qp); -bool ntb_transport_link_query(struct ntb_transport_qp *qp); +#define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) + +/** + * ntb_register_client() - register a client for interest in ntb devices + * @client: Client context. + * + * The client will be added to the list of clients interested in ntb devices. + * The client will be notified of any ntb devices that are not already + * associated with a client, or if ntb devices are registered later. + * + * Return: Zero if the client is registered, otherwise an error number. + */ +#define ntb_register_client(client) \ + __ntb_register_client((client), THIS_MODULE, KBUILD_MODNAME) + +int __ntb_register_client(struct ntb_client *client, struct module *mod, + const char *mod_name); + +/** + * ntb_unregister_client() - unregister a client for interest in ntb devices + * @client: Client context. + * + * The client will be removed from the list of clients interested in ntb + * devices. If any ntb devices are associated with the client, the client will + * be notified to remove those devices. + */ +void ntb_unregister_client(struct ntb_client *client); + +#define module_ntb_client(__ntb_client) \ + module_driver(__ntb_client, ntb_register_client, \ + ntb_unregister_client) + +/** + * ntb_register_device() - register a ntb device + * @ntb: NTB device context. + * + * The device will be added to the list of ntb devices. If any clients are + * interested in ntb devices, each client will be notified of the ntb device, + * until at most one client accepts the device. + * + * Return: Zero if the device is registered, otherwise an error number. + */ +int ntb_register_device(struct ntb_dev *ntb); + +/** + * ntb_register_device() - unregister a ntb device + * @ntb: NTB device context. + * + * The device will be removed from the list of ntb devices. If the ntb device + * is associated with a client, the client will be notified to remove the + * device. + */ +void ntb_unregister_device(struct ntb_dev *ntb); + +/** + * ntb_set_ctx() - associate a driver context with an ntb device + * @ntb: NTB device context. + * @ctx: Driver context. + * @ctx_ops: Driver context operations. + * + * Associate a driver context and operations with a ntb device. The context is + * provided by the client driver, and the driver may associate a different + * context with each ntb device. + * + * Return: Zero if the context is associated, otherwise an error number. + */ +int ntb_set_ctx(struct ntb_dev *ntb, void *ctx, + const struct ntb_ctx_ops *ctx_ops); + +/** + * ntb_clear_ctx() - disassociate any driver context from an ntb device + * @ntb: NTB device context. + * + * Clear any association that may exist between a driver context and the ntb + * device. + */ +void ntb_clear_ctx(struct ntb_dev *ntb); + +/** + * ntb_link_event() - notify driver context of a change in link status + * @ntb: NTB device context. + * + * Notify the driver context that the link status may have changed. The driver + * should call ntb_link_is_up() to get the current status. + */ +void ntb_link_event(struct ntb_dev *ntb); + +/** + * ntb_db_event() - notify driver context of a doorbell event + * @ntb: NTB device context. + * @vector: Interrupt vector number. + * + * Notify the driver context of a doorbell event. If hardware supports + * multiple interrupt vectors for doorbells, the vector number indicates which + * vector received the interrupt. The vector number is relative to the first + * vector used for doorbells, starting at zero, and must be less than + ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * doorbell bits need service, and ntb_db_vector_mask() to determine which of + * those bits are associated with the vector number. + */ +void ntb_db_event(struct ntb_dev *ntb, int vector); + +/** + * ntb_mw_count() - get the number of memory windows + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->mw_count(ntb); +} + +/** + * ntb_mw_get_range() - get the range of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * @base: OUT - the base address for mapping the memory window + * @size: OUT - the size for mapping the memory window + * @align: OUT - the base alignment for translating the memory window + * @align_size: OUT - the size alignment for translating the memory window + * + * Get the range of a memory window. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. The alignment and + * size may be used for translating the memory window, for the peer to access + * memory on the local system. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size, + resource_size_t *align, resource_size_t *align_size) +{ + return ntb->ops->mw_get_range(ntb, idx, base, size, + align, align_size); +} + +/** + * ntb_mw_set_trans() - set the translation of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * @addr: The dma address local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * must be aligned to the alignment specified by ntb_mw_get_range(). The size + * must be aligned to the size alignment specified by ntb_mw_get_range(). + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, + dma_addr_t addr, resource_size_t size) +{ + return ntb->ops->mw_set_trans(ntb, idx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation of a memory window + * @ntb: NTB device context. + * @idx: Memory window number. + * + * Clear the translation of a memory window. The peer may no longer access + * local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, idx); +} + +/** + * ntb_link_is_up() - get the current ntb link state + * @ntb: NTB device context. + * @speed: OUT - The link speed expressed as PCIe generation number. + * @width: OUT - The link width expressed as the number of PCIe lanes. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * must be aligned to the alignment specified by ntb_mw_get_range(). The size + * must be aligned to the size alignment specified by ntb_mw_get_range(). + * + * Return: One if the link is up, zero if the link is down, otherwise a + * negative value indicating the error number. + */ +static inline int ntb_link_is_up(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width) +{ + return ntb->ops->link_is_up(ntb, speed, width); +} + +/** + * ntb_link_enable() - enable the link on the secondary side of the ntb + * @ntb: NTB device context. + * @max_speed: The maximum link speed expressed as PCIe generation number. + * @max_width: The maximum link width expressed as the number of PCIe lanes. + * + * Enable the link on the secondary side of the ntb. This can only be done + * from the primary side of the ntb in primary or b2b topology. The ntb device + * should train the link to its maximum speed and width, or the requested speed + * and width, whichever is smaller, if supported. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_enable(struct ntb_dev *ntb, + enum ntb_speed max_speed, + enum ntb_width max_width) +{ + return ntb->ops->link_enable(ntb, max_speed, max_width); +} + +/** + * ntb_link_disable() - disable the link on the secondary side of the ntb + * @ntb: NTB device context. + * + * Disable the link on the secondary side of the ntb. This can only be + * done from the primary side of the ntb in primary or b2b topology. The ntb + * device should disable the link. Returning from this call must indicate that + * a barrier has passed, though with no more writes may pass in either + * direction across the link, except if this call returns an error number. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_disable(struct ntb_dev *ntb) +{ + return ntb->ops->link_disable(ntb); +} + +/** + * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell + * @ntb: NTB device context. + * + * It is possible for some ntb hardware to be affected by errata. Hardware + * drivers can advise clients to avoid using doorbells. Clients may ignore + * this advice, though caution is recommended. + * + * Return: Zero if it is safe to use doorbells, or One if it is not safe. + */ +static inline int ntb_db_is_unsafe(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_is_unsafe) + return 0; + + return ntb->ops->db_is_unsafe(ntb); +} + +/** + * ntb_db_valid_mask() - get a mask of doorbell bits supported by the ntb + * @ntb: NTB device context. + * + * Hardware may support different number or arrangement of doorbell bits. + * + * Return: A mask of doorbell bits supported by the ntb. + */ +static inline u64 ntb_db_valid_mask(struct ntb_dev *ntb) +{ + return ntb->ops->db_valid_mask(ntb); +} + +/** + * ntb_db_vector_count() - get the number of doorbell interrupt vectors + * @ntb: NTB device context. + * + * Hardware may support different number of interrupt vectors. + * + * Return: The number of doorbell interrupt vectors. + */ +static inline int ntb_db_vector_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_vector_count) + return 1; + + return ntb->ops->db_vector_count(ntb); +} + +/** + * ntb_db_vector_mask() - get a mask of doorbell bits serviced by a vector + * @ntb: NTB device context. + * @vector: Doorbell vector number. + * + * Each interrupt vector may have a different number or arrangement of bits. + * + * Return: A mask of doorbell bits serviced by a vector. + */ +static inline u64 ntb_db_vector_mask(struct ntb_dev *ntb, int vector) +{ + if (!ntb->ops->db_vector_mask) + return ntb_db_valid_mask(ntb); + + return ntb->ops->db_vector_mask(ntb, vector); +} + +/** + * ntb_db_read() - read the local doorbell register + * @ntb: NTB device context. + * + * Read the local doorbell register, and return the bits that are set. + * + * Return: The bits currently set in the local doorbell register. + */ +static inline u64 ntb_db_read(struct ntb_dev *ntb) +{ + return ntb->ops->db_read(ntb); +} + +/** + * ntb_db_set() - set bits in the local doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * Set bits in the local doorbell register, which may generate a local doorbell + * interrupt. Bits that were already set must remain set. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_set) + return -EINVAL; + + return ntb->ops->db_set(ntb, db_bits); +} + +/** + * ntb_db_clear() - clear bits in the local doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the local doorbell register, arming the bits for the next + * doorbell. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_clear(ntb, db_bits); +} + +/** + * ntb_db_read_mask() - read the local doorbell mask + * @ntb: NTB device context. + * + * Read the local doorbell mask register, and return the bits that are set. + * + * This is unusual, though hardware is likely to support it. + * + * Return: The bits currently set in the local doorbell mask register. + */ +static inline u64 ntb_db_read_mask(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_read_mask) + return 0; + + return ntb->ops->db_read_mask(ntb); +} + +/** + * ntb_db_set_mask() - set bits in the local doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * Set bits in the local doorbell mask register, preventing doorbell interrupts + * from being generated for those doorbell bits. Bits that were already set + * must remain set. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_set_mask(ntb, db_bits); +} + +/** + * ntb_db_clear_mask() - clear bits in the local doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the local doorbell mask register, allowing doorbell interrupts + * from being generated for those doorbell bits. If a doorbell bit is already + * set at the time the mask is cleared, and the corresponding mask bit is + * changed from set to clear, then the ntb driver must ensure that + * ntb_db_event() is called. If the hardware does not generate the interrupt + * on clearing the mask bit, then the driver must call ntb_db_event() anyway. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->db_clear_mask(ntb, db_bits); +} + +/** + * ntb_peer_db_addr() - address and size of the peer doorbell register + * @ntb: NTB device context. + * @db_addr: OUT - The address of the peer doorbell register. + * @db_size: OUT - The number of bytes to write the peer doorbell register. + * + * Return the address of the peer doorbell register. This may be used, for + * example, by drivers that offload memory copy operations to a dma engine. + * The drivers may wish to ring the peer doorbell at the completion of memory + * copy operations. For efficiency, and to simplify ordering of operations + * between the dma memory copies and the ringing doorbell, the driver may + * append one additional dma memory copy with the doorbell register as the + * destination, after the memory copy operations. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_addr(struct ntb_dev *ntb, + phys_addr_t *db_addr, + resource_size_t *db_size) +{ + return ntb->ops->peer_db_addr(ntb, db_addr, db_size); +} + +/** + * ntb_peer_db_read() - read the peer doorbell register + * @ntb: NTB device context. + * + * Read the peer doorbell register, and return the bits that are set. + * + * This is unusual, and hardware may not support it. + * + * Return: The bits currently set in the peer doorbell register. + */ +static inline u64 ntb_peer_db_read(struct ntb_dev *ntb) +{ + if (!ntb->ops->peer_db_read) + return 0; + + return ntb->ops->peer_db_read(ntb); +} + +/** + * ntb_peer_db_set() - set bits in the peer doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * Set bits in the peer doorbell register, which may generate a peer doorbell + * interrupt. Bits that were already set must remain set. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + return ntb->ops->peer_db_set(ntb, db_bits); +} + +/** + * ntb_peer_db_clear() - clear bits in the local doorbell register + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the peer doorbell register, arming the bits for the next + * doorbell. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_clear) + return -EINVAL; + + return ntb->ops->peer_db_clear(ntb, db_bits); +} + +/** + * ntb_peer_db_read_mask() - read the peer doorbell mask + * @ntb: NTB device context. + * + * Read the peer doorbell mask register, and return the bits that are set. + * + * This is unusual, and hardware may not support it. + * + * Return: The bits currently set in the peer doorbell mask register. + */ +static inline u64 ntb_peer_db_read_mask(struct ntb_dev *ntb) +{ + if (!ntb->ops->db_read_mask) + return 0; + + return ntb->ops->peer_db_read_mask(ntb); +} + +/** + * ntb_peer_db_set_mask() - set bits in the peer doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * Set bits in the peer doorbell mask register, preventing doorbell interrupts + * from being generated for those doorbell bits. Bits that were already set + * must remain set. + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_set_mask) + return -EINVAL; + + return ntb->ops->peer_db_set_mask(ntb, db_bits); +} + +/** + * ntb_peer_db_clear_mask() - clear bits in the peer doorbell mask + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits in the peer doorbell mask register, allowing doorbell interrupts + * from being generated for those doorbell bits. If the hardware does not + * generate the interrupt on clearing the mask bit, then the driver should not + * implement this function! + * + * This is unusual, and hardware may not support it. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + if (!ntb->ops->db_clear_mask) + return -EINVAL; + + return ntb->ops->peer_db_clear_mask(ntb, db_bits); +} + +/** + * ntb_spad_is_unsafe() - check if it is safe to use the hardware scratchpads + * @ntb: NTB device context. + * + * It is possible for some ntb hardware to be affected by errata. Hardware + * drivers can advise clients to avoid using scratchpads. Clients may ignore + * this advice, though caution is recommended. + * + * Return: Zero if it is safe to use scratchpads, or One if it is not safe. + */ +static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) +{ + if (!ntb->ops->spad_is_unsafe) + return 0; + + return ntb->ops->spad_is_unsafe(ntb); +} + +/** + * ntb_mw_count() - get the number of scratchpads + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of scratchpads. + * + * Return: the number of scratchpads. + */ +static inline int ntb_spad_count(struct ntb_dev *ntb) +{ + return ntb->ops->spad_count(ntb); +} + +/** + * ntb_spad_read() - read the local scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * + * Read the local scratchpad register, and return the value. + * + * Return: The value of the local scratchpad register. + */ +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +{ + return ntb->ops->spad_read(ntb, idx); +} + +/** + * ntb_spad_write() - write the local scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @val: Scratchpad value. + * + * Write the value to the local scratchpad register. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +{ + return ntb->ops->spad_write(ntb, idx, val); +} + +/** + * ntb_peer_spad_addr() - address of the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @spad_addr: OUT - The address of the peer scratchpad register. + * + * Return the address of the peer doorbell register. This may be used, for + * example, by drivers that offload memory copy operations to a dma engine. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *spad_addr) +{ + return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); +} + +/** + * ntb_peer_spad_read() - read the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * + * Read the peer scratchpad register, and return the value. + * + * Return: The value of the local scratchpad register. + */ +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +{ + return ntb->ops->peer_spad_read(ntb, idx); +} + +/** + * ntb_peer_spad_write() - write the peer scratchpad register + * @ntb: NTB device context. + * @idx: Scratchpad index. + * @val: Scratchpad value. + * + * Write the value to the peer scratchpad register. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +{ + return ntb->ops->peer_spad_write(ntb, idx, val); +} + +#endif diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h new file mode 100644 index 000000000000..2862861366a5 --- /dev/null +++ b/include/linux/ntb_transport.h @@ -0,0 +1,85 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * BSD LICENSE + * + * Copyright(c) 2012 Intel Corporation. All rights reserved. + * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copy + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * PCIe NTB Transport Linux driver + * + * Contact Information: + * Jon Mason <jon.mason@intel.com> + */ + +struct ntb_transport_qp; + +struct ntb_transport_client { + struct device_driver driver; + int (*probe)(struct device *client_dev); + void (*remove)(struct device *client_dev); +}; + +int ntb_transport_register_client(struct ntb_transport_client *drvr); +void ntb_transport_unregister_client(struct ntb_transport_client *drvr); +int ntb_transport_register_client_dev(char *device_name); +void ntb_transport_unregister_client_dev(char *device_name); + +struct ntb_queue_handlers { + void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data, + void *data, int len); + void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data, + void *data, int len); + void (*event_handler)(void *data, int status); +}; + +unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp); +unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp); +struct ntb_transport_qp * +ntb_transport_create_queue(void *data, struct device *client_dev, + const struct ntb_queue_handlers *handlers); +void ntb_transport_free_queue(struct ntb_transport_qp *qp); +int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, + unsigned int len); +int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, + unsigned int len); +void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); +void ntb_transport_link_up(struct ntb_transport_qp *qp); +void ntb_transport_link_down(struct ntb_transport_qp *qp); +bool ntb_transport_link_query(struct ntb_transport_qp *qp); diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 8dbd05e70f09..c0d94ed8ce9a 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -74,7 +74,7 @@ struct nvme_dev { struct blk_mq_tag_set tagset; struct blk_mq_tag_set admin_tagset; u32 __iomem *dbs; - struct pci_dev *pci_dev; + struct device *dev; struct dma_pool *prp_page_pool; struct dma_pool *prp_small_pool; int instance; @@ -92,6 +92,7 @@ struct nvme_dev { work_func_t reset_workfn; struct work_struct reset_work; struct work_struct probe_work; + struct work_struct scan_work; char name[12]; char serial[20]; char model[40]; @@ -146,25 +147,15 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) return (sector >> (ns->lba_shift - 9)); } -/** - * nvme_free_iod - frees an nvme_iod - * @dev: The device that the I/O was submitted to - * @iod: The memory to free - */ -void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod); - -int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int, gfp_t); -struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, - unsigned long addr, unsigned length); -void nvme_unmap_user_pages(struct nvme_dev *dev, int write, - struct nvme_iod *iod); -int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_ns *, - struct nvme_command *, u32 *); -int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns); -int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *, - u32 *result); -int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns, - dma_addr_t dma_addr); +int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, + void *buf, unsigned bufflen); +int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, + void *buffer, void __user *ubuffer, unsigned bufflen, + u32 *result, unsigned timeout); +int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id); +int nvme_identify_ns(struct nvme_dev *dev, unsigned nsid, + struct nvme_id_ns **id); +int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log); int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid, dma_addr_t dma_addr, u32 *result); int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, diff --git a/include/linux/nx842.h b/include/linux/nx842.h deleted file mode 100644 index a4d324c6406a..000000000000 --- a/include/linux/nx842.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __NX842_H__ -#define __NX842_H__ - -int nx842_get_workmem_size(void); -int nx842_get_workmem_size_aligned(void); -int nx842_compress(const unsigned char *in, unsigned int in_len, - unsigned char *out, unsigned int *out_len, void *wrkmem); -int nx842_decompress(const unsigned char *in, unsigned int in_len, - unsigned char *out, unsigned int *out_len, void *wrkmem); - -#endif diff --git a/include/linux/of.h b/include/linux/of.h index ddeaae6d2083..edc068d19c79 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -120,13 +120,21 @@ extern struct device_node *of_aliases; extern struct device_node *of_stdout; extern raw_spinlock_t devtree_lock; +/* flag descriptions (need to be visible even when !CONFIG_OF) */ +#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ +#define OF_DETACHED 2 /* node has been detached from the device tree */ +#define OF_POPULATED 3 /* device already created for the node */ +#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ + #ifdef CONFIG_OF +void of_core_init(void); + static inline bool is_of_node(struct fwnode_handle *fwnode) { return fwnode && fwnode->type == FWNODE_OF; } -static inline struct device_node *of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) { return fwnode ? container_of(fwnode, struct device_node, fwnode) : NULL; } @@ -217,12 +225,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) #endif -/* flag descriptions */ -#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ -#define OF_DETACHED 2 /* node has been detached from the device tree */ -#define OF_POPULATED 3 /* device already created for the node */ -#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) @@ -376,12 +378,16 @@ bool of_console_check(struct device_node *dn, char *name, int index); #else /* CONFIG_OF */ +static inline void of_core_init(void) +{ +} + static inline bool is_of_node(struct fwnode_handle *fwnode) { return false; } -static inline struct device_node *of_node(struct fwnode_handle *fwnode) +static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) { return NULL; } @@ -422,6 +428,11 @@ static inline struct device_node *of_find_node_opts_by_path(const char *path, return NULL; } +static inline struct device_node *of_find_node_by_phandle(phandle handle) +{ + return NULL; +} + static inline struct device_node *of_get_parent(const struct device_node *node) { return NULL; @@ -667,7 +678,10 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag #if defined(CONFIG_OF) && defined(CONFIG_NUMA) extern int of_node_to_nid(struct device_node *np); #else -static inline int of_node_to_nid(struct device_node *device) { return 0; } +static inline int of_node_to_nid(struct device_node *device) +{ + return NUMA_NO_NODE; +} #endif static inline struct device_node *of_find_matching_node( @@ -815,7 +829,7 @@ static inline int of_property_read_string_index(struct device_node *np, * @propname: name of the property to be searched. * * Search for a property in a device node. - * Returns true if the property exist false otherwise. + * Returns true if the property exists false otherwise. */ static inline bool of_property_read_bool(const struct device_node *np, const char *propname) diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 22801b10cef5..cc7dd687a89d 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -33,6 +33,8 @@ extern int of_device_add(struct platform_device *pdev); extern int of_device_register(struct platform_device *ofdev); extern void of_device_unregister(struct platform_device *ofdev); +extern const void *of_device_get_match_data(const struct device *dev); + extern ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len); @@ -57,7 +59,7 @@ void of_dma_configure(struct device *dev, struct device_node *np); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, - struct device_driver *drv) + const struct device_driver *drv) { return 0; } @@ -65,6 +67,11 @@ static inline int of_driver_match_device(struct device *dev, static inline void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) { } +static inline const void *of_device_get_match_data(const struct device *dev) +{ + return NULL; +} + static inline int of_device_get_modalias(struct device *dev, char *str, ssize_t len) { diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index 56bc026c143f..98ba7525929e 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -23,6 +23,9 @@ struct of_dma { struct device_node *of_node; struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *); + struct dma_router *dma_router; void *of_dma_data; }; @@ -37,12 +40,20 @@ extern int of_dma_controller_register(struct device_node *np, (struct of_phandle_args *, struct of_dma *), void *data); extern void of_dma_controller_free(struct device_node *np); + +extern int of_dma_router_register(struct device_node *np, + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *), + struct dma_router *dma_router); +#define of_dma_router_free of_dma_controller_free + extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); extern struct dma_chan *of_dma_xlate_by_chan_id(struct of_phandle_args *dma_spec, struct of_dma *ofdma); + #else static inline int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) @@ -56,6 +67,16 @@ static inline void of_dma_controller_free(struct device_node *np) { } +static inline int of_dma_router_register(struct device_node *np, + void *(*of_dma_route_allocate) + (struct of_phandle_args *, struct of_dma *), + struct dma_router *dma_router) +{ + return -ENODEV; +} + +#define of_dma_router_free of_dma_controller_free + static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name) { diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 587ee507965d..df9ef3801812 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -37,7 +37,7 @@ extern bool of_fdt_is_big_endian(const void *blob, unsigned long node); extern int of_fdt_match(const void *blob, unsigned long node, const char *const *compat); -extern void of_fdt_unflatten_tree(unsigned long *blob, +extern void of_fdt_unflatten_tree(const unsigned long *blob, struct device_node **mynodes); /* TBD: Temporary export of fdt globals - remove when code fully merged */ @@ -64,6 +64,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_fdt_scan_reserved_mem(void); +extern void early_init_fdt_reserve_self(void); extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool no_map); @@ -91,6 +92,7 @@ extern u64 fdt_translate_address(const void *blob, int node_offset); extern void of_fdt_limit_memory(int limit); #else /* CONFIG_OF_FLATTREE */ static inline void early_init_fdt_scan_reserved_mem(void) {} +static inline void early_init_fdt_reserve_self(void) {} static inline const char *of_flat_dt_get_machine_name(void) { return NULL; } static inline void unflatten_device_tree(void) {} static inline void unflatten_and_copy_device_tree(void) {} diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index 7bc92e050608..f8bcd0e21a26 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -45,6 +45,8 @@ int of_graph_parse_endpoint(const struct device_node *node, struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); +struct device_node *of_graph_get_endpoint_by_regs( + const struct device_node *parent, int port_reg, int reg); struct device_node *of_graph_get_remote_port_parent( const struct device_node *node); struct device_node *of_graph_get_remote_port(const struct device_node *node); @@ -69,6 +71,12 @@ static inline struct device_node *of_graph_get_next_endpoint( return NULL; } +static inline struct device_node *of_graph_get_endpoint_by_regs( + const struct device_node *parent, int port_reg, int reg) +{ + return NULL; +} + static inline struct device_node *of_graph_get_remote_port_parent( const struct device_node *node) { diff --git a/include/linux/oom.h b/include/linux/oom.h index 44b2f6f7bbd8..7deecb7bca5e 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -32,6 +32,8 @@ enum oom_scan_t { /* Thread is the potential origin of an oom condition; kill first on oom */ #define OOM_FLAG_ORIGIN ((__force oom_flags_t)0x1) +extern struct mutex oom_lock; + static inline void set_current_oom_origin(void) { current->signal->oom_flags |= OOM_FLAG_ORIGIN; @@ -47,9 +49,7 @@ static inline bool oom_task_origin(const struct task_struct *p) return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); } -extern void mark_tsk_oom_victim(struct task_struct *tsk); - -extern void unmark_oom_victim(void); +extern void mark_oom_victim(struct task_struct *tsk); extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, @@ -62,9 +62,6 @@ extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, struct mem_cgroup *memcg, nodemask_t *nodemask, const char *message); -extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags); -extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags); - extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, int order, const nodemask_t *nodemask, struct mem_cgroup *memcg); @@ -75,6 +72,9 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); + +extern void exit_oom_victim(void); + extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 3a6490e81b28..703ea5c30a33 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) extern bool osq_lock(struct optimistic_spin_queue *lock); extern void osq_unlock(struct optimistic_spin_queue *lock); +static inline bool osq_is_locked(struct optimistic_spin_queue *lock) +{ + return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL; +} + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f34e040b34e9..41c93844fb1d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -631,15 +631,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + 1 << PG_unevictable | __PG_MLOCKED | \ __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have any flags set. It they are set, + * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. + * + * __PG_HWPOISON is exceptional because it needs to be kept beyond page's + * alloc-free cycle to prevent from reusing the page. */ -#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) +#define PAGE_FLAGS_CHECK_AT_PREP \ + (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1 << PG_private | 1 << PG_private_2) diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index b48c3471c254..cacaabea8a09 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -8,6 +8,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); +extern gfp_t __get_page_owner_gfp(struct page *page); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -25,6 +26,14 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } + +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + if (likely(!page_owner_inited)) + return 0; + + return __get_page_owner_gfp(page); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -33,6 +42,10 @@ static inline void set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { } +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + return 0; +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4b3736f7065c..a6c78e00ea96 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -651,7 +651,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +extern void __delete_from_page_cache(struct page *page, void *shadow, + struct mem_cgroup *memcg); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* @@ -670,4 +671,10 @@ static inline int add_to_page_cache(struct page *page, return error; } +static inline unsigned long dir_pages(struct inode *inode) +{ + return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; +} + #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/parport.h b/include/linux/parport.h index c22f12547324..58e3c64c6b49 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -13,6 +13,7 @@ #include <linux/wait.h> #include <linux/irqreturn.h> #include <linux/semaphore.h> +#include <linux/device.h> #include <asm/ptrace.h> #include <uapi/linux/parport.h> @@ -145,6 +146,8 @@ struct pardevice { unsigned int flags; struct pardevice *next; struct pardevice *prev; + struct device dev; + bool devmodel; struct parport_state *state; /* saved status over preemption */ wait_queue_head_t wait_q; unsigned long int time; @@ -156,6 +159,8 @@ struct pardevice { void * sysctl_table; }; +#define to_pardevice(n) container_of(n, struct pardevice, dev) + /* IEEE1284 information */ /* IEEE1284 phases. These are exposed to userland through ppdev IOCTL @@ -195,7 +200,7 @@ struct parport { * This may unfortulately be null if the * port has a legacy driver. */ - + struct device bus_dev; /* to link with the bus */ struct parport *physport; /* If this is a non-default mux parport, i.e. we're a clone of a real @@ -245,15 +250,26 @@ struct parport { struct parport *slaves[3]; }; +#define to_parport_dev(n) container_of(n, struct parport, bus_dev) + #define DEFAULT_SPIN_TIME 500 /* us */ struct parport_driver { const char *name; void (*attach) (struct parport *); void (*detach) (struct parport *); + void (*match_port)(struct parport *); + int (*probe)(struct pardevice *); + struct device_driver driver; + bool devmodel; struct list_head list; }; +#define to_parport_driver(n) container_of(n, struct parport_driver, driver) + +int parport_bus_init(void); +void parport_bus_exit(void); + /* parport_register_port registers a new parallel port at the given address (if one does not already exist) and returns a pointer to it. This entails claiming the I/O region, IRQ and DMA. NULL is returned @@ -272,10 +288,20 @@ void parport_announce_port (struct parport *port); extern void parport_remove_port(struct parport *port); /* Register a new high-level driver. */ -extern int parport_register_driver (struct parport_driver *); + +int __must_check __parport_register_driver(struct parport_driver *, + struct module *, + const char *mod_name); +/* + * parport_register_driver must be a macro so that KBUILD_MODNAME can + * be expanded + */ +#define parport_register_driver(driver) \ + __parport_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) /* Unregister a high-level driver. */ extern void parport_unregister_driver (struct parport_driver *); +void parport_unregister_driver(struct parport_driver *); /* If parport_register_driver doesn't fit your needs, perhaps * parport_find_xxx does. */ @@ -288,6 +314,15 @@ extern irqreturn_t parport_irq_handler(int irq, void *dev_id); /* Reference counting for ports. */ extern struct parport *parport_get_port (struct parport *); extern void parport_put_port (struct parport *); +void parport_del_port(struct parport *); + +struct pardev_cb { + int (*preempt)(void *); + void (*wakeup)(void *); + void *private; + void (*irq_func)(void *); + unsigned int flags; +}; /* parport_register_device declares that a device is connected to a port, and tells the kernel all it needs to know. @@ -301,6 +336,10 @@ struct pardevice *parport_register_device(struct parport *port, void (*irq_func)(void *), int flags, void *handle); +struct pardevice * +parport_register_dev_model(struct parport *port, const char *name, + const struct pardev_cb *par_dev_cb, int cnt); + /* parport_unregister unlinks a device from the chain. */ extern void parport_unregister_device(struct pardevice *dev); diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h index 3cc21c9cc1e8..9fade5dd2e86 100644 --- a/include/linux/pata_arasan_cf_data.h +++ b/include/linux/pata_arasan_cf_data.h @@ -4,7 +4,7 @@ * Arasan Compact Flash host controller platform data header file * * Copyright (C) 2011 ST Microelectronics - * Viresh Kumar <viresh.linux@gmail.com> + * Viresh Kumar <vireshk@kernel.org> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/include/linux/pci.h b/include/linux/pci.h index 353db8dc4c6e..8a0321a8fb59 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -355,6 +355,7 @@ struct pci_dev { unsigned int broken_intx_masking:1; unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ unsigned int irq_managed:1; + unsigned int has_secondary_link:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -577,9 +578,15 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 val); +#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT +typedef u64 pci_bus_addr_t; +#else +typedef u32 pci_bus_addr_t; +#endif + struct pci_bus_region { - dma_addr_t start; - dma_addr_t end; + pci_bus_addr_t start; + pci_bus_addr_t end; }; struct pci_dynids { @@ -773,8 +780,6 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res, void pcibios_scan_specific_bus(int busn); struct pci_bus *pci_find_bus(int domain, int busnr); void pci_bus_add_devices(const struct pci_bus *bus); -struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus, - struct pci_ops *ops, void *sysdata); struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata); struct pci_bus *pci_create_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, @@ -974,7 +979,6 @@ void pci_intx(struct pci_dev *dev, int enable); bool pci_intx_mask_supported(struct pci_dev *dev); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); -void pci_msi_off(struct pci_dev *dev); int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask); @@ -1006,6 +1010,7 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); +void pci_ignore_hotplug(struct pci_dev *dev); /* ROM control related routines */ int pci_enable_rom(struct pci_dev *pdev); @@ -1043,11 +1048,6 @@ bool pci_dev_run_wake(struct pci_dev *dev); bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); -static inline void pci_ignore_hotplug(struct pci_dev *dev) -{ - dev->ignore_hotplug = 1; -} - static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { @@ -1128,7 +1128,7 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); -static inline dma_addr_t pci_bus_address(struct pci_dev *pdev, int bar) +static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar) { struct pci_bus_region region; @@ -1197,15 +1197,6 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle) #define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr) -enum pci_dma_burst_strategy { - PCI_DMA_BURST_INFINITY, /* make bursts as large as possible, - strategy_parameter is N/A */ - PCI_DMA_BURST_BOUNDARY, /* disconnect at every strategy_parameter - byte boundaries */ - PCI_DMA_BURST_MULTIPLE, /* disconnect at some multiple of - strategy_parameter byte boundaries */ -}; - struct msix_entry { u32 vector; /* kernel uses to write allocated vector */ u16 entry; /* driver uses to specify entry, OS writes */ @@ -1430,8 +1421,6 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; } static inline void pci_release_regions(struct pci_dev *dev) { } -#define pci_dma_burst_advice(pdev, strat, strategy_parameter) do { } while (0) - static inline void pci_block_cfg_access(struct pci_dev *dev) { } static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev) { return 0; } @@ -1905,4 +1894,15 @@ static inline bool pci_is_dev_assigned(struct pci_dev *pdev) { return (pdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) == PCI_DEV_FLAGS_ASSIGNED; } + +/** + * pci_ari_enabled - query ARI forwarding status + * @bus: the PCI bus + * + * Returns true if ARI forwarding is enabled. + */ +static inline bool pci_ari_enabled(struct pci_bus *bus) +{ + return bus->self && bus->self->ari_enabled; +} #endif /* LINUX_PCI_H */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2f7b9a40f627..fcff8f865341 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -579,6 +579,7 @@ #define PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE 0x7800 #define PCI_DEVICE_ID_AMD_HUDSON2_SMBUS 0x780b #define PCI_DEVICE_ID_AMD_HUDSON2_IDE 0x780c +#define PCI_DEVICE_ID_AMD_KERNCZ_SMBUS 0x790b #define PCI_VENDOR_ID_TRIDENT 0x1023 #define PCI_DEVICE_ID_TRIDENT_4DWAVE_DX 0x2000 @@ -2329,6 +2330,8 @@ #define PCI_DEVICE_ID_ALTIMA_AC9100 0x03ea #define PCI_DEVICE_ID_ALTIMA_AC1003 0x03eb +#define PCI_VENDOR_ID_CAVIUM 0x177d + #define PCI_VENDOR_ID_BELKIN 0x1799 #define PCI_DEVICE_ID_BELKIN_F5D7010V7 0x701f diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 50e50095c8d1..84a109449610 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -41,7 +41,12 @@ void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); -int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs); +int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); + +static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) +{ + return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); +} static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -116,6 +121,12 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) return 0; } +static inline int +__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) +{ + return percpu_counter_compare(fbc, rhs); +} + static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61992cf2e977..2027809433b3 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -92,8 +92,6 @@ struct hw_perf_event_extra { int idx; /* index in shared_regs->regs[] */ }; -struct event_constraint; - /** * struct hw_perf_event - performance event hardware details: */ @@ -112,8 +110,6 @@ struct hw_perf_event { struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; - - struct event_constraint *constraint; }; struct { /* software */ struct hrtimer hrtimer; @@ -124,7 +120,7 @@ struct hw_perf_event { }; struct { /* intel_cqm */ int cqm_state; - int cqm_rmid; + u32 cqm_rmid; struct list_head cqm_events_entry; struct list_head cqm_groups_entry; struct list_head cqm_group_entry; @@ -304,6 +300,11 @@ struct pmu { * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ + + /* + * Filter events for PMU-specific reasons. + */ + int (*filter_match) (struct perf_event *event); /* optional */ }; /** @@ -483,7 +484,7 @@ struct perf_event { void *overflow_handler_context; #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call *tp_event; + struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; @@ -566,8 +567,12 @@ struct perf_cpu_context { struct perf_event_context *task_ctx; int active_oncpu; int exclusive; + + raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; + unsigned int hrtimer_active; + struct pmu *unique_pmu; struct perf_cgroup *cgrp; }; @@ -734,6 +739,22 @@ extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); +extern void perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); + +extern void +perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event); +extern void +perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample); + +extern void +perf_log_lost_samples(struct perf_event *event, u64 lost); + static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; @@ -798,11 +819,33 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) extern struct static_key_deferred perf_sched_events; +static __always_inline bool +perf_sw_migrate_enabled(void) +{ + if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) + return true; + return false; +} + +static inline void perf_event_task_migrate(struct task_struct *task) +{ + if (perf_sw_migrate_enabled()) + task->sched_migrated = 1; +} + static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_in(prev, task); + + if (perf_sw_migrate_enabled() && task->sched_migrated) { + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); + + perf_fetch_caller_regs(regs); + ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); + task->sched_migrated = 0; + } } static inline void perf_event_task_sched_out(struct task_struct *prev, @@ -925,6 +968,8 @@ perf_aux_output_skip(struct perf_output_handle *handle, static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void +perf_event_task_migrate(struct task_struct *task) { } +static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void diff --git a/include/linux/phy.h b/include/linux/phy.h index 685809835b5c..a26c3f84b8dd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -181,6 +181,9 @@ struct mii_bus { /* PHY addresses to be ignored when probing */ u32 phy_mask; + /* PHY addresses to ignore the TA/read failure */ + u32 phy_ignore_ta_mask; + /* * Pointer to an array of interrupts, each PHY's * interrupt at the index matching its address @@ -675,6 +678,17 @@ static inline bool phy_is_internal(struct phy_device *phydev) } /** + * phy_interface_is_rgmii - Convenience function for testing if a PHY interface + * is RGMII (all variants) + * @phydev: the phy_device struct + */ +static inline bool phy_interface_is_rgmii(struct phy_device *phydev) +{ + return phydev->interface >= PHY_INTERFACE_MODE_RGMII && + phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; +} + +/** * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct diff --git a/include/linux/phy/phy-sun4i-usb.h b/include/linux/phy/phy-sun4i-usb.h new file mode 100644 index 000000000000..50aed92ea89c --- /dev/null +++ b/include/linux/phy/phy-sun4i-usb.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2015 Hans de Goede <hdegoede@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef PHY_SUN4I_USB_H_ +#define PHY_SUN4I_USB_H_ + +#include "phy.h" + +/** + * sun4i_usb_phy_set_squelch_detect() - Enable/disable squelch detect + * @phy: reference to a sun4i usb phy + * @enabled: wether to enable or disable squelch detect + */ +void sun4i_usb_phy_set_squelch_detect(struct phy *phy, bool enabled); + +#endif diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index a0197fa1b116..8cf05e341cff 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -133,6 +133,8 @@ struct phy *devm_phy_get(struct device *dev, const char *string); struct phy *devm_phy_optional_get(struct device *dev, const char *string); struct phy *devm_of_phy_get(struct device *dev, struct device_node *np, const char *con_id); +struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, + int index); void phy_put(struct phy *phy); void devm_phy_put(struct device *dev, struct phy *phy); struct phy *of_phy_get(struct device_node *np, const char *con_id); @@ -261,6 +263,13 @@ static inline struct phy *devm_of_phy_get(struct device *dev, return ERR_PTR(-ENOSYS); } +static inline struct phy *devm_of_phy_get_by_index(struct device *dev, + struct device_node *np, + int index) +{ + return ERR_PTR(-ENOSYS); +} + static inline void phy_put(struct phy *phy) { } diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 18eccefea06e..d7e5d608faa7 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -142,7 +142,7 @@ static inline struct pinctrl * __must_check pinctrl_get_select( s = pinctrl_lookup_state(p, name); if (IS_ERR(s)) { pinctrl_put(p); - return ERR_PTR(PTR_ERR(s)); + return ERR_CAST(s); } ret = pinctrl_select_state(p, s); diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 66e4697516de..9ba59fcba549 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -127,7 +127,7 @@ struct pinctrl_ops { */ struct pinctrl_desc { const char *name; - struct pinctrl_pin_desc const *pins; + const struct pinctrl_pin_desc *pins; unsigned int npins; const struct pinctrl_ops *pctlops; const struct pinmux_ops *pmxops; diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h index 511bda9ed4bf..ace60d775b20 100644 --- a/include/linux/pinctrl/pinmux.h +++ b/include/linux/pinctrl/pinmux.h @@ -56,6 +56,9 @@ struct pinctrl_dev; * depending on whether the GPIO is configured as input or output, * a direction selector function may be implemented as a backing * to the GPIO controllers that need pin muxing. + * @strict: do not allow simultaneous use of the same pin for GPIO and another + * function. Check both gpio_owner and mux_owner strictly before approving + * the pin request. */ struct pinmux_ops { int (*request) (struct pinctrl_dev *pctldev, unsigned offset); @@ -66,7 +69,7 @@ struct pinmux_ops { int (*get_function_groups) (struct pinctrl_dev *pctldev, unsigned selector, const char * const **groups, - unsigned * const num_groups); + unsigned *num_groups); int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector, unsigned group_selector); int (*gpio_request_enable) (struct pinctrl_dev *pctldev, @@ -79,6 +82,7 @@ struct pinmux_ops { struct pinctrl_gpio_range *range, unsigned offset, bool input); + bool strict; }; #endif /* CONFIG_PINMUX */ diff --git a/include/linux/platform_data/dma-rcar-audmapp.h b/include/linux/platform_data/dma-rcar-audmapp.h deleted file mode 100644 index 471fffebbeb4..000000000000 --- a/include/linux/platform_data/dma-rcar-audmapp.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * This is for Renesas R-Car Audio-DMAC-peri-peri. - * - * Copyright (C) 2014 Renesas Electronics Corporation - * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> - * - * This file is based on the include/linux/sh_dma.h - * - * Header for the new SH dmaengine driver - * - * Copyright (C) 2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef SH_AUDMAPP_H -#define SH_AUDMAPP_H - -#include <linux/dmaengine.h> - -struct audmapp_slave_config { - int slave_id; - dma_addr_t src; - dma_addr_t dst; - u32 chcr; -}; - -struct audmapp_pdata { - struct audmapp_slave_config *slave; - int slave_num; -}; - -#endif /* SH_AUDMAPP_H */ diff --git a/include/linux/platform_data/gpio-ath79.h b/include/linux/platform_data/gpio-ath79.h new file mode 100644 index 000000000000..88b0db7bee74 --- /dev/null +++ b/include/linux/platform_data/gpio-ath79.h @@ -0,0 +1,19 @@ +/* + * Atheros AR7XXX/AR9XXX GPIO controller platform data + * + * Copyright (C) 2015 Alban Bedel <albeu@free.fr> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_PLATFORM_DATA_GPIO_ATH79_H +#define __LINUX_PLATFORM_DATA_GPIO_ATH79_H + +struct ath79_gpio_platform_data { + unsigned ngpios; + bool oe_inverted; +}; + +#endif diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 5d50b25a73d7..cb2618147c34 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -208,9 +208,17 @@ struct omap_gpio_platform_data { int (*get_context_loss_count)(struct device *dev); }; +#if IS_BUILTIN(CONFIG_GPIO_OMAP) extern void omap2_gpio_prepare_for_idle(int off_mode); extern void omap2_gpio_resume_after_idle(void); -extern void omap_set_gpio_debounce(int gpio, int enable); -extern void omap_set_gpio_debounce_time(int gpio, int enable); +#else +static inline void omap2_gpio_prepare_for_idle(int off_mode) +{ +} + +static inline void omap2_gpio_resume_after_idle(void) +{ +} +#endif #endif diff --git a/include/linux/platform_data/irq-renesas-irqc.h b/include/linux/platform_data/irq-renesas-irqc.h deleted file mode 100644 index 3ae17b3e00ed..000000000000 --- a/include/linux/platform_data/irq-renesas-irqc.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Renesas IRQC Driver - * - * Copyright (C) 2013 Magnus Damm - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef __IRQ_RENESAS_IRQC_H__ -#define __IRQ_RENESAS_IRQC_H__ - -struct renesas_irqc_config { - unsigned int irq_base; -}; - -#endif /* __IRQ_RENESAS_IRQC_H__ */ diff --git a/include/linux/platform_data/keyboard-spear.h b/include/linux/platform_data/keyboard-spear.h index 9248e3a7e333..5e3ff653900c 100644 --- a/include/linux/platform_data/keyboard-spear.h +++ b/include/linux/platform_data/keyboard-spear.h @@ -1,6 +1,6 @@ /* * Copyright (C) 2010 ST Microelectronics - * Rajeev Kumar<rajeev-dlh.kumar@st.com> + * Rajeev Kumar <rajeevkumar.linux@gmail.com> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 044a124bfbbc..21b15f6fee25 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,11 +8,19 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +/** + * struct macb_platform_data - platform data for MACB Ethernet + * @phy_mask: phy mask passed when register the MDIO bus + * within the driver + * @phy_irq_pin: PHY IRQ + * @is_rmii: using RMII interface? + * @rev_eth_addr: reverse Ethernet address byte order + */ struct macb_platform_data { u32 phy_mask; - int phy_irq_pin; /* PHY IRQ */ - u8 is_rmii; /* using RMII interface? */ - u8 rev_eth_addr; /* reverse Ethernet address byte order */ + int phy_irq_pin; + u8 is_rmii; + u8 rev_eth_addr; }; #endif /* __MACB_PDATA_H__ */ diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 75f70f6ac137..e1571efa3f2b 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -43,7 +43,6 @@ struct esdhc_platform_data { enum wp_types wp_type; enum cd_types cd_type; int max_bus_width; - unsigned int f_max; bool support_vsel; unsigned int delay_line; }; diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h new file mode 100644 index 000000000000..ac91707dabcb --- /dev/null +++ b/include/linux/platform_data/nfcmrvl.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2015, Marvell International Ltd. + * + * This software file (the "File") is distributed by Marvell International + * Ltd. under the terms of the GNU General Public License Version 2, June 1991 + * (the "License"). You may use, redistribute and/or modify this File in + * accordance with the terms and conditions of the License, a copy of which + * is available on the worldwide web at + * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. + * + * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE + * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE + * ARE EXPRESSLY DISCLAIMED. The License provides additional details about + * this warranty disclaimer. + */ + +#ifndef _NFCMRVL_PTF_H_ +#define _NFCMRVL_PTF_H_ + +struct nfcmrvl_platform_data { + /* + * Generic + */ + + /* GPIO that is wired to RESET_N signal */ + unsigned int reset_n_io; + /* Tell if transport is muxed in HCI one */ + unsigned int hci_muxed; + + /* + * UART specific + */ + + /* Tell if UART needs flow control at init */ + unsigned int flow_control; + /* Tell if firmware supports break control for power management */ + unsigned int break_control; +}; + +#endif /* _NFCMRVL_PTF_H_ */ diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h index 0a6de4ca4930..aed170588b74 100644 --- a/include/linux/platform_data/ntc_thermistor.h +++ b/include/linux/platform_data/ntc_thermistor.h @@ -27,6 +27,7 @@ enum ntc_thermistor_type { TYPE_NCPXXWB473, TYPE_NCPXXWL333, TYPE_B57330V2103, + TYPE_NCPXXWF104, }; struct ntc_thermistor_platform_data { diff --git a/include/linux/platform_data/si5351.h b/include/linux/platform_data/si5351.h index a947ab8b441a..533d9807e543 100644 --- a/include/linux/platform_data/si5351.h +++ b/include/linux/platform_data/si5351.h @@ -5,8 +5,6 @@ #ifndef __LINUX_PLATFORM_DATA_SI5351_H__ #define __LINUX_PLATFORM_DATA_SI5351_H__ -struct clk; - /** * enum si5351_pll_src - Si5351 pll clock source * @SI5351_PLL_SRC_DEFAULT: default, do not change eeprom config @@ -107,8 +105,6 @@ struct si5351_clkout_config { * @clkout: array of clkout configuration */ struct si5351_platform_data { - struct clk *clk_xtal; - struct clk *clk_clkin; enum si5351_pll_src pll_src[2]; struct si5351_clkout_config clkout[8]; }; diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st-nci.h index b023373d9874..d9d400a297bd 100644 --- a/include/linux/platform_data/st21nfcb.h +++ b/include/linux/platform_data/st-nci.h @@ -1,7 +1,7 @@ /* - * Driver include for the ST21NFCB NFC chip. + * Driver include for ST NCI NFC chip family. * - * Copyright (C) 2014 STMicroelectronics SAS. All rights reserved. + * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -16,14 +16,14 @@ * along with this program; if not, see <http://www.gnu.org/licenses/>. */ -#ifndef _ST21NFCB_NCI_H_ -#define _ST21NFCB_NCI_H_ +#ifndef _ST_NCI_H_ +#define _ST_NCI_H_ -#define ST21NFCB_NCI_DRIVER_NAME "st21nfcb_nci" +#define ST_NCI_DRIVER_NAME "st_nci" -struct st21nfcb_nfc_platform_data { +struct st_nci_nfc_platform_data { unsigned int gpio_reset; unsigned int irq_polarity; }; -#endif /* _ST21NFCB_NCI_H_ */ +#endif /* _ST_NCI_H_ */ diff --git a/include/linux/platform_data/st_nci.h b/include/linux/platform_data/st_nci.h new file mode 100644 index 000000000000..d9d400a297bd --- /dev/null +++ b/include/linux/platform_data/st_nci.h @@ -0,0 +1,29 @@ +/* + * Driver include for ST NCI NFC chip family. + * + * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ST_NCI_H_ +#define _ST_NCI_H_ + +#define ST_NCI_DRIVER_NAME "st_nci" + +struct st_nci_nfc_platform_data { + unsigned int gpio_reset; + unsigned int irq_polarity; +}; + +#endif /* _ST_NCI_H_ */ diff --git a/include/linux/platform_data/usb-rcar-gen2-phy.h b/include/linux/platform_data/usb-rcar-gen2-phy.h deleted file mode 100644 index dd3ba46c0d90..000000000000 --- a/include/linux/platform_data/usb-rcar-gen2-phy.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * Copyright (C) 2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __USB_RCAR_GEN2_PHY_H -#define __USB_RCAR_GEN2_PHY_H - -#include <linux/types.h> - -struct rcar_gen2_phy_platform_data { - /* USB channel 0 configuration */ - bool chan0_pci:1; /* true: PCI USB host 0, false: USBHS */ - /* USB channel 2 configuration */ - bool chan2_pci:1; /* true: PCI USB host 2, false: USBSS */ -}; - -#endif diff --git a/include/linux/platform_data/video-msm_fb.h b/include/linux/platform_data/video-msm_fb.h deleted file mode 100644 index 31449be3eadb..000000000000 --- a/include/linux/platform_data/video-msm_fb.h +++ /dev/null @@ -1,146 +0,0 @@ -/* - * Internal shared definitions for various MSM framebuffer parts. - * - * Copyright (C) 2007 Google Incorporated - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _MSM_FB_H_ -#define _MSM_FB_H_ - -#include <linux/device.h> - -struct mddi_info; - -struct msm_fb_data { - int xres; /* x resolution in pixels */ - int yres; /* y resolution in pixels */ - int width; /* disply width in mm */ - int height; /* display height in mm */ - unsigned output_format; -}; - -struct msmfb_callback { - void (*func)(struct msmfb_callback *); -}; - -enum { - MSM_MDDI_PMDH_INTERFACE, - MSM_MDDI_EMDH_INTERFACE, - MSM_EBI2_INTERFACE, -}; - -#define MSMFB_CAP_PARTIAL_UPDATES (1 << 0) - -struct msm_panel_data { - /* turns off the fb memory */ - int (*suspend)(struct msm_panel_data *); - /* turns on the fb memory */ - int (*resume)(struct msm_panel_data *); - /* turns off the panel */ - int (*blank)(struct msm_panel_data *); - /* turns on the panel */ - int (*unblank)(struct msm_panel_data *); - void (*wait_vsync)(struct msm_panel_data *); - void (*request_vsync)(struct msm_panel_data *, struct msmfb_callback *); - void (*clear_vsync)(struct msm_panel_data *); - /* from the enum above */ - unsigned interface_type; - /* data to be passed to the fb driver */ - struct msm_fb_data *fb_data; - - /* capabilities supported by the panel */ - uint32_t caps; -}; - -struct msm_mddi_client_data { - void (*suspend)(struct msm_mddi_client_data *); - void (*resume)(struct msm_mddi_client_data *); - void (*activate_link)(struct msm_mddi_client_data *); - void (*remote_write)(struct msm_mddi_client_data *, uint32_t val, - uint32_t reg); - uint32_t (*remote_read)(struct msm_mddi_client_data *, uint32_t reg); - void (*auto_hibernate)(struct msm_mddi_client_data *, int); - /* custom data that needs to be passed from the board file to a - * particular client */ - void *private_client_data; - struct resource *fb_resource; - /* from the list above */ - unsigned interface_type; -}; - -struct msm_mddi_platform_data { - unsigned int clk_rate; - void (*power_client)(struct msm_mddi_client_data *, int on); - - /* fixup the mfr name, product id */ - void (*fixup)(uint16_t *mfr_name, uint16_t *product_id); - - struct resource *fb_resource; /*optional*/ - /* number of clients in the list that follows */ - int num_clients; - /* array of client information of clients */ - struct { - unsigned product_id; /* mfr id in top 16 bits, product id - * in lower 16 bits - */ - char *name; /* the device name will be the platform - * device name registered for the client, - * it should match the name of the associated - * driver - */ - unsigned id; /* id for mddi client device node, will also - * be used as device id of panel devices, if - * the client device will have multiple panels - * space must be left here for them - */ - void *client_data; /* required private client data */ - unsigned int clk_rate; /* optional: if the client requires a - * different mddi clk rate - */ - } client_platform_data[]; -}; - -struct mdp_blit_req; -struct fb_info; -struct mdp_device { - struct device dev; - void (*dma)(struct mdp_device *mpd, uint32_t addr, - uint32_t stride, uint32_t w, uint32_t h, uint32_t x, - uint32_t y, struct msmfb_callback *callback, int interface); - void (*dma_wait)(struct mdp_device *mdp); - int (*blit)(struct mdp_device *mdp, struct fb_info *fb, - struct mdp_blit_req *req); - void (*set_grp_disp)(struct mdp_device *mdp, uint32_t disp_id); -}; - -struct class_interface; -int register_mdp_client(struct class_interface *class_intf); - -/**** private client data structs go below this line ***/ - -struct msm_mddi_bridge_platform_data { - /* from board file */ - int (*init)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - int (*uninit)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - /* passed to panel for use by the fb driver */ - int (*blank)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - int (*unblank)(struct msm_mddi_bridge_platform_data *, - struct msm_mddi_client_data *); - struct msm_fb_data fb_data; -}; - - - -#endif diff --git a/include/linux/platform_data/wkup_m3.h b/include/linux/platform_data/wkup_m3.h new file mode 100644 index 000000000000..3f1d77effd71 --- /dev/null +++ b/include/linux/platform_data/wkup_m3.h @@ -0,0 +1,30 @@ +/* + * TI Wakeup M3 remote processor platform data + * + * Copyright (C) 2014-2015 Texas Instruments, Inc. + * + * Dave Gerlach <d-gerlach@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_PLATFORM_DATA_WKUP_M3_H +#define _LINUX_PLATFORM_DATA_WKUP_M3_H + +struct platform_device; + +struct wkup_m3_platform_data { + const char *reset_name; + + int (*assert_reset)(struct platform_device *pdev, const char *name); + int (*deassert_reset)(struct platform_device *pdev, const char *name); +}; + +#endif /* _LINUX_PLATFORM_DATA_WKUP_M3_H */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 58f1e75ba105..bba08f44cc97 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -222,6 +222,15 @@ static inline void platform_set_drvdata(struct platform_device *pdev, module_driver(__platform_driver, platform_driver_register, \ platform_driver_unregister) +/* builtin_platform_driver() - Helper macro for builtin drivers that + * don't do anything special in driver init. This eliminates some + * boilerplate. Each driver may only use this macro once, and + * calling it replaces device_initcall(). Note this is meant to be + * a parallel of module_platform_driver() above, but w/o _exit stuff. + */ +#define builtin_platform_driver(__platform_driver) \ + builtin_driver(__platform_driver, platform_driver_register) + /* module_platform_driver_probe() - Helper macro for drivers that don't do * anything special in module init/exit. This eliminates a lot of * boilerplate. Each module may only use this macro once, and @@ -240,6 +249,20 @@ static void __exit __platform_driver##_exit(void) \ } \ module_exit(__platform_driver##_exit); +/* builtin_platform_driver_probe() - Helper macro for drivers that don't do + * anything special in device init. This eliminates some boilerplate. Each + * driver may only use this macro once, and using it replaces device_initcall. + * This is meant to be a parallel of module_platform_driver_probe above, but + * without the __exit parts. + */ +#define builtin_platform_driver_probe(__platform_driver, __platform_probe) \ +static int __init __platform_driver##_init(void) \ +{ \ + return platform_driver_probe(&(__platform_driver), \ + __platform_probe); \ +} \ +device_initcall(__platform_driver##_init); \ + #define platform_create_bundle(driver, probe, res, n_res, data, size) \ __platform_create_bundle(driver, probe, res, n_res, data, size, THIS_MODULE) extern struct platform_device *__platform_create_bundle( diff --git a/include/linux/pm.h b/include/linux/pm.h index 2d29c64f8fb1..35d599e7250d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -342,6 +342,18 @@ struct dev_pm_ops { #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif +#ifdef CONFIG_PM_SLEEP +#define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_noirq = suspend_fn, \ + .resume_noirq = resume_fn, \ + .freeze_noirq = suspend_fn, \ + .thaw_noirq = resume_fn, \ + .poweroff_noirq = suspend_fn, \ + .restore_noirq = resume_fn, +#else +#define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) +#endif + #ifdef CONFIG_PM #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ .runtime_suspend = suspend_fn, \ @@ -529,6 +541,7 @@ enum rpm_request { }; struct wakeup_source; +struct wake_irq; struct pm_domain_data; struct pm_subsys_data { @@ -568,6 +581,7 @@ struct dev_pm_info { unsigned long timer_expires; struct work_struct work; wait_queue_head_t wait_queue; + struct wake_irq *wakeirq; atomic_t usage_count; atomic_t child_count; unsigned int disable_depth:3; diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 0b0039634410..25266c600021 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -20,6 +20,16 @@ struct pm_clk_notifier_block { struct clk; +#ifdef CONFIG_PM +extern int pm_clk_runtime_suspend(struct device *dev); +extern int pm_clk_runtime_resume(struct device *dev); +#define USE_PM_CLK_RUNTIME_OPS \ + .runtime_suspend = pm_clk_runtime_suspend, \ + .runtime_resume = pm_clk_runtime_resume, +#else +#define USE_PM_CLK_RUNTIME_OPS +#endif + #ifdef CONFIG_PM_CLK static inline bool pm_clk_no_clocks(struct device *dev) { diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h new file mode 100644 index 000000000000..cd5b62db9084 --- /dev/null +++ b/include/linux/pm_wakeirq.h @@ -0,0 +1,51 @@ +/* + * pm_wakeirq.h - Device wakeirq helper functions + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_PM_WAKEIRQ_H +#define _LINUX_PM_WAKEIRQ_H + +#ifdef CONFIG_PM + +extern int dev_pm_set_wake_irq(struct device *dev, int irq); +extern int dev_pm_set_dedicated_wake_irq(struct device *dev, + int irq); +extern void dev_pm_clear_wake_irq(struct device *dev); +extern void dev_pm_enable_wake_irq(struct device *dev); +extern void dev_pm_disable_wake_irq(struct device *dev); + +#else /* !CONFIG_PM */ + +static inline int dev_pm_set_wake_irq(struct device *dev, int irq) +{ + return 0; +} + +static inline int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) +{ + return 0; +} + +static inline void dev_pm_clear_wake_irq(struct device *dev) +{ +} + +static inline void dev_pm_enable_wake_irq(struct device *dev) +{ +} + +static inline void dev_pm_disable_wake_irq(struct device *dev) +{ +} + +#endif /* CONFIG_PM */ +#endif /* _LINUX_PM_WAKEIRQ_H */ diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index a0f70808d7f4..a3447932df1f 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -28,9 +28,17 @@ #include <linux/types.h> +struct wake_irq; + /** * struct wakeup_source - Representation of wakeup sources * + * @name: Name of the wakeup source + * @entry: Wakeup source list entry + * @lock: Wakeup source lock + * @wakeirq: Optional device specific wakeirq + * @timer: Wakeup timer list + * @timer_expires: Wakeup timer expiration * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. * @last_time: Monotonic clock when the wakeup source's was touched last time. @@ -47,6 +55,7 @@ struct wakeup_source { const char *name; struct list_head entry; spinlock_t lock; + struct wake_irq *wakeirq; struct timer_list timer; unsigned long timer_expires; ktime_t total_time; diff --git a/include/linux/pmem.h b/include/linux/pmem.h new file mode 100644 index 000000000000..d2114045a6c4 --- /dev/null +++ b/include/linux/pmem.h @@ -0,0 +1,152 @@ +/* + * Copyright(c) 2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __PMEM_H__ +#define __PMEM_H__ + +#include <linux/io.h> + +#ifdef CONFIG_ARCH_HAS_PMEM_API +#include <asm/cacheflush.h> +#else +static inline void arch_wmb_pmem(void) +{ + BUG(); +} + +static inline bool __arch_has_wmb_pmem(void) +{ + return false; +} + +static inline void __pmem *arch_memremap_pmem(resource_size_t offset, + unsigned long size) +{ + return NULL; +} + +static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t n) +{ + BUG(); +} +#endif + +/* + * Architectures that define ARCH_HAS_PMEM_API must provide + * implementations for arch_memremap_pmem(), arch_memcpy_to_pmem(), + * arch_wmb_pmem(), and __arch_has_wmb_pmem(). + */ + +static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) +{ + memcpy(dst, (void __force const *) src, size); +} + +static inline void memunmap_pmem(void __pmem *addr) +{ + iounmap((void __force __iomem *) addr); +} + +/** + * arch_has_wmb_pmem - true if wmb_pmem() ensures durability + * + * For a given cpu implementation within an architecture it is possible + * that wmb_pmem() resolves to a nop. In the case this returns + * false, pmem api users are unable to ensure durability and may want to + * fall back to a different data consistency model, or otherwise notify + * the user. + */ +static inline bool arch_has_wmb_pmem(void) +{ + if (IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API)) + return __arch_has_wmb_pmem(); + return false; +} + +static inline bool arch_has_pmem_api(void) +{ + return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && arch_has_wmb_pmem(); +} + +/* + * These defaults seek to offer decent performance and minimize the + * window between i/o completion and writes being durable on media. + * However, it is undefined / architecture specific whether + * default_memremap_pmem + default_memcpy_to_pmem is sufficient for + * making data durable relative to i/o completion. + */ +static void default_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t size) +{ + memcpy((void __force *) dst, src, size); +} + +static void __pmem *default_memremap_pmem(resource_size_t offset, + unsigned long size) +{ + return (void __pmem __force *)ioremap_wt(offset, size); +} + +/** + * memremap_pmem - map physical persistent memory for pmem api + * @offset: physical address of persistent memory + * @size: size of the mapping + * + * Establish a mapping of the architecture specific memory type expected + * by memcpy_to_pmem() and wmb_pmem(). For example, it may be + * the case that an uncacheable or writethrough mapping is sufficient, + * or a writeback mapping provided memcpy_to_pmem() and + * wmb_pmem() arrange for the data to be written through the + * cache to persistent media. + */ +static inline void __pmem *memremap_pmem(resource_size_t offset, + unsigned long size) +{ + if (arch_has_pmem_api()) + return arch_memremap_pmem(offset, size); + return default_memremap_pmem(offset, size); +} + +/** + * memcpy_to_pmem - copy data to persistent memory + * @dst: destination buffer for the copy + * @src: source buffer for the copy + * @n: length of the copy in bytes + * + * Perform a memory copy that results in the destination of the copy + * being effectively evicted from, or never written to, the processor + * cache hierarchy after the copy completes. After memcpy_to_pmem() + * data may still reside in cpu or platform buffers, so this operation + * must be followed by a wmb_pmem(). + */ +static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) +{ + if (arch_has_pmem_api()) + arch_memcpy_to_pmem(dst, src, n); + else + default_memcpy_to_pmem(dst, src, n); +} + +/** + * wmb_pmem - synchronize writes to persistent memory + * + * After a series of memcpy_to_pmem() operations this drains data from + * cpu write buffers and any platform (memory controller) buffers to + * ensure that written data is durable on persistent memory media. + */ +static inline void wmb_pmem(void) +{ + if (arch_has_pmem_api()) + arch_wmb_pmem(); +} +#endif /* __PMEM_H__ */ diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index cf112b4075c8..522757ac9cd4 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -215,6 +215,10 @@ struct max17042_platform_data { * the datasheet although it can be changed by board designers. */ unsigned int r_sns; + int vmin; /* in millivolts */ + int vmax; /* in millivolts */ + int temp_min; /* in tenths of degree Celsius */ + int temp_max; /* in tenths of degree Celsius */ }; #endif /* __MAX17042_BATTERY_H_ */ diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 75a1dd8dc56e..ef9f1592185d 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -206,6 +206,11 @@ struct power_supply_desc { int (*set_property)(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); + /* + * property_is_writeable() will be called during registration + * of power supply. If this happens during device probe then it must + * not access internal data of device (because probe did not end). + */ int (*property_is_writeable)(struct power_supply *psy, enum power_supply_property psp); void (*external_power_changed)(struct power_supply *psy); @@ -237,6 +242,7 @@ struct power_supply { /* private */ struct device dev; struct work_struct changed_work; + struct delayed_work deferred_register_work; spinlock_t changed_lock; bool changed; atomic_t use_cnt; @@ -286,10 +292,15 @@ extern void power_supply_put(struct power_supply *psy); #ifdef CONFIG_OF extern struct power_supply *power_supply_get_by_phandle(struct device_node *np, const char *property); +extern struct power_supply *devm_power_supply_get_by_phandle( + struct device *dev, const char *property); #else /* !CONFIG_OF */ static inline struct power_supply * power_supply_get_by_phandle(struct device_node *np, const char *property) { return NULL; } +static inline struct power_supply * +devm_power_supply_get_by_phandle(struct device *dev, const char *property) +{ return NULL; } #endif /* CONFIG_OF */ extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index de83b4eb1642..84991f185173 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -10,13 +10,117 @@ #include <linux/list.h> /* - * We use the MSB mostly because its available; see <linux/preempt_mask.h> for - * the other bits -- can't include that header due to inclusion hell. + * We put the hardirq and softirq counter into the preemption + * counter. The bitmask has the following meaning: + * + * - bits 0-7 are the preemption count (max preemption depth: 256) + * - bits 8-15 are the softirq count (max # of softirqs: 256) + * + * The hardirq count could in theory be the same as the number of + * interrupts in the system, but we run all interrupt handlers with + * interrupts disabled, so we cannot have nesting interrupts. Though + * there are a few palaeontologic drivers which reenable interrupts in + * the handler, so we need more than one bit here. + * + * PREEMPT_MASK: 0x000000ff + * SOFTIRQ_MASK: 0x0000ff00 + * HARDIRQ_MASK: 0x000f0000 + * NMI_MASK: 0x00100000 + * PREEMPT_ACTIVE: 0x00200000 + * PREEMPT_NEED_RESCHED: 0x80000000 */ +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define HARDIRQ_BITS 4 +#define NMI_BITS 1 + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) +#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) + +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + +#define PREEMPT_ACTIVE_BITS 1 +#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) +#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) + +/* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 +/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) + +/* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? + */ +#define in_irq() (hardirq_count()) +#define in_softirq() (softirq_count()) +#define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + +#if defined(CONFIG_PREEMPT_COUNT) +# define PREEMPT_DISABLE_OFFSET 1 +#else +# define PREEMPT_DISABLE_OFFSET 0 +#endif + +/* + * The preempt_count offset needed for things like: + * + * spin_lock_bh() + * + * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and + * softirqs, such that unlock sequences of: + * + * spin_unlock(); + * local_bh_enable(); + * + * Work as expected. + */ +#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET) + +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ +#define in_atomic() (preempt_count() != 0) + +/* + * Check whether we were atomic before we did preempt_disable(): + * (used by the scheduler) + */ +#define in_atomic_preempt_off() \ + ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET) + #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); @@ -33,6 +137,18 @@ extern void preempt_count_sub(int val); #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) +#define preempt_active_enter() \ +do { \ + preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \ + barrier(); \ +} while (0) + +#define preempt_active_exit() \ +do { \ + barrier(); \ + preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \ +} while (0) + #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ @@ -49,6 +165,8 @@ do { \ #define preempt_enable_no_resched() sched_preempt_enable_no_resched() +#define preemptible() (preempt_count() == 0 && !irqs_disabled()) + #ifdef CONFIG_PREEMPT #define preempt_enable() \ do { \ @@ -57,52 +175,46 @@ do { \ __preempt_schedule(); \ } while (0) +#define preempt_enable_notrace() \ +do { \ + barrier(); \ + if (unlikely(__preempt_count_dec_and_test())) \ + __preempt_schedule_notrace(); \ +} while (0) + #define preempt_check_resched() \ do { \ if (should_resched()) \ __preempt_schedule(); \ } while (0) -#else +#else /* !CONFIG_PREEMPT */ #define preempt_enable() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) -#define preempt_check_resched() do { } while (0) -#endif - -#define preempt_disable_notrace() \ -do { \ - __preempt_count_inc(); \ - barrier(); \ -} while (0) -#define preempt_enable_no_resched_notrace() \ +#define preempt_enable_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) -#ifdef CONFIG_PREEMPT - -#ifndef CONFIG_CONTEXT_TRACKING -#define __preempt_schedule_context() __preempt_schedule() -#endif +#define preempt_check_resched() do { } while (0) +#endif /* CONFIG_PREEMPT */ -#define preempt_enable_notrace() \ +#define preempt_disable_notrace() \ do { \ + __preempt_count_inc(); \ barrier(); \ - if (unlikely(__preempt_count_dec_and_test())) \ - __preempt_schedule_context(); \ } while (0) -#else -#define preempt_enable_notrace() \ + +#define preempt_enable_no_resched_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) -#endif #else /* !CONFIG_PREEMPT_COUNT */ @@ -121,6 +233,7 @@ do { \ #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() +#define preemptible() 0 #endif /* CONFIG_PREEMPT_COUNT */ @@ -180,6 +293,8 @@ struct preempt_notifier { struct preempt_ops *ops; }; +void preempt_notifier_inc(void); +void preempt_notifier_dec(void); void preempt_notifier_register(struct preempt_notifier *notifier); void preempt_notifier_unregister(struct preempt_notifier *notifier); diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h deleted file mode 100644 index dbeec4d4a3be..000000000000 --- a/include/linux/preempt_mask.h +++ /dev/null @@ -1,117 +0,0 @@ -#ifndef LINUX_PREEMPT_MASK_H -#define LINUX_PREEMPT_MASK_H - -#include <linux/preempt.h> - -/* - * We put the hardirq and softirq counter into the preemption - * counter. The bitmask has the following meaning: - * - * - bits 0-7 are the preemption count (max preemption depth: 256) - * - bits 8-15 are the softirq count (max # of softirqs: 256) - * - * The hardirq count could in theory be the same as the number of - * interrupts in the system, but we run all interrupt handlers with - * interrupts disabled, so we cannot have nesting interrupts. Though - * there are a few palaeontologic drivers which reenable interrupts in - * the handler, so we need more than one bit here. - * - * PREEMPT_MASK: 0x000000ff - * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00100000 - * PREEMPT_ACTIVE: 0x00200000 - */ -#define PREEMPT_BITS 8 -#define SOFTIRQ_BITS 8 -#define HARDIRQ_BITS 4 -#define NMI_BITS 1 - -#define PREEMPT_SHIFT 0 -#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) -#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) - -#define __IRQ_MASK(x) ((1UL << (x))-1) - -#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) -#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) -#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) -#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) - -#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) -#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) -#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) -#define NMI_OFFSET (1UL << NMI_SHIFT) - -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) - -#define PREEMPT_ACTIVE_BITS 1 -#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) -#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) - -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) - -/* - * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? - */ -#define in_irq() (hardirq_count()) -#define in_softirq() (softirq_count()) -#define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) - -#if defined(CONFIG_PREEMPT_COUNT) -# define PREEMPT_CHECK_OFFSET 1 -#else -# define PREEMPT_CHECK_OFFSET 0 -#endif - -/* - * The preempt_count offset needed for things like: - * - * spin_lock_bh() - * - * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and - * softirqs, such that unlock sequences of: - * - * spin_unlock(); - * local_bh_enable(); - * - * Work as expected. - */ -#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET) - -/* - * Are we running in atomic context? WARNING: this macro cannot - * always detect atomic context; in particular, it cannot know about - * held spinlocks in non-preemptible kernels. Thus it should not be - * used in the general case to determine whether sleeping is possible. - * Do not use in_atomic() in driver code. - */ -#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) - -/* - * Check whether we were atomic before we did preempt_disable(): - * (used by the scheduler, *after* releasing the kernel lock) - */ -#define in_atomic_preempt_off() \ - ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) - -#ifdef CONFIG_PREEMPT_COUNT -# define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#else -# define preemptible() 0 -#endif - -#endif /* LINUX_PREEMPT_MASK_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 9b30871c9149..a6298b27ac99 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -30,6 +30,8 @@ static inline const char *printk_skip_level(const char *buffer) return buffer; } +#define CONSOLE_EXT_LOG_MAX 8192 + /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT @@ -120,7 +122,7 @@ static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif -typedef int(*printk_func_t)(const char *fmt, va_list args); +typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) @@ -164,7 +166,7 @@ char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); -void dump_stack_set_arch_desc(const char *fmt, ...); +__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); #else @@ -215,7 +217,7 @@ static inline void setup_log_buf(int early) { } -static inline void dump_stack_set_arch_desc(const char *fmt, ...) +static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } diff --git a/include/linux/property.h b/include/linux/property.h index de8bdf417a35..76ebde9c11d4 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -164,4 +164,6 @@ struct property_set { void device_add_property_set(struct device *dev, struct property_set *pset); +bool device_dma_is_coherent(struct device *dev); + #endif /* _LINUX_PROPERTY_H_ */ diff --git a/include/linux/pwm.h b/include/linux/pwm.h index e90628cac8fa..36262d08a9da 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -182,6 +182,8 @@ struct pwm_chip { int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); +int pwmchip_add_with_polarity(struct pwm_chip *chip, + enum pwm_polarity polarity); int pwmchip_add(struct pwm_chip *chip); int pwmchip_remove(struct pwm_chip *chip); struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, @@ -217,6 +219,11 @@ static inline int pwmchip_add(struct pwm_chip *chip) return -EINVAL; } +static inline int pwmchip_add_inversed(struct pwm_chip *chip) +{ + return -EINVAL; +} + static inline int pwmchip_remove(struct pwm_chip *chip) { return -EINVAL; @@ -290,10 +297,15 @@ struct pwm_lookup { #if IS_ENABLED(CONFIG_PWM) void pwm_add_table(struct pwm_lookup *table, size_t num); +void pwm_remove_table(struct pwm_lookup *table, size_t num); #else static inline void pwm_add_table(struct pwm_lookup *table, size_t num) { } + +static inline void pwm_remove_table(struct pwm_lookup *table, size_t num) +{ +} #endif #ifdef CONFIG_PWM_SYSFS diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index dab545bb66b3..0485bab061fd 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -194,8 +194,9 @@ enum pxa_ssp_type { PXA168_SSP, PXA910_SSP, CE4100_SSP, - LPSS_SSP, QUARK_X1000_SSP, + LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ + LPSS_BYT_SSP, }; struct ssp_device { diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index d7a974d5f57c..6e7d5ec65838 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2014, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. * * This program is free software; you can redistribute it and/or modify @@ -16,6 +16,17 @@ extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); +#define QCOM_SCM_HDCP_MAX_REQ_CNT 5 + +struct qcom_scm_hdcp_req { + u32 addr; + u32 val; +}; + +extern bool qcom_scm_hdcp_available(void); +extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, + u32 *resp); + #define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 #define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 diff --git a/include/linux/random.h b/include/linux/random.h index b05856e16b75..e651874df2c9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -6,14 +6,23 @@ #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H +#include <linux/list.h> #include <uapi/linux/random.h> +struct random_ready_callback { + struct list_head list; + void (*func)(struct random_ready_callback *rdy); + struct module *owner; +}; + extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); extern void add_interrupt_randomness(int irq, int irq_flags); extern void get_random_bytes(void *buf, int nbytes); +extern int add_random_ready_callback(struct random_ready_callback *rdy); +extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); extern int random_int_secret_init(void); diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index fb31765e935a..830c4992088d 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -31,6 +31,7 @@ #include <linux/kernel.h> #include <linux/stddef.h> +#include <linux/rcupdate.h> struct rb_node { unsigned long __rb_parent_color; @@ -73,11 +74,11 @@ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ -extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, +extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, - struct rb_node ** rb_link) +static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; @@ -85,6 +86,15 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, *rb_link = node; } +static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) +{ + node->__rb_parent_color = (unsigned long)parent; + node->rb_left = node->rb_right = NULL; + + rcu_assign_pointer(*rb_link, node); +} + #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 378c5ee75f78..14d7b831b63a 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -123,11 +123,11 @@ __rb_change_child(struct rb_node *old, struct rb_node *new, { if (parent) { if (parent->rb_left == old) - parent->rb_left = new; + WRITE_ONCE(parent->rb_left, new); else - parent->rb_right = new; + WRITE_ONCE(parent->rb_right, new); } else - root->rb_node = new; + WRITE_ONCE(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, @@ -137,7 +137,8 @@ static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *child = node->rb_right, *tmp = node->rb_left; + struct rb_node *child = node->rb_right; + struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; @@ -167,6 +168,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, tmp = parent; } else { struct rb_node *successor = child, *child2; + tmp = child->rb_left; if (!tmp) { /* @@ -180,6 +182,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, */ parent = successor; child2 = successor->rb_right; + augment->copy(node, successor); } else { /* @@ -201,19 +204,23 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, successor = tmp; tmp = tmp->rb_left; } while (tmp); - parent->rb_left = child2 = successor->rb_right; - successor->rb_right = child; + child2 = successor->rb_right; + WRITE_ONCE(parent->rb_left, child2); + WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); + augment->copy(node, successor); augment->propagate(parent, successor); } - successor->rb_left = tmp = node->rb_left; + tmp = node->rb_left; + WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); + if (child2) { successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h new file mode 100644 index 000000000000..4f3432c61d12 --- /dev/null +++ b/include/linux/rbtree_latch.h @@ -0,0 +1,212 @@ +/* + * Latched RB-trees + * + * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> + * + * Since RB-trees have non-atomic modifications they're not immediately suited + * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for + * lockless lookups; we cannot guarantee they return a correct result. + * + * The simplest solution is a seqlock + RB-tree, this will allow lockless + * lookups; but has the constraint (inherent to the seqlock) that read sides + * cannot nest in write sides. + * + * If we need to allow unconditional lookups (say as required for NMI context + * usage) we need a more complex setup; this data structure provides this by + * employing the latch technique -- see @raw_write_seqcount_latch -- to + * implement a latched RB-tree which does allow for unconditional lookups by + * virtue of always having (at least) one stable copy of the tree. + * + * However, while we have the guarantee that there is at all times one stable + * copy, this does not guarantee an iteration will not observe modifications. + * What might have been a stable copy at the start of the iteration, need not + * remain so for the duration of the iteration. + * + * Therefore, this does require a lockless RB-tree iteration to be non-fatal; + * see the comment in lib/rbtree.c. Note however that we only require the first + * condition -- not seeing partial stores -- because the latch thing isolates + * us from loops. If we were to interrupt a modification the lookup would be + * pointed at the stable tree and complete while the modification was halted. + */ + +#ifndef RB_TREE_LATCH_H +#define RB_TREE_LATCH_H + +#include <linux/rbtree.h> +#include <linux/seqlock.h> + +struct latch_tree_node { + struct rb_node node[2]; +}; + +struct latch_tree_root { + seqcount_t seq; + struct rb_root tree[2]; +}; + +/** + * latch_tree_ops - operators to define the tree order + * @less: used for insertion; provides the (partial) order between two elements. + * @comp: used for lookups; provides the order between the search key and an element. + * + * The operators are related like: + * + * comp(a->key,b) < 0 := less(a,b) + * comp(a->key,b) > 0 := less(b,a) + * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) + * + * If these operators define a partial order on the elements we make no + * guarantee on which of the elements matching the key is found. See + * latch_tree_find(). + */ +struct latch_tree_ops { + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); + int (*comp)(void *key, struct latch_tree_node *b); +}; + +static __always_inline struct latch_tree_node * +__lt_from_rb(struct rb_node *node, int idx) +{ + return container_of(node, struct latch_tree_node, node[idx]); +} + +static __always_inline void +__lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) +{ + struct rb_root *root = <r->tree[idx]; + struct rb_node **link = &root->rb_node; + struct rb_node *node = <n->node[idx]; + struct rb_node *parent = NULL; + struct latch_tree_node *ltp; + + while (*link) { + parent = *link; + ltp = __lt_from_rb(parent, idx); + + if (less(ltn, ltp)) + link = &parent->rb_left; + else + link = &parent->rb_right; + } + + rb_link_node_rcu(node, parent, link); + rb_insert_color(node, root); +} + +static __always_inline void +__lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) +{ + rb_erase(<n->node[idx], <r->tree[idx]); +} + +static __always_inline struct latch_tree_node * +__lt_find(void *key, struct latch_tree_root *ltr, int idx, + int (*comp)(void *key, struct latch_tree_node *node)) +{ + struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); + struct latch_tree_node *ltn; + int c; + + while (node) { + ltn = __lt_from_rb(node, idx); + c = comp(key, ltn); + + if (c < 0) + node = rcu_dereference_raw(node->rb_left); + else if (c > 0) + node = rcu_dereference_raw(node->rb_right); + else + return ltn; + } + + return NULL; +} + +/** + * latch_tree_insert() - insert @node into the trees @root + * @node: nodes to insert + * @root: trees to insert @node into + * @ops: operators defining the node order + * + * It inserts @node into @root in an ordered fashion such that we can always + * observe one complete tree. See the comment for raw_write_seqcount_latch(). + * + * The inserts use rcu_assign_pointer() to publish the element such that the + * tree structure is stored before we can observe the new @node. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_insert(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 0, ops->less); + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 1, ops->less); +} + +/** + * latch_tree_erase() - removes @node from the trees @root + * @node: nodes to remote + * @root: trees to remove @node from + * @ops: operators defining the node order + * + * Removes @node from the trees @root in an ordered fashion such that we can + * always observe one complete tree. See the comment for + * raw_write_seqcount_latch(). + * + * It is assumed that @node will observe one RCU quiescent state before being + * reused of freed. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_erase(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 0); + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 1); +} + +/** + * latch_tree_find() - find the node matching @key in the trees @root + * @key: search key + * @root: trees to search for @key + * @ops: operators defining the node order + * + * Does a lockless lookup in the trees @root for the node matching @key. + * + * It is assumed that this is called while holding the appropriate RCU read + * side lock. + * + * If the operators define a partial order on the elements (there are multiple + * elements which have the same key value) it is undefined which of these + * elements will be found. Nor is it possible to iterate the tree to find + * further elements with the same key value. + * + * Returns: a pointer to the node matching @key or NULL. + */ +static __always_inline struct latch_tree_node * +latch_tree_find(void *key, struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + struct latch_tree_node *node; + unsigned int seq; + + do { + seq = raw_read_seqcount_latch(&root->seq); + node = __lt_find(key, root, seq & 1, ops->comp); + } while (read_seqcount_retry(&root->seq, seq)); + + return node; +} + +#endif /* RB_TREE_LATCH_H */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index a18b16f1dc0e..17c6b1f84a77 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -29,8 +29,8 @@ */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { - ACCESS_ONCE(list->next) = list; - ACCESS_ONCE(list->prev) = list; + WRITE_ONCE(list->next, list); + WRITE_ONCE(list->prev, list); } /* @@ -288,7 +288,7 @@ static inline void list_splice_init_rcu(struct list_head *list, #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ - struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) @@ -549,8 +549,8 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ - pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 573a5afd5ed8..4cf5f51b4c9c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -44,6 +44,8 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/ktime.h> + #include <asm/barrier.h> extern int rcu_expedited; /* for sysctl */ @@ -292,10 +294,6 @@ void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); struct notifier_block; -void rcu_idle_enter(void); -void rcu_idle_exit(void); -void rcu_irq_enter(void); -void rcu_irq_exit(void); int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); @@ -364,8 +362,8 @@ extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ rcu_all_qs(); \ - if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ - ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ + if (READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) @@ -609,7 +607,7 @@ static inline void rcu_preempt_sleep_check(void) #define __rcu_access_pointer(p, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) @@ -628,21 +626,6 @@ static inline void rcu_preempt_sleep_check(void) ((typeof(*p) __force __kernel *)(p)); \ }) -#define __rcu_access_index(p, space) \ -({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - (_________p1); \ -}) -#define __rcu_dereference_index_check(p, c) \ -({ \ - /* Dependency order vs. p above. */ \ - typeof(p) _________p1 = lockless_dereference(p); \ - rcu_lockdep_assert(c, \ - "suspicious rcu_dereference_index_check() usage"); \ - (_________p1); \ -}) - /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. @@ -650,21 +633,6 @@ static inline void rcu_preempt_sleep_check(void) #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** - * lockless_dereference() - safely load a pointer for later dereference - * @p: The pointer to load - * - * Similar to rcu_dereference(), but for situations where the pointed-to - * object's lifetime is managed by something other than RCU. That - * "something other" might be reference counting or simple immortality. - */ -#define lockless_dereference(p) \ -({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - (_________p1); \ -}) - -/** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) @@ -702,7 +670,7 @@ static inline void rcu_preempt_sleep_check(void) * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful + * smp_read_barrier_depends() and keep the READ_ONCE(). This is useful * when the value of this pointer is accessed, but the pointer is not * dereferenced, for example, when testing an RCU-protected pointer against * NULL. Although rcu_access_pointer() may also be used in cases where @@ -787,47 +755,12 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) /** - * rcu_access_index() - fetch RCU index with no dereferencing - * @p: The index to read - * - * Return the value of the specified RCU-protected index, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful - * when the value of this index is accessed, but the index is not - * dereferenced, for example, when testing an RCU-protected index against - * -1. Although rcu_access_index() may also be used in cases where - * update-side locks prevent the value of the index from changing, you - * should instead use rcu_dereference_index_protected() for this use case. - */ -#define rcu_access_index(p) __rcu_access_index((p), __rcu) - -/** - * rcu_dereference_index_check() - rcu_dereference for indices with debug checking - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * Similar to rcu_dereference_check(), but omits the sparse checking. - * This allows rcu_dereference_index_check() to be used on integers, - * which can then be used as array indices. Attempting to use - * rcu_dereference_check() on an integer will give compiler warnings - * because the sparse address-space mechanism relies on dereferencing - * the RCU-protected pointer. Dereferencing integers is not something - * that even gcc will put up with. - * - * Note that this function does not implicitly check for RCU read-side - * critical sections. If this function gains lots of uses, it might - * make sense to provide versions for each flavor of RCU, but it does - * not make sense as of early 2010. - */ -#define rcu_dereference_index_check(p, c) \ - __rcu_dereference_index_check((p), (c)) - -/** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_ONCE(). This + * both the smp_read_barrier_depends() and the READ_ONCE(). This * is useful in cases where update-side locks prevent the value of the * pointer from changing. Please note that this primitive does -not- * prevent the compiler from repeating this reference or combining it @@ -1153,13 +1086,13 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) -#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) -static inline int rcu_needs_cpu(unsigned long *delta_jiffies) +#ifdef CONFIG_TINY_RCU +static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) { - *delta_jiffies = ULONG_MAX; + *nextevt = KTIME_MAX; return 0; } -#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */ +#endif /* #ifdef CONFIG_TINY_RCU */ #if defined(CONFIG_RCU_NOCB_CPU_ALL) static inline bool rcu_is_nocb_cpu(int cpu) { return true; } diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 937edaeb150d..3df6c1ec4e25 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -159,6 +159,22 @@ static inline void rcu_cpu_stall_reset(void) { } +static inline void rcu_idle_enter(void) +{ +} + +static inline void rcu_idle_exit(void) +{ +} + +static inline void rcu_irq_enter(void) +{ +} + +static inline void rcu_irq_exit(void) +{ +} + static inline void exit_rcu(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d2e583a6aaca..456879143f89 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -31,9 +31,7 @@ #define __LINUX_RCUTREE_H void rcu_note_context_switch(void); -#ifndef CONFIG_RCU_NOCB_CPU_ALL -int rcu_needs_cpu(unsigned long *delta_jiffies); -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +int rcu_needs_cpu(u64 basem, u64 *nextevt); void rcu_cpu_stall_reset(void); /* @@ -93,6 +91,11 @@ void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); +void rcu_idle_enter(void); +void rcu_idle_exit(void); +void rcu_irq_enter(void); +void rcu_irq_exit(void); + void exit_rcu(void); void rcu_scheduler_starting(void); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 116655d92269..59c55ea0f0b5 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -433,6 +433,8 @@ int regmap_update_bits_check_async(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); int regmap_get_val_bytes(struct regmap *map); +int regmap_get_max_register(struct regmap *map); +int regmap_get_reg_stride(struct regmap *map); int regmap_async_complete(struct regmap *map); bool regmap_can_raw_write(struct regmap *map); @@ -676,6 +678,18 @@ static inline int regmap_get_val_bytes(struct regmap *map) return -EINVAL; } +static inline int regmap_get_max_register(struct regmap *map) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_get_reg_stride(struct regmap *map) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regcache_sync(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index fffa688ac3a7..4db9fbe4889d 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -91,6 +91,7 @@ struct regulator_linear_range { * @set_current_limit: Configure a limit for a current-limited regulator. * The driver should select the current closest to max_uA. * @get_current_limit: Get the configured limit for a current-limited regulator. + * @set_input_current_limit: Configure an input limit. * * @set_mode: Set the configured operating mode for the regulator. * @get_mode: Get the configured operating mode for the regulator. @@ -111,6 +112,7 @@ struct regulator_linear_range { * to stabilise after being set to a new value, in microseconds. * The function provides the from and to voltage selector, the * function should return the worst case. + * @set_soft_start: Enable soft start for the regulator. * * @set_suspend_voltage: Set the voltage for the regulator when the system * is suspended. @@ -121,6 +123,9 @@ struct regulator_linear_range { * @set_suspend_mode: Set the operating mode for the regulator when the * system is suspended. * + * @set_pull_down: Configure the regulator to pull down when the regulator + * is disabled. + * * This struct describes regulator operations which can be implemented by * regulator chip drivers. */ @@ -142,6 +147,8 @@ struct regulator_ops { int min_uA, int max_uA); int (*get_current_limit) (struct regulator_dev *); + int (*set_input_current_limit) (struct regulator_dev *, int lim_uA); + /* enable/disable regulator */ int (*enable) (struct regulator_dev *); int (*disable) (struct regulator_dev *); @@ -158,6 +165,8 @@ struct regulator_ops { unsigned int old_selector, unsigned int new_selector); + int (*set_soft_start) (struct regulator_dev *); + /* report regulator status ... most other accessors report * control inputs, this reports results of combining inputs * from Linux (and other sources) with the actual load. @@ -187,6 +196,8 @@ struct regulator_ops { /* set regulator suspend operating mode (defined in consumer.h) */ int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode); + + int (*set_pull_down) (struct regulator_dev *); }; /* diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index b07562e082c4..b11be1260129 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -75,6 +75,8 @@ struct regulator_state { * * @min_uA: Smallest current consumers may set. * @max_uA: Largest current consumers may set. + * @ilim_uA: Maximum input current. + * @system_load: Load that isn't captured by any consumer requests. * * @valid_modes_mask: Mask of modes which may be configured by consumers. * @valid_ops_mask: Operations which may be performed by consumers. @@ -86,6 +88,8 @@ struct regulator_state { * applied. * @apply_uV: Apply the voltage constraint when initialising. * @ramp_disable: Disable ramp delay when initialising or when setting voltage. + * @soft_start: Enable soft start so that voltage ramps slowly. + * @pull_down: Enable pull down when regulator is disabled. * * @input_uV: Input voltage for regulator when supplied by another regulator. * @@ -111,6 +115,9 @@ struct regulation_constraints { /* current output range (inclusive) - for current control */ int min_uA; int max_uA; + int ilim_uA; + + int system_load; /* valid regulator operating modes for this machine */ unsigned int valid_modes_mask; @@ -138,6 +145,8 @@ struct regulation_constraints { unsigned boot_on:1; /* bootloader/firmware enabled regulator */ unsigned apply_uV:1; /* apply uV constraint if min == max */ unsigned ramp_disable:1; /* disable ramp delay */ + unsigned soft_start:1; /* ramp voltage slowly */ + unsigned pull_down:1; /* pull down resistor when regulator off */ }; /** diff --git a/include/linux/regulator/max8973-regulator.h b/include/linux/regulator/max8973-regulator.h index f8acc052e353..f6a8a16a0d4d 100644 --- a/include/linux/regulator/max8973-regulator.h +++ b/include/linux/regulator/max8973-regulator.h @@ -58,6 +58,9 @@ * control signal from EN input pin. If it is false then * voltage output will be enabled/disabled through EN bit of * device register. + * @enable_gpio: Enable GPIO. If EN pin is controlled through GPIO from host + * then GPIO number can be provided. If no GPIO controlled then + * it should be -1. * @dvs_gpio: GPIO for dvs. It should be -1 if this is tied with fixed logic. * @dvs_def_state: Default state of dvs. 1 if it is high else 0. */ @@ -65,6 +68,7 @@ struct max8973_regulator_platform_data { struct regulator_init_data *reg_init_data; unsigned long control_flags; bool enable_ext_control; + int enable_gpio; int dvs_gpio; unsigned dvs_def_state:1; }; diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 78b8a9b9d40a..9c4e1384f636 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -36,11 +36,11 @@ #define REMOTEPROC_H #include <linux/types.h> -#include <linux/klist.h> #include <linux/mutex.h> #include <linux/virtio.h> #include <linux/completion.h> #include <linux/idr.h> +#include <linux/of.h> /** * struct resource_table - firmware resource table header @@ -330,11 +330,13 @@ struct rproc; * @start: power on the device and boot it * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) + * @da_to_va: optional platform hook to perform address translations */ struct rproc_ops { int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); + void * (*da_to_va)(struct rproc *rproc, u64 da, int len); }; /** @@ -375,7 +377,7 @@ enum rproc_crash_type { /** * struct rproc - represents a physical remote processor device - * @node: klist node of this rproc object + * @node: list node of this rproc object * @domain: iommu domain * @name: human readable name of the rproc * @firmware: name of firmware file to be loaded @@ -407,7 +409,7 @@ enum rproc_crash_type { * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { - struct klist_node node; + struct list_head node; struct iommu_domain *domain; const char *name; const char *firmware; @@ -481,6 +483,7 @@ struct rproc_vdev { u32 rsc_offset; }; +struct rproc *rproc_get_by_phandle(phandle phandle); struct rproc *rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, const char *firmware, int len); diff --git a/include/linux/reset/bcm63xx_pmb.h b/include/linux/reset/bcm63xx_pmb.h new file mode 100644 index 000000000000..bb4af7b5eb36 --- /dev/null +++ b/include/linux/reset/bcm63xx_pmb.h @@ -0,0 +1,88 @@ +/* + * Broadcom BCM63xx Processor Monitor Bus shared routines (SMP and reset) + * + * Copyright (C) 2015, Broadcom Corporation + * Author: Florian Fainelli <f.fainelli@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef __BCM63XX_PMB_H +#define __BCM63XX_PMB_H + +#include <linux/io.h> +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/err.h> + +/* PMB Master controller register */ +#define PMB_CTRL 0x00 +#define PMC_PMBM_START (1 << 31) +#define PMC_PMBM_TIMEOUT (1 << 30) +#define PMC_PMBM_SLAVE_ERR (1 << 29) +#define PMC_PMBM_BUSY (1 << 28) +#define PMC_PMBM_READ (0 << 20) +#define PMC_PMBM_WRITE (1 << 20) +#define PMB_WR_DATA 0x04 +#define PMB_TIMEOUT 0x08 +#define PMB_RD_DATA 0x0C + +#define PMB_BUS_ID_SHIFT 8 + +/* Perform the low-level PMB master operation, shared between reads and + * writes. + */ +static inline int __bpcm_do_op(void __iomem *master, unsigned int addr, + u32 off, u32 op) +{ + unsigned int timeout = 1000; + u32 cmd; + + cmd = (PMC_PMBM_START | op | (addr & 0xff) << 12 | off); + writel(cmd, master + PMB_CTRL); + do { + cmd = readl(master + PMB_CTRL); + if (!(cmd & PMC_PMBM_START)) + return 0; + + if (cmd & PMC_PMBM_SLAVE_ERR) + return -EIO; + + if (cmd & PMC_PMBM_TIMEOUT) + return -ETIMEDOUT; + + udelay(1); + } while (timeout-- > 0); + + return -ETIMEDOUT; +} + +static inline int bpcm_rd(void __iomem *master, unsigned int addr, + u32 off, u32 *val) +{ + int ret = 0; + + ret = __bpcm_do_op(master, addr, off >> 2, PMC_PMBM_READ); + *val = readl(master + PMB_RD_DATA); + + return ret; +} + +static inline int bpcm_wr(void __iomem *master, unsigned int addr, + u32 off, u32 val) +{ + int ret = 0; + + writel(val, master + PMB_WR_DATA); + ret = __bpcm_do_op(master, addr, off >> 2, PMC_PMBM_WRITE); + + return ret; +} + +#endif /* __BCM63XX_PMB_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index dbcbcc59aa92..843ceca9a21e 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -17,6 +17,7 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H +#include <linux/atomic.h> #include <linux/compiler.h> #include <linux/errno.h> #include <linux/jhash.h> @@ -100,6 +101,7 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed + * @insecure_max_entries: Maximum number of entries (may be exceeded) * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker @@ -115,6 +117,7 @@ struct rhashtable_params { size_t key_len; size_t key_offset; size_t head_offset; + unsigned int insecure_max_entries; unsigned int max_size; unsigned int min_size; u32 nulls_base; @@ -286,6 +289,18 @@ static inline bool rht_grow_above_100(const struct rhashtable *ht, (!ht->p.max_size || tbl->size < ht->p.max_size); } +/** + * rht_grow_above_max - returns true if table is above maximum + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_max(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + return ht->p.insecure_max_entries && + atomic_read(&ht->nelems) >= ht->p.insecure_max_entries; +} + /* The bucket lock is selected based on the hash and protects mutations * on a group of hash buckets. * @@ -589,6 +604,10 @@ restart: goto out; } + err = -E2BIG; + if (unlikely(rht_grow_above_max(ht, tbl))) + goto out; + if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); diff --git a/include/linux/rio.h b/include/linux/rio.h index 6bda06f21930..cde976e86b48 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -298,7 +298,7 @@ struct rio_id_table { * struct rio_net - RIO network info * @node: Node in global list of RIO networks * @devices: List of devices in this network - * @switches: List of switches in this netowrk + * @switches: List of switches in this network * @mports: List of master ports accessing this network * @hport: Default port for accessing this network * @id: RIO network ID diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 8dcf6825fa88..3359f0422c6b 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -24,6 +24,14 @@ extern void rtc_time64_to_tm(time64_t time, struct rtc_time *tm); ktime_t rtc_tm_to_ktime(struct rtc_time tm); struct rtc_time rtc_ktime_to_tm(ktime_t kt); +/* + * rtc_tm_sub - Return the difference in seconds. + */ +static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) +{ + return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); +} + /** * Deprecated. Use rtc_time64_to_tm(). */ @@ -101,8 +109,7 @@ struct rtc_timer { /* flags */ #define RTC_DEV_BUSY 0 -struct rtc_device -{ +struct rtc_device { struct device dev; struct module *owner; @@ -161,7 +168,6 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); extern int rtc_set_ntp_time(struct timespec64 now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, @@ -198,10 +204,10 @@ int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); -void rtc_timer_init(struct rtc_timer *timer, void (*f)(void* p), void* data); -int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer* timer, - ktime_t expires, ktime_t period); -int rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer* timer); +void rtc_timer_init(struct rtc_timer *timer, void (*f)(void *p), void *data); +int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, + ktime_t expires, ktime_t period); +void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer); void rtc_timer_do_work(struct work_struct *work); static inline bool is_leap_year(unsigned int year) diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h index 2c92e1c8e055..aefd997262e4 100644 --- a/include/linux/rtc/sirfsoc_rtciobrg.h +++ b/include/linux/rtc/sirfsoc_rtciobrg.h @@ -9,10 +9,14 @@ #ifndef _SIRFSOC_RTC_IOBRG_H_ #define _SIRFSOC_RTC_IOBRG_H_ +struct regmap_config; + extern void sirfsoc_rtc_iobrg_besyncing(void); extern u32 sirfsoc_rtc_iobrg_readl(u32 addr); extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr); +struct regmap *devm_regmap_init_iobg(struct device *dev, + const struct regmap_config *config); #endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 7b8e260c4a27..39adaa9529eb 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -79,17 +79,9 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS void net_inc_ingress_queue(void); void net_dec_ingress_queue(void); -#else -static inline void net_inc_ingress_queue(void) -{ -} - -static inline void net_dec_ingress_queue(void) -{ -} #endif extern void rtnetlink_init(void); @@ -122,5 +114,9 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm, extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask, int nlflags); + u32 flags, u32 mask, int nlflags, + u32 filter_mask, + int (*vlan_fill)(struct sk_buff *skb, + struct net_device *dev, + u32 filter_mask)); #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index ed8f9e70df9b..9b1ef0c820a7 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -2,13 +2,39 @@ #define _LINUX_SCATTERLIST_H #include <linux/string.h> +#include <linux/types.h> #include <linux/bug.h> #include <linux/mm.h> - -#include <asm/types.h> -#include <asm/scatterlist.h> #include <asm/io.h> +struct scatterlist { +#ifdef CONFIG_DEBUG_SG + unsigned long sg_magic; +#endif + unsigned long page_link; + unsigned int offset; + unsigned int length; + dma_addr_t dma_address; +#ifdef CONFIG_NEED_SG_DMA_LENGTH + unsigned int dma_length; +#endif +}; + +/* + * These macros should be used after a dma_map_sg call has been done + * to get bus addresses of each of the SG entries and their lengths. + * You should only work with the number of sg entries dma_map_sg + * returns, or alternatively stop on the first sg_dma_len(sg) which + * is 0. + */ +#define sg_dma_address(sg) ((sg)->dma_address) + +#ifdef CONFIG_NEED_SG_DMA_LENGTH +#define sg_dma_len(sg) ((sg)->dma_length) +#else +#define sg_dma_len(sg) ((sg)->length) +#endif + struct sg_table { struct scatterlist *sgl; /* the list */ unsigned int nents; /* number of mapped entries */ @@ -18,10 +44,9 @@ struct sg_table { /* * Notes on SG table design. * - * Architectures must provide an unsigned long page_link field in the - * scatterlist struct. We use that to place the page pointer AND encode - * information about the sg table as well. The two lower bits are reserved - * for this information. + * We use the unsigned long page_link field in the scatterlist struct to place + * the page pointer AND encode information about the sg table as well. The two + * lower bits are reserved for this information. * * If bit 0 is set, then the page_link contains a pointer to the next sg * table list. Otherwise the next entry is at sg + 1. @@ -221,6 +246,7 @@ static inline void *sg_virt(struct scatterlist *sg) } int sg_nents(struct scatterlist *sg); +int sg_nents_for_len(struct scatterlist *sg, u64 len); struct scatterlist *sg_next(struct scatterlist *); struct scatterlist *sg_last(struct scatterlist *s, unsigned int); void sg_init_table(struct scatterlist *, unsigned int); @@ -239,13 +265,16 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, unsigned long offset, unsigned long size, gfp_t gfp_mask); +size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, + size_t buflen, off_t skip, bool to_buffer); + size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen); + const void *buf, size_t buflen); size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen); size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen, off_t skip); + const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); diff --git a/include/linux/sched.h b/include/linux/sched.h index 26a2e6122734..04b5ada460b4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,7 +25,7 @@ struct sched_param { #include <linux/errno.h> #include <linux/nodemask.h> #include <linux/mm_types.h> -#include <linux/preempt_mask.h> +#include <linux/preempt.h> #include <asm/page.h> #include <asm/ptrace.h> @@ -58,6 +58,7 @@ struct sched_param { #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/magic.h> +#include <linux/cgroup-defs.h> #include <asm/processor.h> @@ -132,6 +133,7 @@ struct fs_struct; struct perf_event_context; struct blk_plug; struct filename; +struct nameidata; #define VMACACHE_BITS 2 #define VMACACHE_SIZE (1U << VMACACHE_BITS) @@ -173,7 +175,12 @@ extern unsigned long nr_iowait_cpu(int cpu); extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void update_cpu_load_nohz(void); +#else +static inline void update_cpu_load_nohz(void) { } +#endif extern unsigned long get_parent_ip(unsigned long addr); @@ -185,8 +192,6 @@ struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -extern void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #endif /* @@ -213,9 +218,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #define TASK_WAKEKILL 128 #define TASK_WAKING 256 #define TASK_PARKED 512 -#define TASK_STATE_MAX 1024 +#define TASK_NOLOAD 1024 +#define TASK_STATE_MAX 2048 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; @@ -225,6 +231,8 @@ extern char ___assert_task_state[1 - 2*!!( #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) + /* Convenience macros for the sake of wake_up */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) #define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) @@ -240,7 +248,8 @@ extern char ___assert_task_state[1 - 2*!!( ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) #define task_contributes_to_load(task) \ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0) + (task->flags & PF_FROZEN) == 0 && \ + (task->state & TASK_NOLOAD) == 0) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -252,7 +261,7 @@ extern char ___assert_task_state[1 - 2*!!( #define set_task_state(tsk, state_value) \ do { \ (tsk)->task_state_change = _THIS_IP_; \ - set_mb((tsk)->state, (state_value)); \ + smp_store_mb((tsk)->state, (state_value)); \ } while (0) /* @@ -274,7 +283,7 @@ extern char ___assert_task_state[1 - 2*!!( #define set_current_state(state_value) \ do { \ current->task_state_change = _THIS_IP_; \ - set_mb(current->state, (state_value)); \ + smp_store_mb(current->state, (state_value)); \ } while (0) #else @@ -282,7 +291,7 @@ extern char ___assert_task_state[1 - 2*!!( #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ - set_mb((tsk)->state, (state_value)) + smp_store_mb((tsk)->state, (state_value)) /* * set_current_state() includes a barrier so that the write of current->state @@ -298,7 +307,7 @@ extern char ___assert_task_state[1 - 2*!!( #define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) #define set_current_state(state_value) \ - set_mb(current->state, (state_value)) + smp_store_mb(current->state, (state_value)) #endif @@ -335,14 +344,10 @@ extern int runqueue_is_locked(int cpu); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); -extern int get_nohz_timer_target(int pinned); +extern int get_nohz_timer_target(void); #else static inline void nohz_balance_enter_idle(int cpu) { } static inline void set_cpu_sd_state_idle(void) { } -static inline int get_nohz_timer_target(int pinned) -{ - return smp_processor_id(); -} #endif /* @@ -567,6 +572,23 @@ struct task_cputime { .sum_exec_runtime = 0, \ } +/* + * This is the atomic variant of task_cputime, which can be used for + * storing and updating task_cputime statistics without locking. + */ +struct task_cputime_atomic { + atomic64_t utime; + atomic64_t stime; + atomic64_t sum_exec_runtime; +}; + +#define INIT_CPUTIME_ATOMIC \ + (struct task_cputime_atomic) { \ + .utime = ATOMIC64_INIT(0), \ + .stime = ATOMIC64_INIT(0), \ + .sum_exec_runtime = ATOMIC64_INIT(0), \ + } + #ifdef CONFIG_PREEMPT_COUNT #define PREEMPT_DISABLED (1 + PREEMPT_ENABLED) #else @@ -584,18 +606,16 @@ struct task_cputime { /** * struct thread_group_cputimer - thread group interval timer counts - * @cputime: thread group interval timers. + * @cputime_atomic: atomic thread group interval timers. * @running: non-zero when there are timers running and * @cputime receives updates. - * @lock: lock for fields in this struct. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { - struct task_cputime cputime; + struct task_cputime_atomic cputime_atomic; int running; - raw_spinlock_t lock; }; #include <linux/rwsem.h> @@ -734,18 +754,6 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif -#ifdef CONFIG_CGROUPS - /* - * group_rwsem prevents new tasks from entering the threadgroup and - * member tasks from exiting,a more specifically, setting of - * PF_EXITING. fork and exit paths are protected with this rwsem - * using threadgroup_change_begin/end(). Users which require - * threadgroup to remain stable should use threadgroup_[un]lock() - * which also takes care of exec path. Currently, cgroup is the - * only user. - */ - struct rw_semaphore group_rwsem; -#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ @@ -828,7 +836,7 @@ extern struct user_struct root_user; struct backing_dev_info; struct reclaim_state; -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info { /* cumulative counters */ unsigned long pcount; /* # of times run on this cpu */ @@ -838,7 +846,7 @@ struct sched_info { unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ }; -#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ +#endif /* CONFIG_SCHED_INFO */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { @@ -900,6 +908,50 @@ enum cpu_idle_type { #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) /* + * Wake-queues are lists of tasks with a pending wakeup, whose + * callers have already marked the task as woken internally, + * and can thus carry on. A common use case is being able to + * do the wakeups once the corresponding user lock as been + * released. + * + * We hold reference to each task in the list across the wakeup, + * thus guaranteeing that the memory is still valid by the time + * the actual wakeups are performed in wake_up_q(). + * + * One per task suffices, because there's never a need for a task to be + * in two wake queues simultaneously; it is forbidden to abandon a task + * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is + * already in a wake queue, the wakeup will happen soon and the second + * waker can just skip it. + * + * The WAKE_Q macro declares and initializes the list head. + * wake_up_q() does NOT reinitialize the list; it's expected to be + * called near the end of a function, where the fact that the queue is + * not used again will be easy to see by inspection. + * + * Note that this can cause spurious wakeups. schedule() callers + * must ensure the call is done inside a loop, confirming that the + * wakeup condition has in fact occurred. + */ +struct wake_q_node { + struct wake_q_node *next; +}; + +struct wake_q_head { + struct wake_q_node *first; + struct wake_q_node **lastp; +}; + +#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) + +#define WAKE_Q(name) \ + struct wake_q_head name = { WAKE_Q_TAIL, &name.first } + +extern void wake_q_add(struct wake_q_head *head, + struct task_struct *task); +extern void wake_up_q(struct wake_q_head *head); + +/* * sched-domains (multiprocessor balancing) declarations: */ #ifdef CONFIG_SMP @@ -1334,8 +1386,6 @@ struct task_struct { int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; -#endif /* #ifdef CONFIG_PREEMPT_RCU */ -#ifdef CONFIG_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU @@ -1345,7 +1395,7 @@ struct task_struct { int rcu_tasks_idle_cpu; #endif /* #ifdef CONFIG_TASKS_RCU */ -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info sched_info; #endif @@ -1356,9 +1406,6 @@ struct task_struct { #endif struct mm_struct *mm, *active_mm; -#ifdef CONFIG_COMPAT_BRK - unsigned brk_randomized:1; -#endif /* per-thread vma caching */ u32 vmacache_seqnum; struct vm_area_struct *vmacache[VMACACHE_SIZE]; @@ -1369,7 +1416,7 @@ struct task_struct { int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ - unsigned int jobctl; /* JOBCTL_*, siglock protected */ + unsigned long jobctl; /* JOBCTL_*, siglock protected */ /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; @@ -1381,10 +1428,14 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; + unsigned sched_migrated:1; #ifdef CONFIG_MEMCG_KMEM unsigned memcg_kmem_skip_account:1; #endif +#ifdef CONFIG_COMPAT_BRK + unsigned brk_randomized:1; +#endif unsigned long atomic_flags; /* Flags needing atomic access. */ @@ -1461,7 +1512,7 @@ struct task_struct { it with task_lock()) - initialized normally by setup_new_exec */ /* file system info */ - int link_count, total_link_count; + struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC /* ipc stuff */ struct sysv_sem sysvsem; @@ -1471,8 +1522,6 @@ struct task_struct { /* hung task detection */ unsigned long last_switch_count; #endif -/* CPU-specific state of this task */ - struct thread_struct thread; /* filesystem information */ struct fs_struct *fs; /* open file information */ @@ -1511,6 +1560,8 @@ struct task_struct { /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; + struct wake_q_node wake_q; + #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task */ struct rb_root pi_waiters; @@ -1724,8 +1775,23 @@ struct task_struct { #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; #endif + int pagefault_disabled; +/* CPU-specific state of this task */ + struct thread_struct thread; +/* + * WARNING: on x86, 'thread_struct' contains a variable-sized + * structure. It *MUST* be at the end of 'task_struct'. + * + * Do not put anything below here! + */ }; +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +extern int arch_task_struct_size __read_mostly; +#else +# define arch_task_struct_size (sizeof(struct task_struct)) +#endif + /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) @@ -2077,22 +2143,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ -#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT) -#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT) -#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT) -#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT) -#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT) -#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT) -#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT) +#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) +#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) +#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT) +#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT) +#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) +#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, - unsigned int mask); + unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); extern void task_clear_jobctl_pending(struct task_struct *task, - unsigned int mask); + unsigned long mask); static inline void rcu_copy_process(struct task_struct *p) { @@ -2365,7 +2431,6 @@ extern void sched_dead(struct task_struct *p); extern void proc_caches_init(void); extern void flush_signals(struct task_struct *); -extern void __flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); @@ -2489,8 +2554,22 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct */ extern void mm_release(struct task_struct *, struct mm_struct *); +#ifdef CONFIG_HAVE_COPY_THREAD_TLS +extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); +#else extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *); + +/* Architectures that haven't opted into copy_thread_tls get the tls argument + * via pt_regs, so ignore the tls argument passed via C. */ +static inline int copy_thread_tls( + unsigned long clone_flags, unsigned long sp, unsigned long arg, + struct task_struct *p, unsigned long tls) +{ + return copy_thread(clone_flags, sp, arg, p); +} +#endif extern void flush_thread(void); extern void exit_thread(void); @@ -2509,6 +2588,7 @@ extern int do_execveat(int, struct filename *, const char __user * const __user *, const char __user * const __user *, int); +extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); @@ -2532,6 +2612,9 @@ static inline unsigned long wait_task_inactive(struct task_struct *p, } #endif +#define tasklist_empty() \ + list_empty(&init_task.tasks) + #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) @@ -2640,53 +2723,33 @@ static inline void unlock_task_sighand(struct task_struct *tsk, spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); } -#ifdef CONFIG_CGROUPS -static inline void threadgroup_change_begin(struct task_struct *tsk) -{ - down_read(&tsk->signal->group_rwsem); -} -static inline void threadgroup_change_end(struct task_struct *tsk) -{ - up_read(&tsk->signal->group_rwsem); -} - /** - * threadgroup_lock - lock threadgroup - * @tsk: member task of the threadgroup to lock + * threadgroup_change_begin - mark the beginning of changes to a threadgroup + * @tsk: task causing the changes * - * Lock the threadgroup @tsk belongs to. No new task is allowed to enter - * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * change ->group_leader/pid. This is useful for cases where the threadgroup - * needs to stay stable across blockable operations. - * - * fork and exit paths explicitly call threadgroup_change_{begin|end}() for - * synchronization. While held, no new task will be added to threadgroup - * and no existing live task will have its PF_EXITING set. - * - * de_thread() does threadgroup_change_{begin|end}() when a non-leader - * sub-thread becomes a new leader. + * All operations which modify a threadgroup - a new thread joining the + * group, death of a member thread (the assertion of PF_EXITING) and + * exec(2) dethreading the process and replacing the leader - are wrapped + * by threadgroup_change_{begin|end}(). This is to provide a place which + * subsystems needing threadgroup stability can hook into for + * synchronization. */ -static inline void threadgroup_lock(struct task_struct *tsk) +static inline void threadgroup_change_begin(struct task_struct *tsk) { - down_write(&tsk->signal->group_rwsem); + might_sleep(); + cgroup_threadgroup_change_begin(tsk); } /** - * threadgroup_unlock - unlock threadgroup - * @tsk: member task of the threadgroup to unlock + * threadgroup_change_end - mark the end of changes to a threadgroup + * @tsk: task causing the changes * - * Reverse threadgroup_lock(). + * See threadgroup_change_begin(). */ -static inline void threadgroup_unlock(struct task_struct *tsk) +static inline void threadgroup_change_end(struct task_struct *tsk) { - up_write(&tsk->signal->group_rwsem); + cgroup_threadgroup_change_end(tsk); } -#else -static inline void threadgroup_change_begin(struct task_struct *tsk) {} -static inline void threadgroup_change_end(struct task_struct *tsk) {} -static inline void threadgroup_lock(struct task_struct *tsk) {} -static inline void threadgroup_unlock(struct task_struct *tsk) {} -#endif #ifndef __HAVE_THREAD_FUNCTIONS @@ -2962,11 +3025,6 @@ static __always_inline bool need_resched(void) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); -static inline void thread_group_cputime_init(struct signal_struct *sig) -{ - raw_spin_lock_init(&sig->cputimer.lock); -} - /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. @@ -3080,13 +3138,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm) static inline unsigned long task_rlimit(const struct task_struct *tsk, unsigned int limit) { - return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur); + return READ_ONCE(tsk->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *tsk, unsigned int limit) { - return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max); + return READ_ONCE(tsk->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 6341f5be6e24..a30b172df6e1 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -18,7 +18,7 @@ static inline int rt_task(struct task_struct *p) #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); -extern int rt_mutex_check_prio(struct task_struct *task, int newprio); +extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio); extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) @@ -31,9 +31,10 @@ static inline int rt_mutex_getprio(struct task_struct *p) return p->normal_prio; } -static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) +static inline int rt_mutex_get_effective_prio(struct task_struct *task, + int newprio) { - return 0; + return newprio; } static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 596a0e007c62..c9e4731cf10b 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -57,24 +57,12 @@ extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; -extern unsigned int sysctl_timer_migration; extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif -#ifdef CONFIG_SCHED_DEBUG -static inline unsigned int get_sysctl_timer_migration(void) -{ - return sysctl_timer_migration; -} -#else -static inline unsigned int get_sysctl_timer_migration(void) -{ - return 1; -} -#endif /* * control realtime throttling: diff --git a/include/linux/scif.h b/include/linux/scif.h new file mode 100644 index 000000000000..44f4f3898bbe --- /dev/null +++ b/include/linux/scif.h @@ -0,0 +1,993 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * BSD LICENSE + * + * Copyright(c) 2014 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * Intel SCIF driver. + * + */ +#ifndef __SCIF_H__ +#define __SCIF_H__ + +#include <linux/types.h> +#include <linux/poll.h> +#include <linux/scif_ioctl.h> + +#define SCIF_ACCEPT_SYNC 1 +#define SCIF_SEND_BLOCK 1 +#define SCIF_RECV_BLOCK 1 + +enum { + SCIF_PROT_READ = (1 << 0), + SCIF_PROT_WRITE = (1 << 1) +}; + +enum { + SCIF_MAP_FIXED = 0x10, + SCIF_MAP_KERNEL = 0x20, +}; + +enum { + SCIF_FENCE_INIT_SELF = (1 << 0), + SCIF_FENCE_INIT_PEER = (1 << 1), + SCIF_SIGNAL_LOCAL = (1 << 4), + SCIF_SIGNAL_REMOTE = (1 << 5) +}; + +enum { + SCIF_RMA_USECPU = (1 << 0), + SCIF_RMA_USECACHE = (1 << 1), + SCIF_RMA_SYNC = (1 << 2), + SCIF_RMA_ORDERED = (1 << 3) +}; + +/* End of SCIF Admin Reserved Ports */ +#define SCIF_ADMIN_PORT_END 1024 + +/* End of SCIF Reserved Ports */ +#define SCIF_PORT_RSVD 1088 + +typedef struct scif_endpt *scif_epd_t; + +#define SCIF_OPEN_FAILED ((scif_epd_t)-1) +#define SCIF_REGISTER_FAILED ((off_t)-1) +#define SCIF_MMAP_FAILED ((void *)-1) + +/** + * scif_open() - Create an endpoint + * + * Return: + * Upon successful completion, scif_open() returns an endpoint descriptor to + * be used in subsequent SCIF functions calls to refer to that endpoint; + * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is + * returned and errno is set to indicate the error; in kernel mode a NULL + * scif_epd_t is returned. + * + * Errors: + * ENOMEM - Insufficient kernel memory was available + */ +scif_epd_t scif_open(void); + +/** + * scif_bind() - Bind an endpoint to a port + * @epd: endpoint descriptor + * @pn: port number + * + * scif_bind() binds endpoint epd to port pn, where pn is a port number on the + * local node. If pn is zero, a port number greater than or equal to + * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to + * exactly one local port. Ports less than 1024 when requested can only be bound + * by system (or root) processes or by processes executed by privileged users. + * + * Return: + * Upon successful completion, scif_bind() returns the port number to which epd + * is bound; otherwise in user mode -1 is returned and errno is set to + * indicate the error; in kernel mode the negative of one of the following + * errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINVAL - the endpoint or the port is already bound + * EISCONN - The endpoint is already connected + * ENOSPC - No port number available for assignment + * EACCES - The port requested is protected and the user is not the superuser + */ +int scif_bind(scif_epd_t epd, u16 pn); + +/** + * scif_listen() - Listen for connections on an endpoint + * @epd: endpoint descriptor + * @backlog: maximum pending connection requests + * + * scif_listen() marks the endpoint epd as a listening endpoint - that is, as + * an endpoint that will be used to accept incoming connection requests. Once + * so marked, the endpoint is said to be in the listening state and may not be + * used as the endpoint of a connection. + * + * The endpoint, epd, must have been bound to a port. + * + * The backlog argument defines the maximum length to which the queue of + * pending connections for epd may grow. If a connection request arrives when + * the queue is full, the client may receive an error with an indication that + * the connection was refused. + * + * Return: + * Upon successful completion, scif_listen() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINVAL - the endpoint is not bound to a port + * EISCONN - The endpoint is already connected or listening + */ +int scif_listen(scif_epd_t epd, int backlog); + +/** + * scif_connect() - Initiate a connection on a port + * @epd: endpoint descriptor + * @dst: global id of port to which to connect + * + * The scif_connect() function requests the connection of endpoint epd to remote + * port dst. If the connection is successful, a peer endpoint, bound to dst, is + * created on node dst.node. On successful return, the connection is complete. + * + * If the endpoint epd has not already been bound to a port, scif_connect() + * will bind it to an unused local port. + * + * A connection is terminated when an endpoint of the connection is closed, + * either explicitly by scif_close(), or when a process that owns one of the + * endpoints of the connection is terminated. + * + * In user space, scif_connect() supports an asynchronous connection mode + * if the application has set the O_NONBLOCK flag on the endpoint via the + * fcntl() system call. Setting this flag will result in the calling process + * not to wait during scif_connect(). + * + * Return: + * Upon successful completion, scif_connect() returns the port ID to which the + * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is + * set to indicate the error; in kernel mode the negative of one of the + * following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNREFUSED - The destination was not listening for connections or refused + * the connection request + * EINVAL - dst.port is not a valid port ID + * EISCONN - The endpoint is already connected + * ENOMEM - No buffer space is available + * ENODEV - The destination node does not exist, or the node is lost or existed, + * but is not currently in the network since it may have crashed + * ENOSPC - No port number available for assignment + * EOPNOTSUPP - The endpoint is listening and cannot be connected + */ +int scif_connect(scif_epd_t epd, struct scif_port_id *dst); + +/** + * scif_accept() - Accept a connection on an endpoint + * @epd: endpoint descriptor + * @peer: global id of port to which connected + * @newepd: new connected endpoint descriptor + * @flags: flags + * + * The scif_accept() call extracts the first connection request from the queue + * of pending connections for the port on which epd is listening. scif_accept() + * creates a new endpoint, bound to the same port as epd, and allocates a new + * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new + * endpoint is connected to the endpoint through which the connection was + * requested. epd is unaffected by this call, and remains in the listening + * state. + * + * On successful return, peer holds the global port identifier (node id and + * local port number) of the port which requested the connection. + * + * A connection is terminated when an endpoint of the connection is closed, + * either explicitly by scif_close(), or when a process that owns one of the + * endpoints of the connection is terminated. + * + * The number of connections that can (subsequently) be accepted on epd is only + * limited by system resources (memory). + * + * The flags argument is formed by OR'ing together zero or more of the + * following values. + * SCIF_ACCEPT_SYNC - block until a connection request is presented. If + * SCIF_ACCEPT_SYNC is not in flags, and no pending + * connections are present on the queue, scif_accept() + * fails with an EAGAIN error + * + * In user mode, the select() and poll() functions can be used to determine + * when there is a connection request. In kernel mode, the scif_poll() + * function may be used for this purpose. A readable event will be delivered + * when a connection is requested. + * + * Return: + * Upon successful completion, scif_accept() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be + * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete + * its connection request + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * EINTR - Interrupted function + * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is + * NULL, or newepd is NULL + * ENODEV - The requesting node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOENT - Secondary part of epd registration failed + */ +int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t + *newepd, int flags); + +/** + * scif_close() - Close an endpoint + * @epd: endpoint descriptor + * + * scif_close() closes an endpoint and performs necessary teardown of + * facilities associated with that endpoint. + * + * If epd is a listening endpoint then it will no longer accept connection + * requests on the port to which it is bound. Any pending connection requests + * are rejected. + * + * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs + * which are in-process through epd or its peer endpoint will complete before + * scif_close() returns. Registered windows of the local and peer endpoints are + * released as if scif_unregister() was called against each window. + * + * Closing a SCIF endpoint does not affect local registered memory mapped by + * a SCIF endpoint on a remote node. The local memory remains mapped by the peer + * SCIF endpoint explicitly removed by calling munmap(..) by the peer. + * + * If the peer endpoint's receive queue is not empty at the time that epd is + * closed, then the peer endpoint can be passed as the endpoint parameter to + * scif_recv() until the receive queue is empty. + * + * epd is freed and may no longer be accessed. + * + * Return: + * Upon successful completion, scif_close() returns 0; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode the + * negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + */ +int scif_close(scif_epd_t epd); + +/** + * scif_send() - Send a message + * @epd: endpoint descriptor + * @msg: message buffer address + * @len: message length + * @flags: blocking mode flags + * + * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data + * are copied from memory starting at address msg. On successful execution the + * return value of scif_send() is the number of bytes that were sent, and is + * zero if no bytes were sent because len was zero. scif_send() may be called + * only when the endpoint is in a connected state. + * + * If a scif_send() call is non-blocking, then it sends only those bytes which + * can be sent without waiting, up to a maximum of len bytes. + * + * If a scif_send() call is blocking, then it normally returns after sending + * all len bytes. If a blocking call is interrupted or the connection is + * reset, the call is considered successful if some bytes were sent or len is + * zero, otherwise the call is considered unsuccessful. + * + * In user mode, the select() and poll() functions can be used to determine + * when the send queue is not full. In kernel mode, the scif_poll() function + * may be used for this purpose. + * + * It is recommended that scif_send()/scif_recv() only be used for short + * control-type message communication between SCIF endpoints. The SCIF RMA + * APIs are expected to provide better performance for transfer sizes of + * 1024 bytes or longer for the current MIC hardware and software + * implementation. + * + * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK + * is passed as the flags argument. + * + * Return: + * Upon successful completion, scif_send() returns the number of bytes sent; + * otherwise in user mode -1 is returned and errno is set to indicate the + * error; in kernel mode the negative of one of the following errors is + * returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EFAULT - An invalid address was specified for a parameter + * EINVAL - flags is invalid, or len is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +int scif_send(scif_epd_t epd, void *msg, int len, int flags); + +/** + * scif_recv() - Receive a message + * @epd: endpoint descriptor + * @msg: message buffer address + * @len: message buffer length + * @flags: blocking mode flags + * + * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of + * data are copied to memory starting at address msg. On successful execution + * the return value of scif_recv() is the number of bytes that were received, + * and is zero if no bytes were received because len was zero. scif_recv() may + * be called only when the endpoint is in a connected state. + * + * If a scif_recv() call is non-blocking, then it receives only those bytes + * which can be received without waiting, up to a maximum of len bytes. + * + * If a scif_recv() call is blocking, then it normally returns after receiving + * all len bytes. If the blocking call was interrupted due to a disconnection, + * subsequent calls to scif_recv() will copy all bytes received upto the point + * of disconnection. + * + * In user mode, the select() and poll() functions can be used to determine + * when data is available to be received. In kernel mode, the scif_poll() + * function may be used for this purpose. + * + * It is recommended that scif_send()/scif_recv() only be used for short + * control-type message communication between SCIF endpoints. The SCIF RMA + * APIs are expected to provide better performance for transfer sizes of + * 1024 bytes or longer for the current MIC hardware and software + * implementation. + * + * scif_recv() will block until the entire message is received if + * SCIF_RECV_BLOCK is passed as the flags argument. + * + * Return: + * Upon successful completion, scif_recv() returns the number of bytes + * received; otherwise in user mode -1 is returned and errno is set to + * indicate the error; in kernel mode the negative of one of the following + * errors is returned. + * + * Errors: + * EAGAIN - The destination node is returning from a low power state + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EFAULT - An invalid address was specified for a parameter + * EINVAL - flags is invalid, or len is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +int scif_recv(scif_epd_t epd, void *msg, int len, int flags); + +/** + * scif_register() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @addr: starting virtual address + * @len: length of range + * @offset: offset of window + * @prot_flags: read/write protection flags + * @map_flags: mapping flags + * + * The scif_register() function opens a window, a range of whole pages of the + * registered address space of the endpoint epd, starting at offset po and + * continuing for len bytes. The value of po, further described below, is a + * function of the parameters offset and len, and the value of map_flags. Each + * page of the window represents the physical memory page which backs the + * corresponding page of the range of virtual address pages starting at addr + * and continuing for len bytes. addr and len are constrained to be multiples + * of the page size. A successful scif_register() call returns po. + * + * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset + * exactly, and offset is constrained to be a multiple of the page size. The + * mapping established by scif_register() will not replace any existing + * registration; an error is returned if any page within the range [offset, + * offset + len - 1] intersects an existing window. + * + * When SCIF_MAP_FIXED is not set, the implementation uses offset in an + * implementation-defined manner to arrive at po. The po value so chosen will + * be an area of the registered address space that the implementation deems + * suitable for a mapping of len bytes. An offset value of 0 is interpreted as + * granting the implementation complete freedom in selecting po, subject to + * constraints described below. A non-zero value of offset is taken to be a + * suggestion of an offset near which the mapping should be placed. When the + * implementation selects a value for po, it does not replace any extant + * window. In all cases, po will be a multiple of the page size. + * + * The physical pages which are so represented by a window are available for + * access in calls to mmap(), scif_readfrom(), scif_writeto(), + * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the + * physical pages represented by the window will not be reused by the memory + * subsystem for any other purpose. Note that the same physical page may be + * represented by multiple windows. + * + * Subsequent operations which change the memory pages to which virtual + * addresses are mapped (such as mmap(), munmap()) have no effect on + * existing window. + * + * If the process will fork(), it is recommended that the registered + * virtual address range be marked with MADV_DONTFORK. Doing so will prevent + * problems due to copy-on-write semantics. + * + * The prot_flags argument is formed by OR'ing together one or more of the + * following values. + * SCIF_PROT_READ - allow read operations from the window + * SCIF_PROT_WRITE - allow write operations to the window + * + * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a + * fixed offset. + * + * Return: + * Upon successful completion, scif_register() returns the offset at which the + * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that + * is (off_t *)-1) is returned and errno is set to indicate the error; in + * kernel mode the negative of one of the following errors is returned. + * + * Errors: + * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range + * [offset, offset + len -1] are already registered + * EAGAIN - The mapping could not be performed due to lack of resources + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid + * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is + * set in flags, and offset is not a multiple of the page size, or addr is not a + * multiple of the page size, or len is not a multiple of the page size, or is + * 0, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN -The endpoint is not connected + */ +off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset, + int prot_flags, int map_flags); + +/** + * scif_unregister() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @offset: start of range to unregister + * @len: length of range to unregister + * + * The scif_unregister() function closes those previously registered windows + * which are entirely within the range [offset, offset + len - 1]. It is an + * error to specify a range which intersects only a subrange of a window. + * + * On a successful return, pages within the window may no longer be specified + * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(), + * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window, + * however, continues to exist until all previous references against it are + * removed. A window is referenced if there is a mapping to it created by + * mmap(), or if scif_get_pages() was called against the window + * (and the pages have not been returned via scif_put_pages()). A window is + * also referenced while an RMA, in which some range of the window is a source + * or destination, is in progress. Finally a window is referenced while some + * offset in that window was specified to scif_fence_signal(), and the RMAs + * marked by that call to scif_fence_signal() have not completed. While a + * window is in this state, its registered address space pages are not + * available for use in a new registered window. + * + * When all such references to the window have been removed, its references to + * all the physical pages which it represents are removed. Similarly, the + * registered address space pages of the window become available for + * registration in a new window. + * + * Return: + * Upon successful completion, scif_unregister() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. In the event of an + * error, no windows are unregistered. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a + * window, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_unregister(scif_epd_t epd, off_t offset, size_t len); + +/** + * scif_readfrom() - Copy from a remote address space + * @epd: endpoint descriptor + * @loffset: offset in local registered address space to + * which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space + * from which to copy + * @rma_flags: transfer mode flags + * + * scif_readfrom() copies len bytes from the remote registered address space of + * the peer of endpoint epd, starting at the offset roffset to the local + * registered address space of epd, starting at the offset loffset. + * + * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, + * roffset + len - 1] must be within some registered window or windows of the + * local and remote nodes. A range may intersect multiple registered windows, + * but only if those windows are contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * The optimal DMA performance will likely be realized if both + * loffset and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if loffset and roffset are not + * cacheline aligned but are separated by some multiple of 64. The lowest level + * of performance is likely if loffset and roffset are not separated by a + * multiple of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_readfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered + * address space of epd, or, The range [roffset, roffset + len - 1] is invalid + * for the registered address space of the peer of epd, or loffset or roffset + * is negative + */ +int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t + roffset, int rma_flags); + +/** + * scif_writeto() - Copy to a remote address space + * @epd: endpoint descriptor + * @loffset: offset in local registered address space + * from which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space to + * which to copy + * @rma_flags: transfer mode flags + * + * scif_writeto() copies len bytes from the local registered address space of + * epd, starting at the offset loffset to the remote registered address space + * of the peer of endpoint epd, starting at the offset roffset. + * + * Each of the specified ranges [loffset, loffset + len - 1] and [roffset, + * roffset + len - 1] must be within some registered window or windows of the + * local and remote nodes. A range may intersect multiple registered windows, + * but only if those windows are contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * The optimal DMA performance will likely be realized if both + * loffset and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if loffset and roffset are not cacheline + * aligned but are separated by some multiple of 64. The lowest level of + * performance is likely if loffset and roffset are not separated by a multiple + * of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_readfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered + * address space of epd, or, The range [roffset , roffset + len -1] is invalid + * for the registered address space of the peer of epd, or loffset or roffset + * is negative + */ +int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t + roffset, int rma_flags); + +/** + * scif_vreadfrom() - Copy from a remote address space + * @epd: endpoint descriptor + * @addr: address to which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space + * from which to copy + * @rma_flags: transfer mode flags + * + * scif_vreadfrom() copies len bytes from the remote registered address + * space of the peer of endpoint epd, starting at the offset roffset, to local + * memory, starting at addr. + * + * The specified range [roffset, roffset + len - 1] must be within some + * registered window or windows of the remote nodes. The range may + * intersect multiple registered windows, but only if those windows are + * contiguous in the registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back + * the specified local memory range may be remain in a pinned state even after + * the specified transfer completes. This may reduce overhead if some or all of + * the same virtual address range is referenced in a subsequent call of + * scif_vreadfrom() or scif_vwriteto(). + * + * The optimal DMA performance will likely be realized if both + * addr and roffset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if addr and roffset are not + * cacheline aligned but are separated by some multiple of 64. The lowest level + * of performance is likely if addr and roffset are not separated by a + * multiple of 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_USECACHE - enable registration caching + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset, + int rma_flags); + +/** + * scif_vwriteto() - Copy to a remote address space + * @epd: endpoint descriptor + * @addr: address from which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space to + * which to copy + * @rma_flags: transfer mode flags + * + * scif_vwriteto() copies len bytes from the local memory, starting at addr, to + * the remote registered address space of the peer of endpoint epd, starting at + * the offset roffset. + * + * The specified range [roffset, roffset + len - 1] must be within some + * registered window or windows of the remote nodes. The range may intersect + * multiple registered windows, but only if those windows are contiguous in the + * registered address space. + * + * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using + * programmed read/writes. Otherwise the data is copied using DMA. If rma_- + * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the + * transfer is complete. Otherwise, the transfer may be performed asynchron- + * ously. The order in which any two asynchronous RMA operations complete + * is non-deterministic. The synchronization functions, scif_fence_mark()/ + * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to + * the completion of asynchronous RMA operations on the same endpoint. + * + * The DMA transfer of individual bytes is not guaranteed to complete in + * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last + * cacheline or partial cacheline of the source range will become visible on + * the destination node after all other transferred data in the source + * range has become visible on the destination node. + * + * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back + * the specified local memory range may be remain in a pinned state even after + * the specified transfer completes. This may reduce overhead if some or all of + * the same virtual address range is referenced in a subsequent call of + * scif_vreadfrom() or scif_vwriteto(). + * + * The optimal DMA performance will likely be realized if both + * addr and offset are cacheline aligned (are a multiple of 64). Lower + * performance will likely be realized if addr and offset are not cacheline + * aligned but are separated by some multiple of 64. The lowest level of + * performance is likely if addr and offset are not separated by a multiple of + * 64. + * + * The rma_flags argument is formed by ORing together zero or more of the + * following values. + * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA + * engine. + * SCIF_RMA_USECACHE - allow registration caching + * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the + * transfer has completed. Passing this flag results in the + * current implementation busy waiting and consuming CPU cycles + * while the DMA transfer is in progress for best performance by + * avoiding the interrupt latency. + * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of + * the source range becomes visible on the destination node + * after all other transferred data in the source range has + * become visible on the destination + * + * Return: + * Upon successful completion, scif_vwriteto() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EACCESS - Attempt to write to a read-only range + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid + * EINVAL - rma_flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the + * registered address space of epd + */ +int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset, + int rma_flags); + +/** + * scif_fence_mark() - Mark previously issued RMAs + * @epd: endpoint descriptor + * @flags: control flags + * @mark: marked value returned as output. + * + * scif_fence_mark() returns after marking the current set of all uncompleted + * RMAs initiated through the endpoint epd or the current set of all + * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are + * marked with a value returned at mark. The application may subsequently call + * scif_fence_wait(), passing the value returned at mark, to await completion + * of all RMAs so marked. + * + * The flags argument has exactly one of the following values. + * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint + * epd are marked + * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer + * of endpoint epd are marked + * + * Return: + * Upon successful completion, scif_fence_mark() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENOMEM - Insufficient kernel memory was available + */ +int scif_fence_mark(scif_epd_t epd, int flags, int *mark); + +/** + * scif_fence_wait() - Wait for completion of marked RMAs + * @epd: endpoint descriptor + * @mark: mark request + * + * scif_fence_wait() returns after all RMAs marked with mark have completed. + * The value passed in mark must have been obtained in a previous call to + * scif_fence_mark(). + * + * Return: + * Upon successful completion, scif_fence_wait() returns 0; otherwise in user + * mode -1 is returned and errno is set to indicate the error; in kernel mode + * the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENOMEM - Insufficient kernel memory was available + */ +int scif_fence_wait(scif_epd_t epd, int mark); + +/** + * scif_fence_signal() - Request a memory update on completion of RMAs + * @epd: endpoint descriptor + * @loff: local offset + * @lval: local value to write to loffset + * @roff: remote offset + * @rval: remote value to write to roffset + * @flags: flags + * + * scif_fence_signal() returns after marking the current set of all uncompleted + * RMAs initiated through the endpoint epd or marking the current set of all + * uncompleted RMAs initiated through the peer of endpoint epd. + * + * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the + * marked set, lval is written to memory at the address corresponding to offset + * loff in the local registered address space of epd. loff must be within a + * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion + * of the RMAs in the marked set, rval is written to memory at the address + * corresponding to offset roff in the remote registered address space of epd. + * roff must be within a remote registered window of the peer of epd. Note + * that any specified offset must be DWORD (4 byte / 32 bit) aligned. + * + * The flags argument is formed by OR'ing together the following. + * Exactly one of the following values. + * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint + * epd are marked + * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer + * of endpoint epd are marked + * One or more of the following values. + * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to + * memory at the address corresponding to offset loff in the local + * registered address space of epd. + * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to + * memory at the address corresponding to offset roff in the remote + * registered address space of epd. + * + * Return: + * Upon successful completion, scif_fence_signal() returns 0; otherwise in + * user mode -1 is returned and errno is set to indicate the error; in kernel + * mode the negative of one of the following errors is returned. + * + * Errors: + * EBADF, ENOTTY - epd is not a valid endpoint descriptor + * ECONNRESET - Connection reset by peer + * EINVAL - flags is invalid, or loff or roff are not DWORD aligned + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - loff is invalid for the registered address of epd, or roff is invalid + * for the registered address space, of the peer of epd + */ +int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff, + u64 rval, int flags); + +/** + * scif_get_node_ids() - Return information about online nodes + * @nodes: array in which to return online node IDs + * @len: number of entries in the nodes array + * @self: address to place the node ID of the local node + * + * scif_get_node_ids() fills in the nodes array with up to len node IDs of the + * nodes in the SCIF network. If there is not enough space in nodes, as + * indicated by the len parameter, only len node IDs are returned in nodes. The + * return value of scif_get_node_ids() is the total number of nodes currently in + * the SCIF network. By checking the return value against the len parameter, + * the user may determine if enough space for nodes was allocated. + * + * The node ID of the local node is returned at self. + * + * Return: + * Upon successful completion, scif_get_node_ids() returns the actual number of + * online nodes in the SCIF network including 'self'; otherwise in user mode + * -1 is returned and errno is set to indicate the error; in kernel mode no + * errors are returned. + * + * Errors: + * EFAULT - Bad address + */ +int scif_get_node_ids(u16 *nodes, int len, u16 *self); + +#endif /* __SCIF_H__ */ diff --git a/include/linux/security.h b/include/linux/security.h index 18264ea9e314..79d85ddf8093 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/string.h> +#include <linux/mm.h> struct linux_binprm; struct cred; @@ -43,7 +44,6 @@ struct file; struct vfsmount; struct path; struct qstr; -struct nameidata; struct iattr; struct fown_struct; struct file_operations; @@ -54,9 +54,6 @@ struct xattr; struct xfrm_sec_ctx; struct mm_struct; -/* Maximum number of letters for an LSM name string */ -#define SECURITY_NAME_MAX 10 - /* If capable should audit the security request */ #define SECURITY_CAP_NOAUDIT 0 #define SECURITY_CAP_AUDIT 1 @@ -69,10 +66,7 @@ struct audit_krule; struct user_namespace; struct timezone; -/* - * These functions are in security/capability.c and are used - * as the default capabilities functions - */ +/* These functions are in security/commoncap.c */ extern int cap_capable(const struct cred *cred, struct user_namespace *ns, int cap, int audit); extern int cap_settime(const struct timespec *ts, const struct timezone *tz); @@ -114,10 +108,6 @@ struct xfrm_state; struct xfrm_user_sec_ctx; struct seq_file; -extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); - -void reset_security_ops(void); - #ifdef CONFIG_MMU extern unsigned long mmap_min_addr; extern unsigned long dac_mmap_min_addr; @@ -188,1581 +178,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/** - * struct security_operations - main security structure - * - * Security module identifier. - * - * @name: - * A string that acts as a unique identifier for the LSM with max number - * of characters = SECURITY_NAME_MAX. - * - * Security hooks for program execution operations. - * - * @bprm_set_creds: - * Save security information in the bprm->security field, typically based - * on information about the bprm->file, for later use by the apply_creds - * hook. This hook may also optionally check permissions (e.g. for - * transitions between security domains). - * This hook may be called multiple times during a single execve, e.g. for - * interpreters. The hook can tell whether it has already been called by - * checking to see if @bprm->security is non-NULL. If so, then the hook - * may decide either to retain the security information saved earlier or - * to replace it. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check the @bprm->security value which is set in the - * preceding set_creds call. The primary difference from set_creds is - * that the argv list and envp list are reliably available in @bprm. This - * hook may be called multiple times during a single execve; and in each - * pass set_creds is called first. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_committing_creds: - * Prepare to install the new security attributes of a process being - * transformed by an execve operation, based on the old credentials - * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_set_creds hook. @bprm points to the linux_binprm structure. - * This hook is a good place to perform state changes on the process such - * as closing open file descriptors to which access will no longer be - * granted when the attributes are changed. This is called immediately - * before commit_creds(). - * @bprm_committed_creds: - * Tidy up after the installation of the new security attributes of a - * process being transformed by an execve operation. The new credentials - * have, by this point, been set to @current->cred. @bprm points to the - * linux_binprm structure. This hook is a good place to perform state - * changes on the process such as clearing out non-inheritable signal - * state. This is called immediately after commit_creds(). - * @bprm_secureexec: - * Return a boolean value (0 or 1) indicating whether a "secure exec" - * is required. The flag is passed in the auxiliary table - * on the initial stack to the ELF interpreter to indicate whether libc - * should enable secure mode. - * @bprm contains the linux_binprm structure. - * - * Security hooks for filesystem operations. - * - * @sb_alloc_security: - * Allocate and attach a security structure to the sb->s_security field. - * The s_security field is initialized to NULL when the structure is - * allocated. - * @sb contains the super_block structure to be modified. - * Return 0 if operation was successful. - * @sb_free_security: - * Deallocate and clear the sb->s_security field. - * @sb contains the super_block structure to be modified. - * @sb_statfs: - * Check permission before obtaining filesystem statistics for the @mnt - * mountpoint. - * @dentry is a handle on the superblock for the filesystem. - * Return 0 if permission is granted. - * @sb_mount: - * Check permission before an object specified by @dev_name is mounted on - * the mount point named by @nd. For an ordinary mount, @dev_name - * identifies a device if the file system type requires a device. For a - * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a - * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the - * pathname of the object being mounted. - * @dev_name contains the name for object being mounted. - * @path contains the path for mount point object. - * @type contains the filesystem type. - * @flags contains the mount flags. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_copy_data: - * Allow mount option data to be copied prior to parsing by the filesystem, - * so that the security module can extract security-specific mount - * options cleanly (a filesystem may modify the data e.g. with strsep()). - * This also allows the original mount data to be stripped of security- - * specific options to avoid having to make filesystems aware of them. - * @type the type of filesystem being mounted. - * @orig the original mount data copied from userspace. - * @copy copied data which will be passed to the security module. - * Returns 0 if the copy was successful. - * @sb_remount: - * Extracts security system specific mount options and verifies no changes - * are being made to those options. - * @sb superblock being remounted - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_umount: - * Check permission before the @mnt file system is unmounted. - * @mnt contains the mounted file system. - * @flags contains the unmount flags, e.g. MNT_FORCE. - * Return 0 if permission is granted. - * @sb_pivotroot: - * Check permission before pivoting the root filesystem. - * @old_path contains the path for the new location of the current root (put_old). - * @new_path contains the path for the new root (new_root). - * Return 0 if permission is granted. - * @sb_set_mnt_opts: - * Set the security relevant mount options used for a superblock - * @sb the superblock to set security mount options for - * @opts binary data structure containing all lsm mount data - * @sb_clone_mnt_opts: - * Copy all security options from a given superblock to another - * @oldsb old superblock which contain information to clone - * @newsb new superblock which needs filled in - * @sb_parse_opts_str: - * Parse a string of security data filling in the opts structure - * @options string containing all mount options known by the LSM - * @opts binary data structure usable by the LSM - * @dentry_init_security: - * Compute a context for a dentry as the inode is not yet available - * since NFSv4 has no label backed by an EA anyway. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file - * @ctx pointer to place the pointer to the resulting context in. - * @ctxlen point to place the length of the resulting context. - * - * - * Security hooks for inode operations. - * - * @inode_alloc_security: - * Allocate and attach a security structure to @inode->i_security. The - * i_security field is initialized to NULL when the inode structure is - * allocated. - * @inode contains the inode structure. - * Return 0 if operation was successful. - * @inode_free_security: - * @inode contains the inode structure. - * Deallocate the inode security structure and set @inode->i_security to - * NULL. - * @inode_init_security: - * Obtain the security attribute name suffix and value to set on a newly - * created inode and set up the incore security field for the new inode. - * This hook is called by the fs code as part of the inode creation - * transaction and provides for atomic labeling of the inode, unlike - * the post_create/mkdir/... hooks called by the VFS. The hook function - * is expected to allocate the name and value via kmalloc, with the caller - * being responsible for calling kfree after using them. - * If the security module does not use security attributes or does - * not wish to put a security attribute on this particular inode, - * then it should return -EOPNOTSUPP to skip this processing. - * @inode contains the inode structure of the newly created inode. - * @dir contains the inode structure of the parent directory. - * @qstr contains the last path component of the new object - * @name will be set to the allocated name suffix (e.g. selinux). - * @value will be set to the allocated attribute value. - * @len will be set to the length of the value. - * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. - * @inode_create: - * Check permission to create a regular file. - * @dir contains inode structure of the parent of the new file. - * @dentry contains the dentry structure for the file to be created. - * @mode contains the file mode of the file to be created. - * Return 0 if permission is granted. - * @inode_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link to the file. - * @dir contains the inode structure of the parent directory of the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @path_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link - * to the file. - * @new_dir contains the path structure of the parent directory of - * the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @inode_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the inode structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @path_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the path structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @inode_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the inode structure of parent directory of the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @path_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the path structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @inode_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with inode structure @dir. - * @dir contains the inode structure of parent of the directory to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @path_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with path structure @path. - * @dir contains the path structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @inode_rmdir: - * Check the permission to remove a directory. - * @dir contains the inode structure of parent of the directory to be removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @path_rmdir: - * Check the permission to remove a directory. - * @dir contains the path structure of parent of the directory to be - * removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @inode_mknod: - * Check permissions when creating a special file (or a socket or a fifo - * file created via the mknod system call). Note that if mknod operation - * is being done for a regular file, then the create hook will be called - * and not this hook. - * @dir contains the inode structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the device number. - * Return 0 if permission is granted. - * @path_mknod: - * Check permissions when creating a file. Note that this hook is called - * even if mknod operation is being done for a regular file. - * @dir contains the path structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the undecoded device number. Use new_decode_dev() to get - * the decoded device number. - * Return 0 if permission is granted. - * @inode_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the path structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the path structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_chmod: - * Check for permission to change DAC's permission of a file or directory. - * @dentry contains the dentry structure. - * @mnt contains the vfsmnt structure. - * @mode contains DAC's mode. - * Return 0 if permission is granted. - * @path_chown: - * Check for permission to change owner/group of a file or directory. - * @path contains the path structure. - * @uid contains new owner's ID. - * @gid contains new group's ID. - * Return 0 if permission is granted. - * @path_chroot: - * Check for permission to change root directory. - * @path contains the path structure. - * Return 0 if permission is granted. - * @inode_readlink: - * Check the permission to read the symbolic link. - * @dentry contains the dentry structure for the file link. - * Return 0 if permission is granted. - * @inode_follow_link: - * Check permission to follow a symbolic link when looking up a pathname. - * @dentry contains the dentry structure for the link. - * @nd contains the nameidata structure for the parent directory. - * Return 0 if permission is granted. - * @inode_permission: - * Check permission before accessing an inode. This hook is called by the - * existing Linux permission function, so a security module can use it to - * provide additional checking for existing Linux permission checks. - * Notice that this hook is called when a file is opened (as well as many - * other operations), whereas the file_security_ops permission hook is - * called when the actual read/write operations are performed. - * @inode contains the inode structure to check. - * @mask contains the permission mask. - * Return 0 if permission is granted. - * @inode_setattr: - * Check permission before setting file attributes. Note that the kernel - * call to notify_change is performed from several locations, whenever - * file attributes change (such as when a file is truncated, chown/chmod - * operations, transferring disk quotas, etc). - * @dentry contains the dentry structure for the file. - * @attr is the iattr structure containing the new file attributes. - * Return 0 if permission is granted. - * @path_truncate: - * Check permission before truncating a file. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_getattr: - * Check permission before obtaining file attributes. - * @mnt is the vfsmount where the dentry was looked up - * @dentry contains the dentry structure for the file. - * Return 0 if permission is granted. - * @inode_setxattr: - * Check permission before setting the extended attributes - * @value identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_post_setxattr: - * Update inode security field after successful setxattr operation. - * @value identified by @name for @dentry. - * @inode_getxattr: - * Check permission before obtaining the extended attributes - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_listxattr: - * Check permission before obtaining the list of extended attribute - * names for @dentry. - * Return 0 if permission is granted. - * @inode_removexattr: - * Check permission before removing the extended attribute - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_getsecurity: - * Retrieve a copy of the extended attribute representation of the - * security label associated with @name for @inode via @buffer. Note that - * @name is the remainder of the attribute name after the security prefix - * has been removed. @alloc is used to specify of the call should return a - * value via the buffer or just the value length Return size of buffer on - * success. - * @inode_setsecurity: - * Set the security label associated with @name for @inode from the - * extended attribute value @value. @size indicates the size of the - * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. - * Note that @name is the remainder of the attribute name after the - * security. prefix has been removed. - * Return 0 on success. - * @inode_listsecurity: - * Copy the extended attribute names for the security labels - * associated with @inode into @buffer. The maximum size of @buffer - * is specified by @buffer_size. @buffer may be NULL to request - * the size of the buffer required. - * Returns number of bytes used/required on success. - * @inode_need_killpriv: - * Called when an inode has been changed. - * @dentry is the dentry being changed. - * Return <0 on error to abort the inode change operation. - * Return 0 if inode_killpriv does not need to be called. - * Return >0 if inode_killpriv does need to be called. - * @inode_killpriv: - * The setuid bit is being removed. Remove similar security labels. - * Called with the dentry->d_inode->i_mutex held. - * @dentry is the dentry being changed. - * Return 0 on success. If error is returned, then the operation - * causing setuid bit removal is failed. - * @inode_getsecid: - * Get the secid associated with the node. - * @inode contains a pointer to the inode. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for file operations - * - * @file_permission: - * Check file permissions before accessing an open file. This hook is - * called by various operations that read or write files. A security - * module can use this hook to perform additional checking on these - * operations, e.g. to revalidate permissions on use to support privilege - * bracketing or policy changes. Notice that this hook is used when the - * actual read/write operations are performed, whereas the - * inode_security_ops hook is called when a file is opened (as well as - * many other operations). - * Caveat: Although this hook can be used to revalidate permissions for - * various system call operations that read or write files, it does not - * address the revalidation of permissions for memory-mapped files. - * Security modules must handle this separately if they need such - * revalidation. - * @file contains the file structure being accessed. - * @mask contains the requested permissions. - * Return 0 if permission is granted. - * @file_alloc_security: - * Allocate and attach a security structure to the file->f_security field. - * The security field is initialized to NULL when the structure is first - * created. - * @file contains the file structure to secure. - * Return 0 if the hook is successful and permission is granted. - * @file_free_security: - * Deallocate and free any security structures stored in file->f_security. - * @file contains the file structure being modified. - * @file_ioctl: - * @file contains the file structure. - * @cmd contains the operation to perform. - * @arg contains the operational arguments. - * Check permission for an ioctl operation on @file. Note that @arg - * sometimes represents a user space pointer; in other cases, it may be a - * simple integer value. When @arg represents a user space pointer, it - * should never be used by the security module. - * Return 0 if permission is granted. - * @mmap_addr : - * Check permissions for a mmap operation at @addr. - * @addr contains virtual address that will be used for the operation. - * Return 0 if permission is granted. - * @mmap_file : - * Check permissions for a mmap operation. The @file may be NULL, e.g. - * if mapping anonymous memory. - * @file contains the file structure for file to map (may be NULL). - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @file_mprotect: - * Check permissions before changing memory access permissions. - * @vma contains the memory region to modify. - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * Return 0 if permission is granted. - * @file_lock: - * Check permission before performing file locking operations. - * Note: this hook mediates both flock and fcntl style locks. - * @file contains the file structure. - * @cmd contains the posix-translated lock operation to perform - * (e.g. F_RDLCK, F_WRLCK). - * Return 0 if permission is granted. - * @file_fcntl: - * Check permission before allowing the file operation specified by @cmd - * from being performed on the file @file. Note that @arg sometimes - * represents a user space pointer; in other cases, it may be a simple - * integer value. When @arg represents a user space pointer, it should - * never be used by the security module. - * @file contains the file structure. - * @cmd contains the operation to be performed. - * @arg contains the operational arguments. - * Return 0 if permission is granted. - * @file_set_fowner: - * Save owner security information (typically from current->security) in - * file->f_security for later use by the send_sigiotask hook. - * @file contains the file structure to update. - * Return 0 on success. - * @file_send_sigiotask: - * Check permission for the file owner @fown to send SIGIO or SIGURG to the - * process @tsk. Note that this hook is sometimes called from interrupt. - * Note that the fown_struct, @fown, is never outside the context of a - * struct file, so the file structure (and associated security information) - * can always be obtained: - * container_of(fown, struct file, f_owner) - * @tsk contains the structure of task receiving signal. - * @fown contains the file owner information. - * @sig is the signal that will be sent. When 0, kernel sends SIGIO. - * Return 0 if permission is granted. - * @file_receive: - * This hook allows security modules to control the ability of a process - * to receive an open file descriptor via socket IPC. - * @file contains the file structure being received. - * Return 0 if permission is granted. - * @file_open - * Save open-time permission checking state for later use upon - * file_permission, and recheck access if anything has changed - * since inode_permission. - * - * Security hooks for task operations. - * - * @task_create: - * Check permission before creating a child process. See the clone(2) - * manual page for definitions of the @clone_flags. - * @clone_flags contains the flags indicating what should be shared. - * Return 0 if permission is granted. - * @task_free: - * @task task being freed - * Handle release of task-related resources. (Note that this can be called - * from interrupt context.) - * @cred_alloc_blank: - * @cred points to the credentials. - * @gfp indicates the atomicity of any memory allocations. - * Only allocate sufficient memory and attach to @cred such that - * cred_transfer() will not get ENOMEM. - * @cred_free: - * @cred points to the credentials. - * Deallocate and clear the cred->security field in a set of credentials. - * @cred_prepare: - * @new points to the new credentials. - * @old points to the original credentials. - * @gfp indicates the atomicity of any memory allocations. - * Prepare a new set of credentials by copying the data from the old set. - * @cred_transfer: - * @new points to the new credentials. - * @old points to the original credentials. - * Transfer data from original creds to new creds - * @kernel_act_as: - * Set the credentials for a kernel service to act as (subjective context). - * @new points to the credentials to be modified. - * @secid specifies the security ID to be set - * The current task must be the one that nominated @secid. - * Return 0 if successful. - * @kernel_create_files_as: - * Set the file creation context in a set of credentials to be the same as - * the objective context of the specified inode. - * @new points to the credentials to be modified. - * @inode points to the inode to use as a reference. - * The current task must be the one that nominated @inode. - * Return 0 if successful. - * @kernel_fw_from_file: - * Load firmware from userspace (not called for built-in firmware). - * @file contains the file structure pointing to the file containing - * the firmware to load. This argument will be NULL if the firmware - * was loaded via the uevent-triggered blob-based interface exposed - * by CONFIG_FW_LOADER_USER_HELPER. - * @buf pointer to buffer containing firmware contents. - * @size length of the firmware contents. - * Return 0 if permission is granted. - * @kernel_module_request: - * Ability to trigger the kernel to automatically upcall to userspace for - * userspace to load a kernel module with the given name. - * @kmod_name name of the module requested by the kernel - * Return 0 if successful. - * @kernel_module_from_file: - * Load a kernel module from userspace. - * @file contains the file structure pointing to the file containing - * the kernel module to load. If the module is being loaded from a blob, - * this argument will be NULL. - * Return 0 if permission is granted. - * @task_fix_setuid: - * Update the module's state after setting one or more of the user - * identity attributes of the current process. The @flags parameter - * indicates which of the set*uid system calls invoked this hook. If - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaces - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_setpgid: - * Check permission before setting the process group identifier of the - * process @p to @pgid. - * @p contains the task_struct for process being modified. - * @pgid contains the new pgid. - * Return 0 if permission is granted. - * @task_getpgid: - * Check permission before getting the process group identifier of the - * process @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsid: - * Check permission before getting the session identifier of the process - * @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsecid: - * Retrieve the security identifier of the process @p. - * @p contains the task_struct for the process and place is into @secid. - * In case of failure, @secid will be set to zero. - * - * @task_setnice: - * Check permission before setting the nice value of @p to @nice. - * @p contains the task_struct of process. - * @nice contains the new nice value. - * Return 0 if permission is granted. - * @task_setioprio - * Check permission before setting the ioprio value of @p to @ioprio. - * @p contains the task_struct of process. - * @ioprio contains the new ioprio value - * Return 0 if permission is granted. - * @task_getioprio - * Check permission before getting the ioprio value of @p. - * @p contains the task_struct of process. - * Return 0 if permission is granted. - * @task_setrlimit: - * Check permission before setting the resource limits of the current - * process for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (current->signal->rlim + resource). - * @resource contains the resource whose limit is being set. - * @new_rlim contains the new limits for @resource. - * Return 0 if permission is granted. - * @task_setscheduler: - * Check permission before setting scheduling policy and/or parameters of - * process @p based on @policy and @lp. - * @p contains the task_struct for process. - * @policy contains the scheduling policy. - * @lp contains the scheduling parameters. - * Return 0 if permission is granted. - * @task_getscheduler: - * Check permission before obtaining scheduling information for process - * @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_movememory - * Check permission before moving memory owned by process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_kill: - * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a siginfo structure. If @info is 1 or - * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming - * from the kernel and should typically be permitted. - * SIGIO signals are handled separately by the send_sigiotask hook in - * file_security_ops. - * @p contains the task_struct for process. - * @info contains the signal information. - * @sig contains the signal value. - * @secid contains the sid of the process where the signal originated - * Return 0 if permission is granted. - * @task_wait: - * Check permission before allowing a process to reap a child process @p - * and collect its status information. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_prctl: - * Check permission before performing a process control operation on the - * current process. - * @option contains the operation. - * @arg2 contains a argument. - * @arg3 contains a argument. - * @arg4 contains a argument. - * @arg5 contains a argument. - * Return -ENOSYS if no-one wanted to handle this op, any other value to - * cause prctl() to return immediately with that value. - * @task_to_inode: - * Set the security attributes for an inode based on an associated task's - * security attributes, e.g. for /proc/pid inodes. - * @p contains the task_struct for the task. - * @inode contains the inode structure for the inode. - * - * Security hooks for Netlink messaging. - * - * @netlink_send: - * Save security information for a netlink message so that permission - * checking can be performed when the message is processed. The security - * information can be saved using the eff_cap field of the - * netlink_skb_parms structure. Also may be used to provide fine - * grained control over message transmission. - * @sk associated sock of task sending the message. - * @skb contains the sk_buff structure for the netlink message. - * Return 0 if the information was successfully saved and message - * is allowed to be transmitted. - * - * Security hooks for Unix domain networking. - * - * @unix_stream_connect: - * Check permissions before establishing a Unix domain stream connection - * between @sock and @other. - * @sock contains the sock structure. - * @other contains the peer sock structure. - * @newsk contains the new sock structure. - * Return 0 if permission is granted. - * @unix_may_send: - * Check permissions before connecting or sending datagrams from @sock to - * @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. - * Return 0 if permission is granted. - * - * The @unix_stream_connect and @unix_may_send hooks were necessary because - * Linux provides an alternative to the conventional file name space for Unix - * domain sockets. Whereas binding and connecting to sockets in the file name - * space is mediated by the typical file permissions (and caught by the mknod - * and permission hooks in inode_security_ops), binding and connecting to - * sockets in the abstract name space is completely unmediated. Sufficient - * control of Unix domain sockets in the abstract name space isn't possible - * using only the socket layer hooks, since we need to know the actual target - * socket, which is not looked up until we are inside the af_unix code. - * - * Security hooks for socket operations. - * - * @socket_create: - * Check permissions prior to creating a new socket. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. Note that the security field was not added directly to the - * socket structure, but rather, the socket security information is stored - * in the associated inode. Typically, the inode alloc_security hook will - * allocate and and attach security information to - * sock->inode->i_security. This hook may be used to update the - * sock->inode->i_security field with additional information that wasn't - * available when the inode was allocated. - * @sock contains the newly created socket structure. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * @socket_bind: - * Check permission before socket protocol layer bind operation is - * performed and the socket @sock is bound to the address specified in the - * @address parameter. - * @sock contains the socket structure. - * @address contains the address to bind to. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_connect: - * Check permission before socket protocol layer connect operation - * attempts to connect socket @sock to a remote address, @address. - * @sock contains the socket structure. - * @address contains the address of remote endpoint. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_listen: - * Check permission before socket protocol layer listen operation. - * @sock contains the socket structure. - * @backlog contains the maximum length for the pending connection queue. - * Return 0 if permission is granted. - * @socket_accept: - * Check permission before accepting a new connection. Note that the new - * socket, @newsock, has been created and some information copied to it, - * but the accept operation has not actually been performed. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. - * Return 0 if permission is granted. - * @socket_sendmsg: - * Check permission before transmitting a message to another socket. - * @sock contains the socket structure. - * @msg contains the message to be transmitted. - * @size contains the size of message. - * Return 0 if permission is granted. - * @socket_recvmsg: - * Check permission before receiving a message from a socket. - * @sock contains the socket structure. - * @msg contains the message structure. - * @size contains the size of message structure. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @socket_getsockname: - * Check permission before the local address (name) of the socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getpeername: - * Check permission before the remote address (name) of a socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getsockopt: - * Check permissions before retrieving the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to retrieve option from. - * @optname contains the name of option to retrieve. - * Return 0 if permission is granted. - * @socket_setsockopt: - * Check permissions before setting the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to set options for. - * @optname contains the name of the option to set. - * Return 0 if permission is granted. - * @socket_shutdown: - * Checks permission before all or part of a connection on the socket - * @sock is shut down. - * @sock contains the socket structure. - * @how contains the flag indicating how future sends and receives are handled. - * Return 0 if permission is granted. - * @socket_sock_rcv_skb: - * Check permissions on incoming network packets. This hook is distinct - * from Netfilter's IP input hooks since it is the first time that the - * incoming sk_buff @skb has been associated with a particular socket, @sk. - * Must not sleep inside this hook because some callers hold spinlocks. - * @sk contains the sock (not socket) associated with the incoming sk_buff. - * @skb contains the incoming network data. - * @socket_getpeersec_stream: - * This hook allows the security module to provide peer socket security - * state for unix or connected tcp sockets to userspace via getsockopt - * SO_GETPEERSEC. For tcp sockets this can be meaningful if the - * socket is associated with an ipsec SA. - * @sock is the local socket. - * @optval userspace memory where the security state is to be copied. - * @optlen userspace int where the module should copy the actual length - * of the security state. - * @len as input is the maximum length to copy to userspace provided - * by the caller. - * Return 0 if all is well, otherwise, typical getsockopt return - * values. - * @socket_getpeersec_dgram: - * This hook allows the security module to provide peer socket security - * state for udp sockets on a per-packet basis to userspace via - * getsockopt SO_GETPEERSEC. The application must first have indicated - * the IP_PASSSEC option via getsockopt. It can then retrieve the - * security state returned by this hook for a packet via the SCM_SECURITY - * ancillary message type. - * @skb is the skbuff for the packet being queried - * @secdata is a pointer to a buffer in which to copy the security data - * @seclen is the maximum length for @secdata - * Return 0 on success, error on failure. - * @sk_alloc_security: - * Allocate and attach a security structure to the sk->sk_security field, - * which is used to copy security attributes between local stream sockets. - * @sk_free_security: - * Deallocate security structure. - * @sk_clone_security: - * Clone/copy security structure. - * @sk_getsecid: - * Retrieve the LSM-specific secid for the sock to enable caching of network - * authorizations. - * @sock_graft: - * Sets the socket's isec sid to the sock's sid. - * @inet_conn_request: - * Sets the openreq's sid to socket's sid with MLS portion taken from peer sid. - * @inet_csk_clone: - * Sets the new child socket's sid to the openreq sid. - * @inet_conn_established: - * Sets the connection's peersid to the secmark on skb. - * @secmark_relabel_packet: - * check if the process should be allowed to relabel packets to the given secid - * @security_secmark_refcount_inc - * tells the LSM to increment the number of secmark labeling rules loaded - * @security_secmark_refcount_dec - * tells the LSM to decrement the number of secmark labeling rules loaded - * @req_classify_flow: - * Sets the flow's sid to the openreq sid. - * @tun_dev_alloc_security: - * This hook allows a module to allocate a security structure for a TUN - * device. - * @security pointer to a security structure pointer. - * Returns a zero on success, negative values on failure. - * @tun_dev_free_security: - * This hook allows a module to free the security structure for a TUN - * device. - * @security pointer to the TUN device's security structure - * @tun_dev_create: - * Check permissions prior to creating a new TUN device. - * @tun_dev_attach_queue: - * Check permissions prior to attaching to a TUN device queue. - * @security pointer to the TUN device's security structure. - * @tun_dev_attach: - * This hook can be used by the module to update any security state - * associated with the TUN device's sock structure. - * @sk contains the existing sock structure. - * @security pointer to the TUN device's security structure. - * @tun_dev_open: - * This hook can be used by the module to update any security state - * associated with the TUN device's security structure. - * @security pointer to the TUN devices's security structure. - * @skb_owned_by: - * This hook sets the packet's owning sock. - * @skb is the packet. - * @sk the sock which owns the packet. - * - * Security hooks for XFRM operations. - * - * @xfrm_policy_alloc_security: - * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy - * Database used by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level policy update program (e.g., setkey). - * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. - * Return 0 if operation was successful (memory to allocate, legal context) - * @gfp is to specify the context for the allocation - * @xfrm_policy_clone_security: - * @old_ctx contains an existing xfrm_sec_ctx. - * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. - * Allocate a security structure in new_ctxp that contains the - * information from the old_ctx structure. - * Return 0 if operation was successful (memory to allocate). - * @xfrm_policy_free_security: - * @ctx contains the xfrm_sec_ctx - * Deallocate xp->security. - * @xfrm_policy_delete_security: - * @ctx contains the xfrm_sec_ctx. - * Authorize deletion of xp->security. - * @xfrm_state_alloc: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to sec_ctx. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_alloc_acquire: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @polsec contains the policy's security context. - * @secid contains the secid from which to take the mls portion of the - * context. - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to secid. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_free_security: - * @x contains the xfrm_state. - * Deallocate x->security. - * @xfrm_state_delete_security: - * @x contains the xfrm_state. - * Authorize deletion of x->security. - * @xfrm_policy_lookup: - * @ctx contains the xfrm_sec_ctx for which the access control is being - * checked. - * @fl_secid contains the flow security label that is used to authorize - * access to the policy xp. - * @dir contains the direction of the flow (input or output). - * Check permission when a flow selects a xfrm_policy for processing - * XFRMs on a packet. The hook is called when selecting either a - * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted, -ESRCH otherwise, or -errno - * on other errors. - * @xfrm_state_pol_flow_match: - * @x contains the state to match. - * @xp contains the policy to check for a match. - * @fl contains the flow to check for a match. - * Return 1 if there is a match. - * @xfrm_decode_session: - * @skb points to skb to decode. - * @secid points to the flow key secid to set. - * @ckall says if all xfrms used should be checked for same secid. - * Return 0 if ckall is zero or all xfrms used have the same secid. - * - * Security hooks affecting all Key Management operations - * - * @key_alloc: - * Permit allocation of a key and assign security data. Note that key does - * not have a serial number assigned at this point. - * @key points to the key. - * @flags is the allocation flags - * Return 0 if permission is granted, -ve error otherwise. - * @key_free: - * Notification of destruction; free security data. - * @key points to the key. - * No return value. - * @key_permission: - * See whether a specific operational right is granted to a process on a - * key. - * @key_ref refers to the key (key pointer + possession attribute bit). - * @cred points to the credentials to provide the context against which to - * evaluate the security data on the key. - * @perm describes the combination of permissions required of this key. - * Return 0 if permission is granted, -ve error otherwise. - * @key_getsecurity: - * Get a textual representation of the security context attached to a key - * for the purposes of honouring KEYCTL_GETSECURITY. This function - * allocates the storage for the NUL-terminated string and the caller - * should free it. - * @key points to the key to be queried. - * @_buffer points to a pointer that should be set to point to the - * resulting string (if no label or an error occurs). - * Return the length of the string (including terminating NUL) or -ve if - * an error. - * May also return 0 (and a NULL buffer pointer) if there is no label. - * - * Security hooks affecting all System V IPC operations. - * - * @ipc_permission: - * Check permissions for access to IPC - * @ipcp contains the kernel IPC permission structure - * @flag contains the desired (requested) permission set - * Return 0 if permission is granted. - * @ipc_getsecid: - * Get the secid associated with the ipc object. - * @ipcp contains the kernel IPC permission structure. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for individual messages held in System V IPC message queues - * @msg_msg_alloc_security: - * Allocate and attach a security structure to the msg->security field. - * The security field is initialized to NULL when the structure is first - * created. - * @msg contains the message structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_msg_free_security: - * Deallocate the security structure for this message. - * @msg contains the message structure to be modified. - * - * Security hooks for System V IPC Message Queues - * - * @msg_queue_alloc_security: - * Allocate and attach a security structure to the - * msq->q_perm.security field. The security field is initialized to - * NULL when the structure is first created. - * @msq contains the message queue structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_queue_free_security: - * Deallocate security structure for this message queue. - * @msq contains the message queue structure to be modified. - * @msg_queue_associate: - * Check permission when a message queue is requested through the - * msgget system call. This hook is only called when returning the - * message queue identifier for an existing message queue, not when a - * new message queue is created. - * @msq contains the message queue to act upon. - * @msqflg contains the operation control flags. - * Return 0 if permission is granted. - * @msg_queue_msgctl: - * Check permission when a message control operation specified by @cmd - * is to be performed on the message queue @msq. - * The @msq may be NULL, e.g. for IPC_INFO or MSG_INFO. - * @msq contains the message queue to act upon. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @msg_queue_msgsnd: - * Check permission before a message, @msg, is enqueued on the message - * queue, @msq. - * @msq contains the message queue to send message to. - * @msg contains the message to be enqueued. - * @msqflg contains operational flags. - * Return 0 if permission is granted. - * @msg_queue_msgrcv: - * Check permission before a message, @msg, is removed from the message - * queue, @msq. The @target task structure contains a pointer to the - * process that will be receiving the message (not equal to the current - * process when inline receives are being performed). - * @msq contains the message queue to retrieve message from. - * @msg contains the message destination. - * @target contains the task structure for recipient process. - * @type contains the type of message requested. - * @mode contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Shared Memory Segments - * - * @shm_alloc_security: - * Allocate and attach a security structure to the shp->shm_perm.security - * field. The security field is initialized to NULL when the structure is - * first created. - * @shp contains the shared memory structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @shm_free_security: - * Deallocate the security struct for this memory segment. - * @shp contains the shared memory structure to be modified. - * @shm_associate: - * Check permission when a shared memory region is requested through the - * shmget system call. This hook is only called when returning the shared - * memory region identifier for an existing region, not when a new shared - * memory region is created. - * @shp contains the shared memory structure to be modified. - * @shmflg contains the operation control flags. - * Return 0 if permission is granted. - * @shm_shmctl: - * Check permission when a shared memory control operation specified by - * @cmd is to be performed on the shared memory region @shp. - * The @shp may be NULL, e.g. for IPC_INFO or SHM_INFO. - * @shp contains shared memory structure to be modified. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @shm_shmat: - * Check permissions prior to allowing the shmat system call to attach the - * shared memory segment @shp to the data segment of the calling process. - * The attaching address is specified by @shmaddr. - * @shp contains the shared memory structure to be modified. - * @shmaddr contains the address to attach memory region to. - * @shmflg contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Semaphores - * - * @sem_alloc_security: - * Allocate and attach a security structure to the sma->sem_perm.security - * field. The security field is initialized to NULL when the structure is - * first created. - * @sma contains the semaphore structure - * Return 0 if operation was successful and permission is granted. - * @sem_free_security: - * deallocate security struct for this semaphore - * @sma contains the semaphore structure. - * @sem_associate: - * Check permission when a semaphore is requested through the semget - * system call. This hook is only called when returning the semaphore - * identifier for an existing semaphore, not when a new one must be - * created. - * @sma contains the semaphore structure. - * @semflg contains the operation control flags. - * Return 0 if permission is granted. - * @sem_semctl: - * Check permission when a semaphore operation specified by @cmd is to be - * performed on the semaphore @sma. The @sma may be NULL, e.g. for - * IPC_INFO or SEM_INFO. - * @sma contains the semaphore structure. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @sem_semop - * Check permissions before performing operations on members of the - * semaphore set @sma. If the @alter flag is nonzero, the semaphore set - * may be modified. - * @sma contains the semaphore structure. - * @sops contains the operations to perform. - * @nsops contains the number of operations to perform. - * @alter contains the flag indicating whether changes are to be made. - * Return 0 if permission is granted. - * - * @binder_set_context_mgr - * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the task_struct for the task being registered. - * Return 0 if permission is granted. - * @binder_transaction - * Check whether @from is allowed to invoke a binder transaction call - * to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. - * @binder_transfer_binder - * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. - * @binder_transfer_file - * Check whether @from is allowed to transfer @file to @to. - * @from contains the task_struct for the sending task. - * @file contains the struct file being transferred. - * @to contains the task_struct for the receiving task. - * - * @ptrace_access_check: - * Check permission before allowing the current process to trace the - * @child process. - * Security modules may also want to perform a process tracing check - * during an execve in the set_security or apply_creds hooks of - * tracing check during an execve in the bprm_set_creds hook of - * binprm_security_ops if the process is being traced and its security - * attributes would be changed by the execve. - * @child contains the task_struct structure for the target process. - * @mode contains the PTRACE_MODE flags indicating the form of access. - * Return 0 if permission is granted. - * @ptrace_traceme: - * Check that the @parent process has sufficient permission to trace the - * current process before allowing the current process to present itself - * to the @parent process for tracing. - * @parent contains the task_struct structure for debugger process. - * Return 0 if permission is granted. - * @capget: - * Get the @effective, @inheritable, and @permitted capability sets for - * the @target process. The hook may also perform permission checking to - * determine if the current process is allowed to see the capability sets - * of the @target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if the capability sets were successfully obtained. - * @capset: - * Set the @effective, @inheritable, and @permitted capability sets for - * the current process. - * @new contains the new credentials structure for target process. - * @old contains the current credentials structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 and update @new if permission is granted. - * @capable: - * Check whether the @tsk process has the @cap capability in the indicated - * credentials. - * @cred contains the credentials to use. - * @ns contains the user namespace we want the capability in - * @cap contains the capability <include/linux/capability.h>. - * @audit: Whether to write an audit message or not - * Return 0 if the capability is granted for @tsk. - * @syslog: - * Check permission before accessing the kernel message ring or changing - * logging to the console. - * See the syslog(2) manual page for an explanation of the @type values. - * @type contains the type of action. - * @from_file indicates the context of action (if it came from /proc). - * Return 0 if permission is granted. - * @settime: - * Check permission to change the system time. - * struct timespec and timezone are defined in include/linux/time.h - * @ts contains new time - * @tz contains new timezone - * Return 0 if permission is granted. - * @vm_enough_memory: - * Check permissions for allocating a new virtual mapping. - * @mm contains the mm struct it is being added to. - * @pages contains the number of pages. - * Return 0 if permission is granted. - * - * @ismaclabel: - * Check if the extended attribute specified by @name - * represents a MAC label. Returns 1 if name is a MAC - * attribute otherwise returns 0. - * @name full extended attribute name to check against - * LSM as a MAC label. - * - * @secid_to_secctx: - * Convert secid to security context. If secdata is NULL the length of - * the result will be returned in seclen, but no secdata will be returned. - * This does mean that the length could change between calls to check the - * length and the next call which actually allocates and returns the secdata. - * @secid contains the security ID. - * @secdata contains the pointer that stores the converted security context. - * @seclen pointer which contains the length of the data - * @secctx_to_secid: - * Convert security context to secid. - * @secid contains the pointer to the generated security ID. - * @secdata contains the security context. - * - * @release_secctx: - * Release the security context. - * @secdata contains the security context. - * @seclen contains the length of the security context. - * - * Security hooks for Audit - * - * @audit_rule_init: - * Allocate and initialize an LSM audit rule structure. - * @field contains the required Audit action. Fields flags are defined in include/linux/audit.h - * @op contains the operator the rule uses. - * @rulestr contains the context where the rule will be applied to. - * @lsmrule contains a pointer to receive the result. - * Return 0 if @lsmrule has been successfully set, - * -EINVAL in case of an invalid rule. - * - * @audit_rule_known: - * Specifies whether given @rule contains any fields related to current LSM. - * @rule contains the audit rule of interest. - * Return 1 in case of relation found, 0 otherwise. - * - * @audit_rule_match: - * Determine if given @secid matches a rule previously approved - * by @audit_rule_known. - * @secid contains the security id in question. - * @field contains the field which relates to current LSM. - * @op contains the operator that will be used for matching. - * @rule points to the audit rule that will be checked against. - * @actx points to the audit context associated with the check. - * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. - * - * @audit_rule_free: - * Deallocate the LSM audit rule structure previously allocated by - * audit_rule_init. - * @rule contains the allocated rule - * - * @inode_notifysecctx: - * Notify the security module of what the security context of an inode - * should be. Initializes the incore security context managed by the - * security module for this inode. Example usage: NFS client invokes - * this hook to initialize the security context in its incore inode to the - * value provided by the server for the file when the server returned the - * file's attributes to the client. - * - * Must be called with inode->i_mutex locked. - * - * @inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * - * @inode_setsecctx: - * Change the security context of an inode. Updates the - * incore security context managed by the security module and invokes the - * fs code as needed (via __vfs_setxattr_noperm) to update any backing - * xattrs that represent the context. Example usage: NFS server invokes - * this hook to change the security context in its incore inode and on the - * backing filesystem to a value provided by the client on a SETATTR - * operation. - * - * Must be called with inode->i_mutex locked. - * - * @dentry contains the inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * - * @inode_getsecctx: - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. - * - * @inode we wish to get the security context of. - * @ctx is a pointer in which to place the allocated security context. - * @ctxlen points to the place to put the length of @ctx. - * This is the main security structure. - */ -struct security_operations { - char name[SECURITY_NAME_MAX + 1]; - - int (*binder_set_context_mgr) (struct task_struct *mgr); - int (*binder_transaction) (struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_binder) (struct task_struct *from, - struct task_struct *to); - int (*binder_transfer_file) (struct task_struct *from, - struct task_struct *to, struct file *file); - - int (*ptrace_access_check) (struct task_struct *child, unsigned int mode); - int (*ptrace_traceme) (struct task_struct *parent); - int (*capget) (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted); - int (*capset) (struct cred *new, - const struct cred *old, - const kernel_cap_t *effective, - const kernel_cap_t *inheritable, - const kernel_cap_t *permitted); - int (*capable) (const struct cred *cred, struct user_namespace *ns, - int cap, int audit); - int (*quotactl) (int cmds, int type, int id, struct super_block *sb); - int (*quota_on) (struct dentry *dentry); - int (*syslog) (int type); - int (*settime) (const struct timespec *ts, const struct timezone *tz); - int (*vm_enough_memory) (struct mm_struct *mm, long pages); - - int (*bprm_set_creds) (struct linux_binprm *bprm); - int (*bprm_check_security) (struct linux_binprm *bprm); - int (*bprm_secureexec) (struct linux_binprm *bprm); - void (*bprm_committing_creds) (struct linux_binprm *bprm); - void (*bprm_committed_creds) (struct linux_binprm *bprm); - - int (*sb_alloc_security) (struct super_block *sb); - void (*sb_free_security) (struct super_block *sb); - int (*sb_copy_data) (char *orig, char *copy); - int (*sb_remount) (struct super_block *sb, void *data); - int (*sb_kern_mount) (struct super_block *sb, int flags, void *data); - int (*sb_show_options) (struct seq_file *m, struct super_block *sb); - int (*sb_statfs) (struct dentry *dentry); - int (*sb_mount) (const char *dev_name, struct path *path, - const char *type, unsigned long flags, void *data); - int (*sb_umount) (struct vfsmount *mnt, int flags); - int (*sb_pivotroot) (struct path *old_path, - struct path *new_path); - int (*sb_set_mnt_opts) (struct super_block *sb, - struct security_mnt_opts *opts, - unsigned long kern_flags, - unsigned long *set_kern_flags); - int (*sb_clone_mnt_opts) (const struct super_block *oldsb, - struct super_block *newsb); - int (*sb_parse_opts_str) (char *options, struct security_mnt_opts *opts); - int (*dentry_init_security) (struct dentry *dentry, int mode, - struct qstr *name, void **ctx, - u32 *ctxlen); - - -#ifdef CONFIG_SECURITY_PATH - int (*path_unlink) (struct path *dir, struct dentry *dentry); - int (*path_mkdir) (struct path *dir, struct dentry *dentry, umode_t mode); - int (*path_rmdir) (struct path *dir, struct dentry *dentry); - int (*path_mknod) (struct path *dir, struct dentry *dentry, umode_t mode, - unsigned int dev); - int (*path_truncate) (struct path *path); - int (*path_symlink) (struct path *dir, struct dentry *dentry, - const char *old_name); - int (*path_link) (struct dentry *old_dentry, struct path *new_dir, - struct dentry *new_dentry); - int (*path_rename) (struct path *old_dir, struct dentry *old_dentry, - struct path *new_dir, struct dentry *new_dentry); - int (*path_chmod) (struct path *path, umode_t mode); - int (*path_chown) (struct path *path, kuid_t uid, kgid_t gid); - int (*path_chroot) (struct path *path); -#endif - - int (*inode_alloc_security) (struct inode *inode); - void (*inode_free_security) (struct inode *inode); - int (*inode_init_security) (struct inode *inode, struct inode *dir, - const struct qstr *qstr, const char **name, - void **value, size_t *len); - int (*inode_create) (struct inode *dir, - struct dentry *dentry, umode_t mode); - int (*inode_link) (struct dentry *old_dentry, - struct inode *dir, struct dentry *new_dentry); - int (*inode_unlink) (struct inode *dir, struct dentry *dentry); - int (*inode_symlink) (struct inode *dir, - struct dentry *dentry, const char *old_name); - int (*inode_mkdir) (struct inode *dir, struct dentry *dentry, umode_t mode); - int (*inode_rmdir) (struct inode *dir, struct dentry *dentry); - int (*inode_mknod) (struct inode *dir, struct dentry *dentry, - umode_t mode, dev_t dev); - int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry); - int (*inode_readlink) (struct dentry *dentry); - int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); - int (*inode_permission) (struct inode *inode, int mask); - int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); - int (*inode_getattr) (const struct path *path); - int (*inode_setxattr) (struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); - void (*inode_post_setxattr) (struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); - int (*inode_getxattr) (struct dentry *dentry, const char *name); - int (*inode_listxattr) (struct dentry *dentry); - int (*inode_removexattr) (struct dentry *dentry, const char *name); - int (*inode_need_killpriv) (struct dentry *dentry); - int (*inode_killpriv) (struct dentry *dentry); - int (*inode_getsecurity) (const struct inode *inode, const char *name, void **buffer, bool alloc); - int (*inode_setsecurity) (struct inode *inode, const char *name, const void *value, size_t size, int flags); - int (*inode_listsecurity) (struct inode *inode, char *buffer, size_t buffer_size); - void (*inode_getsecid) (const struct inode *inode, u32 *secid); - - int (*file_permission) (struct file *file, int mask); - int (*file_alloc_security) (struct file *file); - void (*file_free_security) (struct file *file); - int (*file_ioctl) (struct file *file, unsigned int cmd, - unsigned long arg); - int (*mmap_addr) (unsigned long addr); - int (*mmap_file) (struct file *file, - unsigned long reqprot, unsigned long prot, - unsigned long flags); - int (*file_mprotect) (struct vm_area_struct *vma, - unsigned long reqprot, - unsigned long prot); - int (*file_lock) (struct file *file, unsigned int cmd); - int (*file_fcntl) (struct file *file, unsigned int cmd, - unsigned long arg); - void (*file_set_fowner) (struct file *file); - int (*file_send_sigiotask) (struct task_struct *tsk, - struct fown_struct *fown, int sig); - int (*file_receive) (struct file *file); - int (*file_open) (struct file *file, const struct cred *cred); - - int (*task_create) (unsigned long clone_flags); - void (*task_free) (struct task_struct *task); - int (*cred_alloc_blank) (struct cred *cred, gfp_t gfp); - void (*cred_free) (struct cred *cred); - int (*cred_prepare)(struct cred *new, const struct cred *old, - gfp_t gfp); - void (*cred_transfer)(struct cred *new, const struct cred *old); - int (*kernel_act_as)(struct cred *new, u32 secid); - int (*kernel_create_files_as)(struct cred *new, struct inode *inode); - int (*kernel_fw_from_file)(struct file *file, char *buf, size_t size); - int (*kernel_module_request)(char *kmod_name); - int (*kernel_module_from_file)(struct file *file); - int (*task_fix_setuid) (struct cred *new, const struct cred *old, - int flags); - int (*task_setpgid) (struct task_struct *p, pid_t pgid); - int (*task_getpgid) (struct task_struct *p); - int (*task_getsid) (struct task_struct *p); - void (*task_getsecid) (struct task_struct *p, u32 *secid); - int (*task_setnice) (struct task_struct *p, int nice); - int (*task_setioprio) (struct task_struct *p, int ioprio); - int (*task_getioprio) (struct task_struct *p); - int (*task_setrlimit) (struct task_struct *p, unsigned int resource, - struct rlimit *new_rlim); - int (*task_setscheduler) (struct task_struct *p); - int (*task_getscheduler) (struct task_struct *p); - int (*task_movememory) (struct task_struct *p); - int (*task_kill) (struct task_struct *p, - struct siginfo *info, int sig, u32 secid); - int (*task_wait) (struct task_struct *p); - int (*task_prctl) (int option, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5); - void (*task_to_inode) (struct task_struct *p, struct inode *inode); - - int (*ipc_permission) (struct kern_ipc_perm *ipcp, short flag); - void (*ipc_getsecid) (struct kern_ipc_perm *ipcp, u32 *secid); - - int (*msg_msg_alloc_security) (struct msg_msg *msg); - void (*msg_msg_free_security) (struct msg_msg *msg); - - int (*msg_queue_alloc_security) (struct msg_queue *msq); - void (*msg_queue_free_security) (struct msg_queue *msq); - int (*msg_queue_associate) (struct msg_queue *msq, int msqflg); - int (*msg_queue_msgctl) (struct msg_queue *msq, int cmd); - int (*msg_queue_msgsnd) (struct msg_queue *msq, - struct msg_msg *msg, int msqflg); - int (*msg_queue_msgrcv) (struct msg_queue *msq, - struct msg_msg *msg, - struct task_struct *target, - long type, int mode); - - int (*shm_alloc_security) (struct shmid_kernel *shp); - void (*shm_free_security) (struct shmid_kernel *shp); - int (*shm_associate) (struct shmid_kernel *shp, int shmflg); - int (*shm_shmctl) (struct shmid_kernel *shp, int cmd); - int (*shm_shmat) (struct shmid_kernel *shp, - char __user *shmaddr, int shmflg); - - int (*sem_alloc_security) (struct sem_array *sma); - void (*sem_free_security) (struct sem_array *sma); - int (*sem_associate) (struct sem_array *sma, int semflg); - int (*sem_semctl) (struct sem_array *sma, int cmd); - int (*sem_semop) (struct sem_array *sma, - struct sembuf *sops, unsigned nsops, int alter); - - int (*netlink_send) (struct sock *sk, struct sk_buff *skb); - - void (*d_instantiate) (struct dentry *dentry, struct inode *inode); - - int (*getprocattr) (struct task_struct *p, char *name, char **value); - int (*setprocattr) (struct task_struct *p, char *name, void *value, size_t size); - int (*ismaclabel) (const char *name); - int (*secid_to_secctx) (u32 secid, char **secdata, u32 *seclen); - int (*secctx_to_secid) (const char *secdata, u32 seclen, u32 *secid); - void (*release_secctx) (char *secdata, u32 seclen); - - int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen); - int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen); - int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); - -#ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect) (struct sock *sock, struct sock *other, struct sock *newsk); - int (*unix_may_send) (struct socket *sock, struct socket *other); - - int (*socket_create) (int family, int type, int protocol, int kern); - int (*socket_post_create) (struct socket *sock, int family, - int type, int protocol, int kern); - int (*socket_bind) (struct socket *sock, - struct sockaddr *address, int addrlen); - int (*socket_connect) (struct socket *sock, - struct sockaddr *address, int addrlen); - int (*socket_listen) (struct socket *sock, int backlog); - int (*socket_accept) (struct socket *sock, struct socket *newsock); - int (*socket_sendmsg) (struct socket *sock, - struct msghdr *msg, int size); - int (*socket_recvmsg) (struct socket *sock, - struct msghdr *msg, int size, int flags); - int (*socket_getsockname) (struct socket *sock); - int (*socket_getpeername) (struct socket *sock); - int (*socket_getsockopt) (struct socket *sock, int level, int optname); - int (*socket_setsockopt) (struct socket *sock, int level, int optname); - int (*socket_shutdown) (struct socket *sock, int how); - int (*socket_sock_rcv_skb) (struct sock *sk, struct sk_buff *skb); - int (*socket_getpeersec_stream) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len); - int (*socket_getpeersec_dgram) (struct socket *sock, struct sk_buff *skb, u32 *secid); - int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority); - void (*sk_free_security) (struct sock *sk); - void (*sk_clone_security) (const struct sock *sk, struct sock *newsk); - void (*sk_getsecid) (struct sock *sk, u32 *secid); - void (*sock_graft) (struct sock *sk, struct socket *parent); - int (*inet_conn_request) (struct sock *sk, struct sk_buff *skb, - struct request_sock *req); - void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req); - void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb); - int (*secmark_relabel_packet) (u32 secid); - void (*secmark_refcount_inc) (void); - void (*secmark_refcount_dec) (void); - void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl); - int (*tun_dev_alloc_security) (void **security); - void (*tun_dev_free_security) (void *security); - int (*tun_dev_create) (void); - int (*tun_dev_attach_queue) (void *security); - int (*tun_dev_attach) (struct sock *sk, void *security); - int (*tun_dev_open) (void *security); -#endif /* CONFIG_SECURITY_NETWORK */ - -#ifdef CONFIG_SECURITY_NETWORK_XFRM - int (*xfrm_policy_alloc_security) (struct xfrm_sec_ctx **ctxp, - struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp); - int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx); - void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx); - int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx); - int (*xfrm_state_alloc) (struct xfrm_state *x, - struct xfrm_user_sec_ctx *sec_ctx); - int (*xfrm_state_alloc_acquire) (struct xfrm_state *x, - struct xfrm_sec_ctx *polsec, - u32 secid); - void (*xfrm_state_free_security) (struct xfrm_state *x); - int (*xfrm_state_delete_security) (struct xfrm_state *x); - int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); - int (*xfrm_state_pol_flow_match) (struct xfrm_state *x, - struct xfrm_policy *xp, - const struct flowi *fl); - int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall); -#endif /* CONFIG_SECURITY_NETWORK_XFRM */ - - /* key management security hooks */ -#ifdef CONFIG_KEYS - int (*key_alloc) (struct key *key, const struct cred *cred, unsigned long flags); - void (*key_free) (struct key *key); - int (*key_permission) (key_ref_t key_ref, - const struct cred *cred, - unsigned perm); - int (*key_getsecurity)(struct key *key, char **_buffer); -#endif /* CONFIG_KEYS */ - -#ifdef CONFIG_AUDIT - int (*audit_rule_init) (u32 field, u32 op, char *rulestr, void **lsmrule); - int (*audit_rule_known) (struct audit_krule *krule); - int (*audit_rule_match) (u32 secid, u32 field, u32 op, void *lsmrule, - struct audit_context *actx); - void (*audit_rule_free) (void *lsmrule); -#endif /* CONFIG_AUDIT */ -}; - /* prototypes */ extern int security_init(void); -extern int security_module_enable(struct security_operations *ops); -extern int register_security(struct security_operations *ops); -extern void __init security_fixup_ops(struct security_operations *ops); - /* Security operations */ int security_binder_set_context_mgr(struct task_struct *mgr); @@ -1839,7 +256,8 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); int security_inode_readlink(struct dentry *dentry); -int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); +int security_inode_follow_link(struct dentry *dentry, struct inode *inode, + bool rcu); int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); @@ -2047,7 +465,7 @@ static inline int security_settime(const struct timespec *ts, static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { - return cap_vm_enough_memory(mm, pages); + return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); } static inline int security_bprm_set_creds(struct linux_binprm *bprm) @@ -2242,7 +660,8 @@ static inline int security_inode_readlink(struct dentry *dentry) } static inline int security_inode_follow_link(struct dentry *dentry, - struct nameidata *nd) + struct inode *inode, + bool rcu) { return 0; } @@ -2650,7 +1069,7 @@ static inline int security_setprocattr(struct task_struct *p, char *name, void * static inline int security_netlink_send(struct sock *sk, struct sk_buff *skb) { - return cap_netlink_send(sk, skb); + return 0; } static inline int security_ismaclabel(const char *name) @@ -3218,36 +1637,5 @@ static inline void free_secdata(void *secdata) { } #endif /* CONFIG_SECURITY */ -#ifdef CONFIG_SECURITY_YAMA -extern int yama_ptrace_access_check(struct task_struct *child, - unsigned int mode); -extern int yama_ptrace_traceme(struct task_struct *parent); -extern void yama_task_free(struct task_struct *task); -extern int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); -#else -static inline int yama_ptrace_access_check(struct task_struct *child, - unsigned int mode) -{ - return 0; -} - -static inline int yama_ptrace_traceme(struct task_struct *parent) -{ - return 0; -} - -static inline void yama_task_free(struct task_struct *task) -{ -} - -static inline int yama_task_prctl(int option, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5) -{ - return -ENOSYS; -} -#endif /* CONFIG_SECURITY_YAMA */ - #endif /* ! __LINUX_SECURITY_H */ diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index afbb1fd77c77..912a7c482649 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -123,6 +123,7 @@ __printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); __printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args); int seq_path(struct seq_file *, const struct path *, const char *); +int seq_file_path(struct seq_file *, struct file *, const char *); int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 5f68d0a391ce..e0582106ef4f 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/preempt.h> #include <linux/lockdep.h> +#include <linux/compiler.h> #include <asm/processor.h> /* @@ -233,9 +234,128 @@ static inline void raw_write_seqcount_end(seqcount_t *s) s->sequence++; } -/* +/** + * raw_write_seqcount_barrier - do a seq write barrier + * @s: pointer to seqcount_t + * + * This can be used to provide an ordering guarantee instead of the + * usual consistency guarantee. It is one wmb cheaper, because we can + * collapse the two back-to-back wmb()s. + * + * seqcount_t seq; + * bool X = true, Y = false; + * + * void read(void) + * { + * bool x, y; + * + * do { + * int s = read_seqcount_begin(&seq); + * + * x = X; y = Y; + * + * } while (read_seqcount_retry(&seq, s)); + * + * BUG_ON(!x && !y); + * } + * + * void write(void) + * { + * Y = true; + * + * raw_write_seqcount_barrier(seq); + * + * X = false; + * } + */ +static inline void raw_write_seqcount_barrier(seqcount_t *s) +{ + s->sequence++; + smp_wmb(); + s->sequence++; +} + +static inline int raw_read_seqcount_latch(seqcount_t *s) +{ + return lockless_dereference(s->sequence); +} + +/** * raw_write_seqcount_latch - redirect readers to even/odd copy * @s: pointer to seqcount_t + * + * The latch technique is a multiversion concurrency control method that allows + * queries during non-atomic modifications. If you can guarantee queries never + * interrupt the modification -- e.g. the concurrency is strictly between CPUs + * -- you most likely do not need this. + * + * Where the traditional RCU/lockless data structures rely on atomic + * modifications to ensure queries observe either the old or the new state the + * latch allows the same for non-atomic updates. The trade-off is doubling the + * cost of storage; we have to maintain two copies of the entire data + * structure. + * + * Very simply put: we first modify one copy and then the other. This ensures + * there is always one copy in a stable state, ready to give us an answer. + * + * The basic form is a data structure like: + * + * struct latch_struct { + * seqcount_t seq; + * struct data_struct data[2]; + * }; + * + * Where a modification, which is assumed to be externally serialized, does the + * following: + * + * void latch_modify(struct latch_struct *latch, ...) + * { + * smp_wmb(); <- Ensure that the last data[1] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[0], ...); + * + * smp_wmb(); <- Ensure that the data[0] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[1], ...); + * } + * + * The query will have a form like: + * + * struct entry *latch_query(struct latch_struct *latch, ...) + * { + * struct entry *entry; + * unsigned seq, idx; + * + * do { + * seq = lockless_dereference(latch->seq); + * + * idx = seq & 0x01; + * entry = data_query(latch->data[idx], ...); + * + * smp_rmb(); + * } while (seq != latch->seq); + * + * return entry; + * } + * + * So during the modification, queries are first redirected to data[1]. Then we + * modify data[0]. When that is complete, we redirect queries back to data[0] + * and we can modify data[1]. + * + * NOTE: The non-requirement for atomic modifications does _NOT_ include + * the publishing of new entries in the case where data is a dynamic + * data structure. + * + * An iteration might start in data[0] and get suspended long enough + * to miss an entire modification sequence, once it resumes it might + * observe the new entry. + * + * NOTE: When data is a dynamic data structure; one should use regular RCU + * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_t *s) { @@ -266,13 +386,13 @@ static inline void write_seqcount_end(seqcount_t *s) } /** - * write_seqcount_barrier - invalidate in-progress read-side seq operations + * write_seqcount_invalidate - invalidate in-progress read-side seq operations * @s: pointer to seqcount_t * - * After write_seqcount_barrier, no read-side seq operations will complete + * After write_seqcount_invalidate, no read-side seq operations will complete * successfully and see data older than this. */ -static inline void write_seqcount_barrier(seqcount_t *s) +static inline void write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); s->sequence+=2; diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 78097e7a330a..ba82c07feb95 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -12,6 +12,7 @@ #define _LINUX_SERIAL_8250_H #include <linux/serial_core.h> +#include <linux/serial_reg.h> #include <linux/platform_device.h> /* @@ -137,6 +138,8 @@ extern int early_serial_setup(struct uart_port *port); extern unsigned int serial8250_early_in(struct uart_port *port, int offset); extern void serial8250_early_out(struct uart_port *port, int offset, int value); +extern int early_serial8250_setup(struct earlycon_device *device, + const char *options); extern void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old); extern int serial8250_do_startup(struct uart_port *port); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 025dad9dcde4..297d4fa1cfe5 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -35,7 +35,7 @@ #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else -#define uart_console(port) (0) +#define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 6c5e3bb282b0..7c536ac5be05 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -1,6 +1,7 @@ #ifndef __LINUX_SERIAL_SCI_H #define __LINUX_SERIAL_SCI_H +#include <linux/bitops.h> #include <linux/serial_core.h> #include <linux/sh_dma.h> @@ -10,59 +11,16 @@ #define SCIx_NOT_SUPPORTED (-1) -/* SCSMR (Serial Mode Register) */ -#define SCSMR_CHR (1 << 6) /* 7-bit Character Length */ -#define SCSMR_PE (1 << 5) /* Parity Enable */ -#define SCSMR_ODD (1 << 4) /* Odd Parity */ -#define SCSMR_STOP (1 << 3) /* Stop Bit Length */ -#define SCSMR_CKS 0x0003 /* Clock Select */ - /* Serial Control Register (@ = not supported by all parts) */ -#define SCSCR_TIE (1 << 7) /* Transmit Interrupt Enable */ -#define SCSCR_RIE (1 << 6) /* Receive Interrupt Enable */ -#define SCSCR_TE (1 << 5) /* Transmit Enable */ -#define SCSCR_RE (1 << 4) /* Receive Enable */ -#define SCSCR_REIE (1 << 3) /* Receive Error Interrupt Enable @ */ -#define SCSCR_TOIE (1 << 2) /* Timeout Interrupt Enable @ */ -#define SCSCR_CKE1 (1 << 1) /* Clock Enable 1 */ -#define SCSCR_CKE0 (1 << 0) /* Clock Enable 0 */ -/* SCIFA/SCIFB only */ -#define SCSCR_TDRQE (1 << 15) /* Tx Data Transfer Request Enable */ -#define SCSCR_RDRQE (1 << 14) /* Rx Data Transfer Request Enable */ - -/* SCxSR (Serial Status Register) on SCI */ -#define SCI_TDRE 0x80 /* Transmit Data Register Empty */ -#define SCI_RDRF 0x40 /* Receive Data Register Full */ -#define SCI_ORER 0x20 /* Overrun Error */ -#define SCI_FER 0x10 /* Framing Error */ -#define SCI_PER 0x08 /* Parity Error */ -#define SCI_TEND 0x04 /* Transmit End */ - -#define SCI_DEFAULT_ERROR_MASK (SCI_PER | SCI_FER) - -/* SCxSR (Serial Status Register) on SCIF, HSCIF */ -#define SCIF_ER 0x0080 /* Receive Error */ -#define SCIF_TEND 0x0040 /* Transmission End */ -#define SCIF_TDFE 0x0020 /* Transmit FIFO Data Empty */ -#define SCIF_BRK 0x0010 /* Break Detect */ -#define SCIF_FER 0x0008 /* Framing Error */ -#define SCIF_PER 0x0004 /* Parity Error */ -#define SCIF_RDF 0x0002 /* Receive FIFO Data Full */ -#define SCIF_DR 0x0001 /* Receive Data Ready */ - -#define SCIF_DEFAULT_ERROR_MASK (SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK) - -/* SCFCR (FIFO Control Register) */ -#define SCFCR_LOOP (1 << 0) /* Loopback Test */ - -/* SCSPTR (Serial Port Register), optional */ -#define SCSPTR_RTSIO (1 << 7) /* Serial Port RTS Pin Input/Output */ -#define SCSPTR_CTSIO (1 << 5) /* Serial Port CTS Pin Input/Output */ -#define SCSPTR_SPB2IO (1 << 1) /* Serial Port Break Input/Output */ -#define SCSPTR_SPB2DT (1 << 0) /* Serial Port Break Data */ - -/* HSSRR HSCIF */ -#define HSCIF_SRE 0x8000 /* Sampling Rate Register Enable */ +#define SCSCR_TIE BIT(7) /* Transmit Interrupt Enable */ +#define SCSCR_RIE BIT(6) /* Receive Interrupt Enable */ +#define SCSCR_TE BIT(5) /* Transmit Enable */ +#define SCSCR_RE BIT(4) /* Receive Enable */ +#define SCSCR_REIE BIT(3) /* Receive Error Interrupt Enable @ */ +#define SCSCR_TOIE BIT(2) /* Timeout Interrupt Enable @ */ +#define SCSCR_CKE1 BIT(1) /* Clock Enable 1 */ +#define SCSCR_CKE0 BIT(0) /* Clock Enable 0 */ + enum { SCIx_PROBE_REGTYPE, @@ -82,28 +40,6 @@ enum { SCIx_NR_REGTYPES, }; -/* - * SCI register subset common for all port types. - * Not all registers will exist on all parts. - */ -enum { - SCSMR, /* Serial Mode Register */ - SCBRR, /* Bit Rate Register */ - SCSCR, /* Serial Control Register */ - SCxSR, /* Serial Status Register */ - SCFCR, /* FIFO Control Register */ - SCFDR, /* FIFO Data Count Register */ - SCxTDR, /* Transmit (FIFO) Data Register */ - SCxRDR, /* Receive (FIFO) Data Register */ - SCLSR, /* Line Status Register */ - SCTFDR, /* Transmit FIFO Data Count Register */ - SCRFDR, /* Receive FIFO Data Count Register */ - SCSPTR, /* Serial Port Register */ - HSSRR, /* Sampling Rate Register */ - - SCIx_NR_REGS, -}; - struct device; struct plat_sci_port_ops { @@ -113,7 +49,7 @@ struct plat_sci_port_ops { /* * Port-specific capabilities */ -#define SCIx_HAVE_RTSCTS (1 << 0) +#define SCIx_HAVE_RTSCTS BIT(0) /* * Platform device specific platform_data struct diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 66e374d62f64..22b6d9ca1654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -34,7 +34,9 @@ #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <linux/sched.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> +#include <linux/splice.h> +#include <linux/in6.h> /* A. Checksumming of received packets by device. * @@ -170,12 +172,19 @@ struct nf_bridge_info { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE - } orig_proto; + } orig_proto:8; bool pkt_otherhost; + __u16 frag_max_size; unsigned int mask; struct net_device *physindev; - struct net_device *physoutdev; - char neigh_header[8]; + union { + struct net_device *physoutdev; + char neigh_header[8]; + }; + union { + __be32 ipv4_daddr; + struct in6_addr ipv6_daddr; + }; }; #endif @@ -858,6 +867,9 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length); +int skb_append_pagefrags(struct sk_buff *skb, struct page *page, + int offset, size_t size); + struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; @@ -918,7 +930,6 @@ skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) skb->hash = hash; } -void __skb_get_hash(struct sk_buff *skb); static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) @@ -927,6 +938,8 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } +__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); + static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; @@ -1934,8 +1947,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect(skb, &keys)) - skb_set_transport_header(skb, keys.thoff); + else if (skb_flow_dissect_flow_keys(skb, &keys)) + skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); } @@ -2126,10 +2139,6 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } -#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) -#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) -#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE - void *netdev_alloc_frag(unsigned int fragsz); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, @@ -2184,6 +2193,11 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } +static inline void skb_free_frag(void *addr) +{ + __free_page_frag(addr); +} + void *napi_alloc_frag(unsigned int fragsz); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int length, gfp_t gfp_mask); @@ -2691,9 +2705,15 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd); +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, - unsigned int flags); + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, @@ -2728,8 +2748,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -static inline void *__skb_header_pointer(const struct sk_buff *skb, int offset, - int len, void *data, int hlen, void *buffer) +static inline void * __must_check +__skb_header_pointer(const struct sk_buff *skb, int offset, + int len, void *data, int hlen, void *buffer) { if (hlen - offset >= len) return data + offset; @@ -2741,8 +2762,8 @@ static inline void *__skb_header_pointer(const struct sk_buff *skb, int offset, return buffer; } -static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, - int len, void *buffer) +static inline void * __must_check +skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); @@ -2863,11 +2884,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, @@ -3049,7 +3070,7 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, } } else if (skb->csum_bad) { /* ip_summed == CHECKSUM_NONE in this case */ - return 1; + return (__force __sum16)1; } skb->csum = psum; @@ -3297,9 +3318,6 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { #ifdef CONFIG_XFRM @@ -3354,15 +3372,14 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) - - skb_transport_offset(skb); - __u16 csum; + skb_transport_offset(skb); + __wsum partial; - csum = csum_fold(csum_partial(skb_transport_header(skb), - plen, skb->csum)); + partial = csum_partial(skb_transport_header(skb), plen, skb->csum); skb->csum = res; SKB_GSO_CB(skb)->csum_start -= plen; - return csum; + return csum_fold(partial); } static inline bool skb_is_gso(const struct sk_buff *skb) @@ -3417,10 +3434,9 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); - -u32 skb_get_poff(const struct sk_buff *skb); -u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen); +struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, + unsigned int transport_len, + __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down diff --git a/include/linux/slab.h b/include/linux/slab.h index ffd24c830151..a99f0e5243e1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -240,8 +240,8 @@ extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes - * 2 = 120 .. 192 bytes - * n = 2^(n-1) .. 2^n -1 + * 2 = 129 .. 192 bytes + * n = 2^(n-1)+1 .. 2^n */ static __always_inline int kmalloc_index(size_t size) { diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index d600afb21926..da3c593f9845 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -27,6 +27,8 @@ struct smpboot_thread_data; * @pre_unpark: Optional unpark function, called before the thread is * unparked (cpu online). This is not guaranteed to be * called on the target cpu of the thread. Careful! + * @cpumask: Internal state. To update which threads are unparked, + * call smpboot_update_cpumask_percpu_thread(). * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ @@ -41,11 +43,14 @@ struct smp_hotplug_thread { void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); void (*pre_unpark)(unsigned int cpu); + cpumask_var_t cpumask; bool selfparking; const char *thread_comm; }; int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread); void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); +int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/include/linux/soc/sunxi/sunxi_sram.h b/include/linux/soc/sunxi/sunxi_sram.h new file mode 100644 index 000000000000..c5f663bba9c2 --- /dev/null +++ b/include/linux/soc/sunxi/sunxi_sram.h @@ -0,0 +1,19 @@ +/* + * Allwinner SoCs SRAM Controller Driver + * + * Copyright (C) 2015 Maxime Ripard + * + * Author: Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _SUNXI_SRAM_H_ +#define _SUNXI_SRAM_H_ + +int sunxi_sram_claim(struct device *dev); +int sunxi_sram_release(struct device *dev); + +#endif /* _SUNXI_SRAM_H_ */ diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 083ac388098e..fddebc617469 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -1,7 +1,10 @@ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ +#include <linux/netlink.h> #include <linux/user_namespace.h> +#include <net/net_namespace.h> +#include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; @@ -11,6 +14,7 @@ struct sock; struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); + int (*get_info)(struct sk_buff *skb, struct sock *sk); }; int sock_diag_register(const struct sock_diag_handler *h); @@ -26,4 +30,42 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); +static inline +enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) +{ + switch (sk->sk_family) { + case AF_INET: + switch (sk->sk_protocol) { + case IPPROTO_TCP: + return SKNLGRP_INET_TCP_DESTROY; + case IPPROTO_UDP: + return SKNLGRP_INET_UDP_DESTROY; + default: + return SKNLGRP_NONE; + } + case AF_INET6: + switch (sk->sk_protocol) { + case IPPROTO_TCP: + return SKNLGRP_INET6_TCP_DESTROY; + case IPPROTO_UDP: + return SKNLGRP_INET6_UDP_DESTROY; + default: + return SKNLGRP_NONE; + } + default: + return SKNLGRP_NONE; + } +} + +static inline +bool sock_diag_has_destroy_listeners(const struct sock *sk) +{ + const struct net *n = sock_net(sk); + const enum sknetlink_groups group = sock_diag_destroy_group(sk); + + return group != SKNLGRP_NONE && n->diag_nlsk && + netlink_has_listeners(n->diag_nlsk, group); +} +void sock_diag_broadcast_destroy(struct sock *sk); + #endif diff --git a/include/linux/spi/cc2520.h b/include/linux/spi/cc2520.h index e741e8baad92..85b8ee67e937 100644 --- a/include/linux/spi/cc2520.h +++ b/include/linux/spi/cc2520.h @@ -21,7 +21,6 @@ struct cc2520_platform_data { int sfd; int reset; int vreg; - bool amplified; }; #endif diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 3e18379dfa6f..0063b24b4f36 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -120,7 +120,7 @@ do { \ /* * Despite its name it doesn't necessarily has to be a full barrier. * It should only guarantee that a STORE before the critical section - * can not be reordered with a LOAD inside this section. + * can not be reordered with LOADs and STOREs inside this section. * spin_lock() is the one-way barrier, this LOAD can not escape out * of the region. So the default implementation simply ensures that * a STORE can not move into the critical section, smp_wmb() should diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 4568a5cc9ab8..c3d1a525bacc 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -29,10 +29,13 @@ struct ssb_sprom { u8 il0mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11b/g */ u8 et0mac[6] __aligned(sizeof(u16)); /* MAC address for Ethernet */ u8 et1mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11a */ + u8 et2mac[6] __aligned(sizeof(u16)); /* MAC address for extra Ethernet */ u8 et0phyaddr; /* MII address for enet0 */ u8 et1phyaddr; /* MII address for enet1 */ + u8 et2phyaddr; /* MII address for enet2 */ u8 et0mdcport; /* MDIO for enet0 */ u8 et1mdcport; /* MDIO for enet1 */ + u8 et2mdcport; /* MDIO for enet2 */ u16 dev_id; /* Device ID overriding e.g. PCI ID */ u16 board_rev; /* Board revision number from SPROM. */ u16 board_num; /* Board number from SPROM. */ @@ -88,11 +91,14 @@ struct ssb_sprom { u32 ofdm5glpo; /* 5.2GHz OFDM power offset */ u32 ofdm5gpo; /* 5.3GHz OFDM power offset */ u32 ofdm5ghpo; /* 5.8GHz OFDM power offset */ + u32 boardflags; + u32 boardflags2; + u32 boardflags3; + /* TODO: Switch all drivers to new u32 fields and drop below ones */ u16 boardflags_lo; /* Board flags (bits 0-15) */ u16 boardflags_hi; /* Board flags (bits 16-31) */ u16 boardflags2_lo; /* Board flags (bits 32-47) */ u16 boardflags2_hi; /* Board flags (bits 48-63) */ - /* TODO store board flags in a single u64 */ struct ssb_sprom_core_pwr_info core_pwr_info[4]; diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 076af437284d..9c61c7cda936 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -3,7 +3,6 @@ #include <uapi/linux/stddef.h> - #undef NULL #define NULL ((void *)0) @@ -14,10 +13,9 @@ enum { #undef offsetof #ifdef __compiler_offsetof -#define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER) +#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) #else -#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) #endif /** @@ -28,3 +26,5 @@ enum { */ #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof(((TYPE *)0)->MEMBER)) + +#endif diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7f484a239f53..c735f5c91eea 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -99,6 +99,7 @@ struct plat_stmmacenet_data { int phy_addr; int interface; struct stmmac_mdio_bus_data *mdio_bus_data; + struct device_node *phy_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; diff --git a/include/linux/string.h b/include/linux/string.h index e40099e585c9..a8d90db9c4b0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,6 +111,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif void *memchr_inv(const void *s, int c, size_t n); +char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 2ca67b55e0fe..8df43c9f11dc 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -37,7 +37,6 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); -int bc_send(struct rpc_rqst *req); /* * Determine if a shared backchannel is in use diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 598ba80ec30c..131032f15cc1 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -56,6 +56,7 @@ struct rpc_clnt { struct rpc_rtt * cl_rtt; /* RTO estimator data */ const struct rpc_timeout *cl_timeout; /* Timeout strategy */ + atomic_t cl_swapper; /* swapfile count */ int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME+1]; struct rpc_pipe_dir_head cl_pipedir_objects; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 5f1e6bd4c316..d703f0ef37d8 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -205,8 +205,7 @@ struct rpc_wait_queue { */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_task(const struct rpc_task_setup *); -struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, - const struct rpc_call_ops *ops); +struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); void rpc_exit_task(struct rpc_task *); @@ -269,4 +268,20 @@ static inline void rpc_assign_waitqueue_name(struct rpc_wait_queue *q, } #endif +#if IS_ENABLED(CONFIG_SUNRPC_SWAP) +int rpc_clnt_swap_activate(struct rpc_clnt *clnt); +void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt); +#else +static inline int +rpc_clnt_swap_activate(struct rpc_clnt *clnt) +{ + return -EINVAL; +} + +static inline void +rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) +{ +} +#endif /* CONFIG_SUNRPC_SWAP */ + #endif /* _LINUX_SUNRPC_SCHED_H_ */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index df8edf8ec914..cb94ee4181d4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -172,6 +172,13 @@ struct svcxprt_rdma { #define RDMAXPRT_SQ_PENDING 2 #define RDMAXPRT_CONN_PENDING 3 +#define RPCRDMA_MAX_SVC_SEGS (64) /* server max scatter/gather */ +#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT) +#define RPCRDMA_MAXPAYLOAD RPCSVC_MAXPAYLOAD +#else +#define RPCRDMA_MAXPAYLOAD (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT) +#endif + #define RPCRDMA_LISTEN_BACKLOG 10 /* The default ORD value is based on two outstanding full-size writes with a * page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ. */ @@ -182,10 +189,9 @@ struct svcxprt_rdma { /* svc_rdma_marshal.c */ extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *); -extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *); extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, struct rpcrdma_msg *, - enum rpcrdma_errcode, u32 *); + enum rpcrdma_errcode, __be32 *); extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int); extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int); extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int, @@ -212,7 +218,6 @@ extern int svc_rdma_sendto(struct svc_rqst *); extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *, enum rpcrdma_errcode); -struct page *svc_rdma_get_page(void); extern int svc_rdma_post_recv(struct svcxprt_rdma *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8b93ef53df3c..0fb9acbb4780 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -133,6 +133,9 @@ struct rpc_xprt_ops { void (*close)(struct rpc_xprt *xprt); void (*destroy)(struct rpc_xprt *xprt); void (*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq); + int (*enable_swap)(struct rpc_xprt *xprt); + void (*disable_swap)(struct rpc_xprt *xprt); + void (*inject_disconnect)(struct rpc_xprt *xprt); }; /* @@ -180,7 +183,7 @@ struct rpc_xprt { atomic_t num_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char resvport : 1; /* use a reserved port */ - unsigned int swapper; /* we're swapping over this + atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ @@ -212,7 +215,8 @@ struct rpc_xprt { #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ /* process the callback */ - unsigned int bc_alloc_count; /* Total number of preallocs */ + int bc_alloc_count; /* Total number of preallocs */ + atomic_t bc_free_slots; spinlock_t bc_pa_lock; /* Protects the preallocated * items */ struct list_head bc_pa_list; /* List of preallocated @@ -241,6 +245,7 @@ struct rpc_xprt { const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *debugfs; /* debugfs directory */ + atomic_t inject_disconnect; #endif }; @@ -327,6 +332,18 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 * return p + xprt->tsh_size; } +static inline int +xprt_enable_swap(struct rpc_xprt *xprt) +{ + return xprt->ops->enable_swap(xprt); +} + +static inline void +xprt_disable_swap(struct rpc_xprt *xprt) +{ + xprt->ops->disable_swap(xprt); +} + /* * Transport switch helper functions */ @@ -345,7 +362,6 @@ void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); -int xs_swapper(struct rpc_xprt *xprt, int enable); bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); void xprt_unlock_connect(struct rpc_xprt *, void *); @@ -431,6 +447,23 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt) return test_and_set_bit(XPRT_BINDING, &xprt->state); } +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +extern unsigned int rpc_inject_disconnect; +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ + if (!rpc_inject_disconnect) + return; + if (atomic_dec_return(&xprt->inject_disconnect)) + return; + atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect); + xprt->ops->inject_disconnect(xprt); +} +#else +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ +} +#endif + #endif /* __KERNEL__*/ #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h index c984c85981ea..b17613052cc3 100644 --- a/include/linux/sunrpc/xprtrdma.h +++ b/include/linux/sunrpc/xprtrdma.h @@ -56,7 +56,8 @@ #define RPCRDMA_INLINE_PAD_THRESH (512)/* payload threshold to pad (bytes) */ -/* memory registration strategies */ +/* Memory registration strategies, by number. + * This is part of a kernel / user space API. Do not remove. */ enum rpcrdma_memreg { RPCRDMA_BOUNCEBUFFERS = 0, RPCRDMA_REGISTER, diff --git a/include/linux/sw842.h b/include/linux/sw842.h new file mode 100644 index 000000000000..109ba041c2ae --- /dev/null +++ b/include/linux/sw842.h @@ -0,0 +1,12 @@ +#ifndef __SW842_H__ +#define __SW842_H__ + +#define SW842_MEM_COMPRESS (0xf000) + +int sw842_compress(const u8 *src, unsigned int srclen, + u8 *dst, unsigned int *destlen, void *wmem); + +int sw842_decompress(const u8 *src, unsigned int srclen, + u8 *dst, unsigned int *destlen); + +#endif diff --git a/include/linux/swap.h b/include/linux/swap.h index cee108cbe2d5..38874729dc5f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -377,7 +377,6 @@ extern void end_swap_bio_write(struct bio *bio, int err); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, void (*end_write_func)(struct bio *, int)); extern int swap_set_page_dirty(struct page *page); -extern void end_swap_bio_read(struct bio *bio, int err); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 76d1e38aabe1..b45c45b8c829 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -111,14 +111,14 @@ union bpf_attr; #define __SC_STR_ADECL(t, a) #a #define __SC_STR_TDECL(t, a) #t -extern struct ftrace_event_class event_class_syscall_enter; -extern struct ftrace_event_class event_class_syscall_exit; +extern struct trace_event_class event_class_syscall_enter; +extern struct trace_event_class event_class_syscall_exit; extern struct trace_event_functions enter_syscall_print_funcs; extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static struct syscall_metadata __syscall_meta_##sname; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ event_enter_##sname = { \ .class = &event_class_syscall_enter, \ { \ @@ -128,13 +128,13 @@ extern struct trace_event_functions exit_syscall_print_funcs; .data = (void *)&__syscall_meta_##sname,\ .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) \ *__event_enter_##sname = &event_enter_##sname; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata __syscall_meta_##sname; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ event_exit_##sname = { \ .class = &event_class_syscall_exit, \ { \ @@ -144,7 +144,7 @@ extern struct trace_event_functions exit_syscall_print_funcs; .data = (void *)&__syscall_meta_##sname,\ .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - static struct ftrace_event_call __used \ + static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) \ *__event_exit_##sname = &event_exit_##sname; @@ -827,15 +827,15 @@ asmlinkage long sys_syncfs(int fd); asmlinkage long sys_fork(void); asmlinkage long sys_vfork(void); #ifdef CONFIG_CLONE_BACKWARDS -asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int, +asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long, int __user *); #else #ifdef CONFIG_CLONE_BACKWARDS3 asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *, - int __user *, int); + int __user *, unsigned long); #else asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, - int __user *, int); + int __user *, unsigned long); #endif #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 795d5fea5697..fa7bc29925c9 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -188,6 +188,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); + +extern struct ctl_table sysctl_mount_point[]; + #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 99382c0df17e..9f65758311a4 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -210,6 +210,10 @@ int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, int __must_check sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns); +int __must_check sysfs_create_mount_point(struct kobject *parent_kobj, + const char *name); +void sysfs_remove_mount_point(struct kobject *parent_kobj, + const char *name); int __must_check sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, @@ -298,6 +302,17 @@ static inline int sysfs_move_dir_ns(struct kobject *kobj, return 0; } +static inline int sysfs_create_mount_point(struct kobject *parent_kobj, + const char *name) +{ + return 0; +} + +static inline void sysfs_remove_mount_point(struct kobject *parent_kobj, + const char *name) +{ +} + static inline int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 4b7b875a7ce1..c3a7f0cc3a27 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -47,12 +47,12 @@ #define SYSLOG_FROM_READER 0 #define SYSLOG_FROM_PROC 1 -int do_syslog(int type, char __user *buf, int count, bool from_file); +int do_syslog(int type, char __user *buf, int count, int source); #ifdef CONFIG_PRINTK -int check_syslog_permissions(int type, bool from_file); +int check_syslog_permissions(int type, int source); #else -static inline int check_syslog_permissions(int type, bool from_file) +static inline int check_syslog_permissions(int type, int source) { return 0; } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0caa3a2d4106..48c3696e8645 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -145,10 +145,25 @@ struct tcp_sock { * read the code and the spec side by side (and laugh ...) * See RFC793 and RFC1122. The RFC writes these in capitals. */ + u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ u32 snd_nxt; /* Next sequence we send */ + u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. + */ + struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */ u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ @@ -191,6 +206,7 @@ struct tcp_sock { syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ @@ -318,6 +334,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock *fastopen_rsk; + u32 *saved_syn; }; enum tsq_flags { @@ -385,4 +402,10 @@ static inline int fastopen_init_queue(struct sock *sk, int backlog) return 0; } +static inline void tcp_saved_syn_free(struct tcp_sock *tp) +{ + kfree(tp->saved_syn); + tp->saved_syn = NULL; +} + #endif /* _LINUX_TCP_H */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 5eac316490ea..037e9df2f610 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -40,6 +40,9 @@ /* No upper/lower limit requirement */ #define THERMAL_NO_LIMIT ((u32)~0) +/* Default weight of a bound cooling device */ +#define THERMAL_WEIGHT_DEFAULT 0 + /* Unit conversion macros */ #define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ ((long)t-2732+5)/10 : ((long)t-2732-5)/10) @@ -56,10 +59,13 @@ #define DEFAULT_THERMAL_GOVERNOR "fair_share" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE) #define DEFAULT_THERMAL_GOVERNOR "user_space" +#elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR) +#define DEFAULT_THERMAL_GOVERNOR "power_allocator" #endif struct thermal_zone_device; struct thermal_cooling_device; +struct thermal_instance; enum thermal_device_mode { THERMAL_DEVICE_DISABLED = 0, @@ -113,6 +119,12 @@ struct thermal_cooling_device_ops { int (*get_max_state) (struct thermal_cooling_device *, unsigned long *); int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *); int (*set_cur_state) (struct thermal_cooling_device *, unsigned long); + int (*get_requested_power)(struct thermal_cooling_device *, + struct thermal_zone_device *, u32 *); + int (*state2power)(struct thermal_cooling_device *, + struct thermal_zone_device *, unsigned long, u32 *); + int (*power2state)(struct thermal_cooling_device *, + struct thermal_zone_device *, u32, unsigned long *); }; struct thermal_cooling_device { @@ -144,8 +156,7 @@ struct thermal_attr { * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports * @passive_delay: number of milliseconds to wait between polls when - * performing passive cooling. Currenty only used by the - * step-wise governor + * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) @@ -155,13 +166,13 @@ struct thermal_attr { * @last_temperature: previous temperature read * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION * @passive: 1 if you've crossed a passive trip point, 0 otherwise. - * Currenty only used by the step-wise governor. * @forced_passive: If > 0, temperature at which to switch on all ACPI * processor cooling devices. Currently only used by the * step-wise governor. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters * @governor: pointer to the governor for this thermal zone + * @governor_data: private pointer for governor data * @thermal_instances: list of &struct thermal_instance of this thermal zone * @idr: &struct idr to generate unique id for this zone's cooling * devices @@ -186,8 +197,9 @@ struct thermal_zone_device { int passive; unsigned int forced_passive; struct thermal_zone_device_ops *ops; - const struct thermal_zone_params *tzp; + struct thermal_zone_params *tzp; struct thermal_governor *governor; + void *governor_data; struct list_head thermal_instances; struct idr idr; struct mutex lock; @@ -198,12 +210,19 @@ struct thermal_zone_device { /** * struct thermal_governor - structure that holds thermal governor information * @name: name of the governor + * @bind_to_tz: callback called when binding to a thermal zone. If it + * returns 0, the governor is bound to the thermal zone, + * otherwise it fails. + * @unbind_from_tz: callback called when a governor is unbound from a + * thermal zone. * @throttle: callback called for every trip point even if temperature is * below the trip point temperature * @governor_list: node in thermal_governor_list (in thermal_core.c) */ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; + int (*bind_to_tz)(struct thermal_zone_device *tz); + void (*unbind_from_tz)(struct thermal_zone_device *tz); int (*throttle)(struct thermal_zone_device *tz, int trip); struct list_head governor_list; }; @@ -214,9 +233,12 @@ struct thermal_bind_params { /* * This is a measure of 'how effectively these devices can - * cool 'this' thermal zone. The shall be determined by platform - * characterization. This is on a 'percentage' scale. - * See Documentation/thermal/sysfs-api.txt for more information. + * cool 'this' thermal zone. It shall be determined by + * platform characterization. This value is relative to the + * rest of the weights so a cooling device whose weight is + * double that of another cooling device is twice as + * effective. See Documentation/thermal/sysfs-api.txt for more + * information. */ int weight; @@ -253,6 +275,44 @@ struct thermal_zone_params { int num_tbps; /* Number of tbp entries */ struct thermal_bind_params *tbp; + + /* + * Sustainable power (heat) that this thermal zone can dissipate in + * mW + */ + u32 sustainable_power; + + /* + * Proportional parameter of the PID controller when + * overshooting (i.e., when temperature is below the target) + */ + s32 k_po; + + /* + * Proportional parameter of the PID controller when + * undershooting + */ + s32 k_pu; + + /* Integral parameter of the PID controller */ + s32 k_i; + + /* Derivative parameter of the PID controller */ + s32 k_d; + + /* threshold below which the error is no longer accumulated */ + s32 integral_cutoff; + + /* + * @slope: slope of a linear temperature adjustment curve. + * Used by thermal zone drivers. + */ + int slope; + /* + * @offset: offset of a linear temperature adjustment curve. + * Used by thermal zone drivers (default 0). + */ + int offset; }; struct thermal_genl_event { @@ -316,14 +376,25 @@ void thermal_zone_of_sensor_unregister(struct device *dev, #endif #if IS_ENABLED(CONFIG_THERMAL) +static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) +{ + return cdev->ops->get_requested_power && cdev->ops->state2power && + cdev->ops->power2state; +} + +int power_actor_get_max_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *max_power); +int power_actor_set_power(struct thermal_cooling_device *, + struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, - const struct thermal_zone_params *, int, int); + struct thermal_zone_params *, int, int); void thermal_zone_device_unregister(struct thermal_zone_device *); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, - unsigned long, unsigned long); + unsigned long, unsigned long, + unsigned int); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *); @@ -343,6 +414,14 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); #else +static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) +{ return false; } +static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, u32 *max_power) +{ return 0; } +static inline int power_actor_set_power(struct thermal_cooling_device *cdev, + struct thermal_instance *tz, u32 power) +{ return 0; } static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, struct thermal_zone_device_ops *ops, diff --git a/include/linux/tick.h b/include/linux/tick.h index f8492da57ad3..edbfc9a5293e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -13,8 +13,6 @@ #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); -extern void tick_freeze(void); -extern void tick_unfreeze(void); /* Should be core only, but ARM BL switcher requires it */ extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ @@ -23,14 +21,20 @@ extern void tick_handover_do_timer(void); extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } -static inline void tick_freeze(void) { } -static inline void tick_unfreeze(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } static inline void tick_handover_do_timer(void) { } static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND) +extern void tick_freeze(void); +extern void tick_unfreeze(void); +#else +static inline void tick_freeze(void) { } +static inline void tick_unfreeze(void) { } +#endif + #ifdef CONFIG_TICK_ONESHOT extern void tick_irq_enter(void); # ifndef arch_needs_cpu @@ -63,10 +67,13 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +#ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else -static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } +static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + return 0; +} #endif static inline void tick_broadcast_enable(void) @@ -134,6 +141,12 @@ static inline bool tick_nohz_full_cpu(int cpu) return cpumask_test_cpu(cpu, tick_nohz_full_mask); } +static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) +{ + if (tick_nohz_full_enabled()) + cpumask_or(mask, mask, tick_nohz_full_mask); +} + extern void __tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); @@ -142,6 +155,7 @@ extern void __tick_nohz_task_switch(struct task_struct *tsk); #else static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } +static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void __tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void tick_nohz_full_kick(void) { } diff --git a/include/linux/time64.h b/include/linux/time64.h index a3831478d9cf..77b5df2acd2a 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -2,6 +2,7 @@ #define _LINUX_TIME64_H #include <uapi/linux/time.h> +#include <linux/math64.h> typedef __s64 time64_t; @@ -28,6 +29,7 @@ struct timespec64 { #define FSEC_PER_SEC 1000000000000000LL /* Located here for timespec[64]_valid_strict */ +#define TIME64_MAX ((s64)~((u64)1 << 63)) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index fb86963859c7..25247220b4b7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -49,6 +49,8 @@ struct tk_read_base { * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai * @tai_offset: The current UTC to TAI offset in seconds + * @clock_was_set_seq: The sequence number of clock was set events + * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second * @raw_time: Monotonic raw base time in timespec64 format * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP @@ -60,6 +62,9 @@ struct tk_read_base { * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. + * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) + * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) + * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffie times) @@ -85,6 +90,8 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; + unsigned int clock_was_set_seq; + ktime_t next_leap_ktime; struct timespec64 raw_time; /* The following members are for timekeeping internal use */ @@ -104,6 +111,18 @@ struct timekeeper { s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; +#ifdef CONFIG_DEBUG_TIMEKEEPING + long last_warning; + /* + * These simple flag variables are managed + * without locks, which is racy, but they are + * ok since we don't really care about being + * super precise about how many events were + * seen, just that a problem was observed. + */ + int underflow_seen; + int overflow_seen; +#endif }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 99176af216af..6e191e4e6ab6 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -145,7 +145,6 @@ static inline void getboottime(struct timespec *ts) } #endif -#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* @@ -163,6 +162,7 @@ extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); +extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format @@ -266,7 +266,6 @@ extern int persistent_clock_is_local; extern void read_persistent_clock(struct timespec *ts); extern void read_persistent_clock64(struct timespec64 *ts); -extern void read_boot_clock(struct timespec *ts); extern void read_boot_clock64(struct timespec64 *ts); extern int update_persistent_clock(struct timespec now); extern int update_persistent_clock64(struct timespec64 now); diff --git a/include/linux/timer.h b/include/linux/timer.h index 8c5a197e1587..61aa61dc410c 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -14,27 +14,23 @@ struct timer_list { * All fields that change during normal runtime grouped to the * same cacheline */ - struct list_head entry; - unsigned long expires; - struct tvec_base *base; - - void (*function)(unsigned long); - unsigned long data; - - int slack; + struct hlist_node entry; + unsigned long expires; + void (*function)(unsigned long); + unsigned long data; + u32 flags; + int slack; #ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; + int start_pid; + void *start_site; + char start_comm[16]; #endif #ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; + struct lockdep_map lockdep_map; #endif }; -extern struct tvec_base boot_tvec_bases; - #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting the lockdep_map key @@ -49,9 +45,6 @@ extern struct tvec_base boot_tvec_bases; #endif /* - * Note that all tvec_bases are at least 4 byte aligned and lower two bits - * of base in timer_list is guaranteed to be zero. Use them for flags. - * * A deferrable timer will work normally when the system is busy, but * will not cause a CPU to come out of idle just to service it; instead, * the timer will be serviced when the CPU eventually wakes up with a @@ -65,17 +58,18 @@ extern struct tvec_base boot_tvec_bases; * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! */ -#define TIMER_DEFERRABLE 0x1LU -#define TIMER_IRQSAFE 0x2LU - -#define TIMER_FLAG_MASK 0x3LU +#define TIMER_CPUMASK 0x0007FFFF +#define TIMER_MIGRATING 0x00080000 +#define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) +#define TIMER_DEFERRABLE 0x00100000 +#define TIMER_IRQSAFE 0x00200000 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ - .entry = { .prev = TIMER_ENTRY_STATIC }, \ + .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ .expires = (_expires), \ .data = (_data), \ - .base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \ + .flags = (_flags), \ .slack = -1, \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ @@ -168,7 +162,7 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, */ static inline int timer_pending(const struct timer_list * timer) { - return timer->entry.next != NULL; + return timer->entry.pprev != NULL; } extern void add_timer_on(struct timer_list *timer, int cpu); @@ -188,26 +182,16 @@ extern void set_timer_slack(struct timer_list *time, int slack_hz); #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) /* - * Return when the next timer-wheel timeout occurs (in absolute jiffies), - * locks the timer base and does the comparison against the given - * jiffie. - */ -extern unsigned long get_next_timer_interrupt(unsigned long now); - -/* * Timer-statistics info: */ #ifdef CONFIG_TIMER_STATS extern int timer_stats_active; -#define TIMER_STATS_FLAG_DEFERRABLE 0x1 - extern void init_timer_stats(void); extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, - unsigned int timer_flag); + void *timerf, char *comm, u32 flags); extern void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr); @@ -254,6 +238,15 @@ extern void run_local_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +#include <linux/sysctl.h> + +extern unsigned int sysctl_timer_migration; +int timer_migration_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index a520fd70a59f..7eec17ad7fa1 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -16,10 +16,10 @@ struct timerqueue_head { }; -extern void timerqueue_add(struct timerqueue_head *head, - struct timerqueue_node *node); -extern void timerqueue_del(struct timerqueue_head *head, - struct timerqueue_node *node); +extern bool timerqueue_add(struct timerqueue_head *head, + struct timerqueue_node *node); +extern bool timerqueue_del(struct timerqueue_head *head, + struct timerqueue_node *node); extern struct timerqueue_node *timerqueue_iterate_next( struct timerqueue_node *node); diff --git a/include/linux/topology.h b/include/linux/topology.h index 909b6e43b694..73ddad1e0fa3 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -191,8 +191,8 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif -#ifndef topology_thread_cpumask -#define topology_thread_cpumask(cpu) cpumask_of(cpu) +#ifndef topology_sibling_cpumask +#define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) @@ -201,7 +201,7 @@ static inline int cpu_to_mem(int cpu) #ifdef CONFIG_SCHED_SMT static inline const struct cpumask *cpu_smt_mask(int cpu) { - return topology_thread_cpumask(cpu); + return topology_sibling_cpumask(cpu); } #endif diff --git a/include/linux/ftrace_event.h b/include/linux/trace_events.h index f9ecf63d47f1..1063c850dbab 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/trace_events.h @@ -1,6 +1,6 @@ -#ifndef _LINUX_FTRACE_EVENT_H -#define _LINUX_FTRACE_EVENT_H +#ifndef _LINUX_TRACE_EVENT_H +#define _LINUX_TRACE_EVENT_H #include <linux/ring_buffer.h> #include <linux/trace_seq.h> @@ -25,35 +25,35 @@ struct trace_print_flags_u64 { const char *name; }; -const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim, - unsigned long flags, - const struct trace_print_flags *flag_array); +const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, + unsigned long flags, + const struct trace_print_flags *flag_array); -const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, - const struct trace_print_flags *symbol_array); +const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val, + const struct trace_print_flags *symbol_array); #if BITS_PER_LONG == 32 -const char *ftrace_print_symbols_seq_u64(struct trace_seq *p, - unsigned long long val, - const struct trace_print_flags_u64 +const char *trace_print_symbols_seq_u64(struct trace_seq *p, + unsigned long long val, + const struct trace_print_flags_u64 *symbol_array); #endif -const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, - unsigned int bitmask_size); +const char *trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, + unsigned int bitmask_size); -const char *ftrace_print_hex_seq(struct trace_seq *p, - const unsigned char *buf, int len); +const char *trace_print_hex_seq(struct trace_seq *p, + const unsigned char *buf, int len); -const char *ftrace_print_array_seq(struct trace_seq *p, +const char *trace_print_array_seq(struct trace_seq *p, const void *buf, int count, size_t el_size); struct trace_iterator; struct trace_event; -int ftrace_raw_output_prep(struct trace_iterator *iter, - struct trace_event *event); +int trace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *event); /* * The trace entry - the most basic unit of tracing. This is what @@ -68,7 +68,7 @@ struct trace_entry { int pid; }; -#define FTRACE_MAX_EVENT \ +#define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1) /* @@ -132,8 +132,8 @@ struct trace_event { struct trace_event_functions *funcs; }; -extern int register_ftrace_event(struct trace_event *event); -extern int unregister_ftrace_event(struct trace_event *event); +extern int register_trace_event(struct trace_event *event); +extern int unregister_trace_event(struct trace_event *event); /* Return values for print_line callback */ enum print_line_t { @@ -157,11 +157,11 @@ static inline enum print_line_t trace_handle_return(struct trace_seq *s) void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); -struct ftrace_event_file; +struct trace_event_file; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, - struct ftrace_event_file *ftrace_file, + struct trace_event_file *trace_file, int type, unsigned long len, unsigned long flags, int pc); struct ring_buffer_event * @@ -183,7 +183,7 @@ void trace_current_buffer_discard_commit(struct ring_buffer *buffer, void tracing_record_cmdline(struct task_struct *tsk); -int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); +int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...); struct event_filter; @@ -200,50 +200,39 @@ enum trace_reg { #endif }; -struct ftrace_event_call; +struct trace_event_call; -struct ftrace_event_class { +struct trace_event_class { const char *system; void *probe; #ifdef CONFIG_PERF_EVENTS void *perf_probe; #endif - int (*reg)(struct ftrace_event_call *event, + int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); - int (*define_fields)(struct ftrace_event_call *); - struct list_head *(*get_fields)(struct ftrace_event_call *); + int (*define_fields)(struct trace_event_call *); + struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; - int (*raw_init)(struct ftrace_event_call *); + int (*raw_init)(struct trace_event_call *); }; -extern int ftrace_event_reg(struct ftrace_event_call *event, +extern int trace_event_reg(struct trace_event_call *event, enum trace_reg type, void *data); -int ftrace_output_event(struct trace_iterator *iter, struct ftrace_event_call *event, - char *fmt, ...); - -int ftrace_event_define_field(struct ftrace_event_call *call, - char *type, int len, char *item, int offset, - int field_size, int sign, int filter); - -struct ftrace_event_buffer { +struct trace_event_buffer { struct ring_buffer *buffer; struct ring_buffer_event *event; - struct ftrace_event_file *ftrace_file; + struct trace_event_file *trace_file; void *entry; unsigned long flags; int pc; }; -void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer, - struct ftrace_event_file *ftrace_file, +void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, + struct trace_event_file *trace_file, unsigned long len); -void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer); - -int ftrace_event_define_field(struct ftrace_event_call *call, - char *type, int len, char *item, int offset, - int field_size, int sign, int filter); +void trace_event_buffer_commit(struct trace_event_buffer *fbuffer); enum { TRACE_EVENT_FL_FILTERED_BIT, @@ -261,11 +250,11 @@ enum { * FILTERED - The event has a filter attached * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored - * IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file + * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file * WAS_ENABLED - Set and stays set when an event was ever enabled * (used for module unloading, if a module event is enabled, * it is best to clear the buffers that used it). - * USE_CALL_FILTER - For ftrace internal events, don't use file filter + * USE_CALL_FILTER - For trace internal events, don't use file filter * TRACEPOINT - Event is a tracepoint * KPROBE - Event is a kprobe */ @@ -280,9 +269,9 @@ enum { TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), }; -struct ftrace_event_call { +struct trace_event_call { struct list_head list; - struct ftrace_event_class *class; + struct trace_event_class *class; union { char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ @@ -297,7 +286,7 @@ struct ftrace_event_call { * bit 0: filter_active * bit 1: allow trace by non root (cap any) * bit 2: failed to apply filter - * bit 3: ftrace internal event (do not enable) + * bit 3: trace internal event (do not enable) * bit 4: Event was enabled by module * bit 5: use call filter rather than file filter * bit 6: Event is a tracepoint @@ -309,13 +298,13 @@ struct ftrace_event_call { struct hlist_head __percpu *perf_events; struct bpf_prog *prog; - int (*perf_perm)(struct ftrace_event_call *, + int (*perf_perm)(struct trace_event_call *, struct perf_event *); #endif }; static inline const char * -ftrace_event_name(struct ftrace_event_call *call) +trace_event_name(struct trace_event_call *call) { if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; @@ -324,21 +313,21 @@ ftrace_event_name(struct ftrace_event_call *call) } struct trace_array; -struct ftrace_subsystem_dir; +struct trace_subsystem_dir; enum { - FTRACE_EVENT_FL_ENABLED_BIT, - FTRACE_EVENT_FL_RECORDED_CMD_BIT, - FTRACE_EVENT_FL_FILTERED_BIT, - FTRACE_EVENT_FL_NO_SET_FILTER_BIT, - FTRACE_EVENT_FL_SOFT_MODE_BIT, - FTRACE_EVENT_FL_SOFT_DISABLED_BIT, - FTRACE_EVENT_FL_TRIGGER_MODE_BIT, - FTRACE_EVENT_FL_TRIGGER_COND_BIT, + EVENT_FILE_FL_ENABLED_BIT, + EVENT_FILE_FL_RECORDED_CMD_BIT, + EVENT_FILE_FL_FILTERED_BIT, + EVENT_FILE_FL_NO_SET_FILTER_BIT, + EVENT_FILE_FL_SOFT_MODE_BIT, + EVENT_FILE_FL_SOFT_DISABLED_BIT, + EVENT_FILE_FL_TRIGGER_MODE_BIT, + EVENT_FILE_FL_TRIGGER_COND_BIT, }; /* - * Ftrace event file flags: + * Event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch * FILTERED - The event has a filter attached @@ -350,23 +339,23 @@ enum { * TRIGGER_COND - When set, one or more triggers has an associated filter */ enum { - FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT), - FTRACE_EVENT_FL_RECORDED_CMD = (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT), - FTRACE_EVENT_FL_FILTERED = (1 << FTRACE_EVENT_FL_FILTERED_BIT), - FTRACE_EVENT_FL_NO_SET_FILTER = (1 << FTRACE_EVENT_FL_NO_SET_FILTER_BIT), - FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT), - FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT), - FTRACE_EVENT_FL_TRIGGER_MODE = (1 << FTRACE_EVENT_FL_TRIGGER_MODE_BIT), - FTRACE_EVENT_FL_TRIGGER_COND = (1 << FTRACE_EVENT_FL_TRIGGER_COND_BIT), + EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), + EVENT_FILE_FL_RECORDED_CMD = (1 << EVENT_FILE_FL_RECORDED_CMD_BIT), + EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), + EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), + EVENT_FILE_FL_SOFT_MODE = (1 << EVENT_FILE_FL_SOFT_MODE_BIT), + EVENT_FILE_FL_SOFT_DISABLED = (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT), + EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), + EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), }; -struct ftrace_event_file { +struct trace_event_file { struct list_head list; - struct ftrace_event_call *event_call; + struct trace_event_call *event_call; struct event_filter *filter; struct dentry *dir; struct trace_array *tr; - struct ftrace_subsystem_dir *system; + struct trace_subsystem_dir *system; struct list_head triggers; /* @@ -399,7 +388,7 @@ struct ftrace_event_file { early_initcall(trace_init_flags_##name); #define __TRACE_EVENT_PERF_PERM(name, expr...) \ - static int perf_perm_##name(struct ftrace_event_call *tp_event, \ + static int perf_perm_##name(struct trace_event_call *tp_event, \ struct perf_event *p_event) \ { \ return ({ expr; }); \ @@ -425,19 +414,19 @@ enum event_trigger_type { extern int filter_match_preds(struct event_filter *filter, void *rec); -extern int filter_check_discard(struct ftrace_event_file *file, void *rec, +extern int filter_check_discard(struct trace_event_file *file, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event); -extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec, +extern int call_filter_check_discard(struct trace_event_call *call, void *rec, struct ring_buffer *buffer, struct ring_buffer_event *event); -extern enum event_trigger_type event_triggers_call(struct ftrace_event_file *file, +extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, void *rec); -extern void event_triggers_post_call(struct ftrace_event_file *file, +extern void event_triggers_post_call(struct trace_event_file *file, enum event_trigger_type tt); /** - * ftrace_trigger_soft_disabled - do triggers and test if soft disabled + * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test * * If any triggers without filters are attached to this event, they @@ -446,14 +435,14 @@ extern void event_triggers_post_call(struct ftrace_event_file *file, * otherwise false. */ static inline bool -ftrace_trigger_soft_disabled(struct ftrace_event_file *file) +trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; - if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) { - if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE) + if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { + if (eflags & EVENT_FILE_FL_TRIGGER_MODE) event_triggers_call(file, NULL); - if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED) + if (eflags & EVENT_FILE_FL_SOFT_DISABLED) return true; } return false; @@ -473,7 +462,7 @@ ftrace_trigger_soft_disabled(struct ftrace_event_file *file) * Returns true if the event is discarded, false otherwise. */ static inline bool -__event_trigger_test_discard(struct ftrace_event_file *file, +__event_trigger_test_discard(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, @@ -481,10 +470,10 @@ __event_trigger_test_discard(struct ftrace_event_file *file, { unsigned long eflags = file->flags; - if (eflags & FTRACE_EVENT_FL_TRIGGER_COND) + if (eflags & EVENT_FILE_FL_TRIGGER_COND) *tt = event_triggers_call(file, entry); - if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags)) + if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags)) ring_buffer_discard_commit(buffer, event); else if (!filter_check_discard(file, entry, buffer, event)) return false; @@ -506,7 +495,7 @@ __event_trigger_test_discard(struct ftrace_event_file *file, * if the event is soft disabled and should be discarded. */ static inline void -event_trigger_unlock_commit(struct ftrace_event_file *file, +event_trigger_unlock_commit(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc) @@ -537,7 +526,7 @@ event_trigger_unlock_commit(struct ftrace_event_file *file, * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). */ static inline void -event_trigger_unlock_commit_regs(struct ftrace_event_file *file, +event_trigger_unlock_commit_regs(struct trace_event_file *file, struct ring_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc, @@ -570,12 +559,12 @@ enum { FILTER_TRACE_FN, }; -extern int trace_event_raw_init(struct ftrace_event_call *call); -extern int trace_define_field(struct ftrace_event_call *call, const char *type, +extern int trace_event_raw_init(struct trace_event_call *call); +extern int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); -extern int trace_add_event_call(struct ftrace_event_call *call); -extern int trace_remove_event_call(struct ftrace_event_call *call); +extern int trace_add_event_call(struct trace_event_call *call); +extern int trace_remove_event_call(struct trace_event_call *call); #define is_signed_type(type) (((type)(-1)) < (type)1) @@ -624,4 +613,4 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, } #endif -#endif /* _LINUX_FTRACE_EVENT_H */ +#endif /* _LINUX_TRACE_EVENT_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index fe5623c9af71..ad6c8913aa3e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -339,6 +339,7 @@ struct tty_file_private { #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ #define TTY_DEBUG 4 /* Debugging */ #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ +#define TTY_OTHER_DONE 6 /* Closed pty has completed input processing */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ @@ -421,7 +422,7 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) extern int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, const char *routine); -extern char *tty_name(struct tty_struct *tty, char *buf); +extern const char *tty_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); extern int tty_check_change(struct tty_struct *tty); extern void __stop_tty(struct tty_struct *tty); @@ -462,7 +463,6 @@ extern int tty_hung_up_p(struct file *filp); extern void do_SAK(struct tty_struct *tty); extern void __do_SAK(struct tty_struct *tty); extern void no_tty(void); -extern void tty_flush_to_ldisc(struct tty_struct *tty); extern void tty_buffer_free_all(struct tty_port *port); extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); extern void tty_buffer_init(struct tty_port *port); diff --git a/include/linux/types.h b/include/linux/types.h index 59698be03490..8715287c3b1f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -139,12 +139,20 @@ typedef unsigned long blkcnt_t; */ #define pgoff_t unsigned long -/* A dma_addr_t can hold any valid DMA or bus address for the platform */ +/* + * A dma_addr_t can hold any valid DMA address, i.e., any address returned + * by the DMA API. + * + * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32 + * bits wide. Bus addresses, e.g., PCI BARs, may be wider than 32 bits, + * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses, + * so they don't care about the size of the actual bus addresses. + */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; #else typedef u32 dma_addr_t; -#endif /* dma_addr_t */ +#endif typedef unsigned __bitwise__ gfp_t; typedef unsigned __bitwise__ fmode_t; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 4b4439e75f45..df89c9bcba7d 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -68,11 +68,12 @@ struct u64_stats_sync { }; +static inline void u64_stats_init(struct u64_stats_sync *syncp) +{ #if BITS_PER_LONG == 32 && defined(CONFIG_SMP) -# define u64_stats_init(syncp) seqcount_init(syncp.seq) -#else -# define u64_stats_init(syncp) do { } while (0) + seqcount_init(&syncp->seq); #endif +} static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ecd3319dac33..ae572c138607 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -1,21 +1,30 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ -#include <linux/preempt.h> +#include <linux/sched.h> #include <asm/uaccess.h> +static __always_inline void pagefault_disabled_inc(void) +{ + current->pagefault_disabled++; +} + +static __always_inline void pagefault_disabled_dec(void) +{ + current->pagefault_disabled--; + WARN_ON(current->pagefault_disabled < 0); +} + /* - * These routines enable/disable the pagefault handler in that - * it will not take any locks and go straight to the fixup table. + * These routines enable/disable the pagefault handler. If disabled, it will + * not take any locks and go straight to the fixup table. * - * They have great resemblance to the preempt_disable/enable calls - * and in fact they are identical; this is because currently there is - * no other way to make the pagefault handlers do this. So we do - * disable preemption but we don't necessarily care about that. + * User access methods will not sleep when called from a pagefault_disabled() + * environment. */ static inline void pagefault_disable(void) { - preempt_count_inc(); + pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. @@ -25,18 +34,31 @@ static inline void pagefault_disable(void) static inline void pagefault_enable(void) { -#ifndef CONFIG_PREEMPT /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); - preempt_count_dec(); -#else - preempt_enable(); -#endif + pagefault_disabled_dec(); } +/* + * Is the pagefault handler disabled? If so, user access methods will not sleep. + */ +#define pagefault_disabled() (current->pagefault_disabled != 0) + +/* + * The pagefault handler is in general disabled by pagefault_disable() or + * when in irq context (via in_atomic()). + * + * This function should only be used by the fault handlers. Other users should + * stick to pagefault_disabled(). + * Please NEVER use preempt_disable() to disable the fault handler. With + * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. + * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. + */ +#define faulthandler_disabled() (pagefault_disabled() || in_atomic()) + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline unsigned long __copy_from_user_inatomic_nocache(void *to, diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 0ee05da38899..03835522dfcb 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -109,12 +109,12 @@ static inline bool gid_lte(kgid_t left, kgid_t right) static inline bool uid_valid(kuid_t uid) { - return !uid_eq(uid, INVALID_UID); + return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { - return !gid_eq(gid, INVALID_GID); + return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS diff --git a/include/linux/ulpi/driver.h b/include/linux/ulpi/driver.h new file mode 100644 index 000000000000..388f6e08b9d4 --- /dev/null +++ b/include/linux/ulpi/driver.h @@ -0,0 +1,60 @@ +#ifndef __LINUX_ULPI_DRIVER_H +#define __LINUX_ULPI_DRIVER_H + +#include <linux/mod_devicetable.h> + +#include <linux/device.h> + +struct ulpi_ops; + +/** + * struct ulpi - describes ULPI PHY device + * @id: vendor and product ids for ULPI device + * @ops: I/O access + * @dev: device interface + */ +struct ulpi { + struct ulpi_device_id id; + struct ulpi_ops *ops; + struct device dev; +}; + +#define to_ulpi_dev(d) container_of(d, struct ulpi, dev) + +static inline void ulpi_set_drvdata(struct ulpi *ulpi, void *data) +{ + dev_set_drvdata(&ulpi->dev, data); +} + +static inline void *ulpi_get_drvdata(struct ulpi *ulpi) +{ + return dev_get_drvdata(&ulpi->dev); +} + +/** + * struct ulpi_driver - describes a ULPI PHY driver + * @id_table: array of device identifiers supported by this driver + * @probe: binds this driver to ULPI device + * @remove: unbinds this driver from ULPI device + * @driver: the name and owner members must be initialized by the drivers + */ +struct ulpi_driver { + const struct ulpi_device_id *id_table; + int (*probe)(struct ulpi *ulpi); + void (*remove)(struct ulpi *ulpi); + struct device_driver driver; +}; + +#define to_ulpi_driver(d) container_of(d, struct ulpi_driver, driver) + +int ulpi_register_driver(struct ulpi_driver *drv); +void ulpi_unregister_driver(struct ulpi_driver *drv); + +#define module_ulpi_driver(__ulpi_driver) \ + module_driver(__ulpi_driver, ulpi_register_driver, \ + ulpi_unregister_driver) + +int ulpi_read(struct ulpi *ulpi, u8 addr); +int ulpi_write(struct ulpi *ulpi, u8 addr, u8 val); + +#endif /* __LINUX_ULPI_DRIVER_H */ diff --git a/include/linux/ulpi/interface.h b/include/linux/ulpi/interface.h new file mode 100644 index 000000000000..4de8ab491038 --- /dev/null +++ b/include/linux/ulpi/interface.h @@ -0,0 +1,23 @@ +#ifndef __LINUX_ULPI_INTERFACE_H +#define __LINUX_ULPI_INTERFACE_H + +#include <linux/types.h> + +struct ulpi; + +/** + * struct ulpi_ops - ULPI register access + * @dev: the interface provider + * @read: read operation for ULPI register access + * @write: write operation for ULPI register access + */ +struct ulpi_ops { + struct device *dev; + int (*read)(struct ulpi_ops *ops, u8 addr); + int (*write)(struct ulpi_ops *ops, u8 addr, u8 val); +}; + +struct ulpi *ulpi_register_interface(struct device *, struct ulpi_ops *); +void ulpi_unregister_interface(struct ulpi *); + +#endif /* __LINUX_ULPI_INTERFACE_H */ diff --git a/include/linux/ulpi/regs.h b/include/linux/ulpi/regs.h new file mode 100644 index 000000000000..b5b8b8804560 --- /dev/null +++ b/include/linux/ulpi/regs.h @@ -0,0 +1,130 @@ +#ifndef __LINUX_ULPI_REGS_H +#define __LINUX_ULPI_REGS_H + +/* + * Macros for Set and Clear + * See ULPI 1.1 specification to find the registers with Set and Clear offsets + */ +#define ULPI_SET(a) (a + 1) +#define ULPI_CLR(a) (a + 2) + +/* + * Register Map + */ +#define ULPI_VENDOR_ID_LOW 0x00 +#define ULPI_VENDOR_ID_HIGH 0x01 +#define ULPI_PRODUCT_ID_LOW 0x02 +#define ULPI_PRODUCT_ID_HIGH 0x03 +#define ULPI_FUNC_CTRL 0x04 +#define ULPI_IFC_CTRL 0x07 +#define ULPI_OTG_CTRL 0x0a +#define ULPI_USB_INT_EN_RISE 0x0d +#define ULPI_USB_INT_EN_FALL 0x10 +#define ULPI_USB_INT_STS 0x13 +#define ULPI_USB_INT_LATCH 0x14 +#define ULPI_DEBUG 0x15 +#define ULPI_SCRATCH 0x16 +/* Optional Carkit Registers */ +#define ULPI_CARKIT_CTRL 0x19 +#define ULPI_CARKIT_INT_DELAY 0x1c +#define ULPI_CARKIT_INT_EN 0x1d +#define ULPI_CARKIT_INT_STS 0x20 +#define ULPI_CARKIT_INT_LATCH 0x21 +#define ULPI_CARKIT_PLS_CTRL 0x22 +/* Other Optional Registers */ +#define ULPI_TX_POS_WIDTH 0x25 +#define ULPI_TX_NEG_WIDTH 0x26 +#define ULPI_POLARITY_RECOVERY 0x27 +/* Access Extended Register Set */ +#define ULPI_ACCESS_EXTENDED 0x2f +/* Vendor Specific */ +#define ULPI_VENDOR_SPECIFIC 0x30 +/* Extended Registers */ +#define ULPI_EXT_VENDOR_SPECIFIC 0x80 + +/* + * Register Bits + */ + +/* Function Control */ +#define ULPI_FUNC_CTRL_XCVRSEL BIT(0) +#define ULPI_FUNC_CTRL_XCVRSEL_MASK 0x3 +#define ULPI_FUNC_CTRL_HIGH_SPEED 0x0 +#define ULPI_FUNC_CTRL_FULL_SPEED 0x1 +#define ULPI_FUNC_CTRL_LOW_SPEED 0x2 +#define ULPI_FUNC_CTRL_FS4LS 0x3 +#define ULPI_FUNC_CTRL_TERMSELECT BIT(2) +#define ULPI_FUNC_CTRL_OPMODE BIT(3) +#define ULPI_FUNC_CTRL_OPMODE_MASK (0x3 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NORMAL (0x0 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NONDRIVING (0x1 << 3) +#define ULPI_FUNC_CTRL_OPMODE_DISABLE_NRZI (0x2 << 3) +#define ULPI_FUNC_CTRL_OPMODE_NOSYNC_NOEOP (0x3 << 3) +#define ULPI_FUNC_CTRL_RESET BIT(5) +#define ULPI_FUNC_CTRL_SUSPENDM BIT(6) + +/* Interface Control */ +#define ULPI_IFC_CTRL_6_PIN_SERIAL_MODE BIT(0) +#define ULPI_IFC_CTRL_3_PIN_SERIAL_MODE BIT(1) +#define ULPI_IFC_CTRL_CARKITMODE BIT(2) +#define ULPI_IFC_CTRL_CLOCKSUSPENDM BIT(3) +#define ULPI_IFC_CTRL_AUTORESUME BIT(4) +#define ULPI_IFC_CTRL_EXTERNAL_VBUS BIT(5) +#define ULPI_IFC_CTRL_PASSTHRU BIT(6) +#define ULPI_IFC_CTRL_PROTECT_IFC_DISABLE BIT(7) + +/* OTG Control */ +#define ULPI_OTG_CTRL_ID_PULLUP BIT(0) +#define ULPI_OTG_CTRL_DP_PULLDOWN BIT(1) +#define ULPI_OTG_CTRL_DM_PULLDOWN BIT(2) +#define ULPI_OTG_CTRL_DISCHRGVBUS BIT(3) +#define ULPI_OTG_CTRL_CHRGVBUS BIT(4) +#define ULPI_OTG_CTRL_DRVVBUS BIT(5) +#define ULPI_OTG_CTRL_DRVVBUS_EXT BIT(6) +#define ULPI_OTG_CTRL_EXTVBUSIND BIT(7) + +/* USB Interrupt Enable Rising, + * USB Interrupt Enable Falling, + * USB Interrupt Status and + * USB Interrupt Latch + */ +#define ULPI_INT_HOST_DISCONNECT BIT(0) +#define ULPI_INT_VBUS_VALID BIT(1) +#define ULPI_INT_SESS_VALID BIT(2) +#define ULPI_INT_SESS_END BIT(3) +#define ULPI_INT_IDGRD BIT(4) + +/* Debug */ +#define ULPI_DEBUG_LINESTATE0 BIT(0) +#define ULPI_DEBUG_LINESTATE1 BIT(1) + +/* Carkit Control */ +#define ULPI_CARKIT_CTRL_CARKITPWR BIT(0) +#define ULPI_CARKIT_CTRL_IDGNDDRV BIT(1) +#define ULPI_CARKIT_CTRL_TXDEN BIT(2) +#define ULPI_CARKIT_CTRL_RXDEN BIT(3) +#define ULPI_CARKIT_CTRL_SPKLEFTEN BIT(4) +#define ULPI_CARKIT_CTRL_SPKRIGHTEN BIT(5) +#define ULPI_CARKIT_CTRL_MICEN BIT(6) + +/* Carkit Interrupt Enable */ +#define ULPI_CARKIT_INT_EN_IDFLOAT_RISE BIT(0) +#define ULPI_CARKIT_INT_EN_IDFLOAT_FALL BIT(1) +#define ULPI_CARKIT_INT_EN_CARINTDET BIT(2) +#define ULPI_CARKIT_INT_EN_DP_RISE BIT(3) +#define ULPI_CARKIT_INT_EN_DP_FALL BIT(4) + +/* Carkit Interrupt Status and + * Carkit Interrupt Latch + */ +#define ULPI_CARKIT_INT_IDFLOAT BIT(0) +#define ULPI_CARKIT_INT_CARINTDET BIT(1) +#define ULPI_CARKIT_INT_DP BIT(2) + +/* Carkit Pulse Control*/ +#define ULPI_CARKIT_PLS_CTRL_TXPLSEN BIT(0) +#define ULPI_CARKIT_PLS_CTRL_RXPLSEN BIT(1) +#define ULPI_CARKIT_PLS_CTRL_SPKRLEFT_BIASEN BIT(2) +#define ULPI_CARKIT_PLS_CTRL_SPKRRIGHT_BIASEN BIT(3) + +#endif /* __LINUX_ULPI_REGS_H */ diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 7c9b484735c5..1f6526c76ee8 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -80,6 +80,9 @@ #define CDC_NCM_TIMER_INTERVAL_MIN 5UL #define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) +/* Driver flags */ +#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ + #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) #define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB) @@ -103,9 +106,11 @@ struct cdc_ncm_ctx { spinlock_t mtx; atomic_t stop; + int drvflags; u32 timer_interval; u32 max_ndp_size; + struct usb_cdc_ncm_ndp16 *delayed_ndp16; u32 tx_timer_pending; u32 tx_curr_frame_num; @@ -133,7 +138,7 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); -int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting); +int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in); diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 68b1e836dff1..c9aa7792de10 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -622,8 +622,6 @@ extern struct list_head usb_bus_list; extern struct mutex usb_bus_list_lock; extern wait_queue_head_t usb_kill_urb_queue; -extern int usb_find_interface_driver(struct usb_device *dev, - struct usb_interface *interface); #define usb_endpoint_out(ep_dir) (!((ep_dir) & USB_DIR_IN)) diff --git a/include/linux/usb/msm_hsusb.h b/include/linux/usb/msm_hsusb.h index 7dbecf9a4656..e55a1504266e 100644 --- a/include/linux/usb/msm_hsusb.h +++ b/include/linux/usb/msm_hsusb.h @@ -18,6 +18,7 @@ #ifndef __ASM_ARCH_MSM_HSUSB_H #define __ASM_ARCH_MSM_HSUSB_H +#include <linux/extcon.h> #include <linux/types.h> #include <linux/usb/otg.h> #include <linux/clk.h> @@ -120,6 +121,17 @@ struct msm_otg_platform_data { }; /** + * struct msm_usb_cable - structure for exteternal connector cable + * state tracking + * @nb: hold event notification callback + * @conn: used for notification registration + */ +struct msm_usb_cable { + struct notifier_block nb; + struct extcon_specific_cable_nb conn; +}; + +/** * struct msm_otg: OTG driver data. Shared by HCD and DCD. * @otg: USB OTG Transceiver structure. * @pdata: otg device platform data. @@ -138,6 +150,11 @@ struct msm_otg_platform_data { * @chg_type: The type of charger attached. * @dcd_retires: The retry count used to track Data contact * detection process. + * @manual_pullup: true if VBUS is not routed to USB controller/phy + * and controller driver therefore enables pull-up explicitly before + * starting controller using usbcmd run/stop bit. + * @vbus: VBUS signal state trakining, using extcon framework + * @id: ID signal state trakining, using extcon framework */ struct msm_otg { struct usb_phy phy; @@ -166,6 +183,11 @@ struct msm_otg { struct reset_control *phy_rst; struct reset_control *link_rst; int vdd_levels[3]; + + bool manual_pullup; + + struct msm_usb_cable vbus; + struct msm_usb_cable id; }; #endif diff --git a/include/linux/usb/msm_hsusb_hw.h b/include/linux/usb/msm_hsusb_hw.h index a29f6030afb1..e159b39f67a2 100644 --- a/include/linux/usb/msm_hsusb_hw.h +++ b/include/linux/usb/msm_hsusb_hw.h @@ -21,6 +21,8 @@ #define USB_AHBBURST (MSM_USB_BASE + 0x0090) #define USB_AHBMODE (MSM_USB_BASE + 0x0098) +#define USB_GENCONFIG_2 (MSM_USB_BASE + 0x00a0) + #define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */ #define USB_USBCMD (MSM_USB_BASE + 0x0140) @@ -30,6 +32,9 @@ #define USB_PHY_CTRL (MSM_USB_BASE + 0x0240) #define USB_PHY_CTRL2 (MSM_USB_BASE + 0x0278) +#define GENCONFIG_2_SESS_VLD_CTRL_EN BIT(7) +#define USBCMD_SESS_VLD_CTRL BIT(25) + #define USBCMD_RESET 2 #define USB_USBINTR (MSM_USB_BASE + 0x0148) @@ -50,6 +55,10 @@ #define ULPI_PWR_CLK_MNG_REG 0x88 #define OTG_COMP_DISABLE BIT(0) +#define ULPI_MISC_A 0x96 +#define ULPI_MISC_A_VBUSVLDEXTSEL BIT(1) +#define ULPI_MISC_A_VBUSVLDEXT BIT(0) + #define ASYNC_INTR_CTRL (1 << 29) /* Enable async interrupt */ #define ULPI_STP_CTRL (1 << 30) /* Block communication with PHY */ #define PHY_RETEN (1 << 1) /* PHY retention enable/disable */ diff --git a/include/linux/usb/net2280.h b/include/linux/usb/net2280.h index 148b8fa5b1a2..725120224472 100644 --- a/include/linux/usb/net2280.h +++ b/include/linux/usb/net2280.h @@ -168,6 +168,9 @@ struct net2280_regs { #define ENDPOINT_B_INTERRUPT 2 #define ENDPOINT_A_INTERRUPT 1 #define ENDPOINT_0_INTERRUPT 0 +#define USB3380_IRQSTAT0_EP_INTR_MASK_IN (0xF << 17) +#define USB3380_IRQSTAT0_EP_INTR_MASK_OUT (0xF << 1) + u32 irqstat1; #define POWER_STATE_CHANGE_INTERRUPT 27 #define PCI_ARBITER_TIMEOUT_INTERRUPT 26 diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index bc91b5d380fd..e39f251cf861 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -205,6 +205,8 @@ extern struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index); extern struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index); extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, const char *phandle, u8 index); +extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, + struct device_node *node, struct notifier_block *nb); extern void usb_put_phy(struct usb_phy *); extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern int usb_bind_phy(const char *dev_name, u8 index, @@ -238,6 +240,12 @@ static inline struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, return ERR_PTR(-ENXIO); } +static inline struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, + struct device_node *node, struct notifier_block *nb) +{ + return ERR_PTR(-ENXIO); +} + static inline void usb_put_phy(struct usb_phy *x) { } diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index f06529c14141..3dd5a781da99 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -169,8 +169,7 @@ struct renesas_usbhs_driver_param { #define USBHS_USB_DMAC_XFER_SIZE 32 /* hardcode the xfer size */ }; -#define USBHS_TYPE_R8A7790 1 -#define USBHS_TYPE_R8A7791 2 +#define USBHS_TYPE_RCAR_GEN2 1 /* * option: diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 5c295c26ad37..5f07407a367a 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -12,6 +12,8 @@ #define __LINUX_USB_ULPI_H #include <linux/usb/otg.h> +#include <linux/ulpi/regs.h> + /*-------------------------------------------------------------------------*/ /* @@ -49,138 +51,6 @@ /*-------------------------------------------------------------------------*/ -/* - * Macros for Set and Clear - * See ULPI 1.1 specification to find the registers with Set and Clear offsets - */ -#define ULPI_SET(a) (a + 1) -#define ULPI_CLR(a) (a + 2) - -/*-------------------------------------------------------------------------*/ - -/* - * Register Map - */ -#define ULPI_VENDOR_ID_LOW 0x00 -#define ULPI_VENDOR_ID_HIGH 0x01 -#define ULPI_PRODUCT_ID_LOW 0x02 -#define ULPI_PRODUCT_ID_HIGH 0x03 -#define ULPI_FUNC_CTRL 0x04 -#define ULPI_IFC_CTRL 0x07 -#define ULPI_OTG_CTRL 0x0a -#define ULPI_USB_INT_EN_RISE 0x0d -#define ULPI_USB_INT_EN_FALL 0x10 -#define ULPI_USB_INT_STS 0x13 -#define ULPI_USB_INT_LATCH 0x14 -#define ULPI_DEBUG 0x15 -#define ULPI_SCRATCH 0x16 -/* Optional Carkit Registers */ -#define ULPI_CARCIT_CTRL 0x19 -#define ULPI_CARCIT_INT_DELAY 0x1c -#define ULPI_CARCIT_INT_EN 0x1d -#define ULPI_CARCIT_INT_STS 0x20 -#define ULPI_CARCIT_INT_LATCH 0x21 -#define ULPI_CARCIT_PLS_CTRL 0x22 -/* Other Optional Registers */ -#define ULPI_TX_POS_WIDTH 0x25 -#define ULPI_TX_NEG_WIDTH 0x26 -#define ULPI_POLARITY_RECOVERY 0x27 -/* Access Extended Register Set */ -#define ULPI_ACCESS_EXTENDED 0x2f -/* Vendor Specific */ -#define ULPI_VENDOR_SPECIFIC 0x30 -/* Extended Registers */ -#define ULPI_EXT_VENDOR_SPECIFIC 0x80 - -/*-------------------------------------------------------------------------*/ - -/* - * Register Bits - */ - -/* Function Control */ -#define ULPI_FUNC_CTRL_XCVRSEL (1 << 0) -#define ULPI_FUNC_CTRL_XCVRSEL_MASK (3 << 0) -#define ULPI_FUNC_CTRL_HIGH_SPEED (0 << 0) -#define ULPI_FUNC_CTRL_FULL_SPEED (1 << 0) -#define ULPI_FUNC_CTRL_LOW_SPEED (2 << 0) -#define ULPI_FUNC_CTRL_FS4LS (3 << 0) -#define ULPI_FUNC_CTRL_TERMSELECT (1 << 2) -#define ULPI_FUNC_CTRL_OPMODE (1 << 3) -#define ULPI_FUNC_CTRL_OPMODE_MASK (3 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NORMAL (0 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NONDRIVING (1 << 3) -#define ULPI_FUNC_CTRL_OPMODE_DISABLE_NRZI (2 << 3) -#define ULPI_FUNC_CTRL_OPMODE_NOSYNC_NOEOP (3 << 3) -#define ULPI_FUNC_CTRL_RESET (1 << 5) -#define ULPI_FUNC_CTRL_SUSPENDM (1 << 6) - -/* Interface Control */ -#define ULPI_IFC_CTRL_6_PIN_SERIAL_MODE (1 << 0) -#define ULPI_IFC_CTRL_3_PIN_SERIAL_MODE (1 << 1) -#define ULPI_IFC_CTRL_CARKITMODE (1 << 2) -#define ULPI_IFC_CTRL_CLOCKSUSPENDM (1 << 3) -#define ULPI_IFC_CTRL_AUTORESUME (1 << 4) -#define ULPI_IFC_CTRL_EXTERNAL_VBUS (1 << 5) -#define ULPI_IFC_CTRL_PASSTHRU (1 << 6) -#define ULPI_IFC_CTRL_PROTECT_IFC_DISABLE (1 << 7) - -/* OTG Control */ -#define ULPI_OTG_CTRL_ID_PULLUP (1 << 0) -#define ULPI_OTG_CTRL_DP_PULLDOWN (1 << 1) -#define ULPI_OTG_CTRL_DM_PULLDOWN (1 << 2) -#define ULPI_OTG_CTRL_DISCHRGVBUS (1 << 3) -#define ULPI_OTG_CTRL_CHRGVBUS (1 << 4) -#define ULPI_OTG_CTRL_DRVVBUS (1 << 5) -#define ULPI_OTG_CTRL_DRVVBUS_EXT (1 << 6) -#define ULPI_OTG_CTRL_EXTVBUSIND (1 << 7) - -/* USB Interrupt Enable Rising, - * USB Interrupt Enable Falling, - * USB Interrupt Status and - * USB Interrupt Latch - */ -#define ULPI_INT_HOST_DISCONNECT (1 << 0) -#define ULPI_INT_VBUS_VALID (1 << 1) -#define ULPI_INT_SESS_VALID (1 << 2) -#define ULPI_INT_SESS_END (1 << 3) -#define ULPI_INT_IDGRD (1 << 4) - -/* Debug */ -#define ULPI_DEBUG_LINESTATE0 (1 << 0) -#define ULPI_DEBUG_LINESTATE1 (1 << 1) - -/* Carkit Control */ -#define ULPI_CARKIT_CTRL_CARKITPWR (1 << 0) -#define ULPI_CARKIT_CTRL_IDGNDDRV (1 << 1) -#define ULPI_CARKIT_CTRL_TXDEN (1 << 2) -#define ULPI_CARKIT_CTRL_RXDEN (1 << 3) -#define ULPI_CARKIT_CTRL_SPKLEFTEN (1 << 4) -#define ULPI_CARKIT_CTRL_SPKRIGHTEN (1 << 5) -#define ULPI_CARKIT_CTRL_MICEN (1 << 6) - -/* Carkit Interrupt Enable */ -#define ULPI_CARKIT_INT_EN_IDFLOAT_RISE (1 << 0) -#define ULPI_CARKIT_INT_EN_IDFLOAT_FALL (1 << 1) -#define ULPI_CARKIT_INT_EN_CARINTDET (1 << 2) -#define ULPI_CARKIT_INT_EN_DP_RISE (1 << 3) -#define ULPI_CARKIT_INT_EN_DP_FALL (1 << 4) - -/* Carkit Interrupt Status and - * Carkit Interrupt Latch - */ -#define ULPI_CARKIT_INT_IDFLOAT (1 << 0) -#define ULPI_CARKIT_INT_CARINTDET (1 << 1) -#define ULPI_CARKIT_INT_DP (1 << 2) - -/* Carkit Pulse Control*/ -#define ULPI_CARKIT_PLS_CTRL_TXPLSEN (1 << 0) -#define ULPI_CARKIT_PLS_CTRL_RXPLSEN (1 << 1) -#define ULPI_CARKIT_PLS_CTRL_SPKRLEFT_BIASEN (1 << 2) -#define ULPI_CARKIT_PLS_CTRL_SPKRRIGHT_BIASEN (1 << 3) - -/*-------------------------------------------------------------------------*/ - #if IS_ENABLED(CONFIG_USB_ULPI) struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops, unsigned int flags); diff --git a/include/linux/usb/usb338x.h b/include/linux/usb/usb338x.h index f92eb635b9d3..11525d8d89a7 100644 --- a/include/linux/usb/usb338x.h +++ b/include/linux/usb/usb338x.h @@ -43,6 +43,10 @@ #define IN_ENDPOINT_TYPE 12 #define OUT_ENDPOINT_ENABLE 10 #define OUT_ENDPOINT_TYPE 8 +#define USB3380_EP_CFG_MASK_IN ((0x3 << IN_ENDPOINT_TYPE) | \ + BIT(IN_ENDPOINT_ENABLE)) +#define USB3380_EP_CFG_MASK_OUT ((0x3 << OUT_ENDPOINT_TYPE) | \ + BIT(OUT_ENDPOINT_ENABLE)) struct usb338x_usb_ext_regs { u32 usbclass; diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h index 51865d05b267..ce63a2c3a612 100644 --- a/include/linux/virtio_byteorder.h +++ b/include/linux/virtio_byteorder.h @@ -3,17 +3,21 @@ #include <linux/types.h> #include <uapi/linux/virtio_types.h> -/* - * Low-level memory accessors for handling virtio in modern little endian and in - * compatibility native endian format. - */ +static inline bool virtio_legacy_is_little_endian(void) +{ +#ifdef __LITTLE_ENDIAN + return true; +#else + return false; +#endif +} static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val) { if (little_endian) return le16_to_cpu((__force __le16)val); else - return (__force u16)val; + return be16_to_cpu((__force __be16)val); } static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) @@ -21,7 +25,7 @@ static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) if (little_endian) return (__force __virtio16)cpu_to_le16(val); else - return (__force __virtio16)val; + return (__force __virtio16)cpu_to_be16(val); } static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) @@ -29,7 +33,7 @@ static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) if (little_endian) return le32_to_cpu((__force __le32)val); else - return (__force u32)val; + return be32_to_cpu((__force __be32)val); } static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) @@ -37,7 +41,7 @@ static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) if (little_endian) return (__force __virtio32)cpu_to_le32(val); else - return (__force __virtio32)val; + return (__force __virtio32)cpu_to_be32(val); } static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) @@ -45,7 +49,7 @@ static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) if (little_endian) return le64_to_cpu((__force __le64)val); else - return (__force u64)val; + return be64_to_cpu((__force __be64)val); } static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) @@ -53,7 +57,7 @@ static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) if (little_endian) return (__force __virtio64)cpu_to_le64(val); else - return (__force __virtio64)val; + return (__force __virtio64)cpu_to_be64(val); } #endif /* _LINUX_VIRTIO_BYTEORDER */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 1e306f727edc..e5ce8ab0b8b0 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -205,35 +205,41 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu) return 0; } +static inline bool virtio_is_little_endian(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || + virtio_legacy_is_little_endian(); +} + /* Memory accessors */ static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) { - return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) { - return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(virtio_is_little_endian(vdev), val); } static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) { - return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) { - return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(virtio_is_little_endian(vdev), val); } static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) { - return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { - return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } /* Config space accessors. */ diff --git a/include/linux/vme.h b/include/linux/vme.h index 79242e9c06b8..c0131358f351 100644 --- a/include/linux/vme.h +++ b/include/linux/vme.h @@ -120,6 +120,8 @@ void vme_free_consistent(struct vme_resource *, size_t, void *, dma_addr_t); size_t vme_get_size(struct vme_resource *); +int vme_check_window(u32 aspace, unsigned long long vme_base, + unsigned long long size); struct vme_resource *vme_slave_request(struct vme_dev *, u32, u32); int vme_slave_set(struct vme_resource *, int, unsigned long long, diff --git a/include/linux/vringh.h b/include/linux/vringh.h index a3fa537e717a..bc6c28d04263 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -226,33 +226,39 @@ static inline void vringh_notify(struct vringh *vrh) vrh->notify(vrh); } +static inline bool vringh_is_little_endian(const struct vringh *vrh) +{ + return vrh->little_endian || + virtio_legacy_is_little_endian(); +} + static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val) { - return __virtio16_to_cpu(vrh->little_endian, val); + return __virtio16_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val) { - return __cpu_to_virtio16(vrh->little_endian, val); + return __cpu_to_virtio16(vringh_is_little_endian(vrh), val); } static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val) { - return __virtio32_to_cpu(vrh->little_endian, val); + return __virtio32_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val) { - return __cpu_to_virtio32(vrh->little_endian, val); + return __cpu_to_virtio32(vringh_is_little_endian(vrh), val); } static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val) { - return __virtio64_to_cpu(vrh->little_endian, val); + return __virtio64_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) { - return __cpu_to_virtio64(vrh->little_endian, val); + return __cpu_to_virtio64(vringh_is_little_endian(vrh), val); } #endif /* _LINUX_VRINGH_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 2db83349865b..1e1bf9f963a9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -358,6 +358,19 @@ do { \ __ret; \ }) +#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ + (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ + cmd1; schedule(); cmd2) +/* + * Just like wait_event_cmd(), except it sets exclusive flag + */ +#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2); \ +} while (0) + #define __wait_event_cmd(wq, condition, cmd1, cmd2) \ (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) @@ -969,7 +982,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *); * on that signal. */ static inline int -wait_on_bit(void *word, int bit, unsigned mode) +wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -994,7 +1007,7 @@ wait_on_bit(void *word, int bit, unsigned mode) * on that signal. */ static inline int -wait_on_bit_io(void *word, int bit, unsigned mode) +wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -1020,7 +1033,8 @@ wait_on_bit_io(void *word, int bit, unsigned mode) * received a signal and the mode permitted wakeup on that signal. */ static inline int -wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) +wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, + unsigned long timeout) { might_sleep(); if (!test_bit(bit, word)) @@ -1047,7 +1061,8 @@ wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) * on that signal. */ static inline int -wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) +wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) { might_sleep(); if (!test_bit(bit, word)) @@ -1075,7 +1090,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock(void *word, int bit, unsigned mode) +wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) @@ -1099,7 +1114,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode) * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock_io(void *word, int bit, unsigned mode) +wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) @@ -1125,7 +1140,8 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode) * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) +wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, + unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index a746bf5216f8..f47feada5b42 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -65,6 +65,8 @@ struct watchdog_ops { * @driver-data:Pointer to the drivers private data. * @lock: Lock for watchdog core internal use only. * @status: Field that contains the devices internal status bits. + * @deferred: entry in wtd_deferred_reg_list which is used to + * register early initialized watchdogs. * * The watchdog_device structure contains all information about a * watchdog timer device. @@ -95,6 +97,7 @@ struct watchdog_device { #define WDOG_ALLOW_RELEASE 2 /* Did we receive the magic char ? */ #define WDOG_NO_WAY_OUT 3 /* Is 'nowayout' feature set ? */ #define WDOG_UNREGISTERED 4 /* Has the device been unregistered */ + struct list_head deferred; }; #define WATCHDOG_NOWAYOUT IS_BUILTIN(CONFIG_WATCHDOG_NOWAYOUT) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index deee212af8e0..738b30b39b68 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -424,6 +424,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); +int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); @@ -434,7 +435,6 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); -extern void flush_scheduled_work(void); extern int schedule_on_each_cpu(work_func_t func); @@ -531,6 +531,35 @@ static inline bool schedule_work(struct work_struct *work) } /** + * flush_scheduled_work - ensure that any scheduled work has run to completion. + * + * Forces execution of the kernel-global workqueue and blocks until its + * completion. + * + * Think twice before calling this function! It's very easy to get into + * trouble if you don't take great care. Either of the following situations + * will lead to deadlock: + * + * One of the work items currently on the workqueue needs to acquire + * a lock held by your code or its caller. + * + * Your code is running in the context of a work routine. + * + * They will be detected by lockdep when they occur, but the first might not + * occur very often. It depends on what work items are on the workqueue and + * what locks they need, which you have no control over. + * + * In most situations flushing the entire workqueue is overkill; you merely + * need to know that a particular work item isn't queued and isn't running. + * In such cases you should use cancel_delayed_work_sync() or + * cancel_work_sync() instead. + */ +static inline void flush_scheduled_work(void) +{ + flush_workqueue(system_wq); +} + +/** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b2dd371ec0ca..b333c945e571 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -7,6 +7,8 @@ #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> +#include <linux/flex_proportions.h> +#include <linux/backing-dev-defs.h> DECLARE_PER_CPU(int, dirty_throttle_leaks); @@ -84,18 +86,95 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *wb; /* wb this writeback is issued under */ + struct inode *inode; /* inode being written out */ + + /* foreign inode detection, see wbc_detach_inode() */ + int wb_id; /* current wb id */ + int wb_lcand_id; /* last foreign candidate wb id */ + int wb_tcand_id; /* this foreign candidate wb id */ + size_t wb_bytes; /* bytes written by current wb */ + size_t wb_lcand_bytes; /* bytes written by last candidate */ + size_t wb_tcand_bytes; /* bytes written by this candidate */ +#endif }; /* + * A wb_domain represents a domain that wb's (bdi_writeback's) belong to + * and are measured against each other in. There always is one global + * domain, global_wb_domain, that every wb in the system is a member of. + * This allows measuring the relative bandwidth of each wb to distribute + * dirtyable memory accordingly. + */ +struct wb_domain { + spinlock_t lock; + + /* + * Scale the writeback cache size proportional to the relative + * writeout speed. + * + * We do this by keeping a floating proportion between BDIs, based + * on page writeback completions [end_page_writeback()]. Those + * devices that write out pages fastest will get the larger share, + * while the slower will get a smaller share. + * + * We use page writeout completions because we are interested in + * getting rid of dirty pages. Having them written out is the + * primary goal. + * + * We introduce a concept of time, a period over which we measure + * these events, because demand can/will vary over time. The length + * of this period itself is measured in page writeback completions. + */ + struct fprop_global completions; + struct timer_list period_timer; /* timer for aging of completions */ + unsigned long period_time; + + /* + * The dirtyable memory and dirty threshold could be suddenly + * knocked down by a large amount (eg. on the startup of KVM in a + * swapless system). This may throw the system into deep dirty + * exceeded state and throttle heavy/light dirtiers alike. To + * retain good responsiveness, maintain global_dirty_limit for + * tracking slowly down to the knocked down dirty threshold. + * + * Both fields are protected by ->lock. + */ + unsigned long dirty_limit_tstamp; + unsigned long dirty_limit; +}; + +/** + * wb_domain_size_changed - memory available to a wb_domain has changed + * @dom: wb_domain of interest + * + * This function should be called when the amount of memory available to + * @dom has changed. It resets @dom's dirty limit parameters to prevent + * the past values which don't match the current configuration from skewing + * dirty throttling. Without this, when memory size of a wb_domain is + * greatly reduced, the dirty throttling logic may allow too many pages to + * be dirtied leading to consecutive unnecessary OOMs and may get stuck in + * that situation. + */ +static inline void wb_domain_size_changed(struct wb_domain *dom) +{ + spin_lock(&dom->lock); + dom->dirty_limit_tstamp = jiffies; + dom->dirty_limit = 0; + spin_unlock(&dom->lock); +} + +/* * fs/fs-writeback.c */ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); -int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, - enum wb_reason reason); +bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); +bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, + enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); @@ -107,6 +186,123 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } +#ifdef CONFIG_CGROUP_WRITEBACK + +#include <linux/cgroup.h> +#include <linux/bio.h> + +void __inode_attach_wb(struct inode *inode, struct page *page); +void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock); +void wbc_detach_inode(struct writeback_control *wbc); +void wbc_account_io(struct writeback_control *wbc, struct page *page, + size_t bytes); + +/** + * inode_attach_wb - associate an inode with its wb + * @inode: inode of interest + * @page: page being dirtied (may be NULL) + * + * If @inode doesn't have its wb, associate it with the wb matching the + * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o + * @inode->i_lock. + */ +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ + if (!inode->i_wb) + __inode_attach_wb(inode, page); +} + +/** + * inode_detach_wb - disassociate an inode from its wb + * @inode: inode of interest + * + * @inode is being freed. Detach from its wb. + */ +static inline void inode_detach_wb(struct inode *inode) +{ + if (inode->i_wb) { + wb_put(inode->i_wb); + inode->i_wb = NULL; + } +} + +/** + * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite + * @wbc: writeback_control of interest + * @inode: target inode + * + * This function is to be used by __filemap_fdatawrite_range(), which is an + * alternative entry point into writeback code, and first ensures @inode is + * associated with a bdi_writeback and attaches it to @wbc. + */ +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ + spin_lock(&inode->i_lock); + inode_attach_wb(inode, NULL); + wbc_attach_and_unlock_inode(wbc, inode); +} + +/** + * wbc_init_bio - writeback specific initializtion of bio + * @wbc: writeback_control for the writeback in progress + * @bio: bio to be initialized + * + * @bio is a part of the writeback in progress controlled by @wbc. Perform + * writeback specific initialization. This is used to apply the cgroup + * writeback context. + */ +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ + /* + * pageout() path doesn't attach @wbc to the inode being written + * out. This is intentional as we don't want the function to block + * behind a slow cgroup. Ultimately, we want pageout() to kick off + * regular writeback instead of writing things out itself. + */ + if (wbc->wb) + bio_associate_blkcg(bio, wbc->wb->blkcg_css); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ +} + +static inline void inode_detach_wb(struct inode *inode) +{ +} + +static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock) +{ + spin_unlock(&inode->i_lock); +} + +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ +} + +static inline void wbc_detach_inode(struct writeback_control *wbc) +{ +} + +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ +} + +static inline void wbc_account_io(struct writeback_control *wbc, + struct page *page, size_t bytes) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * mm/page-writeback.c */ @@ -120,8 +316,12 @@ static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); bool zone_dirty_ok(struct zone *zone); +int wb_domain_init(struct wb_domain *dom, gfp_t gfp); +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom); +#endif -extern unsigned long global_dirty_limit; +extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern int dirty_background_ratio; @@ -155,19 +355,12 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); -unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, - unsigned long dirty); - -void __bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time); +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void page_writeback_init(void); void balance_dirty_pages_ratelimited(struct address_space *mapping); +bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, void *data); diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 56529b34dc63..d30eff3d84d5 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -81,7 +81,8 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops); + void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops, + struct zpool *zpool); void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, @@ -102,6 +103,4 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); -int zpool_evict(void *pool, unsigned long handle); - #endif |