diff options
Diffstat (limited to 'include')
69 files changed, 4372 insertions, 822 deletions
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h index a5de55c04fb2..e539f27ec51b 100644 --- a/include/asm-generic/early_ioremap.h +++ b/include/asm-generic/early_ioremap.h @@ -33,6 +33,12 @@ extern void early_ioremap_setup(void); */ extern void early_ioremap_reset(void); +/* + * Early copy from unmapped memory to kernel mapped memory. + */ +extern void copy_from_early_mem(void *dest, phys_addr_t src, + unsigned long size); + #else static inline void early_ioremap_init(void) { } static inline void early_ioremap_setup(void) { } diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h index f23174fb9ec4..10889b63af8f 100644 --- a/include/asm-generic/fixmap.h +++ b/include/asm-generic/fixmap.h @@ -67,12 +67,12 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) #endif /* Return a pointer with offset calculated */ -#define __set_fixmap_offset(idx, phys, flags) \ -({ \ - unsigned long addr; \ - __set_fixmap(idx, phys, flags); \ - addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \ - addr; \ +#define __set_fixmap_offset(idx, phys, flags) \ +({ \ + unsigned long ________addr; \ + __set_fixmap(idx, phys, flags); \ + ________addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \ + ________addr; \ }) #define set_fixmap_offset(idx, phys) \ diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 14909b0b9cae..f20f407ce45d 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -69,6 +69,12 @@ }) #endif /* CONFIG_FLATMEM/DISCONTIGMEM/SPARSEMEM */ +/* + * Convert a physical address to a Page Frame Number and back + */ +#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) +#define __pfn_to_phys(pfn) ((pfn) << PAGE_SHIFT) + #define page_to_pfn __page_to_pfn #define pfn_to_page __pfn_to_page diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 13671bc9a288..f8e7b9dd8529 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -246,6 +246,7 @@ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_rodata) = .; \ *(.rodata) *(.rodata.*) \ + *(.data..ro_after_init) /* Read only after init */ \ *(__vermagic) /* Kernel version magic */ \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index 9916d0e4eff5..25d0914481a2 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -23,6 +23,12 @@ #define ARCH_TIMER_CTRL_IT_MASK (1 << 1) #define ARCH_TIMER_CTRL_IT_STAT (1 << 2) +#define CNTHCTL_EL1PCTEN (1 << 0) +#define CNTHCTL_EL1PCEN (1 << 1) +#define CNTHCTL_EVNTEN (1 << 2) +#define CNTHCTL_EVNTDIR (1 << 3) +#define CNTHCTL_EVNTI (0xF << 4) + enum arch_timer_reg { ARCH_TIMER_REG_CTRL, ARCH_TIMER_REG_TVAL, diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 133ea00aa83b..e6c88955dd0f 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -264,6 +264,12 @@ struct vgic_v2_cpu_if { u32 vgic_lr[VGIC_V2_MAX_LRS]; }; +/* + * LRs are stored in reverse order in memory. make sure we index them + * correctly. + */ +#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) + struct vgic_v3_cpu_if { #ifdef CONFIG_ARM_GIC_V3 u32 vgic_hcr; diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h new file mode 100644 index 000000000000..b5abfda80465 --- /dev/null +++ b/include/linux/arm-smccc.h @@ -0,0 +1,104 @@ +/* + * Copyright (c) 2015, Linaro Limited + * + * 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 __LINUX_ARM_SMCCC_H +#define __LINUX_ARM_SMCCC_H + +#include <linux/linkage.h> +#include <linux/types.h> + +/* + * This file provides common defines for ARM SMC Calling Convention as + * specified in + * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html + */ + +#define ARM_SMCCC_STD_CALL 0 +#define ARM_SMCCC_FAST_CALL 1 +#define ARM_SMCCC_TYPE_SHIFT 31 + +#define ARM_SMCCC_SMC_32 0 +#define ARM_SMCCC_SMC_64 1 +#define ARM_SMCCC_CALL_CONV_SHIFT 30 + +#define ARM_SMCCC_OWNER_MASK 0x3F +#define ARM_SMCCC_OWNER_SHIFT 24 + +#define ARM_SMCCC_FUNC_MASK 0xFFFF + +#define ARM_SMCCC_IS_FAST_CALL(smc_val) \ + ((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT)) +#define ARM_SMCCC_IS_64(smc_val) \ + ((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT)) +#define ARM_SMCCC_FUNC_NUM(smc_val) ((smc_val) & ARM_SMCCC_FUNC_MASK) +#define ARM_SMCCC_OWNER_NUM(smc_val) \ + (((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK) + +#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \ + (((type) << ARM_SMCCC_TYPE_SHIFT) | \ + ((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \ + (((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \ + ((func_num) & ARM_SMCCC_FUNC_MASK)) + +#define ARM_SMCCC_OWNER_ARCH 0 +#define ARM_SMCCC_OWNER_CPU 1 +#define ARM_SMCCC_OWNER_SIP 2 +#define ARM_SMCCC_OWNER_OEM 3 +#define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_TRUSTED_APP 48 +#define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 +#define ARM_SMCCC_OWNER_TRUSTED_OS 50 +#define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 + +/** + * struct arm_smccc_res - Result from SMC/HVC call + * @a0-a3 result values from registers 0 to 3 + */ +struct arm_smccc_res { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; +}; + +/** + * arm_smccc_smc() - make SMC calls + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This function is used to make SMC calls following SMC Calling Convention. + * The content of the supplied param are copied to registers 0 to 7 prior + * to the SMC instruction. The return values are updated with the content + * from register 0 to 3 on return from the SMC instruction. + */ +asmlinkage void arm_smccc_smc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res); + +/** + * arm_smccc_hvc() - make HVC calls + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This function is used to make HVC calls following SMC Calling + * Convention. The content of the supplied param are copied to registers 0 + * to 7 prior to the HVC instruction. The return values are updated with + * the content from register 0 to 3 on return from the HVC instruction. + */ +asmlinkage void arm_smccc_hvc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res); + +#endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 5b08a8540ecf..41ea776052be 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -2,6 +2,329 @@ #ifndef _LINUX_ATOMIC_H #define _LINUX_ATOMIC_H #include <asm/atomic.h> +#include <asm/barrier.h> + +/* + * Relaxed variants of xchg, cmpxchg and some atomic operations. + * + * We support four variants: + * + * - Fully ordered: The default implementation, no suffix required. + * - Acquire: Provides ACQUIRE semantics, _acquire suffix. + * - Release: Provides RELEASE semantics, _release suffix. + * - Relaxed: No ordering guarantees, _relaxed suffix. + * + * For compound atomics performing both a load and a store, ACQUIRE + * semantics apply only to the load and RELEASE semantics only to the + * store portion of the operation. Note that a failed cmpxchg_acquire + * does -not- imply any memory ordering constraints. + * + * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions. + */ + +#ifndef atomic_read_acquire +#define atomic_read_acquire(v) smp_load_acquire(&(v)->counter) +#endif + +#ifndef atomic_set_release +#define atomic_set_release(v, i) smp_store_release(&(v)->counter, (i)) +#endif + +/* + * The idea here is to build acquire/release variants by adding explicit + * barriers on top of the relaxed variant. In the case where the relaxed + * variant is already fully ordered, no additional barriers are needed. + */ +#define __atomic_op_acquire(op, args...) \ +({ \ + typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \ + smp_mb__after_atomic(); \ + __ret; \ +}) + +#define __atomic_op_release(op, args...) \ +({ \ + smp_mb__before_atomic(); \ + op##_relaxed(args); \ +}) + +#define __atomic_op_fence(op, args...) \ +({ \ + typeof(op##_relaxed(args)) __ret; \ + smp_mb__before_atomic(); \ + __ret = op##_relaxed(args); \ + smp_mb__after_atomic(); \ + __ret; \ +}) + +/* atomic_add_return_relaxed */ +#ifndef atomic_add_return_relaxed +#define atomic_add_return_relaxed atomic_add_return +#define atomic_add_return_acquire atomic_add_return +#define atomic_add_return_release atomic_add_return + +#else /* atomic_add_return_relaxed */ + +#ifndef atomic_add_return_acquire +#define atomic_add_return_acquire(...) \ + __atomic_op_acquire(atomic_add_return, __VA_ARGS__) +#endif + +#ifndef atomic_add_return_release +#define atomic_add_return_release(...) \ + __atomic_op_release(atomic_add_return, __VA_ARGS__) +#endif + +#ifndef atomic_add_return +#define atomic_add_return(...) \ + __atomic_op_fence(atomic_add_return, __VA_ARGS__) +#endif +#endif /* atomic_add_return_relaxed */ + +/* atomic_sub_return_relaxed */ +#ifndef atomic_sub_return_relaxed +#define atomic_sub_return_relaxed atomic_sub_return +#define atomic_sub_return_acquire atomic_sub_return +#define atomic_sub_return_release atomic_sub_return + +#else /* atomic_sub_return_relaxed */ + +#ifndef atomic_sub_return_acquire +#define atomic_sub_return_acquire(...) \ + __atomic_op_acquire(atomic_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic_sub_return_release +#define atomic_sub_return_release(...) \ + __atomic_op_release(atomic_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic_sub_return +#define atomic_sub_return(...) \ + __atomic_op_fence(atomic_sub_return, __VA_ARGS__) +#endif +#endif /* atomic_sub_return_relaxed */ + +/* atomic_xchg_relaxed */ +#ifndef atomic_xchg_relaxed +#define atomic_xchg_relaxed atomic_xchg +#define atomic_xchg_acquire atomic_xchg +#define atomic_xchg_release atomic_xchg + +#else /* atomic_xchg_relaxed */ + +#ifndef atomic_xchg_acquire +#define atomic_xchg_acquire(...) \ + __atomic_op_acquire(atomic_xchg, __VA_ARGS__) +#endif + +#ifndef atomic_xchg_release +#define atomic_xchg_release(...) \ + __atomic_op_release(atomic_xchg, __VA_ARGS__) +#endif + +#ifndef atomic_xchg +#define atomic_xchg(...) \ + __atomic_op_fence(atomic_xchg, __VA_ARGS__) +#endif +#endif /* atomic_xchg_relaxed */ + +/* atomic_cmpxchg_relaxed */ +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_relaxed atomic_cmpxchg +#define atomic_cmpxchg_acquire atomic_cmpxchg +#define atomic_cmpxchg_release atomic_cmpxchg + +#else /* atomic_cmpxchg_relaxed */ + +#ifndef atomic_cmpxchg_acquire +#define atomic_cmpxchg_acquire(...) \ + __atomic_op_acquire(atomic_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic_cmpxchg_release +#define atomic_cmpxchg_release(...) \ + __atomic_op_release(atomic_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic_cmpxchg +#define atomic_cmpxchg(...) \ + __atomic_op_fence(atomic_cmpxchg, __VA_ARGS__) +#endif +#endif /* atomic_cmpxchg_relaxed */ + +#ifndef atomic64_read_acquire +#define atomic64_read_acquire(v) smp_load_acquire(&(v)->counter) +#endif + +#ifndef atomic64_set_release +#define atomic64_set_release(v, i) smp_store_release(&(v)->counter, (i)) +#endif + +/* atomic64_add_return_relaxed */ +#ifndef atomic64_add_return_relaxed +#define atomic64_add_return_relaxed atomic64_add_return +#define atomic64_add_return_acquire atomic64_add_return +#define atomic64_add_return_release atomic64_add_return + +#else /* atomic64_add_return_relaxed */ + +#ifndef atomic64_add_return_acquire +#define atomic64_add_return_acquire(...) \ + __atomic_op_acquire(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return_release +#define atomic64_add_return_release(...) \ + __atomic_op_release(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return +#define atomic64_add_return(...) \ + __atomic_op_fence(atomic64_add_return, __VA_ARGS__) +#endif +#endif /* atomic64_add_return_relaxed */ + +/* atomic64_sub_return_relaxed */ +#ifndef atomic64_sub_return_relaxed +#define atomic64_sub_return_relaxed atomic64_sub_return +#define atomic64_sub_return_acquire atomic64_sub_return +#define atomic64_sub_return_release atomic64_sub_return + +#else /* atomic64_sub_return_relaxed */ + +#ifndef atomic64_sub_return_acquire +#define atomic64_sub_return_acquire(...) \ + __atomic_op_acquire(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return_release +#define atomic64_sub_return_release(...) \ + __atomic_op_release(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return +#define atomic64_sub_return(...) \ + __atomic_op_fence(atomic64_sub_return, __VA_ARGS__) +#endif +#endif /* atomic64_sub_return_relaxed */ + +/* atomic64_xchg_relaxed */ +#ifndef atomic64_xchg_relaxed +#define atomic64_xchg_relaxed atomic64_xchg +#define atomic64_xchg_acquire atomic64_xchg +#define atomic64_xchg_release atomic64_xchg + +#else /* atomic64_xchg_relaxed */ + +#ifndef atomic64_xchg_acquire +#define atomic64_xchg_acquire(...) \ + __atomic_op_acquire(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg_release +#define atomic64_xchg_release(...) \ + __atomic_op_release(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg +#define atomic64_xchg(...) \ + __atomic_op_fence(atomic64_xchg, __VA_ARGS__) +#endif +#endif /* atomic64_xchg_relaxed */ + +/* atomic64_cmpxchg_relaxed */ +#ifndef atomic64_cmpxchg_relaxed +#define atomic64_cmpxchg_relaxed atomic64_cmpxchg +#define atomic64_cmpxchg_acquire atomic64_cmpxchg +#define atomic64_cmpxchg_release atomic64_cmpxchg + +#else /* atomic64_cmpxchg_relaxed */ + +#ifndef atomic64_cmpxchg_acquire +#define atomic64_cmpxchg_acquire(...) \ + __atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg_release +#define atomic64_cmpxchg_release(...) \ + __atomic_op_release(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg +#define atomic64_cmpxchg(...) \ + __atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__) +#endif +#endif /* atomic64_cmpxchg_relaxed */ + +/* cmpxchg_relaxed */ +#ifndef cmpxchg_relaxed +#define cmpxchg_relaxed cmpxchg +#define cmpxchg_acquire cmpxchg +#define cmpxchg_release cmpxchg + +#else /* cmpxchg_relaxed */ + +#ifndef cmpxchg_acquire +#define cmpxchg_acquire(...) \ + __atomic_op_acquire(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg_release +#define cmpxchg_release(...) \ + __atomic_op_release(cmpxchg, __VA_ARGS__) +#endif + +#ifndef cmpxchg +#define cmpxchg(...) \ + __atomic_op_fence(cmpxchg, __VA_ARGS__) +#endif +#endif /* cmpxchg_relaxed */ + +/* cmpxchg64_relaxed */ +#ifndef cmpxchg64_relaxed +#define cmpxchg64_relaxed cmpxchg64 +#define cmpxchg64_acquire cmpxchg64 +#define cmpxchg64_release cmpxchg64 + +#else /* cmpxchg64_relaxed */ + +#ifndef cmpxchg64_acquire +#define cmpxchg64_acquire(...) \ + __atomic_op_acquire(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64_release +#define cmpxchg64_release(...) \ + __atomic_op_release(cmpxchg64, __VA_ARGS__) +#endif + +#ifndef cmpxchg64 +#define cmpxchg64(...) \ + __atomic_op_fence(cmpxchg64, __VA_ARGS__) +#endif +#endif /* cmpxchg64_relaxed */ + +/* xchg_relaxed */ +#ifndef xchg_relaxed +#define xchg_relaxed xchg +#define xchg_acquire xchg +#define xchg_release xchg + +#else /* xchg_relaxed */ + +#ifndef xchg_acquire +#define xchg_acquire(...) __atomic_op_acquire(xchg, __VA_ARGS__) +#endif + +#ifndef xchg_release +#define xchg_release(...) __atomic_op_release(xchg, __VA_ARGS__) +#endif + +#ifndef xchg +#define xchg(...) __atomic_op_fence(xchg, __VA_ARGS__) +#endif +#endif /* xchg_relaxed */ /** * atomic_add_unless - add unless the number is already a given value diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h new file mode 100644 index 000000000000..1b4d69f68c33 --- /dev/null +++ b/include/linux/backing-dev-defs.h @@ -0,0 +1,259 @@ +#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 */ + + struct list_head bdi_node; /* anchored at bdi->wb_list */ + +#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 */ + struct list_head wb_list; /* list of all wbs */ +#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 d87d8eced064..145b50032695 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -8,206 +8,121 @@ #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/memcontrol.h> +#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); +void bdi_exit(struct backing_dev_info *bdi); __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 bdi_destroy(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 void __add_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item, s64 amount) +static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { - __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); + /* + * @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_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item, s64 amount) +{ + __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 @@ -231,50 +146,57 @@ 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, @@ -318,4 +240,280 @@ 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. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. + */ +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + + + return cgroup_subsys_on_dfl(memory_cgrp_subsys) && + cgroup_subsys_on_dfl(io_cgrp_subsys) && + 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, io_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(); +} + +#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) +{ +} + +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/bio.h b/include/linux/bio.h index da3a127c9958..cbc5d1d0e47c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -469,9 +469,12 @@ 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..c02e669945e9 --- /dev/null +++ b/include/linux/blk-cgroup.h @@ -0,0 +1,786 @@ +#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/percpu_counter.h> +#include <linux/seq_file.h> +#include <linux/radix-tree.h> +#include <linux/blkdev.h> +#include <linux/atomic.h> + +/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ +#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) + +/* 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 *cpd[BLKCG_MAX_POLS]; + + struct list_head all_blkcgs_node; +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif +}; + +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children, and, for blkg_rwstat, + * to carry result values from read and sum operations. + */ +struct blkg_stat { + struct percpu_counter cpu_cnt; + atomic64_t aux_cnt; +}; + +struct blkg_rwstat { + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_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 blkg:policy pair is + * represented by a blkg_policy_data which is allocated and freed by each + * policy's pd_alloc/free_fn() methods. A policy can allocate private data + * area by allocating larger data structure which embeds blkg_policy_data + * at the beginning. + */ +struct blkg_policy_data { + /* the blkg and policy id this per-policy data belongs to */ + struct blkcg_gq *blkg; + int plid; +}; + +/* + * Policies that need to keep per-blkcg data which is independent from any + * request_queue associated to it should implement cpd_alloc/free_fn() + * methods. A policy can allocate private data area by allocating larger + * data structure which embeds blkcg_policy_data at the beginning. + * cpd_init() is invoked to let each policy handle per-blkcg data. + */ +struct blkcg_policy_data { + /* the blkcg and policy id this per-policy data belongs to */ + struct blkcg *blkcg; + 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_rwstat stat_bytes; + struct blkg_rwstat stat_ios; + + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; + + struct rcu_head rcu_head; +}; + +typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); +typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); +typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node); +typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); + +struct blkcg_policy { + int plid; + /* cgroup files for the policy */ + struct cftype *dfl_cftypes; + struct cftype *legacy_cftypes; + + /* operations */ + blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; + blkcg_pol_init_cpd_fn *cpd_init_fn; + blkcg_pol_free_cpd_fn *cpd_free_fn; + blkcg_pol_bind_cpd_fn *cpd_bind_fn; + + blkcg_pol_alloc_pd_fn *pd_alloc_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_free_pd_fn *pd_free_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_slowpath(struct blkcg *blkcg, + struct request_queue *q, bool update_hint); +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); + +const char *blkg_dev_name(struct blkcg_gq *blkg); +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); +int blkg_print_stat_bytes(struct seq_file *sf, void *v); +int blkg_print_stat_ios(struct seq_file *sf, void *v); +int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); +int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); + +u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); +struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); + +struct blkg_conf_ctx { + struct gendisk *disk; + struct blkcg_gq *blkg; + char *body; +}; + +int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, + 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, io_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, io_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_lookup - internal version of blkg_lookup() + * @blkcg: blkcg of interest + * @q: request_queue of interest + * @update_hint: whether to update lookup hint with the result or not + * + * This is internal version and shouldn't be used by policy + * implementations. Looks up blkgs for the @blkcg - @q pair regardless of + * @q's bypass state. If @update_hint is %true, the caller should be + * holding @q->queue_lock and lookup hint is updated on success. + */ +static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, + struct request_queue *q, + bool update_hint) +{ + struct blkcg_gq *blkg; + + if (blkcg == &blkcg_root) + return q->root_blkg; + + blkg = rcu_dereference(blkcg->blkg_hint); + if (blkg && blkg->q == q) + return blkg; + + return blkg_lookup_slowpath(blkcg, q, update_hint); +} + +/** + * blkg_lookup - lookup blkg for the specified blkcg - q pair + * @blkcg: blkcg of interest + * @q: request_queue of interest + * + * Lookup blkg for the @blkcg - @q pair. This function should be called + * under RCU read lock and is guaranteed to return %NULL if @q is bypassing + * - see blk_queue_bypass_start() for details. + */ +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, + struct request_queue *q) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (unlikely(blk_queue_bypass(q))) + return NULL; + return __blkg_lookup(blkcg, q, false); +} + +/** + * 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->cpd[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; +} + +static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) +{ + return cpd ? cpd->blkcg : 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); +} + +/** + * 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(blkcg, q); + if (unlikely(!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) +{ + if (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 int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp) +{ + int ret; + + ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp); + if (ret) + return ret; + + atomic64_set(&stat->aux_cnt, 0); + return 0; +} + +static inline void blkg_stat_exit(struct blkg_stat *stat) +{ + percpu_counter_destroy(&stat->cpu_cnt); +} + +/** + * blkg_stat_add - add a value to a blkg_stat + * @stat: target blkg_stat + * @val: value to add + * + * Add @val to @stat. The caller must ensure that IRQ on the same CPU + * don't re-enter this function for the same counter. + */ +static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) +{ + __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_stat_read - read the current value of a blkg_stat + * @stat: blkg_stat to read + */ +static inline uint64_t blkg_stat_read(struct blkg_stat *stat) +{ + return percpu_counter_sum_positive(&stat->cpu_cnt); +} + +/** + * blkg_stat_reset - reset a blkg_stat + * @stat: blkg_stat to reset + */ +static inline void blkg_stat_reset(struct blkg_stat *stat) +{ + percpu_counter_set(&stat->cpu_cnt, 0); + atomic64_set(&stat->aux_cnt, 0); +} + +/** + * blkg_stat_add_aux - add a blkg_stat into another's aux count + * @to: the destination blkg_stat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_stat_add_aux(struct blkg_stat *to, + struct blkg_stat *from) +{ + atomic64_add(blkg_stat_read(from) + atomic64_read(&from->aux_cnt), + &to->aux_cnt); +} + +static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) +{ + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} + +static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); +} + +/** + * 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) +{ + struct percpu_counter *cnt; + + if (rw & REQ_WRITE) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + + if (rw & REQ_SYNC) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; + + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * 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 in the aux counts. + */ +static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat result; + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_set(&result.aux_cnt[i], + percpu_counter_sum_positive(&rwstat->cpu_cnt[i])); + return result; +} + +/** + * 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 atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) + + atomic64_read(&tmp.aux_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) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } +} + +/** + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + struct blkg_rwstat v = blkg_rwstat_read(from); + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_add(atomic64_read(&v.aux_cnt[i]) + + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} + +#ifdef CONFIG_BLK_DEV_THROTTLING +extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio); +#else +static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio) { return false; } +#endif + +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) +{ + struct blkcg *blkcg; + struct blkcg_gq *blkg; + bool throtl = false; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } + + throtl = blk_throtl_bio(q, blkg, bio); + + if (!throtl) { + blkg = blkg ?: q->root_blkg; + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_rw, + bio->bi_iter.bi_size); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_rw, 1); + } + + rcu_read_unlock(); + return !throtl; +} + +#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; } + +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) { return true; } + +#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_types.h b/include/linux/blk_types.h index b7299febc4b4..7fda78fc098a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -118,7 +118,6 @@ struct bio { #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 */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d93a6645e88..b5d7bebbc878 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> @@ -821,25 +821,6 @@ 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 *); -/* - * 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); @@ -1054,6 +1035,7 @@ 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/cache.h b/include/linux/cache.h index 17e7e82d2aa7..1be04f8c563a 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -12,10 +12,24 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/* + * __read_mostly is used to keep rarely changing variables out of frequently + * updated cachelines. If an architecture doesn't support it, ignore the + * hint. + */ #ifndef __read_mostly #define __read_mostly #endif +/* + * __ro_after_init is used to mark things that are read-only after init (i.e. + * after mark_rodata_ro() has been called). These are effectively read-only, + * but may get written to during init, so can't live in .rodata (via "const"). + */ +#ifndef __ro_after_init +#define __ro_after_init __attribute__((__section__(".data..ro_after_init"))) +#endif + #ifndef ____cacheline_aligned #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) #endif diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8d9c7e7a6432..f7dbca9b55c5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -14,6 +14,7 @@ #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 @@ -25,6 +26,7 @@ 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 @@ -32,12 +34,17 @@ struct kernfs_open_file; /* define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _cgrp_id, +#define SUBSYS_TAG(_t) CGROUP_ ## _t, \ + __unused_tag_ ## _t = CGROUP_ ## _t - 1, enum cgroup_subsys_id { #include <linux/cgroup_subsys.h> CGROUP_SUBSYS_COUNT, }; +#undef SUBSYS_TAG #undef SUBSYS +#define CGROUP_CANFORK_COUNT (CGROUP_CANFORK_END - CGROUP_CANFORK_START) + /* bits in struct cgroup_subsys_state flags field */ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ @@ -59,7 +66,6 @@ enum { /* 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 */ }; @@ -69,6 +75,7 @@ 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 */ + CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ @@ -76,6 +83,16 @@ enum { }; /* + * cgroup_file is the handle for a file instance created in a cgroup which + * is used, for example, to generate file changed notifications. This can + * be obtained by setting cftype->file_offset. + */ +struct cgroup_file { + /* do not access any fields from outside cgroup core */ + struct kernfs_node *kn; +}; + +/* * Per-subsystem/per-cgroup state maintained by the system. This is the * fundamental structural building block that controllers deal with. * @@ -195,6 +212,9 @@ struct css_set { */ struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + /* all css_task_iters currently walking this cset */ + struct list_head task_iters; + /* For RCU-protected deletion */ struct rcu_head rcu_head; }; @@ -216,15 +236,16 @@ struct cgroup { 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. + * Each non-empty css_set associated with this cgroup 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" */ + struct cgroup_file procs_file; /* handle for "cgroup.procs" */ + struct cgroup_file events_file; /* handle for "cgroup.events" */ /* * The bitmask of subsystems enabled on the child cgroups. @@ -321,12 +342,7 @@ struct cftype { * 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; + unsigned long private; /* * The maximum length of string, excluding trailing nul, that can @@ -338,6 +354,14 @@ struct cftype { unsigned int flags; /* + * If non-zero, should contain the offset from the start of css to + * a struct cgroup_file field. cgroup will record the handle of + * the created file into it. The recorded handle can be used as + * long as the containing css remains accessible. + */ + unsigned int file_offset; + + /* * Fields used for internal bookkeeping. Initialized automatically * during registration. */ @@ -403,19 +427,16 @@ struct cgroup_subsys { 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); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); + int (*can_fork)(struct task_struct *task, void **priv_p); + void (*cancel_fork)(struct task_struct *task, void *priv); + void (*fork)(struct task_struct *task, void *priv); + void (*exit)(struct task_struct *task); + void (*free)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); - int disabled; int early_init; /* @@ -437,6 +458,9 @@ struct cgroup_subsys { int id; const char *name; + /* optional, initialized automatically during boot if not set */ + const char *legacy_name; + /* link to parent, protected by cgroup_lock() */ struct cgroup_root *root; @@ -466,5 +490,40 @@ struct cgroup_subsys { 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_CANFORK_COUNT 0 +#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 96a2ecd5aa69..56e7af910f89 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -13,25 +13,269 @@ #include <linux/nodemask.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> -#include <linux/rwsem.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> +#include <linux/jump_label.h> #include <linux/cgroup-defs.h> - #ifdef CONFIG_CGROUPS +/* + * All weight knobs on the default hierarhcy should use the following min, + * default and max values. The default value is the logarithmic center of + * MIN and MAX and allows 100x to be expressed in both directions. + */ +#define CGROUP_WEIGHT_MIN 1 +#define CGROUP_WEIGHT_DFL 100 +#define CGROUP_WEIGHT_MAX 10000 + +/* 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; + + struct css_set *cur_cset; + struct task_struct *cur_task; + struct list_head iters_node; /* css_set->task_iters */ +}; + +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> +#undef SUBSYS + +#define SUBSYS(_x) \ + extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ + extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; +#include <linux/cgroup_subsys.h> +#undef SUBSYS + +/** + * cgroup_subsys_enabled - fast test on whether a subsys is enabled + * @ss: subsystem in question + */ +#define cgroup_subsys_enabled(ss) \ + static_branch_likely(&ss ## _enabled_key) + +/** + * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy + * @ss: subsystem in question + */ +#define cgroup_subsys_on_dfl(ss) \ + static_branch_likely(&ss ## _on_dfl_key) + +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); +void cgroup_file_notify(struct cgroup_file *cfile); + +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); +extern int cgroup_can_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]); +extern void cgroup_cancel_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]); +extern void cgroup_post_fork(struct task_struct *p, + void *old_ss_priv[CGROUP_CANFORK_COUNT]); +void cgroup_exit(struct task_struct *p); +void cgroup_free(struct task_struct *p); + +int cgroup_init_early(void); +int cgroup_init(void); + +/* + * Iteration helpers and macros. + */ -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 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); -extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, - struct pid *pid, struct task_struct *tsk); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); + +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 + * + * 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))) + +/** + * 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 + * @dst_css: the destination css + * @tset: taskset to iterate + * + * @tset may contain multiple tasks and they may belong to multiple + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. + * + * Iteration is not in any specific order. + */ +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) + +/** + * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset + * @leader: the loop cursor + * @dst_css: the destination css + * @tset: takset to iterate + * + * Iterate threadgroup leaders of @tset. For single-task migrations, @tset + * may not contain any. + */ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ + if ((leader) != (leader)->group_leader) \ + ; \ + else + +/* + * Inline functions. + */ /** * css_get - obtain a reference on the specified css @@ -118,148 +362,6 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } -extern struct cgroup_root cgrp_dfl_root; -extern struct css_set init_css_set; - -/** - * cgroup_on_dfl - test whether a cgroup is on the default hierarchy - * @cgrp: the cgroup of interest - * - * The default hierarchy is the v2 interface of cgroup and this function - * can be used to test whether a cgroup is on the default hierarchy for - * cases where a subsystem should behave differnetly depending on the - * interface version. - * - * The set of behaviors which change on the default hierarchy are still - * being determined and the mount option is prefixed with __DEVEL__. - * - * List of changed behaviors: - * - * - Mount options "noprefix", "xattr", "clone_children", "release_agent" - * and "name" are disallowed. - * - * - When mounting an existing superblock, mount options should match. - * - * - Remount is disallowed. - * - * - rename(2) is disallowed. - * - * - "tasks" is removed. Everything should be at process granularity. Use - * "cgroup.procs" instead. - * - * - "cgroup.procs" is not sorted. pids will be unique unless they got - * recycled inbetween reads. - * - * - "release_agent" and "notify_on_release" are removed. Replacement - * notification mechanism will be implemented. - * - * - "cgroup.clone_children" is removed. - * - * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup - * and its descendants contain no task; otherwise, 1. The file also - * generates kernfs notification which can be monitored through poll and - * [di]notify when the value of the file changes. - * - * - cpuset: tasks will be kept in empty cpusets when hotplug happens and - * take masks of ancestors with non-empty cpus/mems, instead of being - * moved to an ancestor. - * - * - cpuset: a task can be moved into an empty cpuset, and again it takes - * masks of ancestors. - * - * - memcg: use_hierarchy is on by default and the cgroup file for the flag - * is not created. - * - * - blkcg: blk-throttle becomes properly hierarchical. - * - * - debug: disallowed on the default hierarchy. - */ -static inline bool cgroup_on_dfl(const struct cgroup *cgrp) -{ - return cgrp->root == &cgrp_dfl_root; -} - -/* no synchronization, the result can only be used as a hint */ -static inline bool cgroup_has_tasks(struct cgroup *cgrp) -{ - return !list_empty(&cgrp->cset_links); -} - -/* returns ino associated with a cgroup */ -static inline ino_t cgroup_ino(struct cgroup *cgrp) -{ - return cgrp->kn->ino; -} - -/* cft/css accessors for cftype->write() operation */ -static inline struct cftype *of_cft(struct kernfs_open_file *of) -{ - return of->kn->priv; -} - -struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); - -/* cft/css accessors for cftype->seq_*() operations */ -static inline struct cftype *seq_cft(struct seq_file *seq) -{ - return of_cft(seq->private); -} - -static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) -{ - return of_css(seq->private); -} - -/* - * Name / path handling functions. All are thin wrappers around the kernfs - * counterparts and can be called under any context. - */ - -static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) -{ - return kernfs_name(cgrp->kn, buf, buflen); -} - -static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, - size_t buflen) -{ - return kernfs_path(cgrp->kn, buf, buflen); -} - -static inline void pr_cont_cgroup_name(struct cgroup *cgrp) -{ - pr_cont_kernfs_name(cgrp->kn); -} - -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); - -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))) - -#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 @@ -275,11 +377,11 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); */ #ifdef CONFIG_PROVE_RCU extern struct mutex cgroup_mutex; -extern struct rw_semaphore css_set_rwsem; +extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ lockdep_is_held(&cgroup_mutex) || \ - lockdep_is_held(&css_set_rwsem) || \ + lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ @@ -323,6 +425,31 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, } /** + * 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; +} + +/** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID @@ -342,178 +469,86 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, 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); +/* no synchronization, the result can only be used as a hint */ +static inline bool cgroup_is_populated(struct cgroup *cgrp) +{ + return cgrp->populated_cnt; +} -/** - * 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))) +/* returns ino associated with a cgroup */ +static inline ino_t cgroup_ino(struct cgroup *cgrp) +{ + return cgrp->kn->ino; +} -struct cgroup_subsys_state * -css_next_descendant_pre(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); +/* cft/css accessors for cftype->write() operation */ +static inline struct cftype *of_cft(struct kernfs_open_file *of) +{ + return of->kn->priv; +} -struct cgroup_subsys_state * -css_rightmost_descendant(struct cgroup_subsys_state *pos); +struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); -/** - * 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))) +/* cft/css accessors for cftype->seq_*() operations */ +static inline struct cftype *seq_cft(struct seq_file *seq) +{ + return of_cft(seq->private); +} -struct cgroup_subsys_state * -css_next_descendant_post(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); +static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) +{ + return of_css(seq->private); +} -/** - * 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. +/* + * Name / path handling functions. All are thin wrappers around the kernfs + * counterparts and can be called under any context. */ -#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; -}; +static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) +{ + return kernfs_name(cgrp->kn, buf, buflen); +} -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); +static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, + size_t buflen) +{ + return kernfs_path(cgrp->kn, buf, buflen); +} -int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); +static inline void pr_cont_cgroup_name(struct cgroup *cgrp) +{ + pr_cont_kernfs_name(cgrp->kn); +} -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); +static inline void pr_cont_cgroup_path(struct cgroup *cgrp) +{ + pr_cont_kernfs_path(cgrp->kn); +} #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 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 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; -} + struct dentry *dentry) { return -EINVAL; } -static inline void css_put(struct cgroup_subsys_state *css) {} +static inline void cgroup_fork(struct task_struct *p) {} +static inline int cgroup_can_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) +{ return 0; } +static inline void cgroup_cancel_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) {} +static inline void cgroup_post_fork(struct task_struct *p, + void *ss_priv[CGROUP_CANFORK_COUNT]) {} +static inline void cgroup_exit(struct task_struct *p) {} +static inline void cgroup_free(struct task_struct *p) {} -/* 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/cgroup_subsys.h b/include/linux/cgroup_subsys.h index e4a96fb14403..1a96fdaa33d5 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -3,6 +3,17 @@ * * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS. */ + +/* + * This file *must* be included with SUBSYS() defined. + * SUBSYS_TAG() is a noop if undefined. + */ + +#ifndef SUBSYS_TAG +#define __TMP_SUBSYS_TAG +#define SUBSYS_TAG(_x) +#endif + #if IS_ENABLED(CONFIG_CPUSETS) SUBSYS(cpuset) #endif @@ -16,7 +27,7 @@ SUBSYS(cpuacct) #endif #if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) +SUBSYS(io) #endif #if IS_ENABLED(CONFIG_MEMCG) @@ -48,11 +59,28 @@ SUBSYS(hugetlb) #endif /* + * Subsystems that implement the can_fork() family of callbacks. + */ +SUBSYS_TAG(CANFORK_START) + +#if IS_ENABLED(CONFIG_CGROUP_PIDS) +SUBSYS(pids) +#endif + +SUBSYS_TAG(CANFORK_END) + +/* * The following subsystems are not supported on the default hierarchy. */ #if IS_ENABLED(CONFIG_CGROUP_DEBUG) SUBSYS(debug) #endif + +#ifdef __TMP_SUBSYS_TAG +#undef __TMP_SUBSYS_TAG +#undef SUBSYS_TAG +#endif + /* * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS. */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 27fa57322550..020c2d77b965 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -203,6 +203,23 @@ #define __visible __attribute__((externally_visible)) #endif + +#if GCC_VERSION >= 40900 && !defined(__CHECKER__) +/* + * __assume_aligned(n, k): Tell the optimizer that the returned + * pointer can be assumed to be k modulo n. The second argument is + * optional (default 0), so we use a variadic macro to make the + * shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + */ +#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#endif + /* * GCC 'asm goto' miscompiles certain code sequences: * @@ -230,12 +247,25 @@ #define KASAN_ABI_VERSION 3 #endif +#if GCC_VERSION >= 40902 +/* + * Tell the compiler that address safety instrumentation (KASAN) + * should not be applied to that function. + * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + */ +#define __no_sanitize_address __attribute__((no_sanitize_address)) +#endif + #endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) #define __noclone /* not needed */ #endif +#if !defined(__no_sanitize_address) +#define __no_sanitize_address +#endif + /* * A trick to suppress uninitialized variable warning without generating any * code diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 99728072e536..98be9bdb2105 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -196,19 +196,45 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #include <uapi/linux/types.h> -static __always_inline void __read_once_size(const volatile void *p, void *res, int size) +#define __READ_ONCE_SIZE \ +({ \ + switch (size) { \ + case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ + case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ + case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ + case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ + default: \ + barrier(); \ + __builtin_memcpy((void *)res, (const void *)p, size); \ + barrier(); \ + } \ +}) + +static __always_inline +void __read_once_size(const volatile void *p, void *res, int size) { - switch (size) { - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; - default: - barrier(); - __builtin_memcpy((void *)res, (const void *)p, size); - barrier(); - } + __READ_ONCE_SIZE; +} + +#ifdef CONFIG_KASAN +/* + * This function is not 'inline' because __no_sanitize_address confilcts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +static __no_sanitize_address __maybe_unused +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; +} +#else +static __always_inline +void __read_once_size_nocheck(const volatile void *p, void *res, int size) +{ + __READ_ONCE_SIZE; } +#endif static __always_inline void __write_once_size(volatile void *p, void *res, int size) { @@ -246,8 +272,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * required ordering. */ -#define READ_ONCE(x) \ - ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) +#define __READ_ONCE(x, check) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u; \ + if (check) \ + __read_once_size(&(x), __u.__c, sizeof(x)); \ + else \ + __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) +#define READ_ONCE(x) __READ_ONCE(x, 1) + +/* + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need + * to hide memory access from KASAN. + */ +#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) #define WRITE_ONCE(x, val) \ ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; }) @@ -370,6 +410,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define __visible #endif +/* + * Assume alignment of return value. + */ +#ifndef __assume_aligned +#define __assume_aligned(a, ...) +#endif + + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) 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..26509b509569 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -574,6 +574,8 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); int cpufreq_boost_trigger_state(int state); int cpufreq_boost_supported(void); int cpufreq_boost_enabled(void); +int cpufreq_enable_boost_support(void); +bool policy_has_boost_freq(struct cpufreq_policy *policy); #else static inline int cpufreq_boost_trigger_state(int state) { @@ -587,12 +589,23 @@ static inline int cpufreq_boost_enabled(void) { return 0; } + +static inline int cpufreq_enable_boost_support(void) +{ + return -EINVAL; +} + +static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) +{ + return false; +} #endif /* the following funtion is for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; +extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; extern struct freq_attr *cpufreq_generic_attr[]; int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); diff --git a/include/linux/dax.h b/include/linux/dax.h new file mode 100644 index 000000000000..96a2cbe0b53e --- /dev/null +++ b/include/linux/dax.h @@ -0,0 +1,35 @@ +#ifndef _LINUX_DAX_H +#define _LINUX_DAX_H + +#include <linux/fs.h> +#include <linux/mm.h> +#include <asm/pgtable.h> + +ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, + get_block_t, dio_iodone_t, int flags); +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, + dax_iodone_t); +int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +#else +static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags, get_block_t gb, + dax_iodone_t di) +{ + return VM_FAULT_FALLBACK; +} +#define __dax_pmd_fault dax_pmd_fault +#endif +int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); +#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) + +#endif diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index cb25af461054..fe5b1169a6a7 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -80,6 +80,8 @@ struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); +struct dentry *debugfs_create_ulong(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value); struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); struct dentry *debugfs_create_x16(const char *name, umode_t mode, @@ -93,7 +95,7 @@ struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value); struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, u32 *value); + struct dentry *parent, bool *value); struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, @@ -117,6 +119,12 @@ struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, bool debugfs_initialized(void); +ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos); + +ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos); + #else #include <linux/err.h> @@ -238,7 +246,7 @@ static inline struct dentry *debugfs_create_atomic_t(const char *name, umode_t m static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, - u32 *value) + bool *value) { return ERR_PTR(-ENODEV); } @@ -283,6 +291,20 @@ static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev, return ERR_PTR(-ENODEV); } +static inline ssize_t debugfs_read_file_bool(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + +static inline ssize_t debugfs_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + #endif #endif diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index ce447f0f1bad..68030e22af35 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -65,7 +65,10 @@ struct devfreq_dev_status { * The "flags" parameter's possible values are * explained above with "DEVFREQ_FLAG_*" macros. * @get_dev_status: The device should provide the current performance - * status to devfreq, which is used by governors. + * status to devfreq. Governors are recommended not to + * use this directly. Instead, governors are recommended + * to use devfreq_update_stats() along with + * devfreq.last_status. * @get_cur_freq: The device should provide the current frequency * at which it is operating. * @exit: An optional callback that is called when devfreq @@ -161,6 +164,7 @@ struct devfreq { struct delayed_work work; unsigned long previous_freq; + struct devfreq_dev_status last_status; void *data; /* private data for governors */ @@ -204,6 +208,19 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev, extern void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +/** + * devfreq_update_stats() - update the last_status pointer in struct devfreq + * @df: the devfreq instance whose status needs updating + * + * Governors are recommended to use this function along with last_status, + * which allows other entities to reuse the last_status without affecting + * the values fetched later by governors. + */ +static inline int devfreq_update_stats(struct devfreq *df) +{ + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} + #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq @@ -289,6 +306,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { } + +static inline int devfreq_update_stats(struct devfreq *df) +{ + return -EINVAL; +} #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h new file mode 100644 index 000000000000..7adf6cc4b305 --- /dev/null +++ b/include/linux/devfreq_cooling.h @@ -0,0 +1,81 @@ +/* + * devfreq_cooling: Thermal cooling device implementation for devices using + * devfreq + * + * Copyright (C) 2014-2015 ARM Limited + * + * 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 __DEVFREQ_COOLING_H__ +#define __DEVFREQ_COOLING_H__ + +#include <linux/devfreq.h> +#include <linux/thermal.h> + +#ifdef CONFIG_DEVFREQ_THERMAL + +/** + * struct devfreq_cooling_power - Devfreq cooling power ops + * @get_static_power: Take voltage, in mV, and return the static power + * in mW. If NULL, the static power is assumed + * to be 0. + * @get_dynamic_power: Take voltage, in mV, and frequency, in HZ, and + * return the dynamic power draw in mW. If NULL, + * a simple power model is used. + * @dyn_power_coeff: Coefficient for the simple dynamic power model in + * mW/(MHz mV mV). + * If get_dynamic_power() is NULL, then the + * dynamic power is calculated as + * @dyn_power_coeff * frequency * voltage^2 + */ +struct devfreq_cooling_power { + unsigned long (*get_static_power)(unsigned long voltage); + unsigned long (*get_dynamic_power)(unsigned long freq, + unsigned long voltage); + unsigned long dyn_power_coeff; +}; + +struct thermal_cooling_device * +of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, + struct devfreq_cooling_power *dfc_power); +struct thermal_cooling_device * +of_devfreq_cooling_register(struct device_node *np, struct devfreq *df); +struct thermal_cooling_device *devfreq_cooling_register(struct devfreq *df); +void devfreq_cooling_unregister(struct thermal_cooling_device *dfc); + +#else /* !CONFIG_DEVFREQ_THERMAL */ + +struct thermal_cooling_device * +of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df, + struct devfreq_cooling_power *dfc_power) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct thermal_cooling_device * +of_devfreq_cooling_register(struct device_node *np, struct devfreq *df) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct thermal_cooling_device * +devfreq_cooling_register(struct devfreq *df) +{ + return ERR_PTR(-EINVAL); +} + +static inline void +devfreq_cooling_unregister(struct thermal_cooling_device *dfc) +{ +} + +#endif /* CONFIG_DEVFREQ_THERMAL */ +#endif /* __DEVFREQ_COOLING_H__ */ diff --git a/include/linux/device.h b/include/linux/device.h index 6558af90c8fe..dda6d94ce986 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -683,6 +683,7 @@ struct device_dma_parameters { * along with subsystem-level and driver-level callbacks. * @pins: For device pin management. * See Documentation/pinctrl.txt for details. + * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all @@ -743,6 +744,9 @@ struct device { struct dev_pm_info power; struct dev_pm_domain *pm_domain; +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *msi_domain; +#endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif @@ -830,6 +834,22 @@ static inline void set_dev_node(struct device *dev, int node) } #endif +static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) +{ +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + return dev->msi_domain; +#else + return NULL; +#endif +} + +static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) +{ +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + dev->msi_domain = d; +#endif +} + static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h new file mode 100644 index 000000000000..fc481037478a --- /dev/null +++ b/include/linux/dma-iommu.h @@ -0,0 +1,85 @@ +/* + * Copyright (C) 2014-2015 ARM Ltd. + * + * 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. + * + * 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 __DMA_IOMMU_H +#define __DMA_IOMMU_H + +#ifdef __KERNEL__ +#include <asm/errno.h> + +#ifdef CONFIG_IOMMU_DMA +#include <linux/iommu.h> + +int iommu_dma_init(void); + +/* Domain management interface for IOMMU drivers */ +int iommu_get_dma_cookie(struct iommu_domain *domain); +void iommu_put_dma_cookie(struct iommu_domain *domain); + +/* Setup call for arch DMA mapping code */ +int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size); + +/* General helpers for DMA-API <-> IOMMU-API interaction */ +int dma_direction_to_prot(enum dma_data_direction dir, bool coherent); + +/* + * These implement the bulk of the relevant DMA mapping callbacks, but require + * the arch code to take care of attributes and cache maintenance + */ +struct page **iommu_dma_alloc(struct device *dev, size_t size, + gfp_t gfp, int prot, dma_addr_t *handle, + void (*flush_page)(struct device *, const void *, phys_addr_t)); +void iommu_dma_free(struct device *dev, struct page **pages, size_t size, + dma_addr_t *handle); + +int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma); + +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, int prot); +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int prot); + +/* + * Arch code with no special attribute handling may use these + * directly as DMA mapping callbacks for simplicity + */ +void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs); +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs); +int iommu_dma_supported(struct device *dev, u64 mask); +int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); + +#else + +struct iommu_domain; + +static inline int iommu_dma_init(void) +{ + return 0; +} + +static inline int iommu_get_dma_cookie(struct iommu_domain *domain) +{ + return -ENODEV; +} + +static inline void iommu_put_dma_cookie(struct iommu_domain *domain) +{ +} + +#endif /* CONFIG_IOMMU_DMA */ +#endif /* __KERNEL__ */ +#endif /* __DMA_IOMMU_H */ diff --git a/include/linux/edac.h b/include/linux/edac.h index da3b72e95db3..7c6b7ba55589 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -772,7 +772,7 @@ struct mem_ctl_info { #ifdef CONFIG_EDAC_DEBUG struct dentry *debugfs; u8 fake_inject_layer[EDAC_MAX_LAYERS]; - u32 fake_inject_ue; + bool fake_inject_ue; u16 fake_inject_count; #endif }; 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/fault-inject.h b/include/linux/fault-inject.h index 798fad9e420d..3159a7dba034 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -18,7 +18,7 @@ struct fault_attr { atomic_t times; atomic_t space; unsigned long verbose; - u32 task_filter; + bool task_filter; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; diff --git a/include/linux/fs.h b/include/linux/fs.h index ae327f6a53f6..8ccb136c3980 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,6 +35,7 @@ #include <uapi/linux/fs.h> struct backing_dev_info; +struct bdi_writeback; struct export_operations; struct hd_geometry; struct iovec; @@ -51,7 +52,6 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -635,7 +635,15 @@ struct inode { unsigned long dirtied_time_when; struct hlist_node i_hash; - struct list_head i_wb_list; /* backing dev IO list */ + struct list_head i_io_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 { @@ -1248,6 +1256,8 @@ 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 { @@ -1286,6 +1296,7 @@ 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; @@ -1821,6 +1832,11 @@ 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) @@ -1840,6 +1856,7 @@ 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) @@ -2249,7 +2266,13 @@ 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; } @@ -2572,7 +2595,7 @@ static inline void insert_inode_hash(struct inode *inode) extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { - if (!inode_unhashed(inode)) + if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } @@ -2631,16 +2654,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, - get_block_t, dio_iodone_t, int flags); -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, - dax_iodone_t); -int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); -#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, loff_t file_offset); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f10b20f05159..3d59f075d895 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -33,6 +33,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); +int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned long pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, @@ -164,6 +166,13 @@ static inline bool is_huge_zero_page(struct page *page) return ACCESS_ONCE(huge_zero_page) == page; } +static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return is_huge_zero_page(pmd_page(pmd)); +} + +struct page *get_huge_zero_page(void); + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index bcc853eccc85..7edd30515298 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -48,9 +48,7 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) static inline bool hugetlb_cgroup_disabled(void) { - if (hugetlb_cgrp_subsys.disabled) - return true; - return false; + return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, diff --git a/include/linux/init.h b/include/linux/init.h index 21b6d768edd7..5e386444194b 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -153,6 +153,10 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +#endif + extern void (*late_time_init)(void); extern bool initcall_debug; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 696d22312b31..0cc0bbf20022 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), @@ -56,7 +49,6 @@ extern struct fs_struct init_fs; }, \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ - INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0546b8710ce3..da300b0728f6 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -81,6 +81,7 @@ struct iommu_domain { iommu_fault_handler_t handler; void *handler_token; struct iommu_domain_geometry geometry; + void *iova_cookie; }; enum iommu_cap { @@ -114,6 +115,20 @@ 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 +174,10 @@ 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 +212,7 @@ 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 +224,10 @@ 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 +251,7 @@ 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); @@ -332,6 +357,11 @@ 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 +403,21 @@ 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/iova.h b/include/linux/iova.h index 3920a19d8194..92f7177db2ce 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -68,8 +68,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -int iommu_iova_cache_init(void); -void iommu_iova_cache_destroy(void); +int iova_cache_get(void); +void iova_cache_put(void); struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index cbf1ce800fd1..d14568e05047 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -19,7 +19,7 @@ #define __LINUX_IRQCHIP_ARM_GIC_V3_H #include <asm/sysreg.h> - +#include <asm/barrier.h> /* * Distributor registers. We assume we're running non-secure, with ARE * being set. Secure-only and non-ARE registers are not described. @@ -360,6 +360,7 @@ #ifndef __ASSEMBLY__ #include <linux/stringify.h> +#include <asm/msi.h> /* * We need a value to serve as a irq-type for LPIs. Choose one that will diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 676d7306a360..3c5ca459ac98 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -45,6 +45,20 @@ struct irq_data; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 +/* + * Should several domains have the same device node, but serve + * different purposes (for example one domain is for PCI/MSI, and the + * other for wired IRQs), they can be distinguished using a + * bus-specific token. Most domains are expected to only carry + * DOMAIN_BUS_ANY. + */ +enum irq_domain_bus_token { + DOMAIN_BUS_ANY = 0, + DOMAIN_BUS_PCI_MSI, + DOMAIN_BUS_PLATFORM_MSI, + DOMAIN_BUS_NEXUS, +}; + /** * struct irq_domain_ops - Methods for irq_domain objects * @match: Match an interrupt controller device node to a host, returns @@ -61,7 +75,8 @@ struct irq_data; * to setup the irq_desc when returning from map(). */ struct irq_domain_ops { - int (*match)(struct irq_domain *d, struct device_node *node); + int (*match)(struct irq_domain *d, struct device_node *node, + enum irq_domain_bus_token bus_token); int (*map)(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw); void (*unmap)(struct irq_domain *d, unsigned int virq); int (*xlate)(struct irq_domain *d, struct device_node *node, @@ -116,6 +131,7 @@ struct irq_domain { /* Optional data */ struct device_node *of_node; + enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; @@ -161,9 +177,15 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, irq_hw_number_t first_hwirq, const struct irq_domain_ops *ops, void *host_data); -extern struct irq_domain *irq_find_host(struct device_node *node); +extern struct irq_domain *irq_find_matching_host(struct device_node *node, + enum irq_domain_bus_token bus_token); extern void irq_set_default_host(struct irq_domain *host); +static inline struct irq_domain *irq_find_host(struct device_node *node) +{ + return irq_find_matching_host(node, DOMAIN_BUS_ANY); +} + /** * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f4de473f226b..3f08411305a8 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -86,8 +86,8 @@ struct static_key { #ifndef __ASSEMBLY__ enum jump_label_type { - JUMP_LABEL_DISABLE = 0, - JUMP_LABEL_ENABLE, + JUMP_LABEL_NOP = 0, + JUMP_LABEL_JMP, }; struct module; @@ -101,33 +101,18 @@ static inline int static_key_count(struct static_key *key) #ifdef HAVE_JUMP_LABEL -#define JUMP_LABEL_TYPE_FALSE_BRANCH 0UL -#define JUMP_LABEL_TYPE_TRUE_BRANCH 1UL -#define JUMP_LABEL_TYPE_MASK 1UL - -static -inline struct jump_entry *jump_label_get_entries(struct static_key *key) -{ - return (struct jump_entry *)((unsigned long)key->entries - & ~JUMP_LABEL_TYPE_MASK); -} - -static inline bool jump_label_get_branch_default(struct static_key *key) -{ - if (((unsigned long)key->entries & JUMP_LABEL_TYPE_MASK) == - JUMP_LABEL_TYPE_TRUE_BRANCH) - return true; - return false; -} +#define JUMP_TYPE_FALSE 0UL +#define JUMP_TYPE_TRUE 1UL +#define JUMP_TYPE_MASK 1UL static __always_inline bool static_key_false(struct static_key *key) { - return arch_static_branch(key); + return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { - return !static_key_false(key); + return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; @@ -145,12 +130,12 @@ extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern void jump_label_apply_nops(struct module *mod); -#define STATIC_KEY_INIT_TRUE ((struct static_key) \ +#define STATIC_KEY_INIT_TRUE \ { .enabled = ATOMIC_INIT(1), \ - .entries = (void *)JUMP_LABEL_TYPE_TRUE_BRANCH }) -#define STATIC_KEY_INIT_FALSE ((struct static_key) \ + .entries = (void *)JUMP_TYPE_TRUE } +#define STATIC_KEY_INIT_FALSE \ { .enabled = ATOMIC_INIT(0), \ - .entries = (void *)JUMP_LABEL_TYPE_FALSE_BRANCH }) + .entries = (void *)JUMP_TYPE_FALSE } #else /* !HAVE_JUMP_LABEL */ @@ -198,21 +183,174 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -#define STATIC_KEY_INIT_TRUE ((struct static_key) \ - { .enabled = ATOMIC_INIT(1) }) -#define STATIC_KEY_INIT_FALSE ((struct static_key) \ - { .enabled = ATOMIC_INIT(0) }) +#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } +#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* HAVE_JUMP_LABEL */ #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled -static inline bool static_key_enabled(struct static_key *key) +static inline void static_key_enable(struct static_key *key) { - return static_key_count(key) > 0; + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (!count) + static_key_slow_inc(key); } +static inline void static_key_disable(struct static_key *key) +{ + int count = static_key_count(key); + + WARN_ON_ONCE(count < 0 || count > 1); + + if (count) + static_key_slow_dec(key); +} + +/* -------------------------------------------------------------------------- */ + +/* + * Two type wrappers around static_key, such that we can use compile time + * type differentiation to emit the right code. + * + * All the below code is macros in order to play type games. + */ + +struct static_key_true { + struct static_key key; +}; + +struct static_key_false { + struct static_key key; +}; + +#define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } +#define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } + +#define DEFINE_STATIC_KEY_TRUE(name) \ + struct static_key_true name = STATIC_KEY_TRUE_INIT + +#define DEFINE_STATIC_KEY_FALSE(name) \ + struct static_key_false name = STATIC_KEY_FALSE_INIT + +extern bool ____wrong_branch_error(void); + +#define static_key_enabled(x) \ +({ \ + if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ + !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ + !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + ____wrong_branch_error(); \ + static_key_count((struct static_key *)x) > 0; \ +}) + +#ifdef HAVE_JUMP_LABEL + +/* + * Combine the right initial value (type) with the right branch order + * to generate the desired result. + * + * + * type\branch| likely (1) | unlikely (0) + * -----------+-----------------------+------------------ + * | | + * true (1) | ... | ... + * | NOP | JMP L + * | <br-stmts> | 1: ... + * | L: ... | + * | | + * | | L: <br-stmts> + * | | jmp 1b + * | | + * -----------+-----------------------+------------------ + * | | + * false (0) | ... | ... + * | JMP L | NOP + * | <br-stmts> | 1: ... + * | L: ... | + * | | + * | | L: <br-stmts> + * | | jmp 1b + * | | + * -----------+-----------------------+------------------ + * + * The initial value is encoded in the LSB of static_key::entries, + * type: 0 = false, 1 = true. + * + * The branch type is encoded in the LSB of jump_entry::key, + * branch: 0 = unlikely, 1 = likely. + * + * This gives the following logic table: + * + * enabled type branch instuction + * -----------------------------+----------- + * 0 0 0 | NOP + * 0 0 1 | JMP + * 0 1 0 | NOP + * 0 1 1 | JMP + * + * 1 0 0 | JMP + * 1 0 1 | NOP + * 1 1 0 | JMP + * 1 1 1 | NOP + * + * Which gives the following functions: + * + * dynamic: instruction = enabled ^ branch + * static: instruction = type ^ branch + * + * See jump_label_type() / jump_label_init_type(). + */ + +#define static_branch_likely(x) \ +({ \ + bool branch; \ + if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ + branch = !arch_static_branch(&(x)->key, true); \ + else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + branch = !arch_static_branch_jump(&(x)->key, true); \ + else \ + branch = ____wrong_branch_error(); \ + branch; \ +}) + +#define static_branch_unlikely(x) \ +({ \ + bool branch; \ + if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ + branch = arch_static_branch_jump(&(x)->key, false); \ + else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ + branch = arch_static_branch(&(x)->key, false); \ + else \ + branch = ____wrong_branch_error(); \ + branch; \ +}) + +#else /* !HAVE_JUMP_LABEL */ + +#define static_branch_likely(x) likely(static_key_enabled(&(x)->key)) +#define static_branch_unlikely(x) unlikely(static_key_enabled(&(x)->key)) + +#endif /* HAVE_JUMP_LABEL */ + +/* + * Advanced usage; refcount, branch is enabled when: count != 0 + */ + +#define static_branch_inc(x) static_key_slow_inc(&(x)->key) +#define static_branch_dec(x) static_key_slow_dec(&(x)->key) + +/* + * Normal usage; boolean enable/disable. + */ + +#define static_branch_enable(x) static_key_enable(&(x)->key) +#define static_branch_disable(x) static_key_disable(&(x)->key) + #endif /* _LINUX_JUMP_LABEL_H */ #endif /* __ASSEMBLY__ */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5486d777b706..0fdc798e3ff7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -1,6 +1,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include <linux/sched.h> #include <linux/types.h> struct kmem_cache; @@ -10,10 +11,17 @@ struct vm_struct; #ifdef CONFIG_KASAN #define KASAN_SHADOW_SCALE_SHIFT 3 -#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #include <asm/kasan.h> -#include <linux/sched.h> +#include <asm/pgtable.h> + +extern unsigned char kasan_zero_page[PAGE_SIZE]; +extern pte_t kasan_zero_pte[PTRS_PER_PTE]; +extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; +extern pud_t kasan_zero_pud[PTRS_PER_PUD]; + +void kasan_populate_zero_shadow(const void *shadow_start, + const void *shadow_end); static inline void *kasan_mem_to_shadow(const void *addr) { @@ -35,6 +43,8 @@ static inline void kasan_disable_current(void) void kasan_unpoison_shadow(const void *address, size_t size); +void kasan_unpoison_task_stack(struct task_struct *task); + void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); @@ -58,6 +68,8 @@ void kasan_free_shadow(const struct vm_struct *vm); static inline void kasan_unpoison_shadow(const void *address, size_t size) {} +static inline void kasan_unpoison_task_stack(struct task_struct *task) {} + static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 29d1896c3ba5..5d4e9c4b821d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -266,6 +266,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); +size_t kernfs_path_len(struct kernfs_node *kn); char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); @@ -278,6 +279,7 @@ 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); @@ -331,6 +333,9 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } +static inline size_t kernfs_path_len(struct kernfs_node *kn) +{ return 0; } + static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return NULL; } @@ -355,6 +360,10 @@ 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/kvm_host.h b/include/linux/kvm_host.h index 29a57a5b7cee..110964d19e5a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -773,16 +773,10 @@ 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 @@ -794,12 +788,27 @@ 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/list.h b/include/linux/list.h index feb773c76ee0..3e3e64a61002 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -672,6 +672,11 @@ static inline void hlist_add_fake(struct hlist_node *n) n->pprev = &n->next; } +static inline bool hlist_fake(struct hlist_node *h) +{ + return h->pprev == &h->next; +} + /* * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c8918114804..501597f36721 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -23,6 +23,11 @@ #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> +#include <linux/page_counter.h> +#include <linux/vmpressure.h> +#include <linux/eventfd.h> +#include <linux/mmzone.h> +#include <linux/writeback.h> struct mem_cgroup; struct page; @@ -41,6 +46,7 @@ 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, @@ -66,10 +72,224 @@ enum mem_cgroup_events_index { MEMCG_NR_EVENTS, }; +/* + * Per memcg event counter is incremented at every pagein/pageout. With THP, + * it will be incremated by the number of pages. This counter is used for + * for trigger some periodic events. This is straightforward and better + * than using jiffies etc. to handle periodic memcg event. + */ +enum mem_cgroup_events_target { + MEM_CGROUP_TARGET_THRESH, + MEM_CGROUP_TARGET_SOFTLIMIT, + MEM_CGROUP_TARGET_NUMAINFO, + MEM_CGROUP_NTARGETS, +}; + +/* + * Bits in struct cg_proto.flags + */ +enum cg_proto_flags { + /* Currently active and new sockets should be assigned to cgroups */ + MEMCG_SOCK_ACTIVE, + /* It was ever activated; we must disarm static keys on destruction */ + MEMCG_SOCK_ACTIVATED, +}; + +struct cg_proto { + struct page_counter memory_allocated; /* Current allocated memory. */ + struct percpu_counter sockets_allocated; /* Current number of sockets. */ + int memory_pressure; + long sysctl_mem[3]; + unsigned long flags; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; +}; + #ifdef CONFIG_MEMCG -void mem_cgroup_events(struct mem_cgroup *memcg, +struct mem_cgroup_stat_cpu { + long count[MEM_CGROUP_STAT_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + +struct mem_cgroup_reclaim_iter { + struct mem_cgroup *position; + /* scan generation, increased every round-trip */ + unsigned int generation; +}; + +/* + * per-zone information in memory controller. + */ +struct mem_cgroup_per_zone { + struct lruvec lruvec; + unsigned long lru_size[NR_LRU_LISTS]; + + struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + + struct rb_node tree_node; /* RB tree node */ + unsigned long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ +}; + +struct mem_cgroup_per_node { + struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; +}; + +struct mem_cgroup_threshold { + struct eventfd_ctx *eventfd; + unsigned long threshold; +}; + +/* For threshold */ +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below or equal to usage. */ + int current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +struct mem_cgroup_thresholds { + /* Primary thresholds array */ + struct mem_cgroup_threshold_ary *primary; + /* + * Spare threshold array. + * This is needed to make mem_cgroup_unregister_event() "never fail". + * It must be able to store at least primary->size - 1 entries. + */ + struct mem_cgroup_threshold_ary *spare; +}; + +/* + * The memory controller data structure. The memory controller controls both + * page cache and RSS per cgroup. We would eventually like to provide + * statistics based on the statistics developed by Rik Van Riel for clock-pro, + * to help the administrator determine what knobs to tune. + */ +struct mem_cgroup { + struct cgroup_subsys_state css; + + /* Accounted resources */ + struct page_counter memory; + struct page_counter memsw; + struct page_counter kmem; + + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + + unsigned long soft_limit; + + /* vmpressure notifications */ + struct vmpressure vmpressure; + + /* css_online() has been completed */ + int initialized; + + /* + * Should the accounting and control be hierarchical, per subtree? + */ + bool use_hierarchy; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + int swappiness; + /* OOM-Killer disable */ + int oom_kill_disable; + + /* handle for "memory.events" */ + struct cgroup_file events_file; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; + /* + * percpu counter. + */ + struct mem_cgroup_stat_cpu __percpu *stat; + +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) + struct cg_proto tcp_mem; +#endif +#if defined(CONFIG_MEMCG_KMEM) + /* Index in the kmem_cache->memcg_params.memcg_caches array */ + int kmemcg_id; + bool kmem_acct_activated; + bool kmem_acct_active; +#endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + + struct mem_cgroup_per_node *nodeinfo[0]; + /* WARNING: nodeinfo must be the last member here */ +}; +extern struct cgroup_subsys_state *mem_cgroup_root_css; + +/** + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, - unsigned int nr); + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); + cgroup_file_notify(&memcg->events_file); +} bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -87,15 +307,31 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); -bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, - struct mem_cgroup *root); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); -extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); -extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); +struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); + +struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ + return css ? container_of(css, struct mem_cgroup, css) : NULL; +} -extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); +void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); + +static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, + struct mem_cgroup *root) +{ + if (root == memcg) + return true; + if (!root->use_hierarchy) + return false; + return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); +} static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) @@ -111,39 +347,83 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); -void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +static inline bool mem_cgroup_disabled(void) +{ + return !cgroup_subsys_enabled(memory_cgrp_subsys); +} /* * For memory reclaim. */ -int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); -unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); -void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); -extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, - struct task_struct *p); + +void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, + int nr_pages); + +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + +static inline +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +{ + struct mem_cgroup_per_zone *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + return mz->lru_size[lru]; +} + +static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) +{ + unsigned long inactive_ratio; + unsigned long inactive; + unsigned long active; + unsigned long gb; + + inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); + active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + return inactive * inactive_ratio < active; +} + +void mem_cgroup_handle_over_high(void); + +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); static inline void mem_cgroup_oom_enable(void) { - WARN_ON(current->memcg_oom.may_oom); - current->memcg_oom.may_oom = 1; + WARN_ON(current->memcg_may_oom); + current->memcg_may_oom = 1; } static inline void mem_cgroup_oom_disable(void) { - WARN_ON(!current->memcg_oom.may_oom); - current->memcg_oom.may_oom = 0; + WARN_ON(!current->memcg_may_oom); + current->memcg_may_oom = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { - return p->memcg_oom.memcg; + return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); @@ -152,18 +432,26 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -static inline bool mem_cgroup_disabled(void) -{ - if (memory_cgrp_subsys.disabled) - return true; - return false; -} - struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); -void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, - enum mem_cgroup_stat_index idx, int val); void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, + enum mem_cgroup_stat_index idx, int val) +{ + VM_BUG_ON(!rcu_read_lock_held()); + + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); +} + static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { @@ -180,13 +468,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - __mem_cgroup_count_vm_event(mm, idx); + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + goto out; + + switch (idx) { + case PGFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); + break; + case PGMAJFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); + break; + default: + BUG(); + } +out: + rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); @@ -269,12 +575,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } -static inline struct cgroup_subsys_state - *mem_cgroup_css(struct mem_cgroup *memcg) -{ - return NULL; -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -330,6 +630,10 @@ static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { } +static inline void mem_cgroup_handle_over_high(void) +{ +} + static inline void mem_cgroup_oom_enable(void) { } @@ -382,6 +686,31 @@ 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 *pfilepages, + unsigned long *pheadroom, 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 *pfilepages, + unsigned long *pheadroom, + 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); @@ -399,8 +728,8 @@ static inline void sock_release_memcg(struct sock *sk) extern struct static_key memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; -extern void memcg_get_cache_ids(void); -extern void memcg_put_cache_ids(void); +void memcg_get_cache_ids(void); +void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still @@ -415,7 +744,10 @@ static inline bool memcg_kmem_enabled(void) return static_key_false(&memcg_kmem_enabled_key); } -bool memcg_kmem_is_active(struct mem_cgroup *memcg); +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return memcg->kmem_acct_active; +} /* * In general, we'll do everything in our power to not incur in any overhead @@ -434,7 +766,15 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order); void __memcg_kmem_uncharge_pages(struct page *page, int order); -int memcg_cache_id(struct mem_cgroup *memcg); +/* + * helper for acessing a memcg's index. It will be used as an index in the + * child cache array in kmem_cache, and also to derive its name. This function + * will return -1 when this is not a kmem-limited memcg. + */ +static inline int memcg_cache_id(struct mem_cgroup *memcg) +{ + return memcg ? memcg->kmemcg_id : -1; +} struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); diff --git a/include/linux/mm.h b/include/linux/mm.h index 6b85ec64d302..6f4da6f3f75b 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; @@ -245,6 +246,8 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*pmd_fault)(struct vm_area_struct *, unsigned long address, + pmd_t *, unsigned int flags); void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf); /* notification that a previously read-only page is about to become @@ -915,6 +918,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return page->mem_cgroup; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ + page->mem_cgroup = memcg; +} +#else +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg) +{ +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ @@ -1239,10 +1263,13 @@ 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); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 54d74f6eb233..0a3dc9d6579a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -354,10 +354,10 @@ struct zone { struct per_cpu_pageset __percpu *pageset; /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. + * This is a per-zone reserve of pages that are not available + * to userspace allocations. */ - unsigned long dirty_balance_reserve; + unsigned long totalreserve_pages; #ifndef CONFIG_SPARSEMEM /* diff --git a/include/linux/msi.h b/include/linux/msi.h index 8ac4a68ffae2..692f217ae813 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -108,9 +108,6 @@ struct msi_controller { struct device *dev; struct device_node *of_node; struct list_head list; -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *domain; -#endif int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev, struct msi_desc *desc); diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index d884929a7747..4bcbd586a672 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -74,6 +74,7 @@ static inline int of_irq_to_resource_table(struct device_node *dev, */ extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); extern struct device_node *of_irq_find_parent(struct device_node *child); +extern void of_msi_configure(struct device *dev, struct device_node *np); #else /* !CONFIG_OF */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4b3736f7065c..fb0814ca65c7 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); /* diff --git a/include/linux/pci.h b/include/linux/pci.h index 109ccee9e3e6..dc69aed25ff2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1859,10 +1859,12 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, /* PCI <-> OF binding helpers */ #ifdef CONFIG_OF struct device_node; +struct irq_domain; void pci_set_of_node(struct pci_dev *dev); void pci_release_of_node(struct pci_dev *dev); void pci_set_bus_of_node(struct pci_bus *bus); void pci_release_bus_of_node(struct pci_bus *bus); +struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); /* Arch may override this (weak) */ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); @@ -1885,6 +1887,8 @@ static inline void pci_set_bus_of_node(struct pci_bus *bus) { } static inline void pci_release_bus_of_node(struct pci_bus *bus) { } static inline struct device_node * pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } +static inline struct irq_domain * +pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } #endif /* CONFIG_OF */ #ifdef CONFIG_EEH diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index cec2d4540914..cccaf4a29e9f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -30,7 +30,13 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); +bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); + int dev_pm_opp_get_opp_count(struct device *dev); +unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev); +unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev); +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -51,6 +57,14 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev); +int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, + unsigned int count); +void dev_pm_opp_put_supported_hw(struct device *dev); +int dev_pm_opp_set_prop_name(struct device *dev, const char *name); +void dev_pm_opp_put_prop_name(struct device *dev); +int dev_pm_opp_set_regulator(struct device *dev, const char *name); +void dev_pm_opp_put_regulator(struct device *dev); +int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -62,11 +76,36 @@ static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) return 0; } +static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp) +{ + return false; +} + static inline int dev_pm_opp_get_opp_count(struct device *dev) { return 0; } +static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) +{ + return 0; +} + +static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) +{ + return 0; +} + +static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev) +{ + return 0; +} + +static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + return NULL; +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { @@ -110,19 +149,71 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier( { return ERR_PTR(-EINVAL); } + +static inline int dev_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} + +static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_prop_name(struct device *dev) {} + +static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_regulator(struct device *dev) {} + +static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) +{ + return -EINVAL; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -int of_init_opp_table(struct device *dev); -void of_free_opp_table(struct device *dev); +int dev_pm_opp_of_add_table(struct device *dev); +void dev_pm_opp_of_remove_table(struct device *dev); +int dev_pm_opp_of_cpumask_add_table(cpumask_var_t cpumask); +void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask); +int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask); +int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask); #else -static inline int of_init_opp_table(struct device *dev) +static inline int dev_pm_opp_of_add_table(struct device *dev) { return -EINVAL; } -static inline void of_free_opp_table(struct device *dev) +static inline void dev_pm_opp_of_remove_table(struct device *dev) +{ +} + +static inline int dev_pm_opp_of_cpumask_add_table(cpumask_var_t cpumask) +{ + return -ENOSYS; +} + +static inline void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask) +{ +} + +static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) +{ + return -ENOSYS; +} + +static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask) { + return -ENOSYS; } #endif diff --git a/include/linux/psci.h b/include/linux/psci.h new file mode 100644 index 000000000000..393efe2edf9a --- /dev/null +++ b/include/linux/psci.h @@ -0,0 +1,57 @@ +/* + * 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. + * + * Copyright (C) 2015 ARM Limited + */ + +#ifndef __LINUX_PSCI_H +#define __LINUX_PSCI_H + +#include <linux/init.h> +#include <linux/types.h> + +#define PSCI_POWER_STATE_TYPE_STANDBY 0 +#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 + +bool psci_tos_resident_on(int cpu); +bool psci_power_state_loses_context(u32 state); +bool psci_power_state_is_valid(u32 state); + +int psci_cpu_init_idle(unsigned int cpu); +int psci_cpu_suspend_enter(unsigned long index); + +struct psci_operations { + int (*cpu_suspend)(u32 state, unsigned long entry_point); + int (*cpu_off)(u32 state); + int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); + int (*migrate)(unsigned long cpuid); + int (*affinity_info)(unsigned long target_affinity, + unsigned long lowest_affinity_level); + int (*migrate_info_type)(void); +}; + +extern struct psci_operations psci_ops; + +#if defined(CONFIG_ARM_PSCI_FW) +int __init psci_dt_init(void); +#else +static inline int psci_dt_init(void) { return 0; } +#endif + +#if defined(CONFIG_ARM_PSCI_FW) && defined(CONFIG_ACPI) +int __init psci_acpi_init(void); +bool __init acpi_psci_present(void); +bool __init acpi_psci_use_hvc(void); +#else +static inline int psci_acpi_init(void) { return 0; } +static inline bool acpi_psci_present(void) { return false; } +#endif + +#endif /* __LINUX_PSCI_H */ diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index f8a689ed62a5..e325d4606b62 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -552,6 +552,16 @@ static inline int regulator_count_voltages(struct regulator *regulator) } #endif +static inline int regulator_set_voltage_triplet(struct regulator *regulator, + int min_uV, int target_uV, + int max_uV) +{ + if (regulator_set_voltage(regulator, target_uV, max_uV) == 0) + return 0; + + return regulator_set_voltage(regulator, min_uV, max_uV); +} + static inline int regulator_set_voltage_tol(struct regulator *regulator, int new_uV, int tol_uV) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 9e39deaeddd6..5707c093f78f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.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> @@ -734,18 +735,6 @@ 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 */ @@ -1384,6 +1373,9 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; +#ifdef CONFIG_MEMCG + unsigned memcg_may_oom:1; +#endif #ifdef CONFIG_MEMCG_KMEM unsigned memcg_kmem_skip_account:1; #endif @@ -1709,12 +1701,12 @@ struct task_struct { unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_MEMCG - struct memcg_oom_info { - struct mem_cgroup *memcg; - gfp_t gfp_mask; - int order; - unsigned int may_oom:1; - } memcg_oom; + struct mem_cgroup *memcg_in_oom; + gfp_t memcg_oom_gfp_mask; + int memcg_oom_order; + + /* number of pages to reclaim on returning to userland */ + unsigned int memcg_nr_pages_over_high; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; @@ -2642,53 +2634,33 @@ 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 - * - * 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. + * threadgroup_change_begin - mark the beginning of changes to a threadgroup + * @tsk: task causing the changes * - * 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 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/swap.h b/include/linux/swap.h index cee108cbe2d5..0708ab85aaff 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -287,7 +287,6 @@ static inline void workingset_node_shadows_dec(struct radix_tree_node *node) /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -extern unsigned long dirty_balance_reserve; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); @@ -351,7 +350,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages); extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_MEMCG -extern int mem_cgroup_swappiness(struct mem_cgroup *mem); +static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) +{ + /* root ? */ + if (mem_cgroup_disabled() || !memcg->css.parent) + return vm_swappiness; + + return memcg->swappiness; +} + #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { @@ -377,7 +384,6 @@ 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/thermal.h b/include/linux/thermal.h index 63830c4a49e6..fbb64253a27b 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 + /* use value, which < 0K, to indicate an invalid/uninitialized temperature */ #define THERMAL_TEMP_INVALID -274000 @@ -59,10 +62,13 @@ #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, @@ -116,6 +122,12 @@ 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 { @@ -148,8 +160,7 @@ struct thermal_attr { * @trips: number of trip points the thermal zone supports * @trips_disabled; bitmap for disabled trips * @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) @@ -159,7 +170,6 @@ 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. @@ -167,6 +177,7 @@ struct thermal_attr { * @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 @@ -193,8 +204,9 @@ struct thermal_zone_device { unsigned int forced_passive; atomic_t need_update; 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; @@ -205,12 +217,19 @@ 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; }; @@ -221,9 +240,12 @@ 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; @@ -260,6 +282,44 @@ 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 { @@ -323,14 +383,25 @@ 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 *); @@ -350,6 +421,14 @@ 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/tracehook.h b/include/linux/tracehook.h index 84d497297c5f..26c152122a42 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -50,6 +50,7 @@ #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> +#include <linux/memcontrol.h> struct linux_binprm; /* @@ -188,6 +189,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); + + mem_cgroup_handle_over_high(); } #endif /* <linux/tracehook.h> */ 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/net/sock.h b/include/net/sock.h index 4c4b21c00828..e96b2e84362b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1052,42 +1052,9 @@ struct proto { #endif }; -/* - * Bits in struct cg_proto.flags - */ -enum cg_proto_flags { - /* Currently active and new sockets should be assigned to cgroups */ - MEMCG_SOCK_ACTIVE, - /* It was ever activated; we must disarm static keys on destruction */ - MEMCG_SOCK_ACTIVATED, -}; - -struct cg_proto { - struct page_counter memory_allocated; /* Current allocated memory. */ - struct percpu_counter sockets_allocated; /* Current number of sockets. */ - int memory_pressure; - long sysctl_mem[3]; - unsigned long flags; - /* - * memcg field is used to find which memcg we belong directly - * Each memcg struct can hold more than one cg_proto, so container_of - * won't really cut. - * - * The elegant solution would be having an inverse function to - * proto_cgroup in struct proto, but that means polluting the structure - * for everybody, instead of just for memcg users. - */ - struct mem_cgroup *memcg; -}; - int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); -static inline bool memcg_proto_active(struct cg_proto *cg_proto) -{ - return test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); -} - #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) { diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h index 0f4f95d63c03..5738bb3e2343 100644 --- a/include/trace/events/thermal.h +++ b/include/trace/events/thermal.h @@ -4,6 +4,7 @@ #if !defined(_TRACE_THERMAL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_THERMAL_H +#include <linux/devfreq.h> #include <linux/thermal.h> #include <linux/tracepoint.h> @@ -77,6 +78,116 @@ TRACE_EVENT(thermal_zone_trip, __entry->trip_type) ); +TRACE_EVENT(thermal_power_cpu_get_power, + TP_PROTO(const struct cpumask *cpus, unsigned long freq, u32 *load, + size_t load_len, u32 dynamic_power, u32 static_power), + + TP_ARGS(cpus, freq, load, load_len, dynamic_power, static_power), + + TP_STRUCT__entry( + __bitmask(cpumask, num_possible_cpus()) + __field(unsigned long, freq ) + __dynamic_array(u32, load, load_len) + __field(size_t, load_len ) + __field(u32, dynamic_power ) + __field(u32, static_power ) + ), + + TP_fast_assign( + __assign_bitmask(cpumask, cpumask_bits(cpus), + num_possible_cpus()); + __entry->freq = freq; + memcpy(__get_dynamic_array(load), load, + load_len * sizeof(*load)); + __entry->load_len = load_len; + __entry->dynamic_power = dynamic_power; + __entry->static_power = static_power; + ), + + TP_printk("cpus=%s freq=%lu load={%s} dynamic_power=%d static_power=%d", + __get_bitmask(cpumask), __entry->freq, + __print_array(__get_dynamic_array(load), __entry->load_len, 4), + __entry->dynamic_power, __entry->static_power) +); + +TRACE_EVENT(thermal_power_cpu_limit, + TP_PROTO(const struct cpumask *cpus, unsigned int freq, + unsigned long cdev_state, u32 power), + + TP_ARGS(cpus, freq, cdev_state, power), + + TP_STRUCT__entry( + __bitmask(cpumask, num_possible_cpus()) + __field(unsigned int, freq ) + __field(unsigned long, cdev_state) + __field(u32, power ) + ), + + TP_fast_assign( + __assign_bitmask(cpumask, cpumask_bits(cpus), + num_possible_cpus()); + __entry->freq = freq; + __entry->cdev_state = cdev_state; + __entry->power = power; + ), + + TP_printk("cpus=%s freq=%u cdev_state=%lu power=%u", + __get_bitmask(cpumask), __entry->freq, __entry->cdev_state, + __entry->power) +); + +TRACE_EVENT(thermal_power_devfreq_get_power, + TP_PROTO(struct thermal_cooling_device *cdev, + struct devfreq_dev_status *status, unsigned long freq, + u32 dynamic_power, u32 static_power), + + TP_ARGS(cdev, status, freq, dynamic_power, static_power), + + TP_STRUCT__entry( + __string(type, cdev->type ) + __field(unsigned long, freq ) + __field(u32, load ) + __field(u32, dynamic_power ) + __field(u32, static_power ) + ), + + TP_fast_assign( + __assign_str(type, cdev->type); + __entry->freq = freq; + __entry->load = (100 * status->busy_time) / status->total_time; + __entry->dynamic_power = dynamic_power; + __entry->static_power = static_power; + ), + + TP_printk("type=%s freq=%lu load=%u dynamic_power=%u static_power=%u", + __get_str(type), __entry->freq, + __entry->load, __entry->dynamic_power, __entry->static_power) +); + +TRACE_EVENT(thermal_power_devfreq_limit, + TP_PROTO(struct thermal_cooling_device *cdev, unsigned long freq, + unsigned long cdev_state, u32 power), + + TP_ARGS(cdev, freq, cdev_state, power), + + TP_STRUCT__entry( + __string(type, cdev->type) + __field(unsigned int, freq ) + __field(unsigned long, cdev_state) + __field(u32, power ) + ), + + TP_fast_assign( + __assign_str(type, cdev->type); + __entry->freq = freq; + __entry->cdev_state = cdev_state; + __entry->power = power; + ), + + TP_printk("type=%s freq=%u cdev_state=%lu power=%u", + __get_str(type), __entry->freq, __entry->cdev_state, + __entry->power) +); #endif /* _TRACE_THERMAL_H */ /* This part must be outside protection */ diff --git a/include/trace/events/thermal_power_allocator.h b/include/trace/events/thermal_power_allocator.h new file mode 100644 index 000000000000..12e1321c4e0c --- /dev/null +++ b/include/trace/events/thermal_power_allocator.h @@ -0,0 +1,87 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thermal_power_allocator + +#if !defined(_TRACE_THERMAL_POWER_ALLOCATOR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_POWER_ALLOCATOR_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(thermal_power_allocator, + TP_PROTO(struct thermal_zone_device *tz, u32 *req_power, + u32 total_req_power, u32 *granted_power, + u32 total_granted_power, size_t num_actors, + u32 power_range, u32 max_allocatable_power, + unsigned long current_temp, s32 delta_temp), + TP_ARGS(tz, req_power, total_req_power, granted_power, + total_granted_power, num_actors, power_range, + max_allocatable_power, current_temp, delta_temp), + TP_STRUCT__entry( + __field(int, tz_id ) + __dynamic_array(u32, req_power, num_actors ) + __field(u32, total_req_power ) + __dynamic_array(u32, granted_power, num_actors) + __field(u32, total_granted_power ) + __field(size_t, num_actors ) + __field(u32, power_range ) + __field(u32, max_allocatable_power ) + __field(unsigned long, current_temp ) + __field(s32, delta_temp ) + ), + TP_fast_assign( + __entry->tz_id = tz->id; + memcpy(__get_dynamic_array(req_power), req_power, + num_actors * sizeof(*req_power)); + __entry->total_req_power = total_req_power; + memcpy(__get_dynamic_array(granted_power), granted_power, + num_actors * sizeof(*granted_power)); + __entry->total_granted_power = total_granted_power; + __entry->num_actors = num_actors; + __entry->power_range = power_range; + __entry->max_allocatable_power = max_allocatable_power; + __entry->current_temp = current_temp; + __entry->delta_temp = delta_temp; + ), + + TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%lu delta_temperature=%d", + __entry->tz_id, + __print_array(__get_dynamic_array(req_power), + __entry->num_actors, 4), + __entry->total_req_power, + __print_array(__get_dynamic_array(granted_power), + __entry->num_actors, 4), + __entry->total_granted_power, __entry->power_range, + __entry->max_allocatable_power, __entry->current_temp, + __entry->delta_temp) +); + +TRACE_EVENT(thermal_power_allocator_pid, + TP_PROTO(struct thermal_zone_device *tz, s32 err, s32 err_integral, + s64 p, s64 i, s64 d, s32 output), + TP_ARGS(tz, err, err_integral, p, i, d, output), + TP_STRUCT__entry( + __field(int, tz_id ) + __field(s32, err ) + __field(s32, err_integral) + __field(s64, p ) + __field(s64, i ) + __field(s64, d ) + __field(s32, output ) + ), + TP_fast_assign( + __entry->tz_id = tz->id; + __entry->err = err; + __entry->err_integral = err_integral; + __entry->p = p; + __entry->i = i; + __entry->d = d; + __entry->output = output; + ), + + TP_printk("thermal_zone_id=%d err=%d err_integral=%d p=%lld i=%lld d=%lld output=%d", + __entry->tz_id, __entry->err, __entry->err_integral, + __entry->p, __entry->i, __entry->d, __entry->output) +); +#endif /* _TRACE_THERMAL_POWER_ALLOCATOR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c178d13d6f4c..fff846b512e6 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -131,6 +131,66 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_ARGS(inode, flags) ); +#ifdef CREATE_TRACE_POINTS +#ifdef CONFIG_CGROUP_WRITEBACK + +static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) +{ + return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1; +} + +static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) +{ + struct cgroup *cgrp = wb->memcg_css->cgroup; + char *path; + + path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1); + WARN_ON_ONCE(path != buf); +} + +static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) +{ + if (wbc->wb) + return __trace_wb_cgroup_size(wbc->wb); + else + return 2; +} + +static inline void __trace_wbc_assign_cgroup(char *buf, + struct writeback_control *wbc) +{ + if (wbc->wb) + __trace_wb_assign_cgroup(buf, wbc->wb); + else + strcpy(buf, "/"); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) +{ + return 2; +} + +static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) +{ + strcpy(buf, "/"); +} + +static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) +{ + return 2; +} + +static inline void __trace_wbc_assign_cgroup(char *buf, + struct writeback_control *wbc) +{ + strcpy(buf, "/"); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ +#endif /* CREATE_TRACE_POINTS */ + DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), @@ -141,6 +201,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, __array(char, name, 32) __field(unsigned long, ino) __field(int, sync_mode) + __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ), TP_fast_assign( @@ -148,12 +209,14 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; + __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ), - TP_printk("bdi %s: ino=%lu sync_mode=%d", + TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s", __entry->name, __entry->ino, - __entry->sync_mode + __entry->sync_mode, + __get_str(cgroup) ) ); @@ -172,8 +235,8 @@ DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, ); DECLARE_EVENT_CLASS(writeback_work_class, - TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), - TP_ARGS(bdi, work), + TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), + TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) @@ -183,10 +246,11 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(int, range_cyclic) __field(int, for_background) __field(int, reason) + __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ), TP_fast_assign( strncpy(__entry->name, - bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); + wb->bdi->dev ? dev_name(wb->bdi->dev) : "(unknown)", 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; @@ -194,9 +258,10 @@ DECLARE_EVENT_CLASS(writeback_work_class, __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; + __trace_wb_assign_cgroup(__get_str(cgroup), wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " - "kupdate=%d range_cyclic=%d background=%d reason=%s", + "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, @@ -204,13 +269,14 @@ DECLARE_EVENT_CLASS(writeback_work_class, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, - __print_symbolic(__entry->reason, WB_WORK_REASON) + __print_symbolic(__entry->reason, WB_WORK_REASON), + __get_str(cgroup) ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ - TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \ - TP_ARGS(bdi, work)) + TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ + TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); @@ -230,26 +296,42 @@ TRACE_EVENT(writeback_pages_written, ); DECLARE_EVENT_CLASS(writeback_class, - TP_PROTO(struct backing_dev_info *bdi), - TP_ARGS(bdi), + TP_PROTO(struct bdi_writeback *wb), + TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) + __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + __trace_wb_assign_cgroup(__get_str(cgroup), wb); ), - TP_printk("bdi %s", - __entry->name + TP_printk("bdi %s: cgroup=%s", + __entry->name, + __get_str(cgroup) ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ - TP_PROTO(struct backing_dev_info *bdi), \ - TP_ARGS(bdi)) + TP_PROTO(struct bdi_writeback *wb), \ + TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_nowork); DEFINE_WRITEBACK_EVENT(writeback_wake_background); -DEFINE_WRITEBACK_EVENT(writeback_bdi_register); + +TRACE_EVENT(writeback_bdi_register, + TP_PROTO(struct backing_dev_info *bdi), + TP_ARGS(bdi), + TP_STRUCT__entry( + __array(char, name, 32) + ), + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + ), + TP_printk("bdi %s", + __entry->name + ) +); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), @@ -265,6 +347,7 @@ DECLARE_EVENT_CLASS(wbc_class, __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) + __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ), TP_fast_assign( @@ -278,11 +361,12 @@ DECLARE_EVENT_CLASS(wbc_class, __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; + __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " - "start=0x%lx end=0x%lx", + "start=0x%lx end=0x%lx cgroup=%s", __entry->name, __entry->nr_to_write, __entry->pages_skipped, @@ -292,7 +376,9 @@ DECLARE_EVENT_CLASS(wbc_class, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, - __entry->range_end) + __entry->range_end, + __get_str(cgroup) + ) ) #define DEFINE_WBC_EVENT(name) \ @@ -312,6 +398,7 @@ TRACE_EVENT(writeback_queue_io, __field(long, age) __field(int, moved) __field(int, reason) + __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ), TP_fast_assign( unsigned long *older_than_this = work->older_than_this; @@ -321,13 +408,15 @@ TRACE_EVENT(writeback_queue_io, (jiffies - *older_than_this) * 1000 / HZ : -1; __entry->moved = moved; __entry->reason = work->reason; + __trace_wb_assign_cgroup(__get_str(cgroup), wb); ), - TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s", + TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s", __entry->name, __entry->older, /* older_than_this in jiffies */ __entry->age, /* older_than_this in relative milliseconds */ __entry->moved, - __print_symbolic(__entry->reason, WB_WORK_REASON) + __print_symbolic(__entry->reason, WB_WORK_REASON), + __get_str(cgroup) ) ); @@ -360,7 +449,7 @@ TRACE_EVENT(global_dirty_state, __entry->nr_written = global_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; - __entry->dirty_limit = global_dirty_limit; + __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu unstable=%lu " @@ -381,11 +470,11 @@ TRACE_EVENT(global_dirty_state, TRACE_EVENT(bdi_dirty_ratelimit, - TP_PROTO(struct backing_dev_info *bdi, + TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), - TP_ARGS(bdi, dirty_rate, task_ratelimit), + TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) @@ -395,36 +484,39 @@ TRACE_EVENT(bdi_dirty_ratelimit, __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) + __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ), TP_fast_assign( - strlcpy(__entry->bdi, dev_name(bdi->dev), 32); - __entry->write_bw = KBps(bdi->write_bandwidth); - __entry->avg_write_bw = KBps(bdi->avg_write_bandwidth); + strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); + __entry->write_bw = KBps(wb->write_bandwidth); + __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); - __entry->dirty_ratelimit = KBps(bdi->dirty_ratelimit); + __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = - KBps(bdi->balanced_dirty_ratelimit); + KBps(wb->balanced_dirty_ratelimit); + __trace_wb_assign_cgroup(__get_str(cgroup), wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " - "balanced_dirty_ratelimit=%lu", + "balanced_dirty_ratelimit=%lu cgroup=%s", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ - __entry->balanced_dirty_ratelimit /* the balanced ratelimit */ + __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ + __get_str(cgroup) ) ); TRACE_EVENT(balance_dirty_pages, - TP_PROTO(struct backing_dev_info *bdi, + TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, @@ -437,7 +529,7 @@ TRACE_EVENT(balance_dirty_pages, long pause, unsigned long start_time), - TP_ARGS(bdi, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, + TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), @@ -456,14 +548,16 @@ TRACE_EVENT(balance_dirty_pages, __field( long, pause) __field(unsigned long, period) __field( long, think) + __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; - strlcpy(__entry->bdi, dev_name(bdi->dev), 32); + strlcpy(__entry->bdi, dev_name(wb->bdi->dev), 32); - __entry->limit = global_dirty_limit; - __entry->setpoint = (global_dirty_limit + freerun) / 2; + __entry->limit = global_wb_domain.dirty_limit; + __entry->setpoint = (global_wb_domain.dirty_limit + + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); @@ -477,6 +571,7 @@ TRACE_EVENT(balance_dirty_pages, __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; + __trace_wb_assign_cgroup(__get_str(cgroup), wb); ), @@ -485,7 +580,7 @@ TRACE_EVENT(balance_dirty_pages, "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " - "paused=%lu pause=%ld period=%lu think=%ld", + "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s", __entry->bdi, __entry->limit, __entry->setpoint, @@ -499,7 +594,8 @@ TRACE_EVENT(balance_dirty_pages, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ - __entry->think /* ms */ + __entry->think, /* ms */ + __get_str(cgroup) ) ); @@ -513,6 +609,8 @@ TRACE_EVENT(writeback_sb_inodes_requeue, __field(unsigned long, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) + __dynamic_array(char, cgroup, + __trace_wb_cgroup_size(inode_to_wb(inode))) ), TP_fast_assign( @@ -521,14 +619,16 @@ TRACE_EVENT(writeback_sb_inodes_requeue, __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; + __trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode)); ), - TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu", + TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s", __entry->name, __entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, - (jiffies - __entry->dirtied_when) / HZ + (jiffies - __entry->dirtied_when) / HZ, + __get_str(cgroup) ) ); @@ -584,6 +684,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) + __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ), TP_fast_assign( @@ -595,10 +696,11 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; + __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " - "index=%lu to_write=%ld wrote=%lu", + "index=%lu to_write=%ld wrote=%lu cgroup=%s", __entry->name, __entry->ino, show_inode_state(__entry->state), @@ -606,7 +708,8 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, - __entry->wrote + __entry->wrote, + __get_str(cgroup) ) ); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b60056776d1..2fa7302c25f6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -894,7 +894,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emlation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virtual/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 7b1425a6b370..1dd008c47553 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -54,6 +54,7 @@ #define SMB_SUPER_MAGIC 0x517B #define CGROUP_SUPER_MAGIC 0x27e0eb +#define CGROUP2_SUPER_MAGIC 0x63677270 #define STACK_END_MAGIC 0x57AC6E9D diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 310d83e0a91b..3d7a0fc021a7 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -46,6 +46,11 @@ #define PSCI_0_2_FN64_MIGRATE PSCI_0_2_FN64(5) #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7) +#define PSCI_1_0_FN_PSCI_FEATURES PSCI_0_2_FN(10) +#define PSCI_1_0_FN_SYSTEM_SUSPEND PSCI_0_2_FN(14) + +#define PSCI_1_0_FN64_SYSTEM_SUSPEND PSCI_0_2_FN64(14) + /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff #define PSCI_0_2_POWER_STATE_ID_SHIFT 0 @@ -56,6 +61,13 @@ #define PSCI_0_2_POWER_STATE_AFFL_MASK \ (0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) +/* PSCI extended power state encoding for CPU_SUSPEND function */ +#define PSCI_1_0_EXT_POWER_STATE_ID_MASK 0xfffffff +#define PSCI_1_0_EXT_POWER_STATE_ID_SHIFT 0 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT 30 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_MASK \ + (0x1 << PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT) + /* PSCI v0.2 affinity level state returned by AFFINITY_INFO */ #define PSCI_0_2_AFFINITY_LEVEL_ON 0 #define PSCI_0_2_AFFINITY_LEVEL_OFF 1 @@ -76,6 +88,11 @@ #define PSCI_VERSION_MINOR(ver) \ ((ver) & PSCI_VERSION_MINOR_MASK) +/* PSCI features decoding (>=1.0) */ +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT 1 +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK \ + (0x1 << PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT) + /* PSCI return values (inclusive of all PSCI versions) */ #define PSCI_RET_SUCCESS 0 #define PSCI_RET_NOT_SUPPORTED -1 @@ -86,5 +103,6 @@ #define PSCI_RET_INTERNAL_FAILURE -6 #define PSCI_RET_NOT_PRESENT -7 #define PSCI_RET_DISABLED -8 +#define PSCI_RET_INVALID_ADDRESS -9 #endif /* _UAPI_LINUX_PSCI_H */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index b57b750c222f..e4fa1995f613 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -470,12 +470,23 @@ struct vfio_iommu_spapr_tce_info { * - unfreeze IO/DMA for frozen PE; * - read PE state; * - reset PE; - * - configure PE. + * - configure PE; + * - inject EEH error. */ +struct vfio_eeh_pe_err { + __u32 type; + __u32 func; + __u64 addr; + __u64 mask; +}; + struct vfio_eeh_pe_op { __u32 argsz; __u32 flags; __u32 op; + union { + struct vfio_eeh_pe_err err; + }; }; #define VFIO_EEH_PE_DISABLE 0 /* Disable EEH functionality */ @@ -492,6 +503,7 @@ struct vfio_eeh_pe_op { #define VFIO_EEH_PE_RESET_HOT 6 /* Assert hot reset */ #define VFIO_EEH_PE_RESET_FUNDAMENTAL 7 /* Assert fundamental reset */ #define VFIO_EEH_PE_CONFIGURE 8 /* PE configuration */ +#define VFIO_EEH_PE_INJECT_ERR 9 /* Inject EEH error */ #define VFIO_EEH_PE_OP _IO(VFIO_TYPE, VFIO_BASE + 21) |