diff options
48 files changed, 883 insertions, 355 deletions
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index e6a1578fc000..afe05bfb7e00 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1572,7 +1572,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp) } #define param_check_sfb_size(name, p) __param_check(name, p, void) -static struct kernel_param_ops param_ops_sfb_size = { +static const struct kernel_param_ops param_ops_sfb_size = { .set = param_set_sfb_size, .get = param_get_sfb_size, }; diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c index 9b90fdc4b151..f6b911cc3923 100644 --- a/arch/um/drivers/hostaudio_kern.c +++ b/arch/um/drivers/hostaudio_kern.c @@ -185,9 +185,9 @@ static int hostaudio_open(struct inode *inode, struct file *file) int ret; #ifdef DEBUG - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); printk(KERN_DEBUG "hostaudio: open called (host: %s)\n", dsp); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); #endif state = kmalloc(sizeof(struct hostaudio_state), GFP_KERNEL); @@ -199,11 +199,11 @@ static int hostaudio_open(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) w = 1; - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); mutex_lock(&hostaudio_mutex); ret = os_open_file(dsp, of_set_rw(OPENFLAGS(), r, w), 0); mutex_unlock(&hostaudio_mutex); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); if (ret < 0) { kfree(state); @@ -260,17 +260,17 @@ static int hostmixer_open_mixdev(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) w = 1; - kparam_block_sysfs_write(mixer); + kernel_param_lock(THIS_MODULE); mutex_lock(&hostaudio_mutex); ret = os_open_file(mixer, of_set_rw(OPENFLAGS(), r, w), 0); mutex_unlock(&hostaudio_mutex); - kparam_unblock_sysfs_write(mixer); + kernel_param_unlock(THIS_MODULE); if (ret < 0) { - kparam_block_sysfs_write(dsp); + kernel_param_lock(THIS_MODULE); printk(KERN_ERR "hostaudio_open_mixdev failed to open '%s', " "err = %d\n", dsp, -ret); - kparam_unblock_sysfs_write(dsp); + kernel_param_unlock(THIS_MODULE); kfree(state); return ret; } @@ -326,10 +326,10 @@ MODULE_LICENSE("GPL"); static int __init hostaudio_init_module(void) { - __kernel_param_lock(); + kernel_param_lock(THIS_MODULE); printk(KERN_INFO "UML Audio Relay (host dsp = %s, host mixer = %s)\n", dsp, mixer); - __kernel_param_unlock(); + kernel_param_unlock(THIS_MODULE); module_data.dev_audio = register_sound_dsp(&hostaudio_fops, -1); if (module_data.dev_audio < 0) { diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index a4f62e6f2db2..03d518e499a6 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -297,7 +297,7 @@ static int mmu_audit_set(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops audit_param_ops = { +static const struct kernel_param_ops audit_param_ops = { .set = mmu_audit_set, .get = param_get_bool, }; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 7488cafab955..020c101c255f 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -104,7 +104,7 @@ static int param_set_local64(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_local64 = { +static const struct kernel_param_ops param_ops_local64 = { .get = param_get_local64, .set = param_set_local64, }; diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 6f9b7534928e..69de41a87b74 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -99,7 +99,7 @@ static int null_set_queue_mode(const char *str, const struct kernel_param *kp) return null_param_store_val(str, &queue_mode, NULL_Q_BIO, NULL_Q_MQ); } -static struct kernel_param_ops null_queue_mode_param_ops = { +static const struct kernel_param_ops null_queue_mode_param_ops = { .set = null_set_queue_mode, .get = param_get_int, }; @@ -127,7 +127,7 @@ static int null_set_irqmode(const char *str, const struct kernel_param *kp) NULL_IRQ_TIMER); } -static struct kernel_param_ops null_irqmode_param_ops = { +static const struct kernel_param_ops null_irqmode_param_ops = { .set = null_set_irqmode, .get = param_get_int, }; diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 37b8be7cba95..0ac3bd1a5497 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -208,7 +208,7 @@ static int set_param_timeout(const char *val, const struct kernel_param *kp) return rv; } -static struct kernel_param_ops param_ops_timeout = { +static const struct kernel_param_ops param_ops_timeout = { .set = set_param_timeout, .get = param_get_int, }; @@ -270,14 +270,14 @@ static int set_param_wdog_ifnum(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_wdog_ifnum = { +static const struct kernel_param_ops param_ops_wdog_ifnum = { .set = set_param_wdog_ifnum, .get = param_get_int, }; #define param_check_wdog_ifnum param_check_int -static struct kernel_param_ops param_ops_str = { +static const struct kernel_param_ops param_ops_str = { .set = set_param_str, .get = get_param_str, }; diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 220ee49633e4..b8576fd6bd0e 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -120,7 +120,7 @@ static struct dmatest_info { static int dmatest_run_set(const char *val, const struct kernel_param *kp); static int dmatest_run_get(char *val, const struct kernel_param *kp); -static struct kernel_param_ops run_ops = { +static const struct kernel_param_ops run_ops = { .set = dmatest_run_set, .get = dmatest_run_get, }; @@ -195,7 +195,7 @@ static int dmatest_wait_get(char *val, const struct kernel_param *kp) return param_get_bool(val, kp); } -static struct kernel_param_ops wait_ops = { +static const struct kernel_param_ops wait_ops = { .get = dmatest_wait_get, .set = param_set_bool, }; diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c index e29b02ca9e91..f086ef387475 100644 --- a/drivers/ide/ide.c +++ b/drivers/ide/ide.c @@ -199,7 +199,7 @@ static int ide_set_dev_param_mask(const char *s, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_ide_dev_mask = { +static const struct kernel_param_ops param_ops_ide_dev_mask = { .set = ide_set_dev_param_mask }; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index eada8f758ad4..267dc4f75502 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -99,7 +99,7 @@ module_param(register_always, bool, 0444); MODULE_PARM_DESC(register_always, "Use memory registration even for contiguous memory regions"); -static struct kernel_param_ops srp_tmo_ops; +static const struct kernel_param_ops srp_tmo_ops; static int srp_reconnect_delay = 10; module_param_cb(reconnect_delay, &srp_tmo_ops, &srp_reconnect_delay, @@ -184,7 +184,7 @@ out: return res; } -static struct kernel_param_ops srp_tmo_ops = { +static const struct kernel_param_ops srp_tmo_ops = { .get = srp_tmo_get, .set = srp_tmo_set, }; diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c index f63341f20b91..cfd58e87da26 100644 --- a/drivers/input/misc/ati_remote2.c +++ b/drivers/input/misc/ati_remote2.c @@ -94,7 +94,7 @@ static int ati_remote2_get_mode_mask(char *buffer, static unsigned int channel_mask = ATI_REMOTE2_MAX_CHANNEL_MASK; #define param_check_channel_mask(name, p) __param_check(name, p, unsigned int) -static struct kernel_param_ops param_ops_channel_mask = { +static const struct kernel_param_ops param_ops_channel_mask = { .set = ati_remote2_set_channel_mask, .get = ati_remote2_get_channel_mask, }; @@ -103,7 +103,7 @@ MODULE_PARM_DESC(channel_mask, "Bitmask of channels to accept <15:Channel16>...< static unsigned int mode_mask = ATI_REMOTE2_MAX_MODE_MASK; #define param_check_mode_mask(name, p) __param_check(name, p, unsigned int) -static struct kernel_param_ops param_ops_mode_mask = { +static const struct kernel_param_ops param_ops_mode_mask = { .set = ati_remote2_set_mode_mask, .get = ati_remote2_get_mode_mask, }; diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index 7c4ba43d253e..ec3477036150 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -47,7 +47,7 @@ MODULE_LICENSE("GPL"); static unsigned int psmouse_max_proto = PSMOUSE_AUTO; static int psmouse_set_maxproto(const char *val, const struct kernel_param *); static int psmouse_get_maxproto(char *buffer, const struct kernel_param *kp); -static struct kernel_param_ops param_ops_proto_abbrev = { +static const struct kernel_param_ops param_ops_proto_abbrev = { .set = psmouse_set_maxproto, .get = psmouse_get_maxproto, }; diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index 4739689d23ad..fb8705fc3aca 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -115,7 +115,7 @@ static int param_set_axis(const char *val, const struct kernel_param *kp) return ret; } -static struct kernel_param_ops param_ops_axis = { +static const struct kernel_param_ops param_ops_axis = { .set = param_set_axis, .get = param_get_int, }; diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 1a92d30689e7..ebf46ad2d513 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -162,7 +162,7 @@ static int __init ubiblock_set_param(const char *val, return 0; } -static struct kernel_param_ops ubiblock_param_ops = { +static const struct kernel_param_ops ubiblock_param_ops = { .set = ubiblock_set_param, }; module_param_cb(block, &ubiblock_param_ops, NULL, 0); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 2bae50292dcd..83651ac8ddb9 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -279,7 +279,7 @@ MODULE_FIRMWARE("myri10ge_eth_z8e.dat"); MODULE_FIRMWARE("myri10ge_rss_ethp_z8e.dat"); MODULE_FIRMWARE("myri10ge_rss_eth_z8e.dat"); -/* Careful: must be accessed under kparam_block_sysfs_write */ +/* Careful: must be accessed under kernel_param_lock() */ static char *myri10ge_fw_name = NULL; module_param(myri10ge_fw_name, charp, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(myri10ge_fw_name, "Firmware image name"); @@ -3427,7 +3427,7 @@ static void myri10ge_select_firmware(struct myri10ge_priv *mgp) } } - kparam_block_sysfs_write(myri10ge_fw_name); + kernel_param_lock(THIS_MODULE); if (myri10ge_fw_name != NULL) { char *fw_name = kstrdup(myri10ge_fw_name, GFP_KERNEL); if (fw_name) { @@ -3435,7 +3435,7 @@ static void myri10ge_select_firmware(struct myri10ge_priv *mgp) set_fw_name(mgp, fw_name, true); } } - kparam_unblock_sysfs_write(myri10ge_fw_name); + kernel_param_unlock(THIS_MODULE); if (mgp->board_number < MYRI10GE_MAX_BOARDS && myri10ge_fw_names[mgp->board_number] != NULL && diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c index b9febab89167..6ca6193ab8a6 100644 --- a/drivers/net/wireless/ath/wil6210/main.c +++ b/drivers/net/wireless/ath/wil6210/main.c @@ -62,7 +62,7 @@ static int mtu_max_set(const char *val, const struct kernel_param *kp) return ret; } -static struct kernel_param_ops mtu_max_ops = { +static const struct kernel_param_ops mtu_max_ops = { .set = mtu_max_set, .get = param_get_uint, }; @@ -91,7 +91,7 @@ static int ring_order_set(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops ring_order_ops = { +static const struct kernel_param_ops ring_order_ops = { .set = ring_order_set, .get = param_get_uint, }; diff --git a/drivers/net/wireless/libertas_tf/if_usb.c b/drivers/net/wireless/libertas_tf/if_usb.c index 1a20cee5febe..799a2efe5793 100644 --- a/drivers/net/wireless/libertas_tf/if_usb.c +++ b/drivers/net/wireless/libertas_tf/if_usb.c @@ -821,15 +821,15 @@ static int if_usb_prog_firmware(struct if_usb_card *cardp) lbtf_deb_enter(LBTF_DEB_USB); - kparam_block_sysfs_write(fw_name); + kernel_param_lock(THIS_MODULE); ret = request_firmware(&cardp->fw, lbtf_fw_name, &cardp->udev->dev); if (ret < 0) { pr_err("request_firmware() failed with %#x\n", ret); pr_err("firmware %s not found\n", lbtf_fw_name); - kparam_unblock_sysfs_write(fw_name); + kernel_param_unlock(THIS_MODULE); goto done; } - kparam_unblock_sysfs_write(fw_name); + kernel_param_unlock(THIS_MODULE); if (check_fwfile_format(cardp->fw->data, cardp->fw->size)) goto release_fw; diff --git a/drivers/power/test_power.c b/drivers/power/test_power.c index f986e0cca7ac..83c42ea88f2b 100644 --- a/drivers/power/test_power.c +++ b/drivers/power/test_power.c @@ -448,42 +448,42 @@ static int param_set_battery_voltage(const char *key, #define param_get_battery_voltage param_get_int -static struct kernel_param_ops param_ops_ac_online = { +static const struct kernel_param_ops param_ops_ac_online = { .set = param_set_ac_online, .get = param_get_ac_online, }; -static struct kernel_param_ops param_ops_usb_online = { +static const struct kernel_param_ops param_ops_usb_online = { .set = param_set_usb_online, .get = param_get_usb_online, }; -static struct kernel_param_ops param_ops_battery_status = { +static const struct kernel_param_ops param_ops_battery_status = { .set = param_set_battery_status, .get = param_get_battery_status, }; -static struct kernel_param_ops param_ops_battery_present = { +static const struct kernel_param_ops param_ops_battery_present = { .set = param_set_battery_present, .get = param_get_battery_present, }; -static struct kernel_param_ops param_ops_battery_technology = { +static const struct kernel_param_ops param_ops_battery_technology = { .set = param_set_battery_technology, .get = param_get_battery_technology, }; -static struct kernel_param_ops param_ops_battery_health = { +static const struct kernel_param_ops param_ops_battery_health = { .set = param_set_battery_health, .get = param_get_battery_health, }; -static struct kernel_param_ops param_ops_battery_capacity = { +static const struct kernel_param_ops param_ops_battery_capacity = { .set = param_set_battery_capacity, .get = param_get_battery_capacity, }; -static struct kernel_param_ops param_ops_battery_voltage = { +static const struct kernel_param_ops param_ops_battery_voltage = { .set = param_set_battery_voltage, .get = param_get_battery_voltage, }; diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 2e6716104d3f..5820e8513927 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -119,7 +119,7 @@ exit: return ret; } -static struct kernel_param_ops duration_ops = { +static const struct kernel_param_ops duration_ops = { .set = duration_set, .get = param_get_int, }; @@ -167,7 +167,7 @@ exit_win: return ret; } -static struct kernel_param_ops window_size_ops = { +static const struct kernel_param_ops window_size_ops = { .set = window_size_set, .get = param_get_int, }; diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index f78a87b07872..bb809cf36617 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -1345,7 +1345,7 @@ static int param_get_vmidfilter(char *buffer, const struct kernel_param *kp) #define param_check_vmidfilter(name, p) __param_check(name, p, void) -static struct kernel_param_ops param_ops_vmidfilter = { +static const struct kernel_param_ops param_ops_vmidfilter = { .set = param_set_vmidfilter, .get = param_get_vmidfilter, }; diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 2847108cc8dd..b5b427888b24 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -988,7 +988,7 @@ static int sysrq_reset_seq_param_set(const char *buffer, return 0; } -static struct kernel_param_ops param_ops_sysrq_reset_seq = { +static const struct kernel_param_ops param_ops_sysrq_reset_seq = { .get = param_get_ushort, .set = sysrq_reset_seq_param_set, }; diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c index 888998a7fe31..a2ae88dbda78 100644 --- a/drivers/usb/atm/ueagle-atm.c +++ b/drivers/usb/atm/ueagle-atm.c @@ -1599,7 +1599,7 @@ static void cmvs_file_name(struct uea_softc *sc, char *const cmv_name, int ver) char file_arr[] = "CMVxy.bin"; char *file; - kparam_block_sysfs_write(cmv_file); + kernel_param_lock(THIS_MODULE); /* set proper name corresponding modem version and line type */ if (cmv_file[sc->modem_index] == NULL) { if (UEA_CHIP_VERSION(sc) == ADI930) @@ -1618,7 +1618,7 @@ static void cmvs_file_name(struct uea_softc *sc, char *const cmv_name, int ver) strlcat(cmv_name, file, UEA_FW_NAME_MAX); if (ver == 2) strlcat(cmv_name, ".v2", UEA_FW_NAME_MAX); - kparam_unblock_sysfs_write(cmv_file); + kernel_param_unlock(THIS_MODULE); } static int request_cmvs_old(struct uea_softc *sc, diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index d32d1c4d1b99..178ae93b7ebd 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1977,7 +1977,7 @@ static int param_set_scroll(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_scroll = { +static const struct kernel_param_ops param_ops_scroll = { .set = param_set_scroll, }; #define param_check_scroll(name, p) __param_check(name, p, void) diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c index ea7f056ed5fe..8bac309c24b9 100644 --- a/drivers/video/fbdev/vt8623fb.c +++ b/drivers/video/fbdev/vt8623fb.c @@ -754,9 +754,9 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) /* Prepare startup mode */ - kparam_block_sysfs_write(mode_option); + kernel_param_lock(THIS_MODULE); rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8); - kparam_unblock_sysfs_write(mode_option); + kernel_param_unlock(THIS_MODULE); if (! ((rc == 1) || (rc == 2))) { rc = -EINVAL; dev_err(info->device, "mode %s not found\n", mode_option); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 7a5e60dea6c5..10189b5b627f 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -691,7 +691,7 @@ static int vm_cmdline_get(char *buffer, const struct kernel_param *kp) return strlen(buffer) + 1; } -static struct kernel_param_ops vm_cmdline_param_ops = { +static const struct kernel_param_ops vm_cmdline_param_ops = { .set = vm_cmdline_set, .get = vm_cmdline_get, }; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index f175b833b6ba..aa62004f1706 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2847,7 +2847,7 @@ static int param_set_portnr(const char *val, const struct kernel_param *kp) *((unsigned int *)kp->arg) = num; return 0; } -static struct kernel_param_ops param_ops_portnr = { +static const struct kernel_param_ops param_ops_portnr = { .set = param_set_portnr, .get = param_get_uint, }; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 26fc8bc77f85..7f8ad9593da7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -475,6 +475,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s (volatile typeof(x) *)&(x); }) #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) +/** + * lockless_dereference() - safely load a pointer for later dereference + * @p: The pointer to load + * + * Similar to rcu_dereference(), but for situations where the pointed-to + * object's lifetime is managed by something other than RCU. That + * "something other" might be reference counting or simple immortality. + */ +#define lockless_dereference(p) \ +({ \ + typeof(p) _________p1 = READ_ONCE(p); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) + /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ #ifdef CONFIG_KPROBES # define __kprobes __attribute__((__section__(".kprobes.text"))) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5acf5b70866d..cfa9351c7536 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -813,13 +813,15 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */ -#define VERIFY_OCTAL_PERMISSIONS(perms) \ - (BUILD_BUG_ON_ZERO((perms) < 0) + \ - BUILD_BUG_ON_ZERO((perms) > 0777) + \ - /* User perms >= group perms >= other perms */ \ - BUILD_BUG_ON_ZERO(((perms) >> 6) < (((perms) >> 3) & 7)) + \ - BUILD_BUG_ON_ZERO((((perms) >> 3) & 7) < ((perms) & 7)) + \ - /* Other writable? Generally considered a bad idea. */ \ - BUILD_BUG_ON_ZERO((perms) & 2) + \ +#define VERIFY_OCTAL_PERMISSIONS(perms) \ + (BUILD_BUG_ON_ZERO((perms) < 0) + \ + BUILD_BUG_ON_ZERO((perms) > 0777) + \ + /* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \ + BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \ + /* USER_WRITABLE >= GROUP_WRITABLE */ \ + BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \ + /* OTHER_WRITABLE? Generally considered a bad idea. */ \ + BUILD_BUG_ON_ZERO((perms) & 2) + \ (perms)) #endif diff --git a/include/linux/module.h b/include/linux/module.h index 7ffe0851d244..d67b1932cc59 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -17,6 +17,7 @@ #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> +#include <linux/rbtree_latch.h> #include <linux/percpu.h> #include <asm/module.h> @@ -210,6 +211,13 @@ enum module_state { MODULE_STATE_UNFORMED, /* Still setting it up. */ }; +struct module; + +struct mod_tree_node { + struct module *mod; + struct latch_tree_node node; +}; + struct module { enum module_state state; @@ -232,6 +240,9 @@ struct module { unsigned int num_syms; /* Kernel parameters. */ +#ifdef CONFIG_SYSFS + struct mutex param_lock; +#endif struct kernel_param *kp; unsigned int num_kp; @@ -271,8 +282,15 @@ struct module { /* Startup function. */ int (*init)(void); - /* If this is non-NULL, vfree after init() returns */ - void *module_init; + /* + * If this is non-NULL, vfree() after init() returns. + * + * Cacheline align here, such that: + * module_init, module_core, init_size, core_size, + * init_text_size, core_text_size and mtn_core::{mod,node[0]} + * are on the same cacheline. + */ + void *module_init ____cacheline_aligned; /* Here is the actual code + data, vfree'd on unload. */ void *module_core; @@ -283,6 +301,16 @@ struct module { /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; +#ifdef CONFIG_MODULES_TREE_LOOKUP + /* + * We want mtn_core::{mod,node[0]} to be in the same cacheline as the + * above entries such that a regular lookup will only touch one + * cacheline. + */ + struct mod_tree_node mtn_core; + struct mod_tree_node mtn_init; +#endif + /* Size of RO sections of the module (text+rodata) */ unsigned int init_ro_size, core_ro_size; @@ -369,7 +397,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -}; +} ____cacheline_aligned; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif @@ -423,14 +451,22 @@ struct symsearch { bool unused; }; -/* Search for an exported symbol by name. */ +/* + * Search for an exported symbol by name. + * + * Must be called with module_mutex held or preemption disabled. + */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, const unsigned long **crc, bool gplok, bool warn); -/* Walk the exported symbol table */ +/* + * Walk the exported symbol table + * + * Must be called with module_mutex held or preemption disabled. + */ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, struct module *owner, void *data), void *data); diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 6480dcaca275..c12f2147c350 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -67,8 +67,9 @@ enum { struct kernel_param { const char *name; + struct module *mod; const struct kernel_param_ops *ops; - u16 perm; + const u16 perm; s8 level; u8 flags; union { @@ -108,7 +109,7 @@ struct kparam_array * * @perm is 0 if the the variable is not to appear in sysfs, or 0444 * for world-readable, 0644 for root-writable, etc. Note that if it - * is writable, you may need to use kparam_block_sysfs_write() around + * is writable, you may need to use kernel_param_lock() around * accesses (esp. charp, which can be kfreed when it changes). * * The @type is simply pasted to refer to a param_ops_##type and a @@ -216,16 +217,16 @@ struct kparam_array parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ /* Default value instead of permissions? */ \ - static const char __param_str_##name[] = prefix #name; \ + static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ - = { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm), \ - level, flags, { arg } } + = { __param_str_##name, THIS_MODULE, ops, \ + VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } } /* Obsolete - use module_param_cb() */ #define module_param_call(name, set, get, arg, perm) \ - static struct kernel_param_ops __param_ops_##name = \ + static const struct kernel_param_ops __param_ops_##name = \ { .flags = 0, (void *)set, (void *)get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ name, &__param_ops_##name, arg, \ @@ -238,58 +239,14 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) return 0; } -/** - * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs. - * @name: the name of the parameter - * - * There's no point blocking write on a paramter that isn't writable via sysfs! - */ -#define kparam_block_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_write - allows sysfs to write to a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_write(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0222)); \ - __kernel_param_unlock(); \ - } while (0) - -/** - * kparam_block_sysfs_read - make sure a parameter isn't read via sysfs. - * @name: the name of the parameter - * - * This also blocks sysfs writes. - */ -#define kparam_block_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_lock(); \ - } while (0) - -/** - * kparam_unblock_sysfs_read - allows sysfs to read a parameter again. - * @name: the name of the parameter - */ -#define kparam_unblock_sysfs_read(name) \ - do { \ - BUG_ON(!(__param_##name.perm & 0444)); \ - __kernel_param_unlock(); \ - } while (0) - #ifdef CONFIG_SYSFS -extern void __kernel_param_lock(void); -extern void __kernel_param_unlock(void); +extern void kernel_param_lock(struct module *mod); +extern void kernel_param_unlock(struct module *mod); #else -static inline void __kernel_param_lock(void) +static inline void kernel_param_lock(struct module *mod) { } -static inline void __kernel_param_unlock(void) +static inline void kernel_param_unlock(struct module *mod) { } #endif @@ -386,64 +343,70 @@ static inline void destroy_params(const struct kernel_param *params, #define __param_check(name, p, type) \ static inline type __always_unused *__check_##name(void) { return(p); } -extern struct kernel_param_ops param_ops_byte; +extern const struct kernel_param_ops param_ops_byte; extern int param_set_byte(const char *val, const struct kernel_param *kp); extern int param_get_byte(char *buffer, const struct kernel_param *kp); #define param_check_byte(name, p) __param_check(name, p, unsigned char) -extern struct kernel_param_ops param_ops_short; +extern const struct kernel_param_ops param_ops_short; extern int param_set_short(const char *val, const struct kernel_param *kp); extern int param_get_short(char *buffer, const struct kernel_param *kp); #define param_check_short(name, p) __param_check(name, p, short) -extern struct kernel_param_ops param_ops_ushort; +extern const struct kernel_param_ops param_ops_ushort; extern int param_set_ushort(const char *val, const struct kernel_param *kp); extern int param_get_ushort(char *buffer, const struct kernel_param *kp); #define param_check_ushort(name, p) __param_check(name, p, unsigned short) -extern struct kernel_param_ops param_ops_int; +extern const struct kernel_param_ops param_ops_int; extern int param_set_int(const char *val, const struct kernel_param *kp); extern int param_get_int(char *buffer, const struct kernel_param *kp); #define param_check_int(name, p) __param_check(name, p, int) -extern struct kernel_param_ops param_ops_uint; +extern const struct kernel_param_ops param_ops_uint; extern int param_set_uint(const char *val, const struct kernel_param *kp); extern int param_get_uint(char *buffer, const struct kernel_param *kp); #define param_check_uint(name, p) __param_check(name, p, unsigned int) -extern struct kernel_param_ops param_ops_long; +extern const struct kernel_param_ops param_ops_long; extern int param_set_long(const char *val, const struct kernel_param *kp); extern int param_get_long(char *buffer, const struct kernel_param *kp); #define param_check_long(name, p) __param_check(name, p, long) -extern struct kernel_param_ops param_ops_ulong; +extern const struct kernel_param_ops param_ops_ulong; extern int param_set_ulong(const char *val, const struct kernel_param *kp); extern int param_get_ulong(char *buffer, const struct kernel_param *kp); #define param_check_ulong(name, p) __param_check(name, p, unsigned long) -extern struct kernel_param_ops param_ops_ullong; +extern const struct kernel_param_ops param_ops_ullong; extern int param_set_ullong(const char *val, const struct kernel_param *kp); extern int param_get_ullong(char *buffer, const struct kernel_param *kp); #define param_check_ullong(name, p) __param_check(name, p, unsigned long long) -extern struct kernel_param_ops param_ops_charp; +extern const struct kernel_param_ops param_ops_charp; extern int param_set_charp(const char *val, const struct kernel_param *kp); extern int param_get_charp(char *buffer, const struct kernel_param *kp); #define param_check_charp(name, p) __param_check(name, p, char *) /* We used to allow int as well as bool. We're taking that away! */ -extern struct kernel_param_ops param_ops_bool; +extern const struct kernel_param_ops param_ops_bool; extern int param_set_bool(const char *val, const struct kernel_param *kp); extern int param_get_bool(char *buffer, const struct kernel_param *kp); #define param_check_bool(name, p) __param_check(name, p, bool) -extern struct kernel_param_ops param_ops_invbool; +extern const struct kernel_param_ops param_ops_bool_enable_only; +extern int param_set_bool_enable_only(const char *val, + const struct kernel_param *kp); +/* getter is the same as for the regular bool */ +#define param_check_bool_enable_only param_check_bool + +extern const struct kernel_param_ops param_ops_invbool; extern int param_set_invbool(const char *val, const struct kernel_param *kp); extern int param_get_invbool(char *buffer, const struct kernel_param *kp); #define param_check_invbool(name, p) __param_check(name, p, bool) /* An int, which can only be set like a bool (though it shows as an int). */ -extern struct kernel_param_ops param_ops_bint; +extern const struct kernel_param_ops param_ops_bint; extern int param_set_bint(const char *val, const struct kernel_param *kp); #define param_get_bint param_get_int #define param_check_bint param_check_int @@ -487,9 +450,9 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp); perm, -1, 0); \ __MODULE_PARM_TYPE(name, "array of " #type) -extern struct kernel_param_ops param_array_ops; +extern const struct kernel_param_ops param_array_ops; -extern struct kernel_param_ops param_ops_string; +extern const struct kernel_param_ops param_ops_string; extern int param_set_copystring(const char *val, const struct kernel_param *); extern int param_get_string(char *buffer, const struct kernel_param *kp); diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index fb31765e935a..830c4992088d 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -31,6 +31,7 @@ #include <linux/kernel.h> #include <linux/stddef.h> +#include <linux/rcupdate.h> struct rb_node { unsigned long __rb_parent_color; @@ -73,11 +74,11 @@ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ -extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, +extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, - struct rb_node ** rb_link) +static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; @@ -85,6 +86,15 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, *rb_link = node; } +static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) +{ + node->__rb_parent_color = (unsigned long)parent; + node->rb_left = node->rb_right = NULL; + + rcu_assign_pointer(*rb_link, node); +} + #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 378c5ee75f78..14d7b831b63a 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -123,11 +123,11 @@ __rb_change_child(struct rb_node *old, struct rb_node *new, { if (parent) { if (parent->rb_left == old) - parent->rb_left = new; + WRITE_ONCE(parent->rb_left, new); else - parent->rb_right = new; + WRITE_ONCE(parent->rb_right, new); } else - root->rb_node = new; + WRITE_ONCE(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, @@ -137,7 +137,8 @@ static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *child = node->rb_right, *tmp = node->rb_left; + struct rb_node *child = node->rb_right; + struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; @@ -167,6 +168,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, tmp = parent; } else { struct rb_node *successor = child, *child2; + tmp = child->rb_left; if (!tmp) { /* @@ -180,6 +182,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, */ parent = successor; child2 = successor->rb_right; + augment->copy(node, successor); } else { /* @@ -201,19 +204,23 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, successor = tmp; tmp = tmp->rb_left; } while (tmp); - parent->rb_left = child2 = successor->rb_right; - successor->rb_right = child; + child2 = successor->rb_right; + WRITE_ONCE(parent->rb_left, child2); + WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); + augment->copy(node, successor); augment->propagate(parent, successor); } - successor->rb_left = tmp = node->rb_left; + tmp = node->rb_left; + WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); + if (child2) { successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h new file mode 100644 index 000000000000..4f3432c61d12 --- /dev/null +++ b/include/linux/rbtree_latch.h @@ -0,0 +1,212 @@ +/* + * Latched RB-trees + * + * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> + * + * Since RB-trees have non-atomic modifications they're not immediately suited + * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for + * lockless lookups; we cannot guarantee they return a correct result. + * + * The simplest solution is a seqlock + RB-tree, this will allow lockless + * lookups; but has the constraint (inherent to the seqlock) that read sides + * cannot nest in write sides. + * + * If we need to allow unconditional lookups (say as required for NMI context + * usage) we need a more complex setup; this data structure provides this by + * employing the latch technique -- see @raw_write_seqcount_latch -- to + * implement a latched RB-tree which does allow for unconditional lookups by + * virtue of always having (at least) one stable copy of the tree. + * + * However, while we have the guarantee that there is at all times one stable + * copy, this does not guarantee an iteration will not observe modifications. + * What might have been a stable copy at the start of the iteration, need not + * remain so for the duration of the iteration. + * + * Therefore, this does require a lockless RB-tree iteration to be non-fatal; + * see the comment in lib/rbtree.c. Note however that we only require the first + * condition -- not seeing partial stores -- because the latch thing isolates + * us from loops. If we were to interrupt a modification the lookup would be + * pointed at the stable tree and complete while the modification was halted. + */ + +#ifndef RB_TREE_LATCH_H +#define RB_TREE_LATCH_H + +#include <linux/rbtree.h> +#include <linux/seqlock.h> + +struct latch_tree_node { + struct rb_node node[2]; +}; + +struct latch_tree_root { + seqcount_t seq; + struct rb_root tree[2]; +}; + +/** + * latch_tree_ops - operators to define the tree order + * @less: used for insertion; provides the (partial) order between two elements. + * @comp: used for lookups; provides the order between the search key and an element. + * + * The operators are related like: + * + * comp(a->key,b) < 0 := less(a,b) + * comp(a->key,b) > 0 := less(b,a) + * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) + * + * If these operators define a partial order on the elements we make no + * guarantee on which of the elements matching the key is found. See + * latch_tree_find(). + */ +struct latch_tree_ops { + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); + int (*comp)(void *key, struct latch_tree_node *b); +}; + +static __always_inline struct latch_tree_node * +__lt_from_rb(struct rb_node *node, int idx) +{ + return container_of(node, struct latch_tree_node, node[idx]); +} + +static __always_inline void +__lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, + bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) +{ + struct rb_root *root = <r->tree[idx]; + struct rb_node **link = &root->rb_node; + struct rb_node *node = <n->node[idx]; + struct rb_node *parent = NULL; + struct latch_tree_node *ltp; + + while (*link) { + parent = *link; + ltp = __lt_from_rb(parent, idx); + + if (less(ltn, ltp)) + link = &parent->rb_left; + else + link = &parent->rb_right; + } + + rb_link_node_rcu(node, parent, link); + rb_insert_color(node, root); +} + +static __always_inline void +__lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) +{ + rb_erase(<n->node[idx], <r->tree[idx]); +} + +static __always_inline struct latch_tree_node * +__lt_find(void *key, struct latch_tree_root *ltr, int idx, + int (*comp)(void *key, struct latch_tree_node *node)) +{ + struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); + struct latch_tree_node *ltn; + int c; + + while (node) { + ltn = __lt_from_rb(node, idx); + c = comp(key, ltn); + + if (c < 0) + node = rcu_dereference_raw(node->rb_left); + else if (c > 0) + node = rcu_dereference_raw(node->rb_right); + else + return ltn; + } + + return NULL; +} + +/** + * latch_tree_insert() - insert @node into the trees @root + * @node: nodes to insert + * @root: trees to insert @node into + * @ops: operators defining the node order + * + * It inserts @node into @root in an ordered fashion such that we can always + * observe one complete tree. See the comment for raw_write_seqcount_latch(). + * + * The inserts use rcu_assign_pointer() to publish the element such that the + * tree structure is stored before we can observe the new @node. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_insert(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 0, ops->less); + raw_write_seqcount_latch(&root->seq); + __lt_insert(node, root, 1, ops->less); +} + +/** + * latch_tree_erase() - removes @node from the trees @root + * @node: nodes to remote + * @root: trees to remove @node from + * @ops: operators defining the node order + * + * Removes @node from the trees @root in an ordered fashion such that we can + * always observe one complete tree. See the comment for + * raw_write_seqcount_latch(). + * + * It is assumed that @node will observe one RCU quiescent state before being + * reused of freed. + * + * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be + * serialized. + */ +static __always_inline void +latch_tree_erase(struct latch_tree_node *node, + struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 0); + raw_write_seqcount_latch(&root->seq); + __lt_erase(node, root, 1); +} + +/** + * latch_tree_find() - find the node matching @key in the trees @root + * @key: search key + * @root: trees to search for @key + * @ops: operators defining the node order + * + * Does a lockless lookup in the trees @root for the node matching @key. + * + * It is assumed that this is called while holding the appropriate RCU read + * side lock. + * + * If the operators define a partial order on the elements (there are multiple + * elements which have the same key value) it is undefined which of these + * elements will be found. Nor is it possible to iterate the tree to find + * further elements with the same key value. + * + * Returns: a pointer to the node matching @key or NULL. + */ +static __always_inline struct latch_tree_node * +latch_tree_find(void *key, struct latch_tree_root *root, + const struct latch_tree_ops *ops) +{ + struct latch_tree_node *node; + unsigned int seq; + + do { + seq = raw_read_seqcount_latch(&root->seq); + node = __lt_find(key, root, seq & 1, ops->comp); + } while (read_seqcount_retry(&root->seq, seq)); + + return node; +} + +#endif /* RB_TREE_LATCH_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 33a056bb886f..4cf5f51b4c9c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -633,21 +633,6 @@ static inline void rcu_preempt_sleep_check(void) #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** - * lockless_dereference() - safely load a pointer for later dereference - * @p: The pointer to load - * - * Similar to rcu_dereference(), but for situations where the pointed-to - * object's lifetime is managed by something other than RCU. That - * "something other" might be reference counting or simple immortality. - */ -#define lockless_dereference(p) \ -({ \ - typeof(p) _________p1 = READ_ONCE(p); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - (_________p1); \ -}) - -/** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 486e685a226a..e0582106ef4f 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/preempt.h> #include <linux/lockdep.h> +#include <linux/compiler.h> #include <asm/processor.h> /* @@ -274,9 +275,87 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s) s->sequence++; } -/* +static inline int raw_read_seqcount_latch(seqcount_t *s) +{ + return lockless_dereference(s->sequence); +} + +/** * raw_write_seqcount_latch - redirect readers to even/odd copy * @s: pointer to seqcount_t + * + * The latch technique is a multiversion concurrency control method that allows + * queries during non-atomic modifications. If you can guarantee queries never + * interrupt the modification -- e.g. the concurrency is strictly between CPUs + * -- you most likely do not need this. + * + * Where the traditional RCU/lockless data structures rely on atomic + * modifications to ensure queries observe either the old or the new state the + * latch allows the same for non-atomic updates. The trade-off is doubling the + * cost of storage; we have to maintain two copies of the entire data + * structure. + * + * Very simply put: we first modify one copy and then the other. This ensures + * there is always one copy in a stable state, ready to give us an answer. + * + * The basic form is a data structure like: + * + * struct latch_struct { + * seqcount_t seq; + * struct data_struct data[2]; + * }; + * + * Where a modification, which is assumed to be externally serialized, does the + * following: + * + * void latch_modify(struct latch_struct *latch, ...) + * { + * smp_wmb(); <- Ensure that the last data[1] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[0], ...); + * + * smp_wmb(); <- Ensure that the data[0] update is visible + * latch->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * + * modify(latch->data[1], ...); + * } + * + * The query will have a form like: + * + * struct entry *latch_query(struct latch_struct *latch, ...) + * { + * struct entry *entry; + * unsigned seq, idx; + * + * do { + * seq = lockless_dereference(latch->seq); + * + * idx = seq & 0x01; + * entry = data_query(latch->data[idx], ...); + * + * smp_rmb(); + * } while (seq != latch->seq); + * + * return entry; + * } + * + * So during the modification, queries are first redirected to data[1]. Then we + * modify data[0]. When that is complete, we redirect queries back to data[0] + * and we can modify data[1]. + * + * NOTE: The non-requirement for atomic modifications does _NOT_ include + * the publishing of new entries in the case where data is a dynamic + * data structure. + * + * An iteration might start in data[0] and get suspended long enough + * to miss an entire modification sequence, once it resumes it might + * observe the new entry. + * + * NOTE: When data is a dynamic data structure; one should use regular RCU + * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_t *s) { diff --git a/init/Kconfig b/init/Kconfig index 7d1ffd2ae536..bcc41bd19999 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1941,26 +1941,21 @@ config MODULE_COMPRESS bool "Compress modules on installation" depends on MODULES help - This option compresses the kernel modules when 'make - modules_install' is run. - The modules will be compressed either using gzip or xz depend on the - choice made in "Compression algorithm". + Compresses kernel modules when 'make modules_install' is run; gzip or + xz depending on "Compression algorithm" below. - module-init-tools has support for gzip format while kmod handle gzip - and xz compressed modules. + module-init-tools MAY support gzip, and kmod MAY support gzip and xz. - When a kernel module is installed from outside of the main kernel - source and uses the Kbuild system for installing modules then that - kernel module will also be compressed when it is installed. + Out-of-tree kernel modules installed using Kbuild will also be + compressed upon installation. - This option provides little benefit when the modules are to be used inside - an initrd or initramfs, it generally is more efficient to compress the whole - initrd or initramfs instead. + Note: for modules inside an initrd or initramfs, it's more efficient + to compress the whole initrd or initramfs instead. - This is fully compatible with signed modules while the signed module is - compressed. module-init-tools or kmod handles decompression and provide to - other layer the uncompressed but signed payload. + Note: This is fully compatible with signed modules. + + If in doubt, say N. choice prompt "Compression algorithm" @@ -1982,6 +1977,10 @@ endchoice endif # MODULES +config MODULES_TREE_LOOKUP + def_bool y + depends on PERF_EVENTS || TRACING + config INIT_ALL_POSSIBLE bool help diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 9019f15deab2..52ebaca1b9fc 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -302,7 +302,7 @@ static int jump_label_add_module(struct module *mod) continue; key = iterk; - if (__module_address(iter->key) == mod) { + if (within_module(iter->key, mod)) { /* * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH. */ @@ -339,7 +339,7 @@ static void jump_label_del_module(struct module *mod) key = (struct static_key *)(unsigned long)iter->key; - if (__module_address(iter->key) == mod) + if (within_module(iter->key, mod)) continue; prev = &key->next; @@ -443,14 +443,16 @@ static void jump_label_update(struct static_key *key, int enable) { struct jump_entry *stop = __stop___jump_table; struct jump_entry *entry = jump_label_get_entries(key); - #ifdef CONFIG_MODULES - struct module *mod = __module_address((unsigned long)key); + struct module *mod; __jump_label_mod_update(key, enable); + preempt_disable(); + mod = __module_address((unsigned long)key); if (mod) stop = mod->jump_entries + mod->num_jump_entries; + preempt_enable(); #endif /* if there are no users, entry can be NULL */ if (entry) diff --git a/kernel/module.c b/kernel/module.c index f80a97f7da1f..3e0e19763d24 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -101,48 +101,201 @@ DEFINE_MUTEX(module_mutex); EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); -#ifdef CONFIG_KGDB_KDB -struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ -#endif /* CONFIG_KGDB_KDB */ -#ifdef CONFIG_MODULE_SIG -#ifdef CONFIG_MODULE_SIG_FORCE -static bool sig_enforce = true; -#else -static bool sig_enforce = false; +#ifdef CONFIG_MODULES_TREE_LOOKUP + +/* + * Use a latched RB-tree for __module_address(); this allows us to use + * RCU-sched lookups of the address from any context. + * + * Because modules have two address ranges: init and core, we need two + * latch_tree_nodes entries. Therefore we need the back-pointer from + * mod_tree_node. + * + * Because init ranges are short lived we mark them unlikely and have placed + * them outside the critical cacheline in struct module. + * + * This is conditional on PERF_EVENTS || TRACING because those can really hit + * __module_address() hard by doing a lot of stack unwinding; potentially from + * NMI context. + */ -static int param_set_bool_enable_only(const char *val, - const struct kernel_param *kp) +static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - int err; - bool test; - struct kernel_param dummy_kp = *kp; + struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); + struct module *mod = mtn->mod; - dummy_kp.arg = &test; + if (unlikely(mtn == &mod->mtn_init)) + return (unsigned long)mod->module_init; - err = param_set_bool(val, &dummy_kp); - if (err) - return err; + return (unsigned long)mod->module_core; +} + +static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) +{ + struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); + struct module *mod = mtn->mod; - /* Don't let them unset it once it's set! */ - if (!test && sig_enforce) - return -EROFS; + if (unlikely(mtn == &mod->mtn_init)) + return (unsigned long)mod->init_size; + + return (unsigned long)mod->core_size; +} + +static __always_inline bool +mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) +{ + return __mod_tree_val(a) < __mod_tree_val(b); +} + +static __always_inline int +mod_tree_comp(void *key, struct latch_tree_node *n) +{ + unsigned long val = (unsigned long)key; + unsigned long start, end; + + start = __mod_tree_val(n); + if (val < start) + return -1; + + end = start + __mod_tree_size(n); + if (val >= end) + return 1; - if (test) - sig_enforce = true; return 0; } -static const struct kernel_param_ops param_ops_bool_enable_only = { - .flags = KERNEL_PARAM_OPS_FL_NOARG, - .set = param_set_bool_enable_only, - .get = param_get_bool, +static const struct latch_tree_ops mod_tree_ops = { + .less = mod_tree_less, + .comp = mod_tree_comp, }; -#define param_check_bool_enable_only param_check_bool +static struct mod_tree_root { + struct latch_tree_root root; + unsigned long addr_min; + unsigned long addr_max; +} mod_tree __cacheline_aligned = { + .addr_min = -1UL, +}; + +#define module_addr_min mod_tree.addr_min +#define module_addr_max mod_tree.addr_max + +static noinline void __mod_tree_insert(struct mod_tree_node *node) +{ + latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops); +} + +static void __mod_tree_remove(struct mod_tree_node *node) +{ + latch_tree_erase(&node->node, &mod_tree.root, &mod_tree_ops); +} + +/* + * These modifications: insert, remove_init and remove; are serialized by the + * module_mutex. + */ +static void mod_tree_insert(struct module *mod) +{ + mod->mtn_core.mod = mod; + mod->mtn_init.mod = mod; + + __mod_tree_insert(&mod->mtn_core); + if (mod->init_size) + __mod_tree_insert(&mod->mtn_init); +} + +static void mod_tree_remove_init(struct module *mod) +{ + if (mod->init_size) + __mod_tree_remove(&mod->mtn_init); +} + +static void mod_tree_remove(struct module *mod) +{ + __mod_tree_remove(&mod->mtn_core); + mod_tree_remove_init(mod); +} + +static struct module *mod_find(unsigned long addr) +{ + struct latch_tree_node *ltn; + + ltn = latch_tree_find((void *)addr, &mod_tree.root, &mod_tree_ops); + if (!ltn) + return NULL; + + return container_of(ltn, struct mod_tree_node, node)->mod; +} + +#else /* MODULES_TREE_LOOKUP */ + +static unsigned long module_addr_min = -1UL, module_addr_max = 0; + +static void mod_tree_insert(struct module *mod) { } +static void mod_tree_remove_init(struct module *mod) { } +static void mod_tree_remove(struct module *mod) { } + +static struct module *mod_find(unsigned long addr) +{ + struct module *mod; + + list_for_each_entry_rcu(mod, &modules, list) { + if (within_module(addr, mod)) + return mod; + } + + return NULL; +} + +#endif /* MODULES_TREE_LOOKUP */ + +/* + * Bounds of module text, for speeding up __module_address. + * Protected by module_mutex. + */ +static void __mod_update_bounds(void *base, unsigned int size) +{ + unsigned long min = (unsigned long)base; + unsigned long max = min + size; + + if (min < module_addr_min) + module_addr_min = min; + if (max > module_addr_max) + module_addr_max = max; +} + +static void mod_update_bounds(struct module *mod) +{ + __mod_update_bounds(mod->module_core, mod->core_size); + if (mod->init_size) + __mod_update_bounds(mod->module_init, mod->init_size); +} + +#ifdef CONFIG_KGDB_KDB +struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ +#endif /* CONFIG_KGDB_KDB */ + +static void module_assert_mutex(void) +{ + lockdep_assert_held(&module_mutex); +} + +static void module_assert_mutex_or_preempt(void) +{ +#ifdef CONFIG_LOCKDEP + if (unlikely(!debug_locks)) + return; + + WARN_ON(!rcu_read_lock_sched_held() && + !lockdep_is_held(&module_mutex)); +#endif +} + +static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); +#ifndef CONFIG_MODULE_SIG_FORCE module_param(sig_enforce, bool_enable_only, 0644); #endif /* !CONFIG_MODULE_SIG_FORCE */ -#endif /* CONFIG_MODULE_SIG */ /* Block module loading/unloading? */ int modules_disabled = 0; @@ -153,10 +306,6 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); -/* Bounds of module allocation, for speeding __module_address. - * Protected by module_mutex. */ -static unsigned long module_addr_min = -1UL, module_addr_max = 0; - int register_module_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&module_notify_list, nb); @@ -318,6 +467,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, #endif }; + module_assert_mutex_or_preempt(); + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) return true; @@ -457,6 +608,8 @@ static struct module *find_module_all(const char *name, size_t len, { struct module *mod; + module_assert_mutex(); + list_for_each_entry(mod, &modules, list) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) continue; @@ -1169,11 +1322,17 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; - /* Since this should be found in kernel (which can't be removed), - * no locking is necessary. */ + /* + * Since this should be found in kernel (which can't be removed), no + * locking is necessary -- use preempt_disable() to placate lockdep. + */ + preempt_disable(); if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL, - &crc, true, false)) + &crc, true, false)) { + preempt_enable(); BUG(); + } + preempt_enable(); return check_version(sechdrs, versindex, VMLINUX_SYMBOL_STR(module_layout), mod, crc, NULL); @@ -1661,6 +1820,10 @@ static void mod_sysfs_fini(struct module *mod) mod_kobject_put(mod); } +static void init_param_lock(struct module *mod) +{ + mutex_init(&mod->param_lock); +} #else /* !CONFIG_SYSFS */ static int mod_sysfs_setup(struct module *mod, @@ -1683,6 +1846,9 @@ static void del_usage_links(struct module *mod) { } +static void init_param_lock(struct module *mod) +{ +} #endif /* CONFIG_SYSFS */ static void mod_sysfs_teardown(struct module *mod) @@ -1852,10 +2018,11 @@ static void free_module(struct module *mod) mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + mod_tree_remove(mod); /* Remove this module from bug list, this uses list_del_rcu */ module_bug_cleanup(mod); - /* Wait for RCU synchronizing before releasing mod->list and buglist. */ - synchronize_rcu(); + /* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */ + synchronize_sched(); mutex_unlock(&module_mutex); /* This may be NULL, but that's OK */ @@ -2384,22 +2551,6 @@ void * __weak module_alloc(unsigned long size) return vmalloc_exec(size); } -static void *module_alloc_update_bounds(unsigned long size) -{ - void *ret = module_alloc(size); - - if (ret) { - mutex_lock(&module_mutex); - /* Update module bounds. */ - if ((unsigned long)ret < module_addr_min) - module_addr_min = (unsigned long)ret; - if ((unsigned long)ret + size > module_addr_max) - module_addr_max = (unsigned long)ret + size; - mutex_unlock(&module_mutex); - } - return ret; -} - #ifdef CONFIG_DEBUG_KMEMLEAK static void kmemleak_load_module(const struct module *mod, const struct load_info *info) @@ -2805,7 +2956,7 @@ static int move_module(struct module *mod, struct load_info *info) void *ptr; /* Do the allocs. */ - ptr = module_alloc_update_bounds(mod->core_size); + ptr = module_alloc(mod->core_size); /* * The pointer to this block is stored in the module structure * which is inside the block. Just mark it as not being a @@ -2819,7 +2970,7 @@ static int move_module(struct module *mod, struct load_info *info) mod->module_core = ptr; if (mod->init_size) { - ptr = module_alloc_update_bounds(mod->init_size); + ptr = module_alloc(mod->init_size); /* * The pointer to this block is stored in the module structure * which is inside the block. This block doesn't need to be @@ -3119,6 +3270,7 @@ static noinline int do_init_module(struct module *mod) mod->symtab = mod->core_symtab; mod->strtab = mod->core_strtab; #endif + mod_tree_remove_init(mod); unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); mod->module_init = NULL; @@ -3127,11 +3279,11 @@ static noinline int do_init_module(struct module *mod) mod->init_text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be - * walking this with preempt disabled. In all the failure paths, - * we call synchronize_rcu/synchronize_sched, but we don't want - * to slow down the success path, so use actual RCU here. + * walking this with preempt disabled. In all the failure paths, we + * call synchronize_sched(), but we don't want to slow down the success + * path, so use actual RCU here. */ - call_rcu(&freeinit->rcu, do_free_init); + call_rcu_sched(&freeinit->rcu, do_free_init); mutex_unlock(&module_mutex); wake_up_all(&module_wq); @@ -3188,7 +3340,9 @@ again: err = -EEXIST; goto out; } + mod_update_bounds(mod); list_add_rcu(&mod->list, &modules); + mod_tree_insert(mod); err = 0; out: @@ -3304,6 +3458,8 @@ static int load_module(struct load_info *info, const char __user *uargs, if (err) goto unlink_mod; + init_param_lock(mod); + /* Now we've got everything in the final locations, we can * find optional sections. */ err = find_module_sections(mod, info); @@ -3402,8 +3558,8 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); wake_up_all(&module_wq); - /* Wait for RCU synchronizing before releasing mod->list. */ - synchronize_rcu(); + /* Wait for RCU-sched synchronizing before releasing mod->list. */ + synchronize_sched(); mutex_unlock(&module_mutex); free_module: /* Free lock-classes; relies on the preceding sync_rcu() */ @@ -3527,19 +3683,15 @@ const char *module_address_lookup(unsigned long addr, char **modname, char *namebuf) { - struct module *mod; const char *ret = NULL; + struct module *mod; preempt_disable(); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - if (within_module(addr, mod)) { - if (modname) - *modname = mod->name; - ret = get_ksymbol(mod, addr, size, offset); - break; - } + mod = __module_address(addr); + if (mod) { + if (modname) + *modname = mod->name; + ret = get_ksymbol(mod, addr, size, offset); } /* Make a copy in here where it's safe */ if (ret) { @@ -3547,6 +3699,7 @@ const char *module_address_lookup(unsigned long addr, ret = namebuf; } preempt_enable(); + return ret; } @@ -3670,6 +3823,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned int i; int ret; + module_assert_mutex(); + list_for_each_entry(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; @@ -3844,13 +3999,15 @@ struct module *__module_address(unsigned long addr) if (addr < module_addr_min || addr > module_addr_max) return NULL; - list_for_each_entry_rcu(mod, &modules, list) { + module_assert_mutex_or_preempt(); + + mod = mod_find(addr); + if (mod) { + BUG_ON(!within_module(addr, mod)); if (mod->state == MODULE_STATE_UNFORMED) - continue; - if (within_module(addr, mod)) - return mod; + mod = NULL; } - return NULL; + return mod; } EXPORT_SYMBOL_GPL(__module_address); diff --git a/kernel/params.c b/kernel/params.c index 30288c1e15dd..b6554aa71094 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -25,15 +25,34 @@ #include <linux/slab.h> #include <linux/ctype.h> -/* Protects all parameters, and incidentally kmalloced_param list. */ +#ifdef CONFIG_SYSFS +/* Protects all built-in parameters, modules use their own param_lock */ static DEFINE_MUTEX(param_lock); +/* Use the module's mutex, or if built-in use the built-in mutex */ +#ifdef CONFIG_MODULES +#define KPARAM_MUTEX(mod) ((mod) ? &(mod)->param_lock : ¶m_lock) +#else +#define KPARAM_MUTEX(mod) (¶m_lock) +#endif + +static inline void check_kparam_locked(struct module *mod) +{ + BUG_ON(!mutex_is_locked(KPARAM_MUTEX(mod))); +} +#else +static inline void check_kparam_locked(struct module *mod) +{ +} +#endif /* !CONFIG_SYSFS */ + /* This just allows us to keep track of which parameters are kmalloced. */ struct kmalloced_param { struct list_head list; char val[]; }; static LIST_HEAD(kmalloced_params); +static DEFINE_SPINLOCK(kmalloced_params_lock); static void *kmalloc_parameter(unsigned int size) { @@ -43,7 +62,10 @@ static void *kmalloc_parameter(unsigned int size) if (!p) return NULL; + spin_lock(&kmalloced_params_lock); list_add(&p->list, &kmalloced_params); + spin_unlock(&kmalloced_params_lock); + return p->val; } @@ -52,6 +74,7 @@ static void maybe_kfree_parameter(void *param) { struct kmalloced_param *p; + spin_lock(&kmalloced_params_lock); list_for_each_entry(p, &kmalloced_params, list) { if (p->val == param) { list_del(&p->list); @@ -59,6 +82,7 @@ static void maybe_kfree_parameter(void *param) break; } } + spin_unlock(&kmalloced_params_lock); } static char dash2underscore(char c) @@ -119,10 +143,10 @@ static int parse_one(char *param, return -EINVAL; pr_debug("handling %s with %p\n", param, params[i].ops->set); - mutex_lock(¶m_lock); + kernel_param_lock(params[i].mod); param_check_unsafe(¶ms[i]); err = params[i].ops->set(val, ¶ms[i]); - mutex_unlock(¶m_lock); + kernel_param_unlock(params[i].mod); return err; } } @@ -254,7 +278,7 @@ char *parse_args(const char *doing, return scnprintf(buffer, PAGE_SIZE, format, \ *((type *)kp->arg)); \ } \ - struct kernel_param_ops param_ops_##name = { \ + const struct kernel_param_ops param_ops_##name = { \ .set = param_set_##name, \ .get = param_get_##name, \ }; \ @@ -306,7 +330,7 @@ static void param_free_charp(void *arg) maybe_kfree_parameter(*((char **)arg)); } -struct kernel_param_ops param_ops_charp = { +const struct kernel_param_ops param_ops_charp = { .set = param_set_charp, .get = param_get_charp, .free = param_free_charp, @@ -331,13 +355,44 @@ int param_get_bool(char *buffer, const struct kernel_param *kp) } EXPORT_SYMBOL(param_get_bool); -struct kernel_param_ops param_ops_bool = { +const struct kernel_param_ops param_ops_bool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bool, .get = param_get_bool, }; EXPORT_SYMBOL(param_ops_bool); +int param_set_bool_enable_only(const char *val, const struct kernel_param *kp) +{ + int err = 0; + bool new_value; + bool orig_value = *(bool *)kp->arg; + struct kernel_param dummy_kp = *kp; + + dummy_kp.arg = &new_value; + + err = param_set_bool(val, &dummy_kp); + if (err) + return err; + + /* Don't let them unset it once it's set! */ + if (!new_value && orig_value) + return -EROFS; + + if (new_value) + err = param_set_bool(val, kp); + + return err; +} +EXPORT_SYMBOL_GPL(param_set_bool_enable_only); + +const struct kernel_param_ops param_ops_bool_enable_only = { + .flags = KERNEL_PARAM_OPS_FL_NOARG, + .set = param_set_bool_enable_only, + .get = param_get_bool, +}; +EXPORT_SYMBOL_GPL(param_ops_bool_enable_only); + /* This one must be bool. */ int param_set_invbool(const char *val, const struct kernel_param *kp) { @@ -359,7 +414,7 @@ int param_get_invbool(char *buffer, const struct kernel_param *kp) } EXPORT_SYMBOL(param_get_invbool); -struct kernel_param_ops param_ops_invbool = { +const struct kernel_param_ops param_ops_invbool = { .set = param_set_invbool, .get = param_get_invbool, }; @@ -367,12 +422,11 @@ EXPORT_SYMBOL(param_ops_invbool); int param_set_bint(const char *val, const struct kernel_param *kp) { - struct kernel_param boolkp; + /* Match bool exactly, by re-using it. */ + struct kernel_param boolkp = *kp; bool v; int ret; - /* Match bool exactly, by re-using it. */ - boolkp = *kp; boolkp.arg = &v; ret = param_set_bool(val, &boolkp); @@ -382,7 +436,7 @@ int param_set_bint(const char *val, const struct kernel_param *kp) } EXPORT_SYMBOL(param_set_bint); -struct kernel_param_ops param_ops_bint = { +const struct kernel_param_ops param_ops_bint = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_bint, .get = param_get_int, @@ -390,7 +444,8 @@ struct kernel_param_ops param_ops_bint = { EXPORT_SYMBOL(param_ops_bint); /* We break the rule and mangle the string. */ -static int param_array(const char *name, +static int param_array(struct module *mod, + const char *name, const char *val, unsigned int min, unsigned int max, void *elem, int elemsize, @@ -421,7 +476,7 @@ static int param_array(const char *name, /* nul-terminate and parse */ save = val[len]; ((char *)val)[len] = '\0'; - BUG_ON(!mutex_is_locked(¶m_lock)); + check_kparam_locked(mod); ret = set(val, &kp); if (ret != 0) @@ -443,7 +498,7 @@ static int param_array_set(const char *val, const struct kernel_param *kp) const struct kparam_array *arr = kp->arr; unsigned int temp_num; - return param_array(kp->name, val, 1, arr->max, arr->elem, + return param_array(kp->mod, kp->name, val, 1, arr->max, arr->elem, arr->elemsize, arr->ops->set, kp->level, arr->num ?: &temp_num); } @@ -452,14 +507,13 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) { int i, off, ret; const struct kparam_array *arr = kp->arr; - struct kernel_param p; + struct kernel_param p = *kp; - p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { if (i) buffer[off++] = ','; p.arg = arr->elem + arr->elemsize * i; - BUG_ON(!mutex_is_locked(¶m_lock)); + check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); if (ret < 0) return ret; @@ -479,7 +533,7 @@ static void param_array_free(void *arg) arr->ops->free(arr->elem + arr->elemsize * i); } -struct kernel_param_ops param_array_ops = { +const struct kernel_param_ops param_array_ops = { .set = param_array_set, .get = param_array_get, .free = param_array_free, @@ -507,7 +561,7 @@ int param_get_string(char *buffer, const struct kernel_param *kp) } EXPORT_SYMBOL(param_get_string); -struct kernel_param_ops param_ops_string = { +const struct kernel_param_ops param_ops_string = { .set = param_set_copystring, .get = param_get_string, }; @@ -542,9 +596,9 @@ static ssize_t param_attr_show(struct module_attribute *mattr, if (!attribute->param->ops->get) return -EPERM; - mutex_lock(¶m_lock); + kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); - mutex_unlock(¶m_lock); + kernel_param_unlock(mk->mod); if (count > 0) { strcat(buf, "\n"); ++count; @@ -554,7 +608,7 @@ static ssize_t param_attr_show(struct module_attribute *mattr, /* sysfs always hands a nul-terminated string in buf. We rely on that. */ static ssize_t param_attr_store(struct module_attribute *mattr, - struct module_kobject *km, + struct module_kobject *mk, const char *buf, size_t len) { int err; @@ -563,10 +617,10 @@ static ssize_t param_attr_store(struct module_attribute *mattr, if (!attribute->param->ops->set) return -EPERM; - mutex_lock(¶m_lock); + kernel_param_lock(mk->mod); param_check_unsafe(attribute->param); err = attribute->param->ops->set(buf, attribute->param); - mutex_unlock(¶m_lock); + kernel_param_unlock(mk->mod); if (!err) return len; return err; @@ -580,17 +634,18 @@ static ssize_t param_attr_store(struct module_attribute *mattr, #endif #ifdef CONFIG_SYSFS -void __kernel_param_lock(void) +void kernel_param_lock(struct module *mod) { - mutex_lock(¶m_lock); + mutex_lock(KPARAM_MUTEX(mod)); } -EXPORT_SYMBOL(__kernel_param_lock); -void __kernel_param_unlock(void) +void kernel_param_unlock(struct module *mod) { - mutex_unlock(¶m_lock); + mutex_unlock(KPARAM_MUTEX(mod)); } -EXPORT_SYMBOL(__kernel_param_unlock); + +EXPORT_SYMBOL(kernel_param_lock); +EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs @@ -856,6 +911,7 @@ static void __init version_sysfs_builtin(void) mk = locate_module_kobject(vattr->module_name); if (mk) { err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); + WARN_ON_ONCE(err); kobject_uevent(&mk->kobj, KOBJ_ADD); kobject_put(&mk->kobj); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 30b7a409bf1e..bca3667a2de1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -319,32 +319,7 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * - * So we handle this differently than the other timekeeping accessor - * functions which retry when the sequence count has changed. The - * update side does: - * - * smp_wmb(); <- Ensure that the last base[1] update is visible - * tkf->seq++; - * smp_wmb(); <- Ensure that the seqcount update is visible - * update(tkf->base[0], tkr); - * smp_wmb(); <- Ensure that the base[0] update is visible - * tkf->seq++; - * smp_wmb(); <- Ensure that the seqcount update is visible - * update(tkf->base[1], tkr); - * - * The reader side does: - * - * do { - * seq = tkf->seq; - * smp_rmb(); - * idx = seq & 0x01; - * now = now(tkf->base[idx]); - * smp_rmb(); - * } while (seq != tkf->seq) - * - * As long as we update base[0] readers are forced off to - * base[1]. Once base[0] is updated readers are redirected to base[0] - * and the base[1] update takes place. + * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a @@ -407,7 +382,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) u64 now; do { - seq = raw_read_seqcount(&tkf->seq); + seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); } while (read_seqcount_retry(&tkf->seq, seq)); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5243d4b03087..4c4f06176f74 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -285,12 +285,7 @@ static bool wq_disable_numa; module_param_named(disable_numa, wq_disable_numa, bool, 0444); /* see the comment above the definition of WQ_POWER_EFFICIENT */ -#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT -static bool wq_power_efficient = true; -#else -static bool wq_power_efficient; -#endif - +static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ diff --git a/lib/bug.c b/lib/bug.c index 0c3bd9552b6f..cff145f032a5 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -66,7 +66,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) struct module *mod; const struct bug_entry *bug = NULL; - rcu_read_lock(); + rcu_read_lock_sched(); list_for_each_entry_rcu(mod, &module_bug_list, bug_list) { unsigned i; @@ -77,7 +77,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) } bug = NULL; out: - rcu_read_unlock(); + rcu_read_unlock_sched(); return bug; } @@ -88,6 +88,8 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, char *secstrings; unsigned int i; + lockdep_assert_held(&module_mutex); + mod->bug_table = NULL; mod->num_bugs = 0; @@ -113,6 +115,7 @@ void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, void module_bug_cleanup(struct module *mod) { + lockdep_assert_held(&module_mutex); list_del_rcu(&mod->bug_list); } diff --git a/lib/rbtree.c b/lib/rbtree.c index c16c81a3d430..1356454e36de 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -44,6 +44,30 @@ * parentheses and have some accompanying text comment. */ +/* + * Notes on lockless lookups: + * + * All stores to the tree structure (rb_left and rb_right) must be done using + * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the + * tree structure as seen in program order. + * + * These two requirements will allow lockless iteration of the tree -- not + * correct iteration mind you, tree rotations are not atomic so a lookup might + * miss entire subtrees. + * + * But they do guarantee that any such traversal will only see valid elements + * and that it will indeed complete -- does not get stuck in a loop. + * + * It also guarantees that if the lookup returns an element it is the 'correct' + * one. But not returning an element does _NOT_ mean it's not present. + * + * NOTE: + * + * Stores to __rb_parent_color are not important for simple lookups so those + * are left undone as of now. Nor did I check for loops involving parent + * pointers. + */ + static inline void rb_set_black(struct rb_node *rb) { rb->__rb_parent_color |= RB_BLACK; @@ -129,8 +153,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root, * This still leaves us in violation of 4), the * continuation into Case 3 will fix that. */ - parent->rb_right = tmp = node->rb_left; - node->rb_left = parent; + tmp = node->rb_left; + WRITE_ONCE(parent->rb_right, tmp); + WRITE_ONCE(node->rb_left, parent); if (tmp) rb_set_parent_color(tmp, parent, RB_BLACK); @@ -149,8 +174,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, * / \ * n U */ - gparent->rb_left = tmp; /* == parent->rb_right */ - parent->rb_right = gparent; + WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */ + WRITE_ONCE(parent->rb_right, gparent); if (tmp) rb_set_parent_color(tmp, gparent, RB_BLACK); __rb_rotate_set_parents(gparent, parent, root, RB_RED); @@ -171,8 +196,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root, tmp = parent->rb_left; if (node == tmp) { /* Case 2 - right rotate at parent */ - parent->rb_left = tmp = node->rb_right; - node->rb_right = parent; + tmp = node->rb_right; + WRITE_ONCE(parent->rb_left, tmp); + WRITE_ONCE(node->rb_right, parent); if (tmp) rb_set_parent_color(tmp, parent, RB_BLACK); @@ -183,8 +209,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, } /* Case 3 - left rotate at gparent */ - gparent->rb_right = tmp; /* == parent->rb_left */ - parent->rb_left = gparent; + WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */ + WRITE_ONCE(parent->rb_left, gparent); if (tmp) rb_set_parent_color(tmp, gparent, RB_BLACK); __rb_rotate_set_parents(gparent, parent, root, RB_RED); @@ -224,8 +250,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * Sl Sr N Sl */ - parent->rb_right = tmp1 = sibling->rb_left; - sibling->rb_left = parent; + tmp1 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp1); + WRITE_ONCE(sibling->rb_left, parent); rb_set_parent_color(tmp1, parent, RB_BLACK); __rb_rotate_set_parents(parent, sibling, root, RB_RED); @@ -275,9 +302,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * \ * Sr */ - sibling->rb_left = tmp1 = tmp2->rb_right; - tmp2->rb_right = sibling; - parent->rb_right = tmp2; + tmp1 = tmp2->rb_right; + WRITE_ONCE(sibling->rb_left, tmp1); + WRITE_ONCE(tmp2->rb_right, sibling); + WRITE_ONCE(parent->rb_right, tmp2); if (tmp1) rb_set_parent_color(tmp1, sibling, RB_BLACK); @@ -297,8 +325,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * (sl) sr N (sl) */ - parent->rb_right = tmp2 = sibling->rb_left; - sibling->rb_left = parent; + tmp2 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp2); + WRITE_ONCE(sibling->rb_left, parent); rb_set_parent_color(tmp1, sibling, RB_BLACK); if (tmp2) rb_set_parent(tmp2, parent); @@ -310,8 +339,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, sibling = parent->rb_left; if (rb_is_red(sibling)) { /* Case 1 - right rotate at parent */ - parent->rb_left = tmp1 = sibling->rb_right; - sibling->rb_right = parent; + tmp1 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp1); + WRITE_ONCE(sibling->rb_right, parent); rb_set_parent_color(tmp1, parent, RB_BLACK); __rb_rotate_set_parents(parent, sibling, root, RB_RED); @@ -336,9 +366,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, break; } /* Case 3 - right rotate at sibling */ - sibling->rb_right = tmp1 = tmp2->rb_left; - tmp2->rb_left = sibling; - parent->rb_left = tmp2; + tmp1 = tmp2->rb_left; + WRITE_ONCE(sibling->rb_right, tmp1); + WRITE_ONCE(tmp2->rb_left, sibling); + WRITE_ONCE(parent->rb_left, tmp2); if (tmp1) rb_set_parent_color(tmp1, sibling, RB_BLACK); @@ -347,8 +378,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, sibling = tmp2; } /* Case 4 - left rotate at parent + color flips */ - parent->rb_left = tmp2 = sibling->rb_right; - sibling->rb_right = parent; + tmp2 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp2); + WRITE_ONCE(sibling->rb_right, parent); rb_set_parent_color(tmp1, sibling, RB_BLACK); if (tmp2) rb_set_parent(tmp2, parent); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 36ba7c4f0283..fda33f961d83 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -103,7 +103,7 @@ ieee80211_rate_control_ops_get(const char *name) const struct rate_control_ops *ops; const char *alg_name; - kparam_block_sysfs_write(ieee80211_default_rc_algo); + kernel_param_lock(THIS_MODULE); if (!name) alg_name = ieee80211_default_rc_algo; else @@ -117,7 +117,7 @@ ieee80211_rate_control_ops_get(const char *name) /* try built-in one if specific alg requested but not found */ if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT)) ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT); - kparam_unblock_sysfs_write(ieee80211_default_rc_algo); + kernel_param_unlock(THIS_MODULE); return ops; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 47f38be4155f..02f53674dc39 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -72,7 +72,7 @@ static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp) #define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int); -static struct kernel_param_ops param_ops_hashtbl_sz = { +static const struct kernel_param_ops param_ops_hashtbl_sz = { .set = param_set_hashtbl_sz, .get = param_get_hashtbl_sz, }; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 66891e32c5e3..b0517287075b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2982,7 +2982,7 @@ static int param_set_portnr(const char *val, const struct kernel_param *kp) RPC_MAX_RESVPORT); } -static struct kernel_param_ops param_ops_portnr = { +static const struct kernel_param_ops param_ops_portnr = { .set = param_set_portnr, .get = param_get_uint, }; @@ -3001,7 +3001,7 @@ static int param_set_slot_table_size(const char *val, RPC_MAX_SLOT_TABLE); } -static struct kernel_param_ops param_ops_slot_table_size = { +static const struct kernel_param_ops param_ops_slot_table_size = { .set = param_set_slot_table_size, .get = param_get_uint, }; @@ -3017,7 +3017,7 @@ static int param_set_max_slot_table_size(const char *val, RPC_MAX_SLOT_TABLE_LIMIT); } -static struct kernel_param_ops param_ops_max_slot_table_size = { +static const struct kernel_param_ops param_ops_max_slot_table_size = { .set = param_set_max_slot_table_size, .get = param_get_uint, }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 5696874e8062..dec607c17b64 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -654,7 +654,7 @@ static struct security_hook_list apparmor_hooks[] = { static int param_set_aabool(const char *val, const struct kernel_param *kp); static int param_get_aabool(char *buffer, const struct kernel_param *kp); #define param_check_aabool param_check_bool -static struct kernel_param_ops param_ops_aabool = { +static const struct kernel_param_ops param_ops_aabool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aabool, .get = param_get_aabool @@ -663,7 +663,7 @@ static struct kernel_param_ops param_ops_aabool = { static int param_set_aauint(const char *val, const struct kernel_param *kp); static int param_get_aauint(char *buffer, const struct kernel_param *kp); #define param_check_aauint param_check_uint -static struct kernel_param_ops param_ops_aauint = { +static const struct kernel_param_ops param_ops_aauint = { .set = param_set_aauint, .get = param_get_aauint }; @@ -671,7 +671,7 @@ static struct kernel_param_ops param_ops_aauint = { static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp); static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp); #define param_check_aalockpolicy param_check_bool -static struct kernel_param_ops param_ops_aalockpolicy = { +static const struct kernel_param_ops param_ops_aalockpolicy = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aalockpolicy, .get = param_get_aalockpolicy diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 686355fea7fd..e24121afb2f2 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -55,7 +55,7 @@ static int param_set_bufsize(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_bufsize = { +static const struct kernel_param_ops param_ops_bufsize = { .set = param_set_bufsize, .get = param_get_uint, }; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7dea7987d2af..9913e24d6699 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -171,7 +171,7 @@ MODULE_PARM_DESC(beep_mode, "Select HDA Beep registration mode " #ifdef CONFIG_PM static int param_set_xint(const char *val, const struct kernel_param *kp); -static struct kernel_param_ops param_ops_xint = { +static const struct kernel_param_ops param_ops_xint = { .set = param_set_xint, .get = param_get_int, }; |