From 13662dc5b177d68885695ef513dd4ae0e4d2a099 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 8 Nov 2011 03:16:13 -0700 Subject: ARM: OMAP: HWMOD: Unify DSS resets for OMAPs This patch adds a custom DSS reset function used on OMAPs from OMAP2 forward. The function doesn't actually do a reset, it only waits for the reset to complete. The reason for this is that on OMAP4 there is no possibility to do a SW reset, and on OMAP2/3 doing a SW reset for dss_core resets all the other DSS modules also, thus breaking the HWMOD model where every DSS module is handled independently. This fixes the problem with DSS reset on OMAP4, caused by the fact that because there's no SW reset for dss_core on OMAP4, the HWMOD framework doesn't try to reset dss_core and thus the DSS clocks were never enabled at the same time. This causes causes the HWMOD reset to fail for dss_dispc and dss_rfbi. The common reset function will also allow us to fix another problem in the future: before doing a reset we need to disable DSS outputs, which are in some cases enabled by the bootloader, as otherwise DSS HW seems to get more or less stuck, requiring a power reset to recover. Signed-off-by: Tomi Valkeinen [paul@pwsan.com: modified to build arch/arm/mach-omap2/display.o unconditionally to avoid an error when !CONFIG_OMAP2_DSS] Signed-off-by: Paul Walmsley --- include/video/omapdss.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/video/omapdss.h b/include/video/omapdss.h index b66ebb2032c6..378c7ed6760b 100644 --- a/include/video/omapdss.h +++ b/include/video/omapdss.h @@ -307,15 +307,8 @@ struct omap_dss_board_info { void (*dsi_disable_pads)(int dsi_id, unsigned lane_mask); }; -#if defined(CONFIG_OMAP2_DSS_MODULE) || defined(CONFIG_OMAP2_DSS) /* Init with the board info */ extern int omap_display_init(struct omap_dss_board_info *board_data); -#else -static inline int omap_display_init(struct omap_dss_board_info *board_data) -{ - return 0; -} -#endif struct omap_display_platform_data { struct omap_dss_board_info *board_data; -- cgit v1.3-14-g43fede From d65670a78cdbfae94f20a9e05ec705871d7cdf2b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 31 Oct 2011 17:06:35 -0400 Subject: clocksource: Avoid selecting mult values that might overflow when adjusted For some frequencies, the clocks_calc_mult_shift() function will unfortunately select mult values very close to 0xffffffff. This has the potential to overflow when NTP adjusts the clock, adding to the mult value. This patch adds a clocksource.maxadj value, which provides an approximation of an 11% adjustment(NTP limits adjustments to 500ppm and the tick adjustment is limited to 10%), which could be made to the clocksource.mult value. This is then used to both check that the current mult value won't overflow/underflow, as well as warning us if the timekeeping_adjust() code pushes over that 11% boundary. v2: Fix max_adjustment calculation, and improve WARN_ONCE messages. v3: Don't warn before maxadj has actually been set CC: Yong Zhang CC: David Daney CC: Thomas Gleixner CC: Chen Jie CC: zhangfx CC: stable@kernel.org Reported-by: Chen Jie Reported-by: zhangfx Tested-by: Yong Zhang Signed-off-by: John Stultz --- include/linux/clocksource.h | 3 ++- kernel/time/clocksource.c | 58 +++++++++++++++++++++++++++++++++++++-------- kernel/time/timekeeping.c | 7 ++++++ 3 files changed, 57 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 139c4db55f17..c86c940d1de3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -156,6 +156,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) * @max_idle_ns: max idle time permitted by the clocksource (nsecs) + * @maxadj maximum adjustment value to mult (~11%) * @flags: flags describing special properties * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary @@ -172,7 +173,7 @@ struct clocksource { u32 mult; u32 shift; u64 max_idle_ns; - + u32 maxadj; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cf52fda2e096..cfc65e1eb9fb 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -491,6 +491,22 @@ void clocksource_touch_watchdog(void) clocksource_resume_watchdog(); } +/** + * clocksource_max_adjustment- Returns max adjustment amount + * @cs: Pointer to clocksource + * + */ +static u32 clocksource_max_adjustment(struct clocksource *cs) +{ + u64 ret; + /* + * We won't try to correct for more then 11% adjustments (110,000 ppm), + */ + ret = (u64)cs->mult * 11; + do_div(ret,100); + return (u32)ret; +} + /** * clocksource_max_deferment - Returns max time the clocksource can be deferred * @cs: Pointer to clocksource @@ -503,25 +519,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs) /* * Calculate the maximum number of cycles that we can pass to the * cyc2ns function without overflowing a 64-bit signed result. The - * maximum number of cycles is equal to ULLONG_MAX/cs->mult which - * is equivalent to the below. - * max_cycles < (2^63)/cs->mult - * max_cycles < 2^(log2((2^63)/cs->mult)) - * max_cycles < 2^(log2(2^63) - log2(cs->mult)) - * max_cycles < 2^(63 - log2(cs->mult)) - * max_cycles < 1 << (63 - log2(cs->mult)) + * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj) + * which is equivalent to the below. + * max_cycles < (2^63)/(cs->mult + cs->maxadj) + * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj))) + * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj)) + * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj)) + * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj)) * Please note that we add 1 to the result of the log2 to account for * any rounding errors, ensure the above inequality is satisfied and * no overflow will occur. */ - max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1)); + max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1)); /* * The actual maximum number of cycles we can defer the clocksource is * determined by the minimum of max_cycles and cs->mask. + * Note: Here we subtract the maxadj to make sure we don't sleep for + * too long if there's a large negative adjustment. */ max_cycles = min_t(u64, max_cycles, (u64) cs->mask); - max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift); + max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj, + cs->shift); /* * To ensure that the clocksource does not wrap whilst we are idle, @@ -640,7 +659,6 @@ static void clocksource_enqueue(struct clocksource *cs) void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; - /* * Calc the maximum number of seconds which we can run before * wrapping around. For clocksources which have a mask > 32bit @@ -661,6 +679,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, NSEC_PER_SEC / scale, sec * scale); + + /* + * for clocksources that have large mults, to avoid overflow. + * Since mult may be adjusted by ntp, add an safety extra margin + * + */ + cs->maxadj = clocksource_max_adjustment(cs); + while ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult)) { + cs->mult >>= 1; + cs->shift--; + cs->maxadj = clocksource_max_adjustment(cs); + } + cs->max_idle_ns = clocksource_max_deferment(cs); } EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); @@ -701,6 +733,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale); */ int clocksource_register(struct clocksource *cs) { + /* calculate max adjustment for given mult/shift */ + cs->maxadj = clocksource_max_adjustment(cs); + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + /* calculate max idle time permitted for this clocksource */ cs->max_idle_ns = clocksource_max_deferment(cs); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 2b021b0e8507..e65ff3171102 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -820,6 +820,13 @@ static void timekeeping_adjust(s64 offset) } else return; + WARN_ONCE(timekeeper.clock->maxadj && + (timekeeper.mult + adj > timekeeper.clock->mult + + timekeeper.clock->maxadj), + "Adjusting %s more then 11%% (%ld vs %ld)\n", + timekeeper.clock->name, (long)timekeeper.mult + adj, + (long)timekeeper.clock->mult + + timekeeper.clock->maxadj); timekeeper.mult += adj; timekeeper.xtime_interval += interval; timekeeper.xtime_nsec -= offset; -- cgit v1.3-14-g43fede From f088d5a9c5dd22b6559fa3f3939973bc374c977b Mon Sep 17 00:00:00 2001 From: Inki Dae Date: Sat, 12 Nov 2011 14:51:23 +0900 Subject: drm/exynos: use gem create function generically this patch addes exynos_drm_gem_init() creating and initialzing a gem. allocation functions could use this function to create new gem and it changes size type of exynos_drm_gem_create structure to 64bit and also corrects comments to exynos_drm_gem_create structure. Signed-off-by: Inki Dae Signed-off-by: Kyungmin Park --- drivers/gpu/drm/exynos/exynos_drm_fb.c | 6 +-- drivers/gpu/drm/exynos/exynos_drm_gem.c | 79 ++++++++++++++++++++------------- drivers/gpu/drm/exynos/exynos_drm_gem.h | 6 +-- include/drm/exynos_drm.h | 9 ++-- 4 files changed, 59 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c index 7d91a542c756..8d0f66224045 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fb.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c @@ -165,9 +165,9 @@ exynos_drm_fb_init(struct drm_file *file_priv, struct drm_device *dev, goto out; } else { - exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, - size, - &mode_cmd->handle); + exynos_gem_obj = exynos_drm_gem_create(dev, file_priv, + &mode_cmd->handle, + size); if (IS_ERR(exynos_gem_obj)) { ret = PTR_ERR(exynos_gem_obj); goto err_buffer; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index a8e7a88906ed..bd6ede83b684 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -62,40 +62,28 @@ static unsigned int get_gem_mmap_offset(struct drm_gem_object *obj) return (unsigned int)obj->map_list.hash.key << PAGE_SHIFT; } -struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv, - struct drm_device *dev, unsigned int size, - unsigned int *handle) +static struct exynos_drm_gem_obj + *exynos_drm_gem_init(struct drm_device *drm_dev, + struct drm_file *file_priv, unsigned int *handle, + unsigned int size) { struct exynos_drm_gem_obj *exynos_gem_obj; - struct exynos_drm_buf_entry *entry; struct drm_gem_object *obj; int ret; - DRM_DEBUG_KMS("%s\n", __FILE__); - - size = roundup(size, PAGE_SIZE); - exynos_gem_obj = kzalloc(sizeof(*exynos_gem_obj), GFP_KERNEL); if (!exynos_gem_obj) { DRM_ERROR("failed to allocate exynos gem object.\n"); return ERR_PTR(-ENOMEM); } - /* allocate the new buffer object and memory region. */ - entry = exynos_drm_buf_create(dev, size); - if (!entry) { - kfree(exynos_gem_obj); - return ERR_PTR(-ENOMEM); - } - - exynos_gem_obj->entry = entry; - obj = &exynos_gem_obj->base; - ret = drm_gem_object_init(dev, obj, size); + ret = drm_gem_object_init(drm_dev, obj, size); if (ret < 0) { - DRM_ERROR("failed to initailize gem object.\n"); - goto err_obj_init; + DRM_ERROR("failed to initialize gem object.\n"); + ret = -EINVAL; + goto err_object_init; } DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp); @@ -127,24 +115,55 @@ err_handle_create: err_create_mmap_offset: drm_gem_object_release(obj); -err_obj_init: - exynos_drm_buf_destroy(dev, exynos_gem_obj->entry); - +err_object_init: kfree(exynos_gem_obj); return ERR_PTR(ret); } +struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev, + struct drm_file *file_priv, + unsigned int *handle, unsigned long size) +{ + + struct exynos_drm_gem_obj *exynos_gem_obj = NULL; + struct exynos_drm_buf_entry *entry; + int ret; + + size = roundup(size, PAGE_SIZE); + + DRM_DEBUG_KMS("%s: size = 0x%lx\n", __FILE__, size); + + entry = exynos_drm_buf_create(dev, size); + if (!entry) + return ERR_PTR(-ENOMEM); + + exynos_gem_obj = exynos_drm_gem_init(dev, file_priv, handle, size); + if (IS_ERR(exynos_gem_obj)) { + ret = PTR_ERR(exynos_gem_obj); + goto err_gem_init; + } + + exynos_gem_obj->entry = entry; + + return exynos_gem_obj; + +err_gem_init: + exynos_drm_buf_destroy(dev, exynos_gem_obj->entry); + + return ERR_PTR(ret); +} + int exynos_drm_gem_create_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) + struct drm_file *file_priv) { struct drm_exynos_gem_create *args = data; - struct exynos_drm_gem_obj *exynos_gem_obj; + struct exynos_drm_gem_obj *exynos_gem_obj = NULL; - DRM_DEBUG_KMS("%s : size = 0x%x\n", __FILE__, args->size); + DRM_DEBUG_KMS("%s\n", __FILE__); - exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size, - &args->handle); + exynos_gem_obj = exynos_drm_gem_create(dev, file_priv, + &args->handle, args->size); if (IS_ERR(exynos_gem_obj)) return PTR_ERR(exynos_gem_obj); @@ -302,8 +321,8 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv, args->pitch = args->width * args->bpp >> 3; args->size = args->pitch * args->height; - exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size, - &args->handle); + exynos_gem_obj = exynos_drm_gem_create(dev, file_priv, &args->handle, + args->size); if (IS_ERR(exynos_gem_obj)) return PTR_ERR(exynos_gem_obj); diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index e5fc0148277b..213838d9606e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -49,9 +49,9 @@ struct exynos_drm_gem_obj { }; /* create a new buffer and get a new gem handle. */ -struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv, - struct drm_device *dev, unsigned int size, - unsigned int *handle); +struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev, + struct drm_file *file_priv, + unsigned int *handle, unsigned long size); /* * request gem object creation and buffer allocation as the size diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h index 1d161cb3aca5..12050434d57a 100644 --- a/include/drm/exynos_drm.h +++ b/include/drm/exynos_drm.h @@ -32,17 +32,16 @@ /** * User-desired buffer creation information structure. * - * @size: requested size for the object. + * @size: user-desired memory allocation size. * - this size value would be page-aligned internally. * @flags: user request for setting memory type or cache attributes. - * @handle: returned handle for the object. - * @pad: just padding to be 64-bit aligned. + * @handle: returned a handle to created gem object. + * - this handle will be set by gem module of kernel side. */ struct drm_exynos_gem_create { - unsigned int size; + uint64_t size; unsigned int flags; unsigned int handle; - unsigned int pad; }; /** -- cgit v1.3-14-g43fede From f6f8285132907757ef84ef8dae0a1244b8cde6ac Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Nov 2011 12:58:07 -0800 Subject: pstore: pass allocated memory region back to caller The buf_lock cannot be held while populating the inodes, so make the backend pass forward an allocated and filled buffer instead. This solves the following backtrace. The effect is that "buf" is only ever used to notify the backends that something was written to it, and shouldn't be used in the read path. To replace the buf_lock during the read path, isolate the open/read/close loop with a separate mutex to maintain serialized access to the backend. Note that is is up to the pstore backend to cope if the (*write)() path is called in the middle of the read path. [ 59.691019] BUG: sleeping function called from invalid context at .../mm/slub.c:847 [ 59.691019] in_atomic(): 0, irqs_disabled(): 1, pid: 1819, name: mount [ 59.691019] Pid: 1819, comm: mount Not tainted 3.0.8 #1 [ 59.691019] Call Trace: [ 59.691019] [<810252d5>] __might_sleep+0xc3/0xca [ 59.691019] [<810a26e6>] kmem_cache_alloc+0x32/0xf3 [ 59.691019] [<810b53ac>] ? __d_lookup_rcu+0x6f/0xf4 [ 59.691019] [<810b68b1>] alloc_inode+0x2a/0x64 [ 59.691019] [<810b6903>] new_inode+0x18/0x43 [ 59.691019] [<81142447>] pstore_get_inode.isra.1+0x11/0x98 [ 59.691019] [<81142623>] pstore_mkfile+0xae/0x26f [ 59.691019] [<810a2a66>] ? kmem_cache_free+0x19/0xb1 [ 59.691019] [<8116c821>] ? ida_get_new_above+0x140/0x158 [ 59.691019] [<811708ea>] ? __init_rwsem+0x1e/0x2c [ 59.691019] [<810b67e8>] ? inode_init_always+0x111/0x1b0 [ 59.691019] [<8102127e>] ? should_resched+0xd/0x27 [ 59.691019] [<8137977f>] ? _cond_resched+0xd/0x21 [ 59.691019] [<81142abf>] pstore_get_records+0x52/0xa7 [ 59.691019] [<8114254b>] pstore_fill_super+0x7d/0x91 [ 59.691019] [<810a7ff5>] mount_single+0x46/0x82 [ 59.691019] [<8114231a>] pstore_mount+0x15/0x17 [ 59.691019] [<811424ce>] ? pstore_get_inode.isra.1+0x98/0x98 [ 59.691019] [<810a8199>] mount_fs+0x5a/0x12d [ 59.691019] [<810b9174>] ? alloc_vfsmnt+0xa4/0x14a [ 59.691019] [<810b9474>] vfs_kern_mount+0x4f/0x7d [ 59.691019] [<810b9d7e>] do_kern_mount+0x34/0xb2 [ 59.691019] [<810bb15f>] do_mount+0x5fc/0x64a [ 59.691019] [<810912fb>] ? strndup_user+0x2e/0x3f [ 59.691019] [<810bb3cb>] sys_mount+0x66/0x99 [ 59.691019] [<8137b537>] sysenter_do_call+0x12/0x26 Signed-off-by: Kees Cook Signed-off-by: Tony Luck --- drivers/acpi/apei/erst.c | 31 ++++++++++++++++++++++--------- drivers/firmware/efivars.c | 9 +++++++-- fs/pstore/platform.c | 13 ++++++++----- include/linux/pstore.h | 4 +++- 4 files changed, 40 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 127408069ca7..631b9477b99c 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -932,7 +932,8 @@ static int erst_check_table(struct acpi_table_erst *erst_tab) static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time, struct pstore_info *psi); + struct timespec *time, char **buf, + struct pstore_info *psi); static int erst_writer(enum pstore_type_id type, u64 *id, unsigned int part, size_t size, struct pstore_info *psi); static int erst_clearer(enum pstore_type_id type, u64 id, @@ -986,17 +987,23 @@ static int erst_close_pstore(struct pstore_info *psi) } static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time, struct pstore_info *psi) + struct timespec *time, char **buf, + struct pstore_info *psi) { int rc; ssize_t len = 0; u64 record_id; - struct cper_pstore_record *rcd = (struct cper_pstore_record *) - (erst_info.buf - sizeof(*rcd)); + struct cper_pstore_record *rcd; + size_t rcd_len = sizeof(*rcd) + erst_info.bufsize; if (erst_disable) return -ENODEV; + rcd = kmalloc(rcd_len, GFP_KERNEL); + if (!rcd) { + rc = -ENOMEM; + goto out; + } skip: rc = erst_get_record_id_next(&reader_pos, &record_id); if (rc) @@ -1004,22 +1011,27 @@ skip: /* no more record */ if (record_id == APEI_ERST_INVALID_RECORD_ID) { - rc = -1; + rc = -EINVAL; goto out; } - len = erst_read(record_id, &rcd->hdr, sizeof(*rcd) + - erst_info.bufsize); + len = erst_read(record_id, &rcd->hdr, rcd_len); /* The record may be cleared by others, try read next record */ if (len == -ENOENT) goto skip; - else if (len < 0) { - rc = -1; + else if (len < sizeof(*rcd)) { + rc = -EIO; goto out; } if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0) goto skip; + *buf = kmalloc(len, GFP_KERNEL); + if (*buf == NULL) { + rc = -ENOMEM; + goto out; + } + memcpy(*buf, rcd->data, len - sizeof(*rcd)); *id = record_id; if (uuid_le_cmp(rcd->sec_hdr.section_type, CPER_SECTION_TYPE_DMESG) == 0) @@ -1037,6 +1049,7 @@ skip: time->tv_nsec = 0; out: + kfree(rcd); return (rc < 0) ? rc : (len - sizeof(*rcd)); } diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 8370f72d87ff..a54a6b972ced 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -457,7 +457,8 @@ static int efi_pstore_close(struct pstore_info *psi) } static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, - struct timespec *timespec, struct pstore_info *psi) + struct timespec *timespec, + char **buf, struct pstore_info *psi) { efi_guid_t vendor = LINUX_EFI_CRASH_GUID; struct efivars *efivars = psi->data; @@ -478,7 +479,11 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, timespec->tv_nsec = 0; get_var_data_locked(efivars, &efivars->walk_entry->var); size = efivars->walk_entry->var.DataSize; - memcpy(psi->buf, efivars->walk_entry->var.Data, size); + *buf = kmalloc(size, GFP_KERNEL); + if (*buf == NULL) + return -ENOMEM; + memcpy(*buf, efivars->walk_entry->var.Data, + size); efivars->walk_entry = list_entry(efivars->walk_entry->list.next, struct efivar_entry, list); return size; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 2bd620f0d796..57bbf9078ac8 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -167,6 +167,7 @@ int pstore_register(struct pstore_info *psi) } psinfo = psi; + mutex_init(&psinfo->read_mutex); spin_unlock(&pstore_lock); if (owner && !try_module_get(owner)) { @@ -195,30 +196,32 @@ EXPORT_SYMBOL_GPL(pstore_register); void pstore_get_records(int quiet) { struct pstore_info *psi = psinfo; + char *buf = NULL; ssize_t size; u64 id; enum pstore_type_id type; struct timespec time; int failed = 0, rc; - unsigned long flags; if (!psi) return; - spin_lock_irqsave(&psinfo->buf_lock, flags); + mutex_lock(&psi->read_mutex); rc = psi->open(psi); if (rc) goto out; - while ((size = psi->read(&id, &type, &time, psi)) > 0) { - rc = pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size, + while ((size = psi->read(&id, &type, &time, &buf, psi)) > 0) { + rc = pstore_mkfile(type, psi->name, id, buf, (size_t)size, time, psi); + kfree(buf); + buf = NULL; if (rc && (rc != -EEXIST || !quiet)) failed++; } psi->close(psi); out: - spin_unlock_irqrestore(&psinfo->buf_lock, flags); + mutex_unlock(&psi->read_mutex); if (failed) printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n", diff --git a/include/linux/pstore.h b/include/linux/pstore.h index ea567321ae3c..2ca8cde5459d 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -35,10 +35,12 @@ struct pstore_info { spinlock_t buf_lock; /* serialize access to 'buf' */ char *buf; size_t bufsize; + struct mutex read_mutex; /* serialize open/read/close */ int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, - struct timespec *time, struct pstore_info *psi); + struct timespec *time, char **buf, + struct pstore_info *psi); int (*write)(enum pstore_type_id type, u64 *id, unsigned int part, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, -- cgit v1.3-14-g43fede From f7bc83d87d242917ca0ee041ed509f57f361dd56 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Nov 2011 21:20:32 +0100 Subject: PM: Update comments describing device power management callbacks The comments describing device power management callbacks in include/pm.h are outdated and somewhat confusing, so make them reflect the reality more accurately. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 229 +++++++++++++++++++++++++++++++---------------------- 1 file changed, 134 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index 5c4c8b18c8b7..3f3ed83a9aa5 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -54,118 +54,145 @@ typedef struct pm_message { /** * struct dev_pm_ops - device PM callbacks * - * Several driver power state transitions are externally visible, affecting + * Several device power state transitions are externally visible, affecting * the state of pending I/O queues and (for drivers that touch hardware) * interrupts, wakeups, DMA, and other hardware state. There may also be - * internal transitions to various low power modes, which are transparent + * internal transitions to various low-power modes which are transparent * to the rest of the driver stack (such as a driver that's ON gating off * clocks which are not in active use). * - * The externally visible transitions are handled with the help of the following - * callbacks included in this structure: - * - * @prepare: Prepare the device for the upcoming transition, but do NOT change - * its hardware state. Prevent new children of the device from being - * registered after @prepare() returns (the driver's subsystem and - * generally the rest of the kernel is supposed to prevent new calls to the - * probe method from being made too once @prepare() has succeeded). If - * @prepare() detects a situation it cannot handle (e.g. registration of a - * child already in progress), it may return -EAGAIN, so that the PM core - * can execute it once again (e.g. after the new child has been registered) - * to recover from the race condition. This method is executed for all - * kinds of suspend transitions and is followed by one of the suspend - * callbacks: @suspend(), @freeze(), or @poweroff(). - * The PM core executes @prepare() for all devices before starting to - * execute suspend callbacks for any of them, so drivers may assume all of - * the other devices to be present and functional while @prepare() is being - * executed. In particular, it is safe to make GFP_KERNEL memory - * allocations from within @prepare(). However, drivers may NOT assume - * anything about the availability of the user space at that time and it - * is not correct to request firmware from within @prepare() (it's too - * late to do that). [To work around this limitation, drivers may - * register suspend and hibernation notifiers that are executed before the - * freezing of tasks.] + * The externally visible transitions are handled with the help of callbacks + * included in this structure in such a way that two levels of callbacks are + * involved. First, the PM core executes callbacks provided by PM domains, + * device types, classes and bus types. They are the subsystem-level callbacks + * supposed to execute callbacks provided by device drivers, although they may + * choose not to do that. If the driver callbacks are executed, they have to + * collaborate with the subsystem-level callbacks to achieve the goals + * appropriate for the given system transition, given transition phase and the + * subsystem the device belongs to. + * + * @prepare: The principal role of this callback is to prevent new children of + * the device from being registered after it has returned (the driver's + * subsystem and generally the rest of the kernel is supposed to prevent + * new calls to the probe method from being made too once @prepare() has + * succeeded). If @prepare() detects a situation it cannot handle (e.g. + * registration of a child already in progress), it may return -EAGAIN, so + * that the PM core can execute it once again (e.g. after a new child has + * been registered) to recover from the race condition. + * This method is executed for all kinds of suspend transitions and is + * followed by one of the suspend callbacks: @suspend(), @freeze(), or + * @poweroff(). The PM core executes subsystem-level @prepare() for all + * devices before starting to invoke suspend callbacks for any of them, so + * generally devices may be assumed to be functional or to respond to + * runtime resume requests while @prepare() is being executed. However, + * device drivers may NOT assume anything about the availability of user + * space at that time and it is NOT valid to request firmware from within + * @prepare() (it's too late to do that). It also is NOT valid to allocate + * substantial amounts of memory from @prepare() in the GFP_KERNEL mode. + * [To work around these limitations, drivers may register suspend and + * hibernation notifiers to be executed before the freezing of tasks.] * * @complete: Undo the changes made by @prepare(). This method is executed for * all kinds of resume transitions, following one of the resume callbacks: * @resume(), @thaw(), @restore(). Also called if the state transition - * fails before the driver's suspend callback (@suspend(), @freeze(), - * @poweroff()) can be executed (e.g. if the suspend callback fails for one + * fails before the driver's suspend callback: @suspend(), @freeze() or + * @poweroff(), can be executed (e.g. if the suspend callback fails for one * of the other devices that the PM core has unsuccessfully attempted to * suspend earlier). - * The PM core executes @complete() after it has executed the appropriate - * resume callback for all devices. + * The PM core executes subsystem-level @complete() after it has executed + * the appropriate resume callbacks for all devices. * * @suspend: Executed before putting the system into a sleep state in which the - * contents of main memory are preserved. Quiesce the device, put it into - * a low power state appropriate for the upcoming system state (such as - * PCI_D3hot), and enable wakeup events as appropriate. + * contents of main memory are preserved. The exact action to perform + * depends on the device's subsystem (PM domain, device type, class or bus + * type), but generally the device must be quiescent after subsystem-level + * @suspend() has returned, so that it doesn't do any I/O or DMA. + * Subsystem-level @suspend() is executed for all devices after invoking + * subsystem-level @prepare() for all of them. * * @resume: Executed after waking the system up from a sleep state in which the - * contents of main memory were preserved. Put the device into the - * appropriate state, according to the information saved in memory by the - * preceding @suspend(). The driver starts working again, responding to - * hardware events and software requests. The hardware may have gone - * through a power-off reset, or it may have maintained state from the - * previous suspend() which the driver may rely on while resuming. On most - * platforms, there are no restrictions on availability of resources like - * clocks during @resume(). + * contents of main memory were preserved. The exact action to perform + * depends on the device's subsystem, but generally the driver is expected + * to start working again, responding to hardware events and software + * requests (the device itself may be left in a low-power state, waiting + * for a runtime resume to occur). The state of the device at the time its + * driver's @resume() callback is run depends on the platform and subsystem + * the device belongs to. On most platforms, there are no restrictions on + * availability of resources like clocks during @resume(). + * Subsystem-level @resume() is executed for all devices after invoking + * subsystem-level @resume_noirq() for all of them. * * @freeze: Hibernation-specific, executed before creating a hibernation image. - * Quiesce operations so that a consistent image can be created, but do NOT - * otherwise put the device into a low power device state and do NOT emit - * system wakeup events. Save in main memory the device settings to be - * used by @restore() during the subsequent resume from hibernation or by - * the subsequent @thaw(), if the creation of the image or the restoration - * of main memory contents from it fails. + * Analogous to @suspend(), but it should not enable the device to signal + * wakeup events or change its power state. The majority of subsystems + * (with the notable exception of the PCI bus type) expect the driver-level + * @freeze() to save the device settings in memory to be used by @restore() + * during the subsequent resume from hibernation. + * Subsystem-level @freeze() is executed for all devices after invoking + * subsystem-level @prepare() for all of them. * * @thaw: Hibernation-specific, executed after creating a hibernation image OR - * if the creation of the image fails. Also executed after a failing + * if the creation of an image has failed. Also executed after a failing * attempt to restore the contents of main memory from such an image. * Undo the changes made by the preceding @freeze(), so the device can be * operated in the same way as immediately before the call to @freeze(). + * Subsystem-level @thaw() is executed for all devices after invoking + * subsystem-level @thaw_noirq() for all of them. It also may be executed + * directly after @freeze() in case of a transition error. * * @poweroff: Hibernation-specific, executed after saving a hibernation image. - * Quiesce the device, put it into a low power state appropriate for the - * upcoming system state (such as PCI_D3hot), and enable wakeup events as - * appropriate. + * Analogous to @suspend(), but it need not save the device's settings in + * memory. + * Subsystem-level @poweroff() is executed for all devices after invoking + * subsystem-level @prepare() for all of them. * * @restore: Hibernation-specific, executed after restoring the contents of main - * memory from a hibernation image. Driver starts working again, - * responding to hardware events and software requests. Drivers may NOT - * make ANY assumptions about the hardware state right prior to @restore(). - * On most platforms, there are no restrictions on availability of - * resources like clocks during @restore(). - * - * @suspend_noirq: Complete the operations of ->suspend() by carrying out any - * actions required for suspending the device that need interrupts to be - * disabled - * - * @resume_noirq: Prepare for the execution of ->resume() by carrying out any - * actions required for resuming the device that need interrupts to be - * disabled - * - * @freeze_noirq: Complete the operations of ->freeze() by carrying out any - * actions required for freezing the device that need interrupts to be - * disabled - * - * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any - * actions required for thawing the device that need interrupts to be - * disabled - * - * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any - * actions required for handling the device that need interrupts to be - * disabled - * - * @restore_noirq: Prepare for the execution of ->restore() by carrying out any - * actions required for restoring the operations of the device that need - * interrupts to be disabled + * memory from a hibernation image, analogous to @resume(). + * + * @suspend_noirq: Complete the actions started by @suspend(). Carry out any + * additional operations required for suspending the device that might be + * racing with its driver's interrupt handler, which is guaranteed not to + * run while @suspend_noirq() is being executed. + * It generally is expected that the device will be in a low-power state + * (appropriate for the target system sleep state) after subsystem-level + * @suspend_noirq() has returned successfully. If the device can generate + * system wakeup signals and is enabled to wake up the system, it should be + * configured to do so at that time. However, depending on the platform + * and device's subsystem, @suspend() may be allowed to put the device into + * the low-power state and configure it to generate wakeup signals, in + * which case it generally is not necessary to define @suspend_noirq(). + * + * @resume_noirq: Prepare for the execution of @resume() by carrying out any + * operations required for resuming the device that might be racing with + * its driver's interrupt handler, which is guaranteed not to run while + * @resume_noirq() is being executed. + * + * @freeze_noirq: Complete the actions started by @freeze(). Carry out any + * additional operations required for freezing the device that might be + * racing with its driver's interrupt handler, which is guaranteed not to + * run while @freeze_noirq() is being executed. + * The power state of the device should not be changed by either @freeze() + * or @freeze_noirq() and it should not be configured to signal system + * wakeup by any of these callbacks. + * + * @thaw_noirq: Prepare for the execution of @thaw() by carrying out any + * operations required for thawing the device that might be racing with its + * driver's interrupt handler, which is guaranteed not to run while + * @thaw_noirq() is being executed. + * + * @poweroff_noirq: Complete the actions started by @poweroff(). Analogous to + * @suspend_noirq(), but it need not save the device's settings in memory. + * + * @restore_noirq: Prepare for the execution of @restore() by carrying out any + * operations required for thawing the device that might be racing with its + * driver's interrupt handler, which is guaranteed not to run while + * @restore_noirq() is being executed. Analogous to @resume_noirq(). * * All of the above callbacks, except for @complete(), return error codes. * However, the error codes returned by the resume operations, @resume(), - * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq() do + * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do * not cause the PM core to abort the resume transition during which they are - * returned. The error codes returned in that cases are only printed by the PM + * returned. The error codes returned in those cases are only printed by the PM * core to the system logs for debugging purposes. Still, it is recommended * that drivers only return error codes from their resume methods in case of an * unrecoverable failure (i.e. when the device being handled refuses to resume @@ -174,31 +201,43 @@ typedef struct pm_message { * their children. * * It is allowed to unregister devices while the above callbacks are being - * executed. However, it is not allowed to unregister a device from within any - * of its own callbacks. + * executed. However, a callback routine must NOT try to unregister the device + * it was called for, although it may unregister children of that device (for + * example, if it detects that a child was unplugged while the system was + * asleep). + * + * Refer to Documentation/power/devices.txt for more information about the role + * of the above callbacks in the system suspend process. * - * There also are the following callbacks related to run-time power management - * of devices: + * There also are callbacks related to runtime power management of devices. + * Again, these callbacks are executed by the PM core only for subsystems + * (PM domains, device types, classes and bus types) and the subsystem-level + * callbacks are supposed to invoke the driver callbacks. Moreover, the exact + * actions to be performed by a device driver's callbacks generally depend on + * the platform and subsystem the device belongs to. * * @runtime_suspend: Prepare the device for a condition in which it won't be * able to communicate with the CPU(s) and RAM due to power management. - * This need not mean that the device should be put into a low power state. + * This need not mean that the device should be put into a low-power state. * For example, if the device is behind a link which is about to be turned * off, the device may remain at full power. If the device does go to low - * power and is capable of generating run-time wake-up events, remote - * wake-up (i.e., a hardware mechanism allowing the device to request a - * change of its power state via a wake-up event, such as PCI PME) should - * be enabled for it. + * power and is capable of generating runtime wakeup events, remote wakeup + * (i.e., a hardware mechanism allowing the device to request a change of + * its power state via an interrupt) should be enabled for it. * * @runtime_resume: Put the device into the fully active state in response to a - * wake-up event generated by hardware or at the request of software. If - * necessary, put the device into the full power state and restore its + * wakeup event generated by hardware or at the request of software. If + * necessary, put the device into the full-power state and restore its * registers, so that it is fully operational. * - * @runtime_idle: Device appears to be inactive and it might be put into a low - * power state if all of the necessary conditions are satisfied. Check + * @runtime_idle: Device appears to be inactive and it might be put into a + * low-power state if all of the necessary conditions are satisfied. Check * these conditions and handle the device as appropriate, possibly queueing * a suspend request for it. The return value is ignored by the PM core. + * + * Refer to Documentation/power/runtime_pm.txt for more information about the + * role of the above callbacks in device runtime power management. + * */ struct dev_pm_ops { -- cgit v1.3-14-g43fede