From 98a1eebda3cb2a84ecf1f219bb3a95769033d1bf Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 10 Oct 2012 10:55:28 +0300 Subject: UBIFS: introduce categorized lprops counter This commit is a preparation for a subsequent bugfix. We introduce a counter for categorized lprops. Signed-off-by: Artem Bityutskiy Cc: stable@vger.kernel.org --- fs/ubifs/lprops.c | 6 ++++++ fs/ubifs/ubifs.h | 3 +++ 2 files changed, 9 insertions(+) (limited to 'fs') diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index e5a2a35a46dc..46190a7c42a6 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops, default: ubifs_assert(0); } + lprops->flags &= ~LPROPS_CAT_MASK; lprops->flags |= cat; + c->in_a_category_cnt += 1; + ubifs_assert(c->in_a_category_cnt <= c->main_lebs); } /** @@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c, default: ubifs_assert(0); } + + c->in_a_category_cnt -= 1; + ubifs_assert(c->in_a_category_cnt >= 0); } /** diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 5486346d0a3f..d133c276fe05 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1183,6 +1183,8 @@ struct ubifs_debug_info; * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size) * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size) * @freeable_cnt: number of freeable LEBs in @freeable_list + * @in_a_category_cnt: count of lprops which are in a certain category, which + * basically meants that they were loaded from the flash * * @ltab_lnum: LEB number of LPT's own lprops table * @ltab_offs: offset of LPT's own lprops table @@ -1412,6 +1414,7 @@ struct ubifs_info { struct list_head freeable_list; struct list_head frdi_idx_list; int freeable_cnt; + int in_a_category_cnt; int ltab_lnum; int ltab_offs; -- cgit v1.2.3 From a28ad42a4a0c6f302f488f26488b8b37c9b30024 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 9 Oct 2012 16:20:15 +0300 Subject: UBIFS: fix mounting problems after power cuts This is a bugfix for a problem with the following symptoms: 1. A power cut happens 2. After reboot, we try to mount UBIFS 3. Mount fails with "No space left on device" error message UBIFS complains like this: UBIFS error (pid 28225): grab_empty_leb: could not find an empty LEB The root cause of this problem is that when we mount, not all LEBs are categorized. Only those which were read are. However, the 'ubifs_find_free_leb_for_idx()' function assumes that all LEBs were categorized and 'c->freeable_cnt' is valid, which is a false assumption. This patch fixes the problem by teaching 'ubifs_find_free_leb_for_idx()' to always fall back to LPT scanning if no freeable LEBs were found. This problem was reported by few people in the past, but Brent Taylor was able to reproduce it and send me a flash image which cannot be mounted, which made it easy to hunt the bug. Kudos to Brent. Reported-by: Brent Taylor Signed-off-by: Artem Bityutskiy Cc: stable@vger.kernel.org --- fs/ubifs/find.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 28ec13af28d9..2dcf3d473fec 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c) if (!lprops) { lprops = ubifs_fast_find_freeable(c); if (!lprops) { - ubifs_assert(c->freeable_cnt == 0); - if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + /* + * The first condition means the following: go scan the + * LPT if there are uncategorized lprops, which means + * there may be freeable LEBs there (UBIFS does not + * store the information about freeable LEBs in the + * master node). + */ + if (c->in_a_category_cnt != c->main_lebs || + c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + ubifs_assert(c->freeable_cnt == 0); lprops = scan_for_leb_for_idx(c); if (IS_ERR(lprops)) { err = PTR_ERR(lprops); -- cgit v1.2.3 From 70a6f46d7b0ec03653b9ab3f8063a9717a4a53ef Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 14 Nov 2012 11:49:53 +0000 Subject: pstore: Fix NULL pointer dereference in console writes Passing a NULL id causes a NULL pointer deference in writers such as erst_writer and efi_pstore_write because they expect to update this id. Pass a dummy id instead. This avoids a cascade of oopses caused when the initial pstore_console_write passes a null which in turn causes writes to the console causing further oopses in subsequent pstore_console_write calls. Signed-off-by: Colin Ian King Acked-by: Kees Cook Cc: stable@vger.kernel.org Signed-off-by: Anton Vorontsov --- fs/pstore/platform.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index a40da07e93d6..947fbe06c3b1 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -161,6 +161,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) while (s < e) { unsigned long flags; + u64 id; if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -172,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) spin_lock_irqsave(&psinfo->buf_lock, flags); } memcpy(psinfo->buf, s, c); - psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo); + psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; -- cgit v1.2.3 From fa0cbbf145aabbf29c6f28f8a11935c0b0fd86fc Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 12 Nov 2012 17:53:04 -0800 Subject: mm, oom: reintroduce /proc/pid/oom_adj This is mostly a revert of 01dc52ebdf47 ("oom: remove deprecated oom_adj") from Davidlohr Bueso. It reintroduces /proc/pid/oom_adj for backwards compatibility with earlier kernels. It simply scales the value linearly when /proc/pid/oom_score_adj is written. The major difference is that its scheduled removal is no longer included in Documentation/feature-removal-schedule.txt. We do warn users with a single printk, though, to suggest the more powerful and supported /proc/pid/oom_score_adj interface. Reported-by: Artem S. Tashkinov Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 16 ++++-- fs/proc/base.c | 109 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/oom.h | 9 +++ 3 files changed, 130 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index a1793d670cd0..3844d21d6ca3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -33,7 +33,7 @@ Table of Contents 2 Modifying System Parameters 3 Per-Process Parameters - 3.1 /proc//oom_score_adj - Adjust the oom-killer + 3.1 /proc//oom_adj & /proc//oom_score_adj - Adjust the oom-killer score 3.2 /proc//oom_score - Display current oom-killer score 3.3 /proc//io - Display the IO accounting fields @@ -1320,10 +1320,10 @@ of the kernel. CHAPTER 3: PER-PROCESS PARAMETERS ------------------------------------------------------------------------------ -3.1 /proc//oom_score_adj- Adjust the oom-killer score +3.1 /proc//oom_adj & /proc//oom_score_adj- Adjust the oom-killer score -------------------------------------------------------------------------------- -This file can be used to adjust the badness heuristic used to select which +These file can be used to adjust the badness heuristic used to select which process gets killed in out of memory conditions. The badness heuristic assigns a value to each candidate task ranging from 0 @@ -1361,6 +1361,12 @@ same system, cpuset, mempolicy, or memory controller resources to use at least equivalent to discounting 50% of the task's allowed memory from being considered as scoring against the task. +For backwards compatibility with previous kernels, /proc//oom_adj may also +be used to tune the badness score. Its acceptable values range from -16 +(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 +(OOM_DISABLE) to disable oom killing entirely for that task. Its value is +scaled linearly with /proc//oom_score_adj. + The value of /proc//oom_score_adj may be reduced no lower than the last value set by a CAP_SYS_RESOURCE process. To reduce the value any lower requires CAP_SYS_RESOURCE. @@ -1375,7 +1381,9 @@ minimal amount of work. ------------------------------------------------------------- This file can be used to check the current score used by the oom-killer is for -any given . +any given . Use it together with /proc//oom_score_adj to tune which +process should be killed in an out-of-memory situation. + 3.3 /proc//io - Display the IO accounting fields ------------------------------------------------------- diff --git a/fs/proc/base.c b/fs/proc/base.c index 144a96732dd7..3c231adf8450 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = { .release = mem_release, }; +static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, +}; + static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -2598,6 +2705,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), @@ -2964,6 +3072,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), diff --git a/include/uapi/linux/oom.h b/include/uapi/linux/oom.h index a49c4afc7060..b29272d621ce 100644 --- a/include/uapi/linux/oom.h +++ b/include/uapi/linux/oom.h @@ -8,4 +8,13 @@ #define OOM_SCORE_ADJ_MIN (-1000) #define OOM_SCORE_ADJ_MAX 1000 +/* + * /proc//oom_adj set to -17 protects from the oom killer for legacy + * purposes. + */ +#define OOM_DISABLE (-17) +/* inclusive */ +#define OOM_ADJUST_MIN (-16) +#define OOM_ADJUST_MAX 15 + #endif /* _UAPI__INCLUDE_LINUX_OOM_H */ -- cgit v1.2.3