From 9b1bf12d5d51bca178dea21b04a0805e29d60cf1 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 27 Oct 2010 15:34:08 -0700 Subject: signals: move cred_guard_mutex from task_struct to signal_struct Oleg Nesterov pointed out we have to prevent multiple-threads-inside-exec itself and we can reuse ->cred_guard_mutex for it. Yes, concurrent execve() has no worth. Let's move ->cred_guard_mutex from task_struct to signal_struct. It naturally prevent multiple-threads-inside-exec. Signed-off-by: KOSAKI Motohiro Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 9b094c1c8465..f3d02ca461ec 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -226,7 +226,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) { struct mm_struct *mm; - if (mutex_lock_killable(&task->cred_guard_mutex)) + if (mutex_lock_killable(&task->signal->cred_guard_mutex)) return NULL; mm = get_task_mm(task); @@ -235,7 +235,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) mmput(mm); mm = NULL; } - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); return mm; } @@ -2354,14 +2354,14 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, goto out_free; /* Guard against adverse ptrace interaction */ - length = mutex_lock_interruptible(&task->cred_guard_mutex); + length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); if (length < 0) goto out_free; length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, (void*)page, count); - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); out_free: free_page((unsigned long) page); out: -- cgit v1.2.2 From b40d4f84becd69275451baee7f0801c85eb58437 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Wed, 27 Oct 2010 15:34:10 -0700 Subject: /proc/pid/smaps: export amount of anonymous memory in a mapping Export the number of anonymous pages in a mapping via smaps. Even the private pages in a mapping backed by a file, would be marked as anonymous, when they are modified. Export this information to user-space via smaps. Exporting this count will help gdb to make a better decision on which areas need to be dumped in its coredump; and should be useful to others studying the memory usage of a process. Signed-off-by: Nikanth Karthikesan Acked-by: Hugh Dickins Reviewed-by: KOSAKI Motohiro Cc: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/proc') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 871e25ed0069..da6b01d70f01 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -327,6 +327,7 @@ struct mem_size_stats { unsigned long private_clean; unsigned long private_dirty; unsigned long referenced; + unsigned long anonymous; unsigned long swap; u64 pss; }; @@ -357,6 +358,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (!page) continue; + if (PageAnon(page)) + mss->anonymous += PAGE_SIZE; + mss->resident += PAGE_SIZE; /* Accumulate the size in pages that have been accessed. */ if (pte_young(ptent) || PageReferenced(page)) @@ -410,6 +414,7 @@ static int show_smap(struct seq_file *m, void *v) "Private_Clean: %8lu kB\n" "Private_Dirty: %8lu kB\n" "Referenced: %8lu kB\n" + "Anonymous: %8lu kB\n" "Swap: %8lu kB\n" "KernelPageSize: %8lu kB\n" "MMUPageSize: %8lu kB\n", @@ -421,6 +426,7 @@ static int show_smap(struct seq_file *m, void *v) mss.private_clean >> 10, mss.private_dirty >> 10, mss.referenced >> 10, + mss.anonymous >> 10, mss.swap >> 10, vma_kernel_pagesize(vma) >> 10, vma_mmu_pagesize(vma) >> 10); -- cgit v1.2.2 From 19cd56c48da58bebc3a638e036bcab69469acd27 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 27 Oct 2010 15:34:12 -0700 Subject: procfs: fix /proc/softirqs formatting The length of the BLOCK_IPOLL string is making i's value be printed too far to the right. This patch fixes this and makes the output a bit neater. Currently: CPU0 HI: 0 TIMER: 599792 NET_TX: 2 NET_RX: 6 BLOCK: 80807 BLOCK_IOPOLL: 0 TASKLET: 20012 SCHED: 0 HRTIMER: 63 RCU: 619279 With patch: CPU0 HI: 0 TIMER: 585582 NET_TX: 2 NET_RX: 6 BLOCK: 80320 BLOCK_IOPOLL: 0 TASKLET: 19287 SCHED: 0 HRTIMER: 62 RCU: 604441 Signed-off-by: Davidlohr Bueso Acked-by: Keika Kobayashi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/softirqs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 1807c2419f17..37994737c983 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -10,13 +10,13 @@ static int show_softirqs(struct seq_file *p, void *v) { int i, j; - seq_printf(p, " "); + seq_printf(p, " "); for_each_possible_cpu(i) seq_printf(p, "CPU%-8d", i); seq_printf(p, "\n"); for (i = 0; i < NR_SOFTIRQS; i++) { - seq_printf(p, "%8s:", softirq_to_name[i]); + seq_printf(p, "%12s:", softirq_to_name[i]); for_each_possible_cpu(j) seq_printf(p, " %10u", kstat_softirqs_cpu(i, j)); seq_printf(p, "\n"); -- cgit v1.2.2 From f2c66cd8eeddedb440f33bc0f5cec1ed7ae376cb Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 27 Oct 2010 15:34:13 -0700 Subject: /proc/stat: scalability of irq num per cpu /proc/stat shows the total number of all interrupts to each cpu. But when the number of IRQs are very large, it take very long time and 'cat /proc/stat' takes more than 10 secs. This is because sum of all irq events are counted when /proc/stat is read. This patch adds "sum of all irq" counter percpu and reduce read costs. The cost of reading /proc/stat is important because it's used by major applications as 'top', 'ps', 'w', etc.... A test on a mechin (4096cpu, 256 nodes, 4592 irqs) shows %time cat /proc/stat > /dev/null Before Patch: 12.627 sec After Patch: 2.459 sec Signed-off-by: KAMEZAWA Hiroyuki Tested-by: Jack Steiner Acked-by: Jack Steiner Cc: Yinghai Lu Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/stat.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index bf31b03fc275..b80c620565bf 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -52,9 +52,7 @@ static int show_stat(struct seq_file *p, void *v) guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); guest_nice = cputime64_add(guest_nice, kstat_cpu(i).cpustat.guest_nice); - for_each_irq_nr(j) { - sum += kstat_irqs_cpu(j, i); - } + sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); for (j = 0; j < NR_SOFTIRQS; j++) { -- cgit v1.2.2 From 478735e38887077ac77a9756121b6ce0cb956e2f Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 27 Oct 2010 15:34:15 -0700 Subject: /proc/stat: fix scalability of irq sum of all cpu In /proc/stat, the number of per-IRQ event is shown by making a sum each irq's events on all cpus. But we can make use of kstat_irqs(). kstat_irqs() do the same calculation, If !CONFIG_GENERIC_HARDIRQ, it's not a big cost. (Both of the number of cpus and irqs are small.) If a system is very big and CONFIG_GENERIC_HARDIRQ, it does for_each_irq() for_each_cpu() - look up a radix tree - read desc->irq_stat[cpu] This seems not efficient. This patch adds kstat_irqs() for CONFIG_GENRIC_HARDIRQ and change the calculation as for_each_irq() look up radix tree for_each_cpu() - read desc->irq_stat[cpu] This reduces cost. A test on (4096cpusp, 256 nodes, 4592 irqs) host (by Jack Steiner) %time cat /proc/stat > /dev/null Before Patch: 2.459 sec After Patch : .561 sec [akpm@linux-foundation.org: unexport kstat_irqs, coding-style tweaks] [akpm@linux-foundation.org: fix unused variable 'per_irq_sum'] Signed-off-by: KAMEZAWA Hiroyuki Tested-by: Jack Steiner Acked-by: Jack Steiner Cc: Yinghai Lu Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/stat.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index b80c620565bf..e15a19c93bae 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -31,7 +31,6 @@ static int show_stat(struct seq_file *p, void *v) u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; struct timespec boottime; - unsigned int per_irq_sum; user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; @@ -108,13 +107,8 @@ static int show_stat(struct seq_file *p, void *v) seq_printf(p, "intr %llu", (unsigned long long)sum); /* sum again ? it could be updated? */ - for_each_irq_nr(j) { - per_irq_sum = 0; - for_each_possible_cpu(i) - per_irq_sum += kstat_irqs_cpu(j, i); - - seq_printf(p, " %u", per_irq_sum); - } + for_each_irq_nr(j) + seq_printf(p, " %u", kstat_irqs(j)); seq_printf(p, "\nctxt %llu\n" -- cgit v1.2.2 From 579441a39bbbbc408acd5b228d63e76cff708fe6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 26 Jul 2010 13:09:36 +0400 Subject: setting ->proc_mnt doesn't belong in proc_get_sb() take that to kern_mount_data()-using callers Signed-off-by: Al Viro --- fs/proc/root.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/root.c b/fs/proc/root.c index 93d99b316325..03b4f6fe4984 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -79,7 +79,6 @@ static int proc_get_sb(struct file_system_type *fs_type, } sb->s_flags |= MS_ACTIVE; - ns->proc_mnt = mnt; } simple_set_mnt(mnt, sb); @@ -115,6 +114,7 @@ void __init proc_root_init(void) return; } + init_pid_ns.proc_mnt = proc_mnt; proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); @@ -213,6 +213,7 @@ int pid_ns_prepare_proc(struct pid_namespace *ns) if (IS_ERR(mnt)) return PTR_ERR(mnt); + ns->proc_mnt = mnt; return 0; } -- cgit v1.2.2 From aed1d84f98738bcc1c605e1ff442de9890441315 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 26 Jul 2010 13:12:54 +0400 Subject: switch procfs to ->mount() Signed-off-by: Al Viro --- fs/proc/root.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/root.c b/fs/proc/root.c index 03b4f6fe4984..ef9fa8e24ad6 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -35,8 +35,8 @@ static int proc_set_super(struct super_block *sb, void *data) return set_anon_super(sb, NULL); } -static int proc_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *proc_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { int err; struct super_block *sb; @@ -61,14 +61,14 @@ static int proc_get_sb(struct file_system_type *fs_type, sb = sget(fs_type, proc_test_super, proc_set_super, ns); if (IS_ERR(sb)) - return PTR_ERR(sb); + return ERR_CAST(sb); if (!sb->s_root) { sb->s_flags = flags; err = proc_fill_super(sb); if (err) { deactivate_locked_super(sb); - return err; + return ERR_PTR(err); } ei = PROC_I(sb->s_root->d_inode); @@ -81,8 +81,7 @@ static int proc_get_sb(struct file_system_type *fs_type, sb->s_flags |= MS_ACTIVE; } - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); } static void proc_kill_sb(struct super_block *sb) @@ -96,7 +95,7 @@ static void proc_kill_sb(struct super_block *sb) static struct file_system_type proc_fs_type = { .name = "proc", - .get_sb = proc_get_sb, + .mount = proc_mount, .kill_sb = proc_kill_sb, }; -- cgit v1.2.2