From fae1fa0fc6cca8beee3ab8ed71d54f9a78fa3f64 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 1 May 2018 15:31:45 -0700 Subject: proc: Provide details on speculation flaw mitigations As done with seccomp and no_new_privs, also show speculation flaw mitigation state in /proc/$pid/status. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner --- fs/proc/array.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index ae2c807fd719..303c155f9b04 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -85,6 +85,7 @@ #include #include #include +#include #include #include #include @@ -335,6 +336,27 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif + seq_printf(m, "\nSpeculation Store Bypass:\t"); + switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { + case -EINVAL: + seq_printf(m, "unknown"); + break; + case PR_SPEC_NOT_AFFECTED: + seq_printf(m, "not vulnerable"); + break; + case PR_SPEC_PRCTL | PR_SPEC_DISABLE: + seq_printf(m, "thread mitigated"); + break; + case PR_SPEC_PRCTL | PR_SPEC_ENABLE: + seq_printf(m, "thread vulnerable"); + break; + case PR_SPEC_DISABLE: + seq_printf(m, "globally mitigated"); + break; + default: + seq_printf(m, "vulnerable"); + break; + } seq_putc(m, '\n'); } -- cgit From 356e4bfff2c5489e016fdb925adbf12a1e3950ee Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 3 May 2018 22:09:15 +0200 Subject: prctl: Add force disable speculation For certain use cases it is desired to enforce mitigations so they cannot be undone afterwards. That's important for loader stubs which want to prevent a child from disabling the mitigation again. Will also be used for seccomp(). The extra state preserving of the prctl state for SSB is a preparatory step for EBPF dymanic speculation control. Signed-off-by: Thomas Gleixner --- Documentation/userspace-api/spec_ctrl.rst | 34 ++++++++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 35 ++++++++++++++++++++++--------- fs/proc/array.c | 3 +++ include/linux/sched.h | 10 ++++++++- include/uapi/linux/prctl.h | 1 + 5 files changed, 59 insertions(+), 24 deletions(-) (limited to 'fs/proc/array.c') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index ddbebcd01208..1b3690d30943 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -25,19 +25,21 @@ PR_GET_SPECULATION_CTRL ----------------------- PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature -which is selected with arg2 of prctl(2). The return value uses bits 0-2 with +which is selected with arg2 of prctl(2). The return value uses bits 0-3 with the following meaning: -==== ================ =================================================== -Bit Define Description -==== ================ =================================================== -0 PR_SPEC_PRCTL Mitigation can be controlled per task by - PR_SET_SPECULATION_CTRL -1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is - disabled -2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is - enabled -==== ================ =================================================== +==== ===================== =================================================== +Bit Define Description +==== ===================== =================================================== +0 PR_SPEC_PRCTL Mitigation can be controlled per task by + PR_SET_SPECULATION_CTRL +1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is + disabled +2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is + enabled +3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A + subsequent prctl(..., PR_SPEC_ENABLE) will fail. +==== ===================== =================================================== If all bits are 0 the CPU is not affected by the speculation misfeature. @@ -47,9 +49,11 @@ misfeature will fail. PR_SET_SPECULATION_CTRL ----------------------- + PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand -in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE. +in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or +PR_SPEC_FORCE_DISABLE. Common error codes ------------------ @@ -70,10 +74,13 @@ Value Meaning 0 Success ERANGE arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor - PR_SPEC_DISABLE + PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE ENXIO Control of the selected speculation misfeature is not possible. See PR_GET_SPECULATION_CTRL. + +EPERM Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller + tried to enable it again. ======= ================================================================= Speculation misfeature controls @@ -84,3 +91,4 @@ Speculation misfeature controls * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f8d9be0e86b1..7e0f28160e5e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -533,21 +533,37 @@ static void ssb_select_mitigation() static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) { - bool rds = !!test_tsk_thread_flag(task, TIF_RDS); + bool update; if (ssb_mode != SPEC_STORE_BYPASS_PRCTL) return -ENXIO; - if (ctrl == PR_SPEC_ENABLE) - clear_tsk_thread_flag(task, TIF_RDS); - else - set_tsk_thread_flag(task, TIF_RDS); + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_RDS); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_RDS); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_RDS); + break; + default: + return -ERANGE; + } /* * If being set on non-current task, delay setting the CPU * mitigation until it is next scheduled. */ - if (task == current && rds != !!test_tsk_thread_flag(task, TIF_RDS)) + if (task == current && update) speculative_store_bypass_update(); return 0; @@ -559,7 +575,9 @@ static int ssb_prctl_get(struct task_struct *task) case SPEC_STORE_BYPASS_DISABLE: return PR_SPEC_DISABLE; case SPEC_STORE_BYPASS_PRCTL: - if (test_tsk_thread_flag(task, TIF_RDS)) + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; default: @@ -572,9 +590,6 @@ static int ssb_prctl_get(struct task_struct *task) int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { - if (ctrl != PR_SPEC_ENABLE && ctrl != PR_SPEC_DISABLE) - return -ERANGE; - switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); diff --git a/fs/proc/array.c b/fs/proc/array.c index 303c155f9b04..d178a0236514 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -344,6 +344,9 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) case PR_SPEC_NOT_AFFECTED: seq_printf(m, "not vulnerable"); break; + case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: + seq_printf(m, "thread force mitigated"); + break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: seq_printf(m, "thread mitigated"); break; diff --git a/include/linux/sched.h b/include/linux/sched.h index b3d697f3b573..e4218d4deba0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1393,7 +1393,8 @@ static inline bool is_percpu_thread(void) #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ - +#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ +#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1418,6 +1419,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) +TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) + +TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index ebf057ac1346..db9f15f5db04 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -217,5 +217,6 @@ struct prctl_mm_map { # define PR_SPEC_PRCTL (1UL << 0) # define PR_SPEC_ENABLE (1UL << 1) # define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) #endif /* _LINUX_PRCTL_H */ -- cgit From e96f46ee8587607a828f783daa6eb5b44d25004d Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 9 May 2018 21:41:38 +0200 Subject: proc: Use underscores for SSBD in 'status' The style for the 'status' file is CamelCase or this. _. Fixes: fae1fa0fc ("proc: Provide details on speculation flaw mitigations") Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Thomas Gleixner --- fs/proc/array.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index d178a0236514..72391b3f6927 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -336,7 +336,7 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif - seq_printf(m, "\nSpeculation Store Bypass:\t"); + seq_printf(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: seq_printf(m, "unknown"); -- cgit From 76f668be1e8e87d235fbd50037f50fdde948b46d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 May 2018 07:19:01 +0200 Subject: proc: introduce a proc_pid_ns helper Factor out retrieving the per-sb pid namespaces from the sb private data into an easier to understand helper. Suggested-by: Eric W. Biederman Signed-off-by: Christoph Hellwig --- fs/proc/array.c | 7 +------ fs/proc/base.c | 18 ++++++++---------- fs/proc/self.c | 4 ++-- fs/proc/thread_self.c | 4 ++-- include/linux/proc_fs.h | 6 ++++++ 5 files changed, 19 insertions(+), 20 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index ae2c807fd719..911f66924d81 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -677,12 +677,7 @@ out: static int children_seq_show(struct seq_file *seq, void *v) { - struct inode *inode = seq->private; - pid_t pid; - - pid = pid_nr_ns(v, inode->i_sb->s_fs_info); - seq_printf(seq, "%d ", pid); - + seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(seq->private))); return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 1b2ede6abcdf..29237cad19fd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -698,7 +698,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, static int proc_pid_permission(struct inode *inode, int mask) { - struct pid_namespace *pid = inode->i_sb->s_fs_info; + struct pid_namespace *pid = proc_pid_ns(inode); struct task_struct *task; bool has_perms; @@ -733,13 +733,11 @@ static const struct inode_operations proc_def_inode_operations = { static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns; - struct pid *pid; + struct pid_namespace *ns = proc_pid_ns(inode); + struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; - ns = inode->i_sb->s_fs_info; - pid = proc_pid(inode); task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; @@ -1410,7 +1408,7 @@ static const struct file_operations proc_fail_nth_operations = { static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); struct task_struct *p; p = get_proc_task(inode); @@ -1782,8 +1780,8 @@ int pid_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); + struct pid_namespace *pid = proc_pid_ns(inode); struct task_struct *task; - struct pid_namespace *pid = path->dentry->d_sb->s_fs_info; generic_fillattr(inode, stat); @@ -2337,7 +2335,7 @@ static int proc_timers_open(struct inode *inode, struct file *file) return -ENOMEM; tp->pid = proc_pid(inode); - tp->ns = inode->i_sb->s_fs_info; + tp->ns = proc_pid_ns(inode); return 0; } @@ -3239,7 +3237,7 @@ retry: int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; - struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(file_inode(file)); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) @@ -3588,7 +3586,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - ns = inode->i_sb->s_fs_info; + ns = proc_pid_ns(inode); tid = (int)file->f_version; file->f_version = 0; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); diff --git a/fs/proc/self.c b/fs/proc/self.c index 4d7d061696b3..127265e5c55f 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -12,7 +12,7 @@ static const char *proc_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; @@ -36,7 +36,7 @@ static unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = s->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; inode_lock(root_inode); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 9d2efaca499f..b905010ca9eb 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -12,7 +12,7 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; @@ -36,7 +36,7 @@ static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = s->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; inode_lock(root_inode); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 928ef9e4d912..4edcde510631 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -83,4 +83,10 @@ struct ns_common; int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); +/* get the associated pid namespace for a file in procfs */ +static inline struct pid_namespace *proc_pid_ns(struct inode *inode) +{ + return inode->i_sb->s_fs_info; +} + #endif /* _LINUX_PROC_FS_H */ -- cgit From 04015e3fa235eba28cc058c73d7d346c1bcffee8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 May 2018 07:21:53 +0200 Subject: proc: don't detour through seq->private to get the inode Signed-off-by: Christoph Hellwig --- fs/proc/array.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index 911f66924d81..4a8e413bf59b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -677,20 +677,22 @@ out: static int children_seq_show(struct seq_file *seq, void *v) { - seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(seq->private))); + struct inode *inode = file_inode(seq->file); + + seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode))); return 0; } static void *children_seq_start(struct seq_file *seq, loff_t *pos) { - return get_children_pid(seq->private, NULL, *pos); + return get_children_pid(file_inode(seq->file), NULL, *pos); } static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct pid *pid; - pid = get_children_pid(seq->private, v, *pos + 1); + pid = get_children_pid(file_inode(seq->file), v, *pos + 1); put_pid(v); ++*pos; @@ -711,17 +713,7 @@ static const struct seq_operations children_seq_ops = { static int children_seq_open(struct inode *inode, struct file *file) { - struct seq_file *m; - int ret; - - ret = seq_open(file, &children_seq_ops); - if (ret) - return ret; - - m = file->private_data; - m->private = inode; - - return ret; + return seq_open(file, &children_seq_ops); } const struct file_operations proc_tid_children_operations = { -- cgit From 88b72b31e15f9dfed069ede5416bb71040e0d299 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 18 May 2018 08:47:13 -0700 Subject: proc: Consolidate task->comm formatting into proc_task_name() proc shows task->comm in three places - comm, stat, status - and each is fetching and formatting task->comm slighly differently. This patch renames task_name() to proc_task_name(), makes it more generic, and updates all three paths to use it. This will enable expanding comm reporting for workqueue workers. Signed-off-by: Tejun Heo --- fs/proc/array.c | 26 +++++++++++++++----------- fs/proc/base.c | 5 ++--- fs/proc/internal.h | 2 ++ 3 files changed, 19 insertions(+), 14 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index ae2c807fd719..f29221e95792 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -95,7 +95,7 @@ #include #include "internal.h" -static inline void task_name(struct seq_file *m, struct task_struct *p) +void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char *buf; size_t size; @@ -104,13 +104,17 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) get_task_comm(tcomm, p); - seq_puts(m, "Name:\t"); - size = seq_get_buf(m, &buf); - ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); - seq_commit(m, ret < size ? ret : -1); + if (escape) { + ret = string_escape_str(tcomm, buf, size, + ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + if (ret >= size) + ret = -1; + } else { + ret = strscpy(buf, tcomm, size); + } - seq_putc(m, '\n'); + seq_commit(m, ret); } /* @@ -365,7 +369,10 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, { struct mm_struct *mm = get_task_mm(task); - task_name(m, task); + seq_puts(m, "Name:\t"); + proc_task_name(m, task, true); + seq_putc(m, '\n'); + task_state(m, ns, pid, task); if (mm) { @@ -400,7 +407,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cutime, cstime, utime, stime; u64 cgtime, gtime; unsigned long rsslim = 0; - char tcomm[sizeof(task->comm)]; unsigned long flags; state = *get_task_state(task); @@ -427,8 +433,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } } - get_task_comm(tcomm, task); - sigemptyset(&sigign); sigemptyset(&sigcatch); cutime = cstime = utime = stime = 0; @@ -495,7 +499,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); - seq_puts(m, tcomm); + proc_task_name(m, task, false); seq_puts(m, ") "); seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); diff --git a/fs/proc/base.c b/fs/proc/base.c index 1b2ede6abcdf..bb192a699bce 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1565,9 +1565,8 @@ static int comm_show(struct seq_file *m, void *v) if (!p) return -ESRCH; - task_lock(p); - seq_printf(m, "%s\n", p->comm); - task_unlock(p); + proc_task_name(m, p, false); + seq_putc(m, '\n'); put_task_struct(p); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 0f1692e63cb6..b823fac621d2 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -131,6 +131,8 @@ unsigned name_to_int(const struct qstr *qstr); */ extern const struct file_operations proc_tid_children_operations; +extern void proc_task_name(struct seq_file *m, struct task_struct *p, + bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, -- cgit From 6b59808bfe482642287ddf3fe9d4cccb10756652 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 18 May 2018 08:47:13 -0700 Subject: workqueue: Show the latest workqueue name in /proc/PID/{comm,stat,status} There can be a lot of workqueue workers and they all show up with the cryptic kworker/* names making it difficult to understand which is doing what and how they came to be. # ps -ef | grep kworker root 4 2 0 Feb25 ? 00:00:00 [kworker/0:0H] root 6 2 0 Feb25 ? 00:00:00 [kworker/u112:0] root 19 2 0 Feb25 ? 00:00:00 [kworker/1:0H] root 25 2 0 Feb25 ? 00:00:00 [kworker/2:0H] root 31 2 0 Feb25 ? 00:00:00 [kworker/3:0H] ... This patch makes workqueue workers report the latest workqueue it was executing for through /proc/PID/{comm,stat,status}. The extra information is appended to the kthread name with intervening '+' if currently executing, otherwise '-'. # cat /proc/25/comm kworker/2:0-events_power_efficient # cat /proc/25/stat 25 (kworker/2:0-events_power_efficient) I 2 0 0 0 -1 69238880 0 0... # grep Name /proc/25/status Name: kworker/2:0-events_power_efficient Unfortunately, ps(1) truncates comm to 15 characters, # ps 25 PID TTY STAT TIME COMMAND 25 ? I 0:00 [kworker/2:0-eve] making it a lot less useful; however, this should be an easy fix from ps(1) side. Signed-off-by: Tejun Heo Suggested-by: Linus Torvalds Cc: Craig Small --- fs/proc/array.c | 7 +++++-- include/linux/workqueue.h | 1 + kernel/workqueue.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 2 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index f29221e95792..bb1d3619ca12 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -99,10 +99,13 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char *buf; size_t size; - char tcomm[sizeof(p->comm)]; + char tcomm[64]; int ret; - get_task_comm(tcomm, p); + if (p->flags & PF_WQ_WORKER) + wq_worker_comm(tcomm, sizeof(tcomm), p); + else + __get_task_comm(tcomm, sizeof(tcomm), p); size = seq_get_buf(m, &buf); if (escape) { diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 39a0e215022a..60d673e15632 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -494,6 +494,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); +extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3fbe0076492c..b4a39a15c931 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4577,6 +4577,45 @@ void show_workqueue_state(void) rcu_read_unlock_sched(); } +/* used to show worker information through /proc/PID/{comm,stat,status} */ +void wq_worker_comm(char *buf, size_t size, struct task_struct *task) +{ + struct worker *worker; + struct worker_pool *pool; + int off; + + /* always show the actual comm */ + off = strscpy(buf, task->comm, size); + if (off < 0) + return; + + /* stabilize worker pool association */ + mutex_lock(&wq_pool_attach_mutex); + + worker = kthread_data(task); + pool = worker->pool; + + if (pool) { + spin_lock_irq(&pool->lock); + /* + * ->desc tracks information (wq name or set_worker_desc()) + * for the latest execution. If current, prepend '+', + * otherwise '-'. + */ + if (worker->desc[0] != '\0') { + if (worker->current_work) + scnprintf(buf + off, size - off, "+%s", + worker->desc); + else + scnprintf(buf + off, size - off, "-%s", + worker->desc); + } + spin_unlock_irq(&pool->lock); + } + + mutex_unlock(&wq_pool_attach_mutex); +} + /* * CPU hotplug. * -- cgit From 197850a1e04ab586953a4434a6c4c6575b7d2122 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 7 Jun 2018 17:10:13 -0700 Subject: proc: use "unsigned int" for sigqueue length It's defined as atomic_t and really long signal queues are unheard of. Link: http://lkml.kernel.org/r/20180423215119.GF9043@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index 004077f1a7bf..0ceb3b6b37e7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -268,7 +268,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; - unsigned long qsize = 0; + unsigned int qsize = 0; unsigned long qlim = 0; sigemptyset(&pending); -- cgit