diff options
Diffstat (limited to 'fs/proc')
-rw-r--r-- | fs/proc/Kconfig | 7 | ||||
-rw-r--r-- | fs/proc/array.c | 140 | ||||
-rw-r--r-- | fs/proc/base.c | 449 | ||||
-rw-r--r-- | fs/proc/bootconfig.c | 17 | ||||
-rw-r--r-- | fs/proc/cpuinfo.c | 9 | ||||
-rw-r--r-- | fs/proc/devices.c | 7 | ||||
-rw-r--r-- | fs/proc/fd.c | 94 | ||||
-rw-r--r-- | fs/proc/fd.h | 3 | ||||
-rw-r--r-- | fs/proc/generic.c | 100 | ||||
-rw-r--r-- | fs/proc/inode.c | 425 | ||||
-rw-r--r-- | fs/proc/internal.h | 38 | ||||
-rw-r--r-- | fs/proc/kcore.c | 86 | ||||
-rw-r--r-- | fs/proc/kmsg.c | 4 | ||||
-rw-r--r-- | fs/proc/loadavg.c | 8 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 42 | ||||
-rw-r--r-- | fs/proc/nommu.c | 2 | ||||
-rw-r--r-- | fs/proc/page.c | 7 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 79 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 458 | ||||
-rw-r--r-- | fs/proc/proc_tty.c | 2 | ||||
-rw-r--r-- | fs/proc/root.c | 177 | ||||
-rw-r--r-- | fs/proc/self.c | 10 | ||||
-rw-r--r-- | fs/proc/softirqs.c | 6 | ||||
-rw-r--r-- | fs/proc/stat.c | 14 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 512 | ||||
-rw-r--r-- | fs/proc/task_nommu.c | 61 | ||||
-rw-r--r-- | fs/proc/thread_self.c | 10 | ||||
-rw-r--r-- | fs/proc/uptime.c | 20 | ||||
-rw-r--r-- | fs/proc/version.c | 6 | ||||
-rw-r--r-- | fs/proc/vmcore.c | 250 |
30 files changed, 1984 insertions, 1059 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 27ef84d99f59..32b1116ae137 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -23,7 +23,7 @@ config PROC_FS /proc" or the equivalent line in /etc/fstab does the job. The /proc file system is explained in the file - <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage + <file:Documentation/filesystems/proc.rst> and on the proc(5) manpage ("man 5 proc"). This option will enlarge your kernel by about 67 KB. Several @@ -66,7 +66,7 @@ config PROC_SYSCTL depends on PROC_FS select SYSCTL default y - ---help--- + help The sysctl interface provides a means of dynamically changing certain kernel parameters and variables on the fly without requiring a recompile of the kernel or reboot of the system. The primary @@ -92,10 +92,11 @@ config PROC_PAGE_MONITOR config PROC_CHILDREN bool "Include /proc/<pid>/task/<tid>/children file" + depends on PROC_FS default n help Provides a fast way to retrieve first level children pids of a task. See - <file:Documentation/filesystems/proc.txt> for more information. + <file:Documentation/filesystems/proc.rst> for more information. Say Y if you are running any user-space software which takes benefit from this interface. For example, rkt is such a piece of software. diff --git a/fs/proc/array.c b/fs/proc/array.c index 5efaf3708ec6..49283b8103c7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -56,6 +56,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/time.h> +#include <linux/time_namespace.h> #include <linux/kernel.h> #include <linux/kernel_stat.h> #include <linux/tty.h> @@ -68,7 +69,6 @@ #include <linux/sched/cputime.h> #include <linux/proc_fs.h> #include <linux/ioport.h> -#include <linux/uaccess.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/hugetlb.h> @@ -87,38 +87,33 @@ #include <linux/pid_namespace.h> #include <linux/prctl.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/string_helpers.h> #include <linux/user_namespace.h> #include <linux/fs_struct.h> +#include <linux/kthread.h> -#include <asm/pgtable.h> #include <asm/processor.h> #include "internal.h" void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { - char *buf; - size_t size; char tcomm[64]; - int ret; + /* + * Test before PF_KTHREAD because all workqueue worker threads are + * kernel threads. + */ if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); + else if (p->flags & PF_KTHREAD) + get_kthread_comm(tcomm, sizeof(tcomm), p); else __get_task_comm(tcomm, sizeof(tcomm), p); - size = seq_get_buf(m, &buf); - 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_commit(m, ret); + if (escape) + seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + else + seq_printf(m, "%.64s", tcomm); } /* @@ -248,8 +243,8 @@ void render_sigset_t(struct seq_file *m, const char *header, seq_putc(m, '\n'); } -static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, - sigset_t *catch) +static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *sigign, + sigset_t *sigcatch) { struct k_sigaction *k; int i; @@ -257,9 +252,9 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, k = p->sighand->action; for (i = 1; i <= _NSIG; ++i, ++k) { if (k->sa.sa_handler == SIG_IGN) - sigaddset(ign, i); + sigaddset(sigign, i); else if (k->sa.sa_handler != SIG_DFL) - sigaddset(catch, i); + sigaddset(sigcatch, i); } } @@ -284,7 +279,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) collect_sigign_sigcatch(p, &ignored, &caught); num_threads = get_nr_threads(p); rcu_read_lock(); /* FIXME: is this correct? */ - qsize = atomic_read(&__task_cred(p)->user->sigpending); + qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); @@ -342,6 +337,10 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p)); #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); +#ifdef CONFIG_SECCOMP_FILTER + seq_put_decimal_ull(m, "\nSeccomp_filters:\t", + atomic_read(&p->seccomp.filter_count)); +#endif #endif seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { @@ -367,6 +366,34 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) seq_puts(m, "vulnerable"); break; } + + seq_puts(m, "\nSpeculationIndirectBranch:\t"); + switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_INDIRECT_BRANCH)) { + case -EINVAL: + seq_puts(m, "unsupported"); + break; + case PR_SPEC_NOT_AFFECTED: + seq_puts(m, "not affected"); + break; + case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: + seq_puts(m, "conditional force disabled"); + break; + case PR_SPEC_PRCTL | PR_SPEC_DISABLE: + seq_puts(m, "conditional disabled"); + break; + case PR_SPEC_PRCTL | PR_SPEC_ENABLE: + seq_puts(m, "conditional enabled"); + break; + case PR_SPEC_ENABLE: + seq_puts(m, "always enabled"); + break; + case PR_SPEC_DISABLE: + seq_puts(m, "always disabled"); + break; + default: + seq_puts(m, "unknown"); + break; + } seq_putc(m, '\n'); } @@ -381,14 +408,14 @@ static inline void task_context_switch_counts(struct seq_file *m, static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", - cpumask_pr_args(task->cpus_ptr)); + cpumask_pr_args(&task->cpus_mask)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", - cpumask_pr_args(task->cpus_ptr)); + cpumask_pr_args(&task->cpus_mask)); } -static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) +static inline void task_core_dumping(struct seq_file *m, struct task_struct *task) { - seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state); + seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state); seq_putc(m, '\n'); } @@ -414,7 +441,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, if (mm) { task_mem(m, mm); - task_core_dumping(m, mm); + task_core_dumping(m, task); task_thp_status(m, mm); mmput(mm); } @@ -446,6 +473,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cgtime, gtime; unsigned long rsslim = 0; unsigned long flags; + int exit_code = task->exit_code; state = *get_task_state(task); vsize = eip = esp = 0; @@ -509,6 +537,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, maj_flt += sig->maj_flt; thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; + + if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) + exit_code = sig->group_exit_code; } sid = task_session_nr_ns(task, ns); @@ -519,7 +550,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } if (permitted && (!whole || num_threads < 2)) - wchan = get_wchan(task); + wchan = !task_is_running(task); if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; @@ -532,8 +563,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, priority = task_prio(task); nice = task_nice(task); - /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(task->start_boottime); + /* apply timens offset for boottime and convert nsec -> ticks */ + start_time = + nsec_to_clock_t(timens_add_boottime_ns(task->start_boottime)); seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); @@ -583,10 +615,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * * This works with older implementations of procps as well. */ - if (wchan) - seq_puts(m, " 1"); - else - seq_puts(m, " 0"); + seq_put_decimal_ull(m, " ", wchan); seq_put_decimal_ull(m, " ", 0); seq_put_decimal_ull(m, " ", 0); @@ -610,7 +639,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_puts(m, " 0 0 0 0 0 0 0"); if (permitted) - seq_put_decimal_ll(m, " ", task->exit_code); + seq_put_decimal_ll(m, " ", exit_code); else seq_puts(m, " 0"); @@ -635,28 +664,35 @@ int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns, int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0; struct mm_struct *mm = get_task_mm(task); if (mm) { + unsigned long size; + unsigned long resident = 0; + unsigned long shared = 0; + unsigned long text = 0; + unsigned long data = 0; + size = task_statm(mm, &shared, &text, &data, &resident); mmput(mm); - } - /* - * For quick read, open code by putting numbers directly - * expected format is - * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", - * size, resident, shared, text, data); - */ - seq_put_decimal_ull(m, "", size); - seq_put_decimal_ull(m, " ", resident); - seq_put_decimal_ull(m, " ", shared); - seq_put_decimal_ull(m, " ", text); - seq_put_decimal_ull(m, " ", 0); - seq_put_decimal_ull(m, " ", data); - seq_put_decimal_ull(m, " ", 0); - seq_putc(m, '\n'); + /* + * For quick read, open code by putting numbers directly + * expected format is + * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n", + * size, resident, shared, text, data); + */ + seq_put_decimal_ull(m, "", size); + seq_put_decimal_ull(m, " ", resident); + seq_put_decimal_ull(m, " ", shared); + seq_put_decimal_ull(m, " ", text); + seq_put_decimal_ull(m, " ", 0); + seq_put_decimal_ull(m, " ", data); + seq_put_decimal_ull(m, " ", 0); + seq_putc(m, '\n'); + } else { + seq_write(m, "0 0 0 0 0 0 0\n", 14); + } return 0; } @@ -721,7 +757,7 @@ static int children_seq_show(struct seq_file *seq, void *v) { struct inode *inode = file_inode(seq->file); - seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode))); + seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode->i_sb))); return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index c7c64272b0fa..9e479d7d202b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -74,7 +74,6 @@ #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> @@ -96,6 +95,7 @@ #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> +#include <linux/cn_proc.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" @@ -405,11 +405,11 @@ print0: static int lock_trace(struct task_struct *task) { - int err = mutex_lock_killable(&task->signal->cred_guard_mutex); + int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { - mutex_unlock(&task->signal->cred_guard_mutex); + up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; @@ -417,7 +417,7 @@ static int lock_trace(struct task_struct *task) static void unlock_trace(struct task_struct *task) { - mutex_unlock(&task->signal->cred_guard_mutex); + up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE @@ -551,8 +551,17 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; + long badness; + + badness = oom_badness(task, totalpages); + /* + * Special case OOM_SCORE_ADJ_MIN for all others scale the + * badness value into [0, 2000] range which we have been + * exporting for a long time so userspace might depend on it. + */ + if (badness != LONG_MIN) + points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; - points = oom_badness(task, totalpages) * 1000 / totalpages; seq_printf(m, "%lu\n", points); return 0; @@ -660,10 +669,10 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, /************************************************************************/ /* permission checks */ -static int proc_fd_access_allowed(struct inode *inode) +static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; - int allowed = 0; + bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. @@ -676,7 +685,8 @@ static int proc_fd_access_allowed(struct inode *inode) return allowed; } -int proc_setattr(struct dentry *dentry, struct iattr *attr) +int proc_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); @@ -684,11 +694,11 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) return -EPERM; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } @@ -697,32 +707,41 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ -static bool has_pid_permissions(struct pid_namespace *pid, +static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, - int hide_pid_min) + enum proc_hidepid hide_pid_min) { - if (pid->hide_pid < hide_pid_min) + /* + * If 'hidpid' mount option is set force a ptrace check, + * we indicate that we are using a filesystem syscall + * by passing PTRACE_MODE_READ_FSCREDS + */ + if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); + + if (fs_info->hide_pid < hide_pid_min) return true; - if (in_group_p(pid->pid_gid)) + if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } -static int proc_pid_permission(struct inode *inode, int mask) +static int proc_pid_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { - struct pid_namespace *pid = proc_pid_ns(inode); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; - has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS); + has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { - if (pid->hide_pid == HIDEPID_INVISIBLE) { + if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process @@ -734,7 +753,7 @@ static int proc_pid_permission(struct inode *inode, int mask) return -EPERM; } - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } @@ -746,7 +765,7 @@ 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 = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; @@ -838,7 +857,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, flags = FOLL_FORCE | (write ? FOLL_WRITE : 0); while (count > 0) { - int this_len = min_t(int, count, PAGE_SIZE); + size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; @@ -1032,13 +1051,14 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); + if (oom_adj > OOM_ADJUST_MAX) + oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { - static DEFINE_MUTEX(oom_adj_mutex); struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; @@ -1078,7 +1098,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) struct task_struct *p = find_lock_task_mm(task); if (p) { - if (atomic_read(&p->mm->mm_users) > 1) { + if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } @@ -1252,6 +1272,10 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, kuid_t kloginuid; int rv; + /* Don't let kthreads write their own loginuid */ + if (current->flags & PF_KTHREAD) + return -EPERM; + rcu_read_lock(); if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { rcu_read_unlock(); @@ -1415,7 +1439,7 @@ 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 = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); @@ -1573,6 +1597,7 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf, noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; + char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ @@ -1584,10 +1609,21 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf, next_line = NULL; } - err = sscanf(pos, "%u %lld %lu", &off->clockid, + err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; + + clock[sizeof(clock) - 1] = 0; + if (strcmp(clock, "monotonic") == 0 || + strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) + off->clockid = CLOCK_MONOTONIC; + else if (strcmp(clock, "boottime") == 0 || + strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) + off->clockid = CLOCK_BOOTTIME; + else + goto out; + noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) @@ -1641,8 +1677,10 @@ static ssize_t comm_write(struct file *file, const char __user *buf, if (!p) return -ESRCH; - if (same_thread_group(current, p)) + if (same_thread_group(current, p)) { set_task_comm(p, buffer); + proc_comm_connector(p); + } else count = -EINVAL; @@ -1723,27 +1761,27 @@ out: return ERR_PTR(error); } -static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) +static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { - char *tmp = (char *)__get_free_page(GFP_KERNEL); + char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; - pathname = d_path(path, tmp, PAGE_SIZE); + pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; - len = tmp + PAGE_SIZE - 1 - pathname; + len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: - free_page((unsigned long)tmp); + kfree(tmp); return len; } @@ -1834,11 +1872,25 @@ void task_dump_owner(struct task_struct *task, umode_t mode, *rgid = gid; } -struct inode *proc_pid_make_inode(struct super_block * sb, +void proc_pid_evict_inode(struct proc_inode *ei) +{ + struct pid *pid = ei->pid; + + if (S_ISDIR(ei->vfs_inode.i_mode)) { + spin_lock(&pid->lock); + hlist_del_init_rcu(&ei->sibling_inodes); + spin_unlock(&pid->lock); + } + + put_pid(pid); +} + +struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; + struct pid *pid; /* We need a new inode */ @@ -1856,10 +1908,13 @@ struct inode *proc_pid_make_inode(struct super_block * sb, /* * grab the reference to task. */ - ei->pid = get_task_pid(task, PIDTYPE_PID); - if (!ei->pid) + pid = get_task_pid(task, PIDTYPE_PID); + if (!pid) goto out_unlock; + /* Let the pid remember us for quick removal */ + ei->pid = pid; + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); @@ -1871,21 +1926,54 @@ out_unlock: return NULL; } -int pid_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +/* + * Generating an inode and adding it into @pid->inodes, so that task will + * invalidate inode's dentry before being released. + * + * This helper is used for creating dir-type entries under '/proc' and + * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' + * can be released by invalidating '/proc/<tgid>' dentry. + * In theory, dentries under '/proc/<tgid>/task' can also be released by + * invalidating '/proc/<tgid>' dentry, we reserve it to handle single + * thread exiting situation: Any one of threads should invalidate its + * '/proc/<tgid>/task/<pid>' dentry before released. + */ +static struct inode *proc_pid_make_base_inode(struct super_block *sb, + struct task_struct *task, umode_t mode) +{ + struct inode *inode; + struct proc_inode *ei; + struct pid *pid; + + inode = proc_pid_make_inode(sb, task, mode); + if (!inode) + return NULL; + + /* Let proc_flush_pid find this directory inode */ + ei = PROC_I(inode); + pid = ei->pid; + spin_lock(&pid->lock); + hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); + spin_unlock(&pid->lock); + + return inode; +} + +int pid_getattr(struct user_namespace *mnt_userns, 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 proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { - if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) { + if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, @@ -1921,19 +2009,21 @@ static int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; + int ret = 0; - if (flags & LOOKUP_RCU) - return -ECHILD; - - inode = d_inode(dentry); - task = get_proc_task(inode); + rcu_read_lock(); + inode = d_inode_rcu(dentry); + if (!inode) + goto out; + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { pid_update_inode(task, inode); - put_task_struct(task); - return 1; + ret = 1; } - return 0; +out: + rcu_read_unlock(); + return ret; } static inline bool proc_inode_is_dead(struct inode *inode) @@ -1965,7 +2055,7 @@ const struct dentry_operations pid_dentry_operations = * file type from dcache entry. * * Since all of the proc inode numbers are dynamically generated, the inode - * numbers do not exist until the inode is cache. This means creating the + * numbers do not exist until the inode is cache. This means creating * the dcache entry in readdir is necessary to keep the inode numbers * reported by readdir in sync with the inode numbers reported * by stat. @@ -2070,11 +2160,11 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { - status = down_read_killable(&mm->mmap_sem); + status = mmap_read_lock_killable(mm); if (!status) { exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); } } @@ -2121,7 +2211,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; - rc = down_read_killable(&mm->mmap_sem); + rc = mmap_read_lock_killable(mm); if (rc) goto out_mmput; @@ -2132,7 +2222,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) path_get(path); rc = 0; } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); out_mmput: mmput(mm); @@ -2147,16 +2237,16 @@ struct map_files_info { }; /* - * Only allow CAP_SYS_ADMIN to follow the links, due to concerns about how the - * symlinks may be used to bypass permissions on ancestor directories in the - * path to the file in question. + * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due + * to concerns about how the symlinks may be used to bypass permissions on + * ancestor directories in the path to the file in question. */ static const char * proc_map_files_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - if (!capable(CAP_SYS_ADMIN)) + if (!checkpoint_restore_ns_capable(&init_user_ns)) return ERR_PTR(-EPERM); return proc_pid_get_link(dentry, inode, done); @@ -2222,7 +2312,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out_put_task; result = ERR_PTR(-EINTR); - if (down_read_killable(&mm->mmap_sem)) + if (mmap_read_lock_killable(mm)) goto out_put_mm; result = ERR_PTR(-ENOENT); @@ -2235,7 +2325,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); out_put_mm: mmput(mm); out_put_task: @@ -2260,6 +2350,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; + struct vma_iterator vmi; genradix_init(&fa); @@ -2280,7 +2371,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) if (!mm) goto out_put_task; - ret = down_read_killable(&mm->mmap_sem); + ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); goto out_put_task; @@ -2291,14 +2382,16 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) /* * We need two passes here: * - * 1) Collect vmas of mapped files with mmap_sem taken - * 2) Release mmap_sem and instantiate entries + * 1) Collect vmas of mapped files with mmap_lock taken + * 2) Release mmap_lock and instantiate entries * * otherwise we get lockdep complained, since filldir() - * routine might require mmap_sem taken in might_fault(). + * routine might require mmap_lock taken in might_fault(). */ - for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { + pos = 2; + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) @@ -2307,7 +2400,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL); if (!p) { ret = -ENOMEM; - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); mmput(mm); goto out_put_task; } @@ -2316,7 +2409,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) p->end = vma->vm_end; p->mode = vma->vm_file->f_mode; } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); mmput(mm); for (i = 0; i < nr_files; i++) { @@ -2436,7 +2529,7 @@ static int proc_timers_open(struct inode *inode, struct file *file) return -ENOMEM; tp->pid = proc_pid(inode); - tp->ns = proc_pid_ns(inode); + tp->ns = proc_pid_ns(inode->i_sb); return 0; } @@ -2619,6 +2712,13 @@ out: } #ifdef CONFIG_SECURITY +static int proc_pid_attr_open(struct inode *inode, struct file *file) +{ + file->private_data = NULL; + __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); + return 0; +} + static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { @@ -2631,7 +2731,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsm, - (char*)file->f_path.dentry->d_name.name, + file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) @@ -2648,6 +2748,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, void *page; int rv; + /* A task may only write when it was the opener. */ + if (file->private_data != current->mm) + return -EPERM; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { @@ -2695,9 +2799,11 @@ out: } static const struct file_operations proc_pid_attr_operations = { + .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, + .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ @@ -2736,6 +2842,15 @@ static const struct pid_entry smack_attr_dir_stuff[] = { LSM_DIR_OPS(smack); #endif +#ifdef CONFIG_SECURITY_APPARMOR +static const struct pid_entry apparmor_attr_dir_stuff[] = { + ATTR("apparmor", "current", 0666), + ATTR("apparmor", "prev", 0444), + ATTR("apparmor", "exec", 0666), +}; +LSM_DIR_OPS(apparmor); +#endif + static const struct pid_entry attr_dir_stuff[] = { ATTR(NULL, "current", 0666), ATTR(NULL, "prev", 0444), @@ -2747,6 +2862,10 @@ static const struct pid_entry attr_dir_stuff[] = { DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif +#ifdef CONFIG_SECURITY_APPARMOR + DIR("apparmor", 0555, + proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), +#endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) @@ -2861,7 +2980,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh unsigned long flags; int result; - result = mutex_lock_killable(&task->signal->cred_guard_mutex); + result = down_read_killable(&task->signal->exec_update_lock); if (result) return result; @@ -2897,7 +3016,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh result = 0; out_unlock: - mutex_unlock(&task->signal->cred_guard_mutex); + up_read(&task->signal->exec_update_lock); return result; } @@ -3066,6 +3185,35 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_KSM +static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct mm_struct *mm; + + mm = get_task_mm(task); + if (mm) { + seq_printf(m, "%lu\n", mm->ksm_merging_pages); + mmput(mm); + } + + return 0; +} +static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct mm_struct *mm; + + mm = get_task_mm(task); + if (mm) { + seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); + mmput(mm); + } + + return 0; +} +#endif /* CONFIG_KSM */ + #ifdef CONFIG_STACKLEAK_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) @@ -3091,7 +3239,7 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), - DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), @@ -3194,6 +3342,13 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif +#ifdef CONFIG_SECCOMP_CACHE_DEBUG + ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), +#endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), + ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3230,90 +3385,28 @@ static const struct inode_operations proc_tgid_base_inode_operations = { .permission = proc_pid_permission, }; -static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) -{ - struct dentry *dentry, *leader, *dir; - char buf[10 + 1]; - struct qstr name; - - name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%u", pid); - /* no ->d_hash() rejects on procfs */ - dentry = d_hash_and_lookup(mnt->mnt_root, &name); - if (dentry) { - d_invalidate(dentry); - dput(dentry); - } - - if (pid == tgid) - return; - - name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%u", tgid); - leader = d_hash_and_lookup(mnt->mnt_root, &name); - if (!leader) - goto out; - - name.name = "task"; - name.len = strlen(name.name); - dir = d_hash_and_lookup(leader, &name); - if (!dir) - goto out_put_leader; - - name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%u", pid); - dentry = d_hash_and_lookup(dir, &name); - if (dentry) { - d_invalidate(dentry); - dput(dentry); - } - - dput(dir); -out_put_leader: - dput(leader); -out: - return; -} - /** - * proc_flush_task - Remove dcache entries for @task from the /proc dcache. - * @task: task that should be flushed. - * - * When flushing dentries from proc, one needs to flush them from global - * proc (proc_mnt) and from all the namespaces' procs this task was seen - * in. This call is supposed to do all of this job. + * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache. + * @pid: pid that should be flushed. * - * Looks in the dcache for - * /proc/@pid - * /proc/@tgid/task/@pid - * if either directory is present flushes it and all of it'ts children - * from the dcache. + * This function walks a list of inodes (that belong to any proc + * filesystem) that are attached to the pid and flushes them from + * the dentry cache. * * It is safe and reasonable to cache /proc entries for a task until * that task exits. After that they just clog up the dcache with * useless entries, possibly causing useful dcache entries to be - * flushed instead. This routine is proved to flush those useless - * dcache entries at process exit time. + * flushed instead. This routine is provided to flush those useless + * dcache entries when a process is reaped. * * NOTE: This routine is just an optimization so it does not guarantee - * that no dcache entries will exist at process exit time it - * just makes it very unlikely that any will persist. + * that no dcache entries will exist after a process is reaped + * it just makes it very unlikely that any will persist. */ -void proc_flush_task(struct task_struct *task) +void proc_flush_pid(struct pid *pid) { - int i; - struct pid *pid, *tgid; - struct upid *upid; - - pid = task_pid(task); - tgid = task_tgid(task); - - for (i = 0; i <= pid->level; i++) { - upid = &pid->numbers[i]; - proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, - tgid->numbers[i].nr); - } + proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, @@ -3321,7 +3414,8 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); @@ -3340,6 +3434,7 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; + struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); @@ -3347,7 +3442,8 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) if (tgid == ~0U) goto out; - ns = dentry->d_sb->s_fs_info; + fs_info = proc_sb_info(dentry->d_sb); + ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) @@ -3356,7 +3452,14 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) if (!task) goto out; + /* Limit procfs to only ptraceable tasks */ + if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { + if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) + goto out_put_task; + } + result = proc_pid_instantiate(dentry, task, NULL); +out_put_task: put_task_struct(task); out: return result; @@ -3382,20 +3485,8 @@ retry: pid = find_ge_pid(iter.tgid, ns); if (pid) { iter.tgid = pid_nr_ns(pid, ns); - iter.task = pid_task(pid, PIDTYPE_PID); - /* What we to know is if the pid we have find is the - * pid of a thread_group_leader. Testing for task - * being a thread_group_leader is the obvious thing - * todo but there is a window when it fails, due to - * the pid transfer logic in de_thread. - * - * So we perform the straight forward test of seeing - * if the pid we have found is the pid of a thread - * group leader, and don't worry if the task we have - * found doesn't happen to be a thread group leader. - * As we don't care in the case of readdir. - */ - if (!iter.task || !has_group_leader_pid(iter.task)) { + iter.task = pid_task(pid, PIDTYPE_TGID); + if (!iter.task) { iter.tgid += 1; goto retry; } @@ -3411,20 +3502,21 @@ retry: int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; - struct pid_namespace *ns = proc_pid_ns(file_inode(file)); + struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); + struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { - struct inode *inode = d_inode(ns->proc_self); + struct inode *inode = d_inode(fs_info->proc_self); if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { - struct inode *inode = d_inode(ns->proc_thread_self); + struct inode *inode = d_inode(fs_info->proc_thread_self); if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK)) return 0; ctx->pos = pos = pos + 1; @@ -3438,7 +3530,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) unsigned int len; cond_resched(); - if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) + if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); @@ -3465,7 +3557,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) * This function makes sure that the node is always accessible for members of * same thread group. */ -static int proc_tid_comm_permission(struct inode *inode, int mask) +static int proc_tid_comm_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; @@ -3484,7 +3577,7 @@ static int proc_tid_comm_permission(struct inode *inode, int mask) return 0; } - return generic_permission(inode, mask); + return generic_permission(&init_user_ns, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { @@ -3496,7 +3589,7 @@ static const struct inode_operations proc_tid_comm_inode_operations = { */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), - DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), @@ -3587,6 +3680,13 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif +#ifdef CONFIG_SECCOMP_CACHE_DEBUG + ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), +#endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), + ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3618,7 +3718,8 @@ static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); @@ -3638,6 +3739,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; + struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); @@ -3648,7 +3750,8 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry if (tid == ~0U) goto out; - ns = dentry->d_sb->s_fs_info; + fs_info = proc_sb_info(dentry->d_sb); + ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) @@ -3762,7 +3865,7 @@ 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 = proc_pid_ns(inode); + ns = proc_pid_ns(inode->i_sb); tid = (int)file->f_version; file->f_version = 0; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); @@ -3770,7 +3873,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) task = next_tid(task), ctx->pos++) { char name[10 + 1]; unsigned int len; + tid = task_pid_nr_ns(task, ns); + if (!tid) + continue; /* The task has just exited. */ len = snprintf(name, sizeof(name), "%u", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { @@ -3785,12 +3891,13 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) return 0; } -static int proc_task_getattr(const struct path *path, struct kstat *stat, +static int proc_task_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (p) { stat->nlink += get_nr_threads(p); diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c index 9955d75c0585..2e244ada1f97 100644 --- a/fs/proc/bootconfig.c +++ b/fs/proc/bootconfig.c @@ -26,11 +26,14 @@ static int boot_config_proc_show(struct seq_file *m, void *v) static int __init copy_xbc_key_value_list(char *dst, size_t size) { struct xbc_node *leaf, *vnode; - const char *val; char *key, *end = dst + size; + const char *val; + char q; int ret = 0; key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL); + if (!key) + return -ENOMEM; xbc_for_each_key_value(leaf, val) { ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX); @@ -41,16 +44,20 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size) break; dst += ret; vnode = xbc_node_get_child(leaf); - if (vnode && xbc_node_is_array(vnode)) { + if (vnode) { xbc_array_for_each_value(vnode, val) { - ret = snprintf(dst, rest(dst, end), "\"%s\"%s", - val, vnode->next ? ", " : "\n"); + if (strchr(val, '"')) + q = '\''; + else + q = '"'; + ret = snprintf(dst, rest(dst, end), "%c%s%c%s", + q, val, q, xbc_node_is_array(vnode) ? ", " : "\n"); if (ret < 0) goto out; dst += ret; } } else { - ret = snprintf(dst, rest(dst, end), "\"%s\"\n", val); + ret = snprintf(dst, rest(dst, end), "\"\"\n"); if (ret < 0) break; dst += ret; diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index c1dea9b8222e..f38bda5b83ec 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -5,20 +5,17 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> -__weak void arch_freq_prepare_all(void) -{ -} - extern const struct seq_operations cpuinfo_op; + static int cpuinfo_open(struct inode *inode, struct file *file) { - arch_freq_prepare_all(); return seq_open(file, &cpuinfo_op); } static const struct proc_ops cpuinfo_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = cpuinfo_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = seq_release, }; diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 37d38697eaf8..fe7bfcb7d049 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -3,6 +3,8 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/blkdev.h> +#include "internal.h" static int devinfo_show(struct seq_file *f, void *v) { @@ -53,7 +55,10 @@ static const struct seq_operations devinfo_ops = { static int __init proc_devices_init(void) { - proc_create_seq("devices", 0, NULL, &devinfo_ops); + struct proc_dir_entry *pde; + + pde = proc_create_seq("devices", 0, NULL, &devinfo_ops); + pde_make_permanent(pde); return 0; } fs_initcall(proc_devices_init); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 81882a13212d..913bef0d2a36 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -6,6 +6,7 @@ #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/pid.h> +#include <linux/ptrace.h> #include <linux/security.h> #include <linux/file.h> #include <linux/seq_file.h> @@ -28,14 +29,13 @@ static int seq_show(struct seq_file *m, void *v) if (!task) return -ENOENT; - files = get_files_struct(task); - put_task_struct(task); - + task_lock(task); + files = task->files; if (files) { unsigned int fd = proc_fd(m->private); spin_lock(&files->file_lock); - file = fcheck_files(files, fd); + file = files_lookup_fd_locked(files, fd); if (file) { struct fdtable *fdt = files_fdtable(files); @@ -47,16 +47,19 @@ static int seq_show(struct seq_file *m, void *v) ret = 0; } spin_unlock(&files->file_lock); - put_files_struct(files); } + task_unlock(task); + put_task_struct(task); if (ret) return ret; - seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", + seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%lu\n", (long long)file->f_pos, f_flags, - real_mount(file->f_path.mnt)->mnt_id); + real_mount(file->f_path.mnt)->mnt_id, + file_inode(file)->i_ino); + /* show_fd_locks() never deferences files so a stale value is safe */ show_fd_locks(m, file, files); if (seq_has_overflowed(m)) goto out; @@ -69,8 +72,30 @@ out: return 0; } +static int proc_fdinfo_access_allowed(struct inode *inode) +{ + bool allowed = false; + struct task_struct *task = get_proc_task(inode); + + if (!task) + return -ESRCH; + + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); + put_task_struct(task); + + if (!allowed) + return -EACCES; + + return 0; +} + static int seq_fdinfo_open(struct inode *inode, struct file *file) { + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + return single_open(file, seq_show, inode); } @@ -83,18 +108,13 @@ static const struct file_operations proc_fdinfo_file_operations = { static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode) { - struct files_struct *files = get_files_struct(task); struct file *file; - if (!files) - return false; - rcu_read_lock(); - file = fcheck_files(files, fd); + file = task_lookup_fd_rcu(task, fd); if (file) *mode = file->f_mode; rcu_read_unlock(); - put_files_struct(files); return !!file; } @@ -146,29 +166,22 @@ static const struct dentry_operations tid_fd_dentry_operations = { static int proc_fd_link(struct dentry *dentry, struct path *path) { - struct files_struct *files = NULL; struct task_struct *task; int ret = -ENOENT; task = get_proc_task(d_inode(dentry)); if (task) { - files = get_files_struct(task); - put_task_struct(task); - } - - if (files) { unsigned int fd = proc_fd(d_inode(dentry)); struct file *fd_file; - spin_lock(&files->file_lock); - fd_file = fcheck_files(files, fd); + fd_file = fget_task(task, fd); if (fd_file) { *path = fd_file->f_path; path_get(&fd_file->f_path); ret = 0; + fput(fd_file); } - spin_unlock(&files->file_lock); - put_files_struct(files); + put_task_struct(task); } return ret; @@ -229,7 +242,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, instantiate_t instantiate) { struct task_struct *p = get_proc_task(file_inode(file)); - struct files_struct *files; unsigned int fd; if (!p) @@ -237,22 +249,18 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, if (!dir_emit_dots(file, ctx)) goto out; - files = get_files_struct(p); - if (!files) - goto out; rcu_read_lock(); - for (fd = ctx->pos - 2; - fd < files_fdtable(files)->max_fds; - fd++, ctx->pos++) { + for (fd = ctx->pos - 2;; fd++) { struct file *f; struct fd_data data; char name[10 + 1]; unsigned int len; - f = fcheck_files(files, fd); + f = task_lookup_next_fd_rcu(p, &fd); + ctx->pos = fd + 2LL; if (!f) - continue; + break; data.mode = f->f_mode; rcu_read_unlock(); data.fd = fd; @@ -261,13 +269,11 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, if (!proc_fill_cache(file, ctx, name, len, instantiate, p, &data)) - goto out_fd_loop; + goto out; cond_resched(); rcu_read_lock(); } rcu_read_unlock(); -out_fd_loop: - put_files_struct(files); out: put_task_struct(p); return 0; @@ -294,12 +300,13 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, * /proc/pid/fd needs a special permission handler so that a process can still * access /proc/self/fd after it has executed a setuid(). */ -int proc_fd_permission(struct inode *inode, int mask) +int proc_fd_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { struct task_struct *p; int rv; - rv = generic_permission(inode, mask); + rv = generic_permission(&init_user_ns, inode, mask); if (rv == 0) return rv; @@ -325,7 +332,7 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, struct proc_inode *ei; struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO); if (!inode) return ERR_PTR(-ENOENT); @@ -351,12 +358,23 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } +static int proc_open_fdinfo(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + + return 0; +} + const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { + .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/proc/fd.h b/fs/proc/fd.h index f371a602bf58..c5a921a06a0b 100644 --- a/fs/proc/fd.h +++ b/fs/proc/fd.h @@ -10,7 +10,8 @@ extern const struct inode_operations proc_fd_inode_operations; extern const struct file_operations proc_fdinfo_operations; extern const struct inode_operations proc_fdinfo_inode_operations; -extern int proc_fd_permission(struct inode *inode, int mask); +extern int proc_fd_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask); static inline unsigned int proc_fd(struct inode *inode) { diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 3faed94e4b65..587b91d9d998 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -115,17 +115,18 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, return true; } -static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) +static int proc_notify_change(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); int error; - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) return error; - setattr_copy(inode, iattr); + setattr_copy(&init_user_ns, inode, iattr); mark_inode_dirty(inode); proc_set_user(de, inode->i_uid, inode->i_gid); @@ -133,7 +134,8 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) return 0; } -static int proc_getattr(const struct path *path, struct kstat *stat, +static int proc_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -145,7 +147,7 @@ static int proc_getattr(const struct path *path, struct kstat *stat, } } - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); return 0; } @@ -164,15 +166,8 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, const char *cp = name, *next; struct proc_dir_entry *de; - de = *ret; - if (!de) - de = &proc_root; - - while (1) { - next = strchr(cp, '/'); - if (!next) - break; - + de = *ret ?: &proc_root; + while ((next = strchr(cp, '/')) != NULL) { de = pde_subdir_find(de, cp, next - cp); if (!de) { WARN(1, "name '%s'\n", name); @@ -269,6 +264,11 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { + struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return ERR_PTR(-ENOENT); + return proc_lookup_de(dir, dentry, PDE(dir)); } @@ -325,6 +325,10 @@ int proc_readdir_de(struct file *file, struct dir_context *ctx, int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return 1; return proc_readdir_de(file, ctx, PDE(inode)); } @@ -340,6 +344,16 @@ static const struct file_operations proc_dir_operations = { .iterate_shared = proc_readdir, }; +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + /* * proc directories can do almost nothing.. */ @@ -434,6 +448,9 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, proc_set_user(ent, (*parent)->uid, (*parent)->gid); ent->proc_dops = &proc_misc_dentry_ops; + /* Revalidate everything under /proc/${pid}/net */ + if ((*parent)->proc_dops == &proc_net_dentry_ops) + pde_force_lookup(ent); out: return ent; @@ -462,8 +479,8 @@ struct proc_dir_entry *proc_symlink(const char *name, } EXPORT_SYMBOL(proc_symlink); -struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, void *data) +struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data, bool force_lookup) { struct proc_dir_entry *ent; @@ -475,10 +492,20 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent->data = data; ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; + if (force_lookup) { + pde_force_lookup(ent); + } ent = proc_register(parent, ent); } return ent; } +EXPORT_SYMBOL_GPL(_proc_mkdir); + +struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data) +{ + return _proc_mkdir(name, mode, parent, data, false); +} EXPORT_SYMBOL_GPL(proc_mkdir_data); struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, @@ -531,6 +558,12 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, return p; } +static inline void pde_set_flags(struct proc_dir_entry *pde) +{ + if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT) + pde->flags |= PROC_ENTRY_PERMANENT; +} + struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops, void *data) @@ -541,6 +574,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, if (!p) return NULL; p->proc_ops = proc_ops; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); @@ -572,8 +606,9 @@ static int proc_seq_release(struct inode *inode, struct file *file) } static const struct proc_ops proc_seq_ops = { + /* not permanent -- can call into arbitrary seq_operations */ .proc_open = proc_seq_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = proc_seq_release, }; @@ -602,8 +637,9 @@ static int proc_single_open(struct inode *inode, struct file *file) } static const struct proc_ops proc_single_ops = { + /* not permanent -- can call into arbitrary ->single_show */ .proc_open = proc_single_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; @@ -662,9 +698,13 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = pde_subdir_find(parent, fn, len); if (de) { - rb_erase(&de->subdir_node, &parent->subdir); - if (S_ISDIR(de->mode)) { - parent->nlink--; + if (unlikely(pde_is_permanent(de))) { + WARN(1, "removing permanent /proc entry '%s'", de->name); + de = NULL; + } else { + rb_erase(&de->subdir_node, &parent->subdir); + if (S_ISDIR(de->mode)) + parent->nlink--; } } write_unlock(&proc_subdir_lock); @@ -700,12 +740,24 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) write_unlock(&proc_subdir_lock); return -ENOENT; } + if (unlikely(pde_is_permanent(root))) { + write_unlock(&proc_subdir_lock); + WARN(1, "removing permanent /proc entry '%s/%s'", + root->parent->name, root->name); + return -EINVAL; + } rb_erase(&root->subdir_node, &parent->subdir); de = root; while (1) { next = pde_subdir_first(de); if (next) { + if (unlikely(pde_is_permanent(next))) { + write_unlock(&proc_subdir_lock); + WARN(1, "removing permanent /proc entry '%s/%s'", + next->parent->name, next->name); + return -EINVAL; + } rb_erase(&next->subdir_node, &de->subdir); de = next; continue; @@ -742,12 +794,6 @@ void proc_remove(struct proc_dir_entry *de) } EXPORT_SYMBOL(proc_remove); -void *PDE_DATA(const struct inode *inode) -{ - return __PDE_DATA(inode); -} -EXPORT_SYMBOL(PDE_DATA); - /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 6da18316d209..f495fdb39151 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -24,8 +24,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/mount.h> - -#include <linux/uaccess.h> +#include <linux/bug.h> #include "internal.h" @@ -33,21 +32,27 @@ static void proc_evict_inode(struct inode *inode) { struct proc_dir_entry *de; struct ctl_table_header *head; + struct proc_inode *ei = PROC_I(inode); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ - put_pid(PROC_I(inode)->pid); + if (ei->pid) { + proc_pid_evict_inode(ei); + ei->pid = NULL; + } /* Let go of any associated proc directory entry */ - de = PDE(inode); - if (de) + de = ei->pde; + if (de) { pde_put(de); + ei->pde = NULL; + } - head = PROC_I(inode)->sysctl; + head = ei->sysctl; if (head) { - RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); + RCU_INIT_POINTER(ei->sysctl, NULL); proc_sys_evict_inode(inode, head); } } @@ -59,7 +64,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; - ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL); + ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL); if (!ei) return NULL; ei->pid = NULL; @@ -68,6 +73,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb) ei->pde = NULL; ei->sysctl = NULL; ei->sysctl_entry = NULL; + INIT_HLIST_NODE(&ei->sibling_inodes); ei->ns_ops = NULL; return &ei->vfs_inode; } @@ -102,15 +108,84 @@ void __init proc_init_kmemcache(void) BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE); } +void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock) +{ + struct inode *inode; + struct proc_inode *ei; + struct hlist_node *node; + struct super_block *old_sb = NULL; + + rcu_read_lock(); + for (;;) { + struct super_block *sb; + node = hlist_first_rcu(inodes); + if (!node) + break; + ei = hlist_entry(node, struct proc_inode, sibling_inodes); + spin_lock(lock); + hlist_del_init_rcu(&ei->sibling_inodes); + spin_unlock(lock); + + inode = &ei->vfs_inode; + sb = inode->i_sb; + if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active)) + continue; + inode = igrab(inode); + rcu_read_unlock(); + if (sb != old_sb) { + if (old_sb) + deactivate_super(old_sb); + old_sb = sb; + } + if (unlikely(!inode)) { + rcu_read_lock(); + continue; + } + + if (S_ISDIR(inode->i_mode)) { + struct dentry *dir = d_find_any_alias(inode); + if (dir) { + d_invalidate(dir); + dput(dir); + } + } else { + struct dentry *dentry; + while ((dentry = d_find_alias(inode))) { + d_invalidate(dentry); + dput(dentry); + } + } + iput(inode); + + rcu_read_lock(); + } + rcu_read_unlock(); + if (old_sb) + deactivate_super(old_sb); +} + +static inline const char *hidepid2str(enum proc_hidepid v) +{ + switch (v) { + case HIDEPID_OFF: return "off"; + case HIDEPID_NO_ACCESS: return "noaccess"; + case HIDEPID_INVISIBLE: return "invisible"; + case HIDEPID_NOT_PTRACEABLE: return "ptraceable"; + } + WARN_ONCE(1, "bad hide_pid value: %d\n", v); + return "unknown"; +} + static int proc_show_options(struct seq_file *seq, struct dentry *root) { - struct super_block *sb = root->d_sb; - struct pid_namespace *pid = sb->s_fs_info; + struct proc_fs_info *fs_info = proc_sb_info(root->d_sb); - if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID)) - seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid)); - if (pid->hide_pid != HIDEPID_OFF) - seq_printf(seq, ",hidepid=%u", pid->hide_pid); + if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid)); + if (fs_info->hide_pid != HIDEPID_OFF) + seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid)); + if (fs_info->pidonly != PROC_PIDONLY_OFF) + seq_printf(seq, ",subset=pid"); return 0; } @@ -137,8 +212,17 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked on entry, unlocked on exit */ +/* + * At most 2 contexts can enter this function: the one doing the last + * close on the descriptor and whoever is deleting PDE itself. + * + * First to enter calls ->proc_release hook and signals its completion + * to the second one which waits and then does nothing. + * + * PDE is locked on entry, unlocked on exit. + */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) + __releases(&pde->pde_unload_lock) { /* * close() (proc_reg_release()) can't delete an entry and proceed: @@ -146,9 +230,6 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) * * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: * "struct file" needs to be available at the right moment. - * - * Therefore, first process to enter this function does ->release() and - * signals its completion to the other process which does nothing. */ if (pdeo->closing) { /* somebody else is doing that, just wait */ @@ -162,10 +243,12 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); + file = pdeo->file; pde->proc_ops->proc_release(file_inode(file), file); + spin_lock(&pde->pde_unload_lock); - /* After ->release. */ + /* Strictly after ->proc_release, see above. */ list_del(&pdeo->lh); c = pdeo->c; spin_unlock(&pde->pde_unload_lock); @@ -199,131 +282,205 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) { struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_lseek) lseek; - lseek = pde->proc_ops->proc_lseek; - if (!lseek) - lseek = default_llseek; - rv = lseek(file, offset, whence); + if (pde_is_permanent(pde)) { + return pde->proc_ops->proc_lseek(file, offset, whence); + } else if (use_pde(pde)) { + rv = pde->proc_ops->proc_lseek(file, offset, whence); unuse_pde(pde); } return rv; } +static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp)); + ssize_t ret; + + if (pde_is_permanent(pde)) + return pde->proc_ops->proc_read_iter(iocb, iter); + + if (!use_pde(pde)) + return -EIO; + ret = pde->proc_ops->proc_read_iter(iocb, iter); + unuse_pde(pde); + return ret; +} + +static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + typeof_member(struct proc_ops, proc_read) read; + + read = pde->proc_ops->proc_read; + if (read) + return read(file, buf, count, ppos); + return -EIO; +} + static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_read) read; - read = pde->proc_ops->proc_read; - if (read) - rv = read(file, buf, count, ppos); + if (pde_is_permanent(pde)) { + return pde_read(pde, file, buf, count, ppos); + } else if (use_pde(pde)) { + rv = pde_read(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } +static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + typeof_member(struct proc_ops, proc_write) write; + + write = pde->proc_ops->proc_write; + if (write) + return write(file, buf, count, ppos); + return -EIO; +} + static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_write) write; - write = pde->proc_ops->proc_write; - if (write) - rv = write(file, buf, count, ppos); + if (pde_is_permanent(pde)) { + return pde_write(pde, file, buf, count, ppos); + } else if (use_pde(pde)) { + rv = pde_write(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } +static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts) +{ + typeof_member(struct proc_ops, proc_poll) poll; + + poll = pde->proc_ops->proc_poll; + if (poll) + return poll(file, pts); + return DEFAULT_POLLMASK; +} + static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) { struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_poll) poll; - poll = pde->proc_ops->proc_poll; - if (poll) - rv = poll(file, pts); + if (pde_is_permanent(pde)) { + return pde_poll(pde, file, pts); + } else if (use_pde(pde)) { + rv = pde_poll(pde, file, pts); unuse_pde(pde); } return rv; } +static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) +{ + typeof_member(struct proc_ops, proc_ioctl) ioctl; + + ioctl = pde->proc_ops->proc_ioctl; + if (ioctl) + return ioctl(file, cmd, arg); + return -ENOTTY; +} + static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_ioctl) ioctl; - ioctl = pde->proc_ops->proc_ioctl; - if (ioctl) - rv = ioctl(file, cmd, arg); + if (pde_is_permanent(pde)) { + return pde_ioctl(pde, file, cmd, arg); + } else if (use_pde(pde)) { + rv = pde_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #ifdef CONFIG_COMPAT +static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) +{ + typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl; + + compat_ioctl = pde->proc_ops->proc_compat_ioctl; + if (compat_ioctl) + return compat_ioctl(file, cmd, arg); + return -ENOTTY; +} + static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl; - - compat_ioctl = pde->proc_ops->proc_compat_ioctl; - if (compat_ioctl) - rv = compat_ioctl(file, cmd, arg); + if (pde_is_permanent(pde)) { + return pde_compat_ioctl(pde, file, cmd, arg); + } else if (use_pde(pde)) { + rv = pde_compat_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #endif +static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma) +{ + typeof_member(struct proc_ops, proc_mmap) mmap; + + mmap = pde->proc_ops->proc_mmap; + if (mmap) + return mmap(file, vma); + return -EIO; +} + static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) { struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_mmap) mmap; - mmap = pde->proc_ops->proc_mmap; - if (mmap) - rv = mmap(file, vma); + if (pde_is_permanent(pde)) { + return pde_mmap(pde, file, vma); + } else if (use_pde(pde)) { + rv = pde_mmap(pde, file, vma); unuse_pde(pde); } return rv; } static unsigned long -proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, +pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - struct proc_dir_entry *pde = PDE(file_inode(file)); - unsigned long rv = -EIO; + typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; - if (use_pde(pde)) { - typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; - - get_area = pde->proc_ops->proc_get_unmapped_area; + get_area = pde->proc_ops->proc_get_unmapped_area; #ifdef CONFIG_MMU - if (!get_area) - get_area = current->mm->get_unmapped_area; + if (!get_area) + get_area = current->mm->get_unmapped_area; #endif + if (get_area) + return get_area(file, orig_addr, len, pgoff, flags); + return orig_addr; +} - if (get_area) - rv = get_area(file, orig_addr, len, pgoff, flags); - else - rv = orig_addr; +static unsigned long +proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct proc_dir_entry *pde = PDE(file_inode(file)); + unsigned long rv = -EIO; + + if (pde_is_permanent(pde)) { + return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); + } else if (use_pde(pde)) { + rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); unuse_pde(pde); } return rv; @@ -337,6 +494,16 @@ static int proc_reg_open(struct inode *inode, struct file *file) typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; + if (!pde->proc_ops->proc_lseek) + file->f_mode &= ~FMODE_LSEEK; + + if (pde_is_permanent(pde)) { + open = pde->proc_ops->proc_open; + if (open) + rv = open(inode, file); + return rv; + } + /* * Ensure that * 1) PDE's ->release hook will be called no matter what @@ -386,6 +553,17 @@ static int proc_reg_release(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); struct pde_opener *pdeo; + + if (pde_is_permanent(pde)) { + typeof_member(struct proc_ops, proc_release) release; + + release = pde->proc_ops->proc_release; + if (release) { + return release(inode, file); + } + return 0; + } + spin_lock(&pde->pde_unload_lock); list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { @@ -403,9 +581,19 @@ static const struct file_operations proc_reg_file_ops = { .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = proc_reg_compat_ioctl, -#endif + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +static const struct file_operations proc_iter_file_ops = { + .llseek = proc_reg_llseek, + .read_iter = proc_reg_read_iter, + .write = proc_reg_write, + .splice_read = generic_file_splice_read, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, @@ -413,12 +601,27 @@ static const struct file_operations proc_reg_file_ops = { }; #ifdef CONFIG_COMPAT -static const struct file_operations proc_reg_file_ops_no_compat = { +static const struct file_operations proc_reg_file_ops_compat = { .llseek = proc_reg_llseek, .read = proc_reg_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, + .compat_ioctl = proc_reg_compat_ioctl, + .mmap = proc_reg_mmap, + .get_unmapped_area = proc_reg_get_unmapped_area, + .open = proc_reg_open, + .release = proc_reg_release, +}; + +static const struct file_operations proc_iter_file_ops_compat = { + .llseek = proc_reg_llseek, + .read_iter = proc_reg_read_iter, + .splice_read = generic_file_splice_read, + .write = proc_reg_write, + .poll = proc_reg_poll, + .unlocked_ioctl = proc_reg_unlocked_ioctl, + .compat_ioctl = proc_reg_compat_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, @@ -448,44 +651,54 @@ const struct inode_operations proc_link_inode_operations = { struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { - struct inode *inode = new_inode_pseudo(sb); + struct inode *inode = new_inode(sb); - if (inode) { - inode->i_ino = de->low_ino; - inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); - PROC_I(inode)->pde = de; + if (!inode) { + pde_put(de); + return NULL; + } - if (is_empty_pde(de)) { - make_empty_dir_inode(inode); - return inode; - } - if (de->mode) { - inode->i_mode = de->mode; - inode->i_uid = de->uid; - inode->i_gid = de->gid; - } - if (de->size) - inode->i_size = de->size; - if (de->nlink) - set_nlink(inode, de->nlink); + inode->i_private = de->data; + inode->i_ino = de->low_ino; + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); + PROC_I(inode)->pde = de; + if (is_empty_pde(de)) { + make_empty_dir_inode(inode); + return inode; + } - if (S_ISREG(inode->i_mode)) { - inode->i_op = de->proc_iops; + if (de->mode) { + inode->i_mode = de->mode; + inode->i_uid = de->uid; + inode->i_gid = de->gid; + } + if (de->size) + inode->i_size = de->size; + if (de->nlink) + set_nlink(inode, de->nlink); + + if (S_ISREG(inode->i_mode)) { + inode->i_op = de->proc_iops; + if (de->proc_ops->proc_read_iter) + inode->i_fop = &proc_iter_file_ops; + else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (!de->proc_ops->proc_compat_ioctl) { - inode->i_fop = &proc_reg_file_ops_no_compat; - } + if (de->proc_ops->proc_compat_ioctl) { + if (de->proc_ops->proc_read_iter) + inode->i_fop = &proc_iter_file_ops_compat; + else + inode->i_fop = &proc_reg_file_ops_compat; + } #endif - } else if (S_ISDIR(inode->i_mode)) { - inode->i_op = de->proc_iops; - inode->i_fop = de->proc_dir_ops; - } else if (S_ISLNK(inode->i_mode)) { - inode->i_op = de->proc_iops; - inode->i_fop = NULL; - } else - BUG(); - } else - pde_put(de); + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = de->proc_dir_ops; + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = NULL; + } else { + BUG(); + } return inode; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 41587276798e..b701d0207edf 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -61,6 +61,7 @@ struct proc_dir_entry { struct rb_node subdir_node; char *name; umode_t mode; + u8 flags; u8 namelen; char inline_name[]; } __randomize_layout; @@ -73,6 +74,16 @@ struct proc_dir_entry { 0) #define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry)) +static inline bool pde_is_permanent(const struct proc_dir_entry *pde) +{ + return pde->flags & PROC_ENTRY_PERMANENT; +} + +static inline void pde_make_permanent(struct proc_dir_entry *pde) +{ + pde->flags |= PROC_ENTRY_PERMANENT; +} + extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); @@ -91,7 +102,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; - struct hlist_node sysctl_inodes; + struct hlist_node sibling_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; } __randomize_layout; @@ -109,11 +120,6 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) return PROC_I(inode)->pde; } -static inline void *__PDE_DATA(const struct inode *inode) -{ - return PDE(inode)->data; -} - static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; @@ -156,8 +162,11 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, * base.c */ extern const struct dentry_operations pid_dentry_operations; -extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int); -extern int proc_setattr(struct dentry *, struct iattr *); +extern int pid_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); +extern int proc_setattr(struct user_namespace *, struct dentry *, + struct iattr *); +extern void proc_pid_evict_inode(struct proc_inode *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); @@ -183,10 +192,9 @@ struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_e extern int proc_readdir(struct file *, struct dir_context *); int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *); -static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) +static inline void pde_get(struct proc_dir_entry *pde) { refcount_inc(&pde->refcnt); - return pde; } extern void pde_put(struct proc_dir_entry *); @@ -210,6 +218,7 @@ extern const struct inode_operations proc_pid_link_inode_operations; extern const struct super_operations proc_sops; void proc_init_kmemcache(void); +void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern void proc_entry_rundown(struct proc_dir_entry *); @@ -281,7 +290,7 @@ struct proc_maps_private { struct task_struct *task; struct mm_struct *mm; #ifdef CONFIG_MMU - struct vm_area_struct *tail_vma; + struct vma_iterator iter; #endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; @@ -302,3 +311,10 @@ extern unsigned long task_statm(struct mm_struct *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void task_mem(struct seq_file *, struct mm_struct *); + +extern const struct dentry_operations proc_net_dentry_ops; +static inline void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 8ba492d44e68..dff921f7ca33 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -193,8 +193,6 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) return 1; p = pfn_to_page(pfn); - if (!memmap_valid_within(pfn, p, page_zone(p))) - return 1; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) @@ -315,6 +313,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) { char *buf = file->private_data; size_t phdrs_offset, notes_offset, data_offset; + size_t page_offline_frozen = 1; size_t phdrs_len, notes_len; struct kcore_list *m; size_t tsz; @@ -324,6 +323,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) int ret = 0; down_read(&kclist_lock); + /* + * Don't race against drivers that set PageOffline() and expect no + * further page access. + */ + page_offline_freeze(); get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset); phdrs_offset = sizeof(struct elfhdr); @@ -382,11 +386,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) phdr->p_type = PT_LOAD; phdr->p_flags = PF_R | PF_W | PF_X; phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset; - if (m->type == KCORE_REMAP) - phdr->p_vaddr = (size_t)m->vaddr; - else - phdr->p_vaddr = (size_t)m->addr; - if (m->type == KCORE_RAM || m->type == KCORE_REMAP) + phdr->p_vaddr = (size_t)m->addr; + if (m->type == KCORE_RAM) phdr->p_paddr = __pa(m->addr); else if (m->type == KCORE_TEXT) phdr->p_paddr = __pa_symbol(m->addr); @@ -470,49 +471,83 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) m = NULL; while (buflen) { + struct page *page; + unsigned long pfn; + /* * If this is the first iteration or the address is not within * the previous entry, search for a matching entry. */ if (!m || start < m->addr || start >= m->addr + m->size) { - list_for_each_entry(m, &kclist_head, list) { - if (start >= m->addr && - start < m->addr + m->size) + struct kcore_list *iter; + + m = NULL; + list_for_each_entry(iter, &kclist_head, list) { + if (start >= iter->addr && + start < iter->addr + iter->size) { + m = iter; break; + } } } - if (&m->list == &kclist_head) { - if (clear_user(buffer, tsz)) { - ret = -EFAULT; - goto out; - } - m = NULL; /* skip the list anchor */ - } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) { + if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) { + page_offline_thaw(); + cond_resched(); + page_offline_freeze(); + } + + if (!m) { if (clear_user(buffer, tsz)) { ret = -EFAULT; goto out; } - } else if (m->type == KCORE_VMALLOC) { + goto skip; + } + + switch (m->type) { + case KCORE_VMALLOC: vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) { ret = -EFAULT; goto out; } - } else if (m->type == KCORE_USER) { + break; + case KCORE_USER: /* User page is handled prior to normal kernel page: */ if (copy_to_user(buffer, (char *)start, tsz)) { ret = -EFAULT; goto out; } - } else { + break; + case KCORE_RAM: + pfn = __pa(start) >> PAGE_SHIFT; + page = pfn_to_online_page(pfn); + + /* + * Don't read offline sections, logically offline pages + * (e.g., inflated in a balloon), hwpoisoned pages, + * and explicitly excluded physical ranges. + */ + if (!page || PageOffline(page) || + is_page_hwpoison(page) || !pfn_is_ram(pfn)) { + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } + break; + } + fallthrough; + case KCORE_VMEMMAP: + case KCORE_TEXT: if (kern_addr_valid(start)) { /* * Using bounce buffer to bypass the * hardened user copy kernel text checks. */ - if (probe_kernel_read(buf, (void *) start, tsz)) { + if (copy_from_kernel_nofault(buf, (void *)start, + tsz)) { if (clear_user(buffer, tsz)) { ret = -EFAULT; goto out; @@ -529,7 +564,15 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) goto out; } } + break; + default: + pr_warn_once("Unhandled KCORE type: %d\n", m->type); + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } } +skip: buflen -= tsz; *fpos += tsz; buffer += tsz; @@ -538,6 +581,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) } out: + page_offline_thaw(); up_read(&kclist_lock); if (ret) return ret; diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index ec1b7d2fb773..2fc92a13f9f8 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -15,11 +15,8 @@ #include <linux/fs.h> #include <linux/syslog.h> -#include <linux/uaccess.h> #include <asm/io.h> -extern wait_queue_head_t log_wait; - static int kmsg_open(struct inode * inode, struct file * file) { return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC); @@ -50,6 +47,7 @@ static __poll_t kmsg_poll(struct file *file, poll_table *wait) static const struct proc_ops kmsg_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_read = kmsg_read, .proc_poll = kmsg_poll, .proc_open = kmsg_open, diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 8468baee951d..817981e57223 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -9,6 +9,7 @@ #include <linux/seq_file.h> #include <linux/seqlock.h> #include <linux/time.h> +#include "internal.h" static int loadavg_proc_show(struct seq_file *m, void *v) { @@ -16,7 +17,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v) get_avenrun(avnrun, FIXED_1/200, 0); - seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n", + seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %u/%d %d\n", LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]), LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]), LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]), @@ -27,7 +28,10 @@ static int loadavg_proc_show(struct seq_file *m, void *v) static int __init proc_loadavg_init(void) { - proc_create_single("loadavg", 0, NULL, loadavg_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("loadavg", 0, NULL, loadavg_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 8c1f1bb1a5ce..5101131e6047 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -17,7 +17,6 @@ #include <linux/cma.h> #endif #include <asm/page.h> -#include <asm/pgtable.h> #include "internal.h" void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) @@ -42,7 +41,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) si_meminfo(&i); si_swapinfo(&i); - committed = percpu_counter_read_positive(&vm_committed_as); + committed = vm_memory_committed(); cached = global_node_page_state(NR_FILE_PAGES) - total_swapcache_pages() - i.bufferram; @@ -53,8 +52,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) pages[lru] = global_node_page_state(NR_LRU_BASE + lru); available = si_mem_available(); - sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE); - sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE); + sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B); + sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B); show_val_kb(m, "MemTotal: ", i.totalram); show_val_kb(m, "MemFree: ", i.freeram); @@ -87,6 +86,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SwapTotal: ", i.totalswap); show_val_kb(m, "SwapFree: ", i.freeswap); +#ifdef CONFIG_ZSWAP + seq_printf(m, "Zswap: %8lu kB\n", + (unsigned long)(zswap_pool_total_size >> 10)); + seq_printf(m, "Zswapped: %8lu kB\n", + (unsigned long)atomic_read(&zswap_stored_pages) << + (PAGE_SHIFT - 10)); +#endif show_val_kb(m, "Dirty: ", global_node_page_state(NR_FILE_DIRTY)); show_val_kb(m, "Writeback: ", @@ -102,12 +108,17 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SReclaimable: ", sreclaimable); show_val_kb(m, "SUnreclaim: ", sunreclaim); seq_printf(m, "KernelStack: %8lu kB\n", - global_zone_page_state(NR_KERNEL_STACK_KB)); + global_node_page_state(NR_KERNEL_STACK_KB)); +#ifdef CONFIG_SHADOW_CALL_STACK + seq_printf(m, "ShadowCallStack:%8lu kB\n", + global_node_page_state(NR_KERNEL_SCS_KB)); +#endif show_val_kb(m, "PageTables: ", - global_zone_page_state(NR_PAGETABLE)); + global_node_page_state(NR_PAGETABLE)); + show_val_kb(m, "SecPageTables: ", + global_node_page_state(NR_SECONDARY_PAGETABLE)); - show_val_kb(m, "NFS_Unstable: ", - global_node_page_state(NR_UNSTABLE_NFS)); + show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", @@ -127,15 +138,15 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_TRANSPARENT_HUGEPAGE show_val_kb(m, "AnonHugePages: ", - global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_ANON_THPS)); show_val_kb(m, "ShmemHugePages: ", - global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_SHMEM_THPS)); show_val_kb(m, "ShmemPmdMapped: ", - global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); + global_node_page_state(NR_SHMEM_PMDMAPPED)); show_val_kb(m, "FileHugePages: ", - global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); + global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", - global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); + global_node_page_state(NR_FILE_PMDMAPPED)); #endif #ifdef CONFIG_CMA @@ -153,7 +164,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) static int __init proc_meminfo_init(void) { - proc_create_single("meminfo", 0, NULL, meminfo_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("meminfo", 0, NULL, meminfo_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_meminfo_init); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 14c2badb8fd9..4d3493579458 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -21,8 +21,6 @@ #include <linux/seq_file.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> -#include <linux/uaccess.h> -#include <asm/pgtable.h> #include <asm/tlb.h> #include <asm/div64.h> #include "internal.h" diff --git a/fs/proc/page.c b/fs/proc/page.c index f909243d4a66..f2273b164535 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -10,6 +10,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/hugetlb.h> +#include <linux/memremap.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> @@ -90,6 +91,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, } static const struct proc_ops kpagecount_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpagecount_read, }; @@ -217,6 +219,9 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2); u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1); u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1); +#ifdef CONFIG_64BIT + u |= kpf_copy_bit(k, KPF_ARCH_2, PG_arch_2); +#endif return u; }; @@ -264,6 +269,7 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, } static const struct proc_ops kpageflags_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpageflags_read, }; @@ -318,6 +324,7 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, } static const struct proc_ops kpagecgroup_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpagecgroup_read, }; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 4888c5224442..856839b8ae8b 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -8,9 +8,6 @@ * * proc net directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -39,22 +36,6 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } -static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) -{ - return 0; -} - -static const struct dentry_operations proc_net_dentry_ops = { - .d_revalidate = proc_net_d_revalidate, - .d_delete = always_delete_dentry, -}; - -static void pde_force_lookup(struct proc_dir_entry *pde) -{ - /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ - pde->proc_dops = &proc_net_dentry_ops; -} - static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -77,15 +58,27 @@ static int seq_open_net(struct inode *inode, struct file *file) } #ifdef CONFIG_NET_NS p->net = net; + netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } +static void seq_file_net_put_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *priv = seq->private; + + put_net_track(priv->net, &priv->ns_tracker); +#else + put_net(&init_net); +#endif +} + static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; - put_net(seq_file_net(seq)); + seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } @@ -98,6 +91,26 @@ static const struct proc_ops proc_net_seq_ops = { .proc_release = seq_release_net, }; +int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *p = priv_data; + + p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, + GFP_KERNEL); +#endif + return 0; +} + +void bpf_iter_fini_seq_net(void *priv_data) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *p = priv_data; + + put_net_track(p->net, &p->ns_tracker); +#endif +} + struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) @@ -121,8 +134,8 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * @mode: The file's access mode. * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. - * @write: The write method which which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @write: The write method with which to 'modify' the file. + * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -137,7 +150,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, @@ -213,8 +226,8 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * @mode: The file's access mode. * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. - * @write: The write method which which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @write: The write method with which to 'modify' the file. + * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -229,7 +242,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, @@ -286,7 +299,8 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir, return de; } -static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat, +static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -294,7 +308,7 @@ static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat, net = get_proc_task_net(inode); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; @@ -336,6 +350,12 @@ static __net_init int proc_net_ns_init(struct net *net) kgid_t gid; int err; + /* + * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. + * Corresponding inode (PDE(inode) == net->proc_net) is never + * instantiated therefore blanket zeroing is fine. + * net->proc_net_stat inode is instantiated normally. + */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) @@ -359,6 +379,9 @@ static __net_init int proc_net_ns_init(struct net *net) proc_set_user(netd, uid, gid); + /* Seed dentry revalidation for /proc/${pid}/net */ + pde_force_lookup(netd); + err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c75bb4632ed1..48f2d60bd78a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -12,26 +12,42 @@ #include <linux/cred.h> #include <linux/namei.h> #include <linux/mm.h> +#include <linux/uio.h> #include <linux/module.h> #include <linux/bpf-cgroup.h> +#include <linux/mount.h> +#include <linux/kmemleak.h> #include "internal.h" +#define list_for_each_table_entry(entry, table) \ + for ((entry) = (table); (entry)->procname; (entry)++) + static const struct dentry_operations proc_sys_dentry_operations; static const struct file_operations proc_sys_file_operations; static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; -/* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, INT_MAX }; -EXPORT_SYMBOL(sysctl_vals); - /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { { } }; +/** + * register_sysctl_mount_point() - registers a sysctl mount point + * @path: path for the mount point + * + * Used to create a permanently empty directory to serve as mount point. + * There are some subtle but important permission checks this allows in the + * case of unprivileged mounts. + */ +struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return register_sysctl(path, sysctl_mount_point); +} +EXPORT_SYMBOL(register_sysctl_mount_point); + static bool is_empty_dir(struct ctl_table_header *head) { return head->ctl_table[0].child == sysctl_mount_point; @@ -92,14 +108,9 @@ static void sysctl_print_dir(struct ctl_dir *dir) static int namecmp(const char *name1, int len1, const char *name2, int len2) { - int minlen; int cmp; - minlen = len1; - if (minlen > len2) - minlen = len2; - - cmp = memcmp(name1, name2, minlen); + cmp = memcmp(name1, name2, min(len1, len2)); if (cmp == 0) cmp = len1 - len2; return cmp; @@ -166,7 +177,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else { pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - pr_cont("/%s\n", entry->procname); + pr_cont("%s\n", entry->procname); return -EEXIST; } } @@ -200,15 +211,19 @@ static void init_header(struct ctl_table_header *head, INIT_HLIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; - for (entry = table; entry->procname; entry++, node++) + + list_for_each_table_entry(entry, table) { node->header = head; + node++; + } } } static void erase_header(struct ctl_table_header *head) { struct ctl_table *entry; - for (entry = head->ctl_table; entry->procname; entry++) + + list_for_each_table_entry(entry, head->ctl_table) erase_entry(head, entry); } @@ -233,7 +248,7 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) err = insert_links(header); if (err) goto fail_links; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header->ctl_table) { err = insert_entry(header, entry); if (err) goto fail; @@ -267,42 +282,9 @@ static void unuse_table(struct ctl_table_header *p) complete(p->unregistering); } -static void proc_sys_prune_dcache(struct ctl_table_header *head) +static void proc_sys_invalidate_dcache(struct ctl_table_header *head) { - struct inode *inode; - struct proc_inode *ei; - struct hlist_node *node; - struct super_block *sb; - - rcu_read_lock(); - for (;;) { - node = hlist_first_rcu(&head->inodes); - if (!node) - break; - ei = hlist_entry(node, struct proc_inode, sysctl_inodes); - spin_lock(&sysctl_lock); - hlist_del_init_rcu(&ei->sysctl_inodes); - spin_unlock(&sysctl_lock); - - inode = &ei->vfs_inode; - sb = inode->i_sb; - if (!atomic_inc_not_zero(&sb->s_active)) - continue; - inode = igrab(inode); - rcu_read_unlock(); - if (unlikely(!inode)) { - deactivate_super(sb); - rcu_read_lock(); - continue; - } - - d_prune_aliases(inode); - iput(inode); - deactivate_super(sb); - - rcu_read_lock(); - } - rcu_read_unlock(); + proc_invalidate_siblings_dcache(&head->inodes, &sysctl_lock); } /* called under sysctl_lock, will reacquire if has to wait */ @@ -324,10 +306,10 @@ static void start_unregistering(struct ctl_table_header *p) spin_unlock(&sysctl_lock); } /* - * Prune dentries for unregistered sysctls: namespaced sysctls + * Invalidate dentries for unregistered sysctls: namespaced sysctls * can have duplicate names and contaminate dcache very badly. */ - proc_sys_prune_dcache(p); + proc_sys_invalidate_dcache(p); /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. @@ -483,7 +465,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, } ei->sysctl = head; ei->sysctl_entry = table; - hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes); + hlist_add_head_rcu(&ei->sibling_inodes, &head->inodes); head->count++; spin_unlock(&sysctl_lock); @@ -514,7 +496,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { spin_lock(&sysctl_lock); - hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes); + hlist_del_init_rcu(&PROC_I(inode)->sibling_inodes); if (!--head->count) kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); @@ -572,13 +554,14 @@ out: return err; } -static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, - size_t count, loff_t *ppos, int write) +static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter, + int write) { - struct inode *inode = file_inode(filp); + struct inode *inode = file_inode(iocb->ki_filp); struct ctl_table_header *head = grab_header(inode); struct ctl_table *table = PROC_I(inode)->sysctl_entry; - void *new_buf = NULL; + size_t count = iov_iter_count(iter); + char *kbuf; ssize_t error; if (IS_ERR(head)) @@ -597,43 +580,54 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, if (!table->proc_handler) goto out; - error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count, - ppos, &new_buf); - if (error) + /* don't even try if the size is too large */ + error = -ENOMEM; + if (count >= KMALLOC_MAX_SIZE) + goto out; + kbuf = kvzalloc(count + 1, GFP_KERNEL); + if (!kbuf) goto out; + if (write) { + error = -EFAULT; + if (!copy_from_iter_full(kbuf, count, iter)) + goto out_free_buf; + kbuf[count] = '\0'; + } + + error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count, + &iocb->ki_pos); + if (error) + goto out_free_buf; + /* careful: calling conventions are nasty here */ - if (new_buf) { - mm_segment_t old_fs; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - error = table->proc_handler(table, write, (void __user *)new_buf, - &count, ppos); - set_fs(old_fs); - kfree(new_buf); - } else { - error = table->proc_handler(table, write, buf, &count, ppos); + error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos); + if (error) + goto out_free_buf; + + if (!write) { + error = -EFAULT; + if (copy_to_iter(kbuf, count, iter) < count) + goto out_free_buf; } - if (!error) - error = count; + error = count; +out_free_buf: + kvfree(kbuf); out: sysctl_head_finish(head); return error; } -static ssize_t proc_sys_read(struct file *filp, char __user *buf, - size_t count, loff_t *ppos) +static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter) { - return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0); + return proc_sys_call_handler(iocb, iter, 0); } -static ssize_t proc_sys_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter) { - return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1); + return proc_sys_call_handler(iocb, iter, 1); } static int proc_sys_open(struct inode *inode, struct file *filp) @@ -804,7 +798,8 @@ out: return 0; } -static int proc_sys_permission(struct inode *inode, int mask) +static int proc_sys_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { /* * sysctl entries that are not writeable, @@ -832,7 +827,8 @@ static int proc_sys_permission(struct inode *inode, int mask) return error; } -static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) +static int proc_sys_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; @@ -840,16 +836,17 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = setattr_prepare(dentry, attr); + error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; - setattr_copy(inode, attr); + setattr_copy(&init_user_ns, inode, attr); mark_inode_dirty(inode); return 0; } -static int proc_sys_getattr(const struct path *path, struct kstat *stat, +static int proc_sys_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); @@ -859,7 +856,7 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat, if (IS_ERR(head)) return PTR_ERR(head); - generic_fillattr(inode, stat); + generic_fillattr(&init_user_ns, inode, stat); if (table) stat->mode = (stat->mode & S_IFMT) | table->mode; @@ -870,8 +867,10 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat, static const struct file_operations proc_sys_file_operations = { .open = proc_sys_open, .poll = proc_sys_poll, - .read = proc_sys_read, - .write = proc_sys_write, + .read_iter = proc_sys_read, + .write_iter = proc_sys_write, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .llseek = default_llseek, }; @@ -979,7 +978,6 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set, table = (struct ctl_table *)(node + 1); new_name = (char *)(table + 2); memcpy(new_name, name, namelen); - new_name[namelen] = '\0'; table[0].procname = new_name; table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO; init_header(&new->header, set->dir.header.root, set, node, table); @@ -1039,8 +1037,8 @@ failed: if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - pr_cont("/%*.*s %ld\n", - namelen, namelen, name, PTR_ERR(subdir)); + pr_cont("%*.*s %ld\n", namelen, namelen, name, + PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); if (new) @@ -1072,7 +1070,6 @@ static int sysctl_follow_link(struct ctl_table_header **phead, struct ctl_dir *dir; int ret; - ret = 0; spin_lock(&sysctl_lock); root = (*pentry)->data; set = lookup_header_set(root); @@ -1122,39 +1119,46 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) err |= sysctl_err(path, table, "array not allowed"); } + if (table->proc_handler == proc_dou8vec_minmax) { + if (table->maxlen != sizeof(u8)) + err |= sysctl_err(path, table, "array not allowed"); + } + return err; } static int sysctl_check_table(const char *path, struct ctl_table *table) { + struct ctl_table *entry; int err = 0; - for (; table->procname; table++) { - if (table->child) - err |= sysctl_err(path, table, "Not a file"); - - if ((table->proc_handler == proc_dostring) || - (table->proc_handler == proc_dointvec) || - (table->proc_handler == proc_douintvec) || - (table->proc_handler == proc_douintvec_minmax) || - (table->proc_handler == proc_dointvec_minmax) || - (table->proc_handler == proc_dointvec_jiffies) || - (table->proc_handler == proc_dointvec_userhz_jiffies) || - (table->proc_handler == proc_dointvec_ms_jiffies) || - (table->proc_handler == proc_doulongvec_minmax) || - (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { - if (!table->data) - err |= sysctl_err(path, table, "No data"); - if (!table->maxlen) - err |= sysctl_err(path, table, "No maxlen"); + list_for_each_table_entry(entry, table) { + if (entry->child) + err |= sysctl_err(path, entry, "Not a file"); + + if ((entry->proc_handler == proc_dostring) || + (entry->proc_handler == proc_dointvec) || + (entry->proc_handler == proc_douintvec) || + (entry->proc_handler == proc_douintvec_minmax) || + (entry->proc_handler == proc_dointvec_minmax) || + (entry->proc_handler == proc_dou8vec_minmax) || + (entry->proc_handler == proc_dointvec_jiffies) || + (entry->proc_handler == proc_dointvec_userhz_jiffies) || + (entry->proc_handler == proc_dointvec_ms_jiffies) || + (entry->proc_handler == proc_doulongvec_minmax) || + (entry->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { + if (!entry->data) + err |= sysctl_err(path, entry, "No data"); + if (!entry->maxlen) + err |= sysctl_err(path, entry, "No maxlen"); else - err |= sysctl_check_table_array(path, table); + err |= sysctl_check_table_array(path, entry); } - if (!table->proc_handler) - err |= sysctl_err(path, table, "No proc_handler"); + if (!entry->proc_handler) + err |= sysctl_err(path, entry, "No proc_handler"); - if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err |= sysctl_err(path, table, "bogus .mode 0%o", - table->mode); + if ((entry->mode & (S_IRUGO|S_IWUGO)) != entry->mode) + err |= sysctl_err(path, entry, "bogus .mode 0%o", + entry->mode); } return err; } @@ -1170,7 +1174,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table name_bytes = 0; nr_entries = 0; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { nr_entries++; name_bytes += strlen(entry->procname) + 1; } @@ -1187,14 +1191,16 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table node = (struct ctl_node *)(links + 1); link_table = (struct ctl_table *)(node + nr_entries); link_name = (char *)&link_table[nr_entries + 1]; + link = link_table; - for (link = link_table, entry = table; entry->procname; link++, entry++) { + list_for_each_table_entry(entry, table) { int len = strlen(entry->procname) + 1; memcpy(link_name, entry->procname, len); link->procname = link_name; link->mode = S_IFLNK|S_IRWXUGO; link->data = link_root; link_name += len; + link++; } init_header(links, dir->header.root, dir->header.set, node, link_table); links->nreg = nr_entries; @@ -1209,7 +1215,7 @@ static bool get_links(struct ctl_dir *dir, struct ctl_table *entry, *link; /* Are there links available for every entry in table? */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { const char *procname = entry->procname; link = find_entry(&head, dir, procname, strlen(procname)); if (!link) @@ -1222,7 +1228,7 @@ static bool get_links(struct ctl_dir *dir, } /* The checks passed. Increase the registration count on the links */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { const char *procname = entry->procname; link = find_entry(&head, dir, procname, strlen(procname)); head->nreg++; @@ -1233,7 +1239,7 @@ static bool get_links(struct ctl_dir *dir, static int insert_links(struct ctl_table_header *head) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; - struct ctl_dir *core_parent = NULL; + struct ctl_dir *core_parent; struct ctl_table_header *links; int err; @@ -1325,11 +1331,11 @@ struct ctl_table_header *__register_sysctl_table( struct ctl_node *node; int nr_entries = 0; - for (entry = table; entry->procname; entry++) + list_for_each_table_entry(entry, table) nr_entries++; header = kzalloc(sizeof(struct ctl_table_header) + - sizeof(struct ctl_node)*nr_entries, GFP_KERNEL); + sizeof(struct ctl_node)*nr_entries, GFP_KERNEL_ACCOUNT); if (!header) return NULL; @@ -1397,6 +1403,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init_bases(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; @@ -1420,7 +1458,7 @@ static int count_subheaders(struct ctl_table *table) if (!table || !table->procname) return 1; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { if (entry->child) nr_subheaders += count_subheaders(entry->child); else @@ -1439,7 +1477,7 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, int nr_dirs = 0; int err = -ENOMEM; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { if (entry->child) nr_dirs++; else @@ -1456,7 +1494,9 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, goto out; ctl_table_arg = files; - for (new = files, entry = table; entry->procname; entry++) { + new = files; + + list_for_each_table_entry(entry, table) { if (entry->child) continue; *new = *entry; @@ -1480,7 +1520,7 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, } /* Recurse into the subdirectories. */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { char *child_pos; if (!entry->child) @@ -1576,7 +1616,7 @@ err_register_leaves: } /** - * register_sysctl_table_path - register a sysctl table hierarchy + * register_sysctl_paths - register a sysctl table hierarchy * @path: The path to the directory the sysctl table is in. * @table: the top-level table structure * @@ -1610,6 +1650,15 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table *table) } EXPORT_SYMBOL(register_sysctl_table); +int __register_sysctl_base(struct ctl_table *base_table) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(base_table); + kmemleak_not_leak(hdr); + return 0; +} + static void put_links(struct ctl_table_header *header) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; @@ -1625,7 +1674,7 @@ static void put_links(struct ctl_table_header *header) if (IS_ERR(core_parent)) return; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header->ctl_table) { struct ctl_table_header *link_head; struct ctl_table *link; const char *name = entry->procname; @@ -1639,7 +1688,7 @@ static void put_links(struct ctl_table_header *header) else { pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - pr_cont("/%s\n", name); + pr_cont("%s\n", name); } } } @@ -1723,5 +1772,154 @@ int __init proc_sys_init(void) proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; - return sysctl_init(); + return sysctl_init_bases(); +} + +struct sysctl_alias { + const char *kernel_param; + const char *sysctl_param; +}; + +/* + * Historically some settings had both sysctl and a command line parameter. + * With the generic sysctl. parameter support, we can handle them at a single + * place and only keep the historical name for compatibility. This is not meant + * to add brand new aliases. When adding existing aliases, consider whether + * the possibly different moment of changing the value (e.g. from early_param + * to the moment do_sysctl_args() is called) is an issue for the specific + * parameter. + */ +static const struct sysctl_alias sysctl_aliases[] = { + {"hardlockup_all_cpu_backtrace", "kernel.hardlockup_all_cpu_backtrace" }, + {"hung_task_panic", "kernel.hung_task_panic" }, + {"numa_zonelist_order", "vm.numa_zonelist_order" }, + {"softlockup_all_cpu_backtrace", "kernel.softlockup_all_cpu_backtrace" }, + {"softlockup_panic", "kernel.softlockup_panic" }, + { } +}; + +static const char *sysctl_find_alias(char *param) +{ + const struct sysctl_alias *alias; + + for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) { + if (strcmp(alias->kernel_param, param) == 0) + return alias->sysctl_param; + } + + return NULL; +} + +/* Set sysctl value passed on kernel command line. */ +static int process_sysctl_arg(char *param, char *val, + const char *unused, void *arg) +{ + char *path; + struct vfsmount **proc_mnt = arg; + struct file_system_type *proc_fs_type; + struct file *file; + int len; + int err; + loff_t pos = 0; + ssize_t wret; + + if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) { + param += sizeof("sysctl") - 1; + + if (param[0] != '/' && param[0] != '.') + return 0; + + param++; + } else { + param = (char *) sysctl_find_alias(param); + if (!param) + return 0; + } + + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + + /* + * To set sysctl options, we use a temporary mount of proc, look up the + * respective sys/ file and write to it. To avoid mounting it when no + * options were given, we mount it only when the first sysctl option is + * found. Why not a persistent mount? There are problems with a + * persistent mount of proc in that it forces userspace not to use any + * proc mount options. + */ + if (!*proc_mnt) { + proc_fs_type = get_fs_type("proc"); + if (!proc_fs_type) { + pr_err("Failed to find procfs to set sysctl from command line\n"); + return 0; + } + *proc_mnt = kern_mount(proc_fs_type); + put_filesystem(proc_fs_type); + if (IS_ERR(*proc_mnt)) { + pr_err("Failed to mount procfs to set sysctl from command line\n"); + return 0; + } + } + + path = kasprintf(GFP_KERNEL, "sys/%s", param); + if (!path) + panic("%s: Failed to allocate path for %s\n", __func__, param); + strreplace(path, '.', '/'); + + file = file_open_root_mnt(*proc_mnt, path, O_WRONLY, 0); + if (IS_ERR(file)) { + err = PTR_ERR(file); + if (err == -ENOENT) + pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n", + param, val); + else if (err == -EACCES) + pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n", + param, val); + else + pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n", + file, param, val); + goto out; + } + wret = kernel_write(file, val, len, &pos); + if (wret < 0) { + err = wret; + if (err == -EINVAL) + pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n", + param, val); + else + pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n", + ERR_PTR(err), param, val); + } else if (wret != len) { + pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n", + wret, len, path, param, val); + } + + err = filp_close(file, NULL); + if (err) + pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n", + ERR_PTR(err), param, val); +out: + kfree(path); + return 0; +} + +void do_sysctl_args(void) +{ + char *command_line; + struct vfsmount *proc_mnt = NULL; + + command_line = kstrdup(saved_command_line, GFP_KERNEL); + if (!command_line) + panic("%s: Failed to allocate copy of command line\n", __func__); + + parse_args("Setting sysctl args", command_line, + NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg); + + if (proc_mnt) + kern_unmount(proc_mnt); + + kfree(command_line); } diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index c69ff191e5d8..5c6a5ceab2f1 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -4,8 +4,6 @@ * * Copyright 1997, Theodore Ts'o */ - -#include <linux/uaccess.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> diff --git a/fs/proc/root.c b/fs/proc/root.c index 608233dfd29c..3c2ee3eb1138 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -6,9 +6,6 @@ * * proc root directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -32,21 +29,86 @@ struct proc_fs_context { struct pid_namespace *pid_ns; unsigned int mask; - int hidepid; + enum proc_hidepid hidepid; int gid; + enum proc_pidonly pidonly; }; enum proc_param { Opt_gid, Opt_hidepid, + Opt_subset, }; static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), - fsparam_u32("hidepid", Opt_hidepid), + fsparam_string("hidepid", Opt_hidepid), + fsparam_string("subset", Opt_subset), {} }; +static inline int valid_hidepid(unsigned int value) +{ + return (value == HIDEPID_OFF || + value == HIDEPID_NO_ACCESS || + value == HIDEPID_INVISIBLE || + value == HIDEPID_NOT_PTRACEABLE); +} + +static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct proc_fs_context *ctx = fc->fs_private; + struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid); + struct fs_parse_result result; + int base = (unsigned long)hidepid_u32_spec.data; + + if (param->type != fs_value_is_string) + return invalf(fc, "proc: unexpected type of hidepid value\n"); + + if (!kstrtouint(param->string, base, &result.uint_32)) { + if (!valid_hidepid(result.uint_32)) + return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); + ctx->hidepid = result.uint_32; + return 0; + } + + if (!strcmp(param->string, "off")) + ctx->hidepid = HIDEPID_OFF; + else if (!strcmp(param->string, "noaccess")) + ctx->hidepid = HIDEPID_NO_ACCESS; + else if (!strcmp(param->string, "invisible")) + ctx->hidepid = HIDEPID_INVISIBLE; + else if (!strcmp(param->string, "ptraceable")) + ctx->hidepid = HIDEPID_NOT_PTRACEABLE; + else + return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); + + return 0; +} + +static int proc_parse_subset_param(struct fs_context *fc, char *value) +{ + struct proc_fs_context *ctx = fc->fs_private; + + while (value) { + char *ptr = strchr(value, ','); + + if (ptr != NULL) + *ptr++ = '\0'; + + if (*value != '\0') { + if (!strcmp(value, "pid")) { + ctx->pidonly = PROC_PIDONLY_ON; + } else { + return invalf(fc, "proc: unsupported subset option - %s\n", value); + } + } + value = ptr; + } + + return 0; +} + static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; @@ -63,10 +125,13 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_hidepid: - ctx->hidepid = result.uint_32; - if (ctx->hidepid < HIDEPID_OFF || - ctx->hidepid > HIDEPID_INVISIBLE) - return invalfc(fc, "hidepid value must be between 0 and 2.\n"); + if (proc_parse_hidepid_param(fc, param)) + return -EINVAL; + break; + + case Opt_subset: + if (proc_parse_subset_param(fc, param->string) < 0) + return -EINVAL; break; default: @@ -77,26 +142,33 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) return 0; } -static void proc_apply_options(struct super_block *s, +static void proc_apply_options(struct proc_fs_info *fs_info, struct fs_context *fc, - struct pid_namespace *pid_ns, struct user_namespace *user_ns) { struct proc_fs_context *ctx = fc->fs_private; if (ctx->mask & (1 << Opt_gid)) - pid_ns->pid_gid = make_kgid(user_ns, ctx->gid); + fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) - pid_ns->hide_pid = ctx->hidepid; + fs_info->hide_pid = ctx->hidepid; + if (ctx->mask & (1 << Opt_subset)) + fs_info->pidonly = ctx->pidonly; } static int proc_fill_super(struct super_block *s, struct fs_context *fc) { - struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info); + struct proc_fs_context *ctx = fc->fs_private; struct inode *root_inode; + struct proc_fs_info *fs_info; int ret; - proc_apply_options(s, fc, pid_ns, current_user_ns()); + fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL); + if (!fs_info) + return -ENOMEM; + + fs_info->pid_ns = get_pid_ns(ctx->pid_ns); + proc_apply_options(fs_info, fc, current_user_ns()); /* User space would break if executables or devices appear on proc */ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; @@ -106,6 +178,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; + s->s_fs_info = fs_info; /* * procfs isn't actually a stacking filesystem; however, there is @@ -113,7 +186,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) * top of it */ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; - + /* procfs dentries and inodes don't require IO to create */ s->s_shrink.seeks = 0; @@ -140,19 +213,17 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) static int proc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; - struct pid_namespace *pid = sb->s_fs_info; + struct proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); - proc_apply_options(sb, fc, pid, current_user_ns()); + proc_apply_options(fs_info, fc, current_user_ns()); return 0; } static int proc_get_tree(struct fs_context *fc) { - struct proc_fs_context *ctx = fc->fs_private; - - return get_tree_keyed(fc, proc_fill_super, ctx->pid_ns); + return get_tree_nodev(fc, proc_fill_super); } static void proc_fs_context_free(struct fs_context *fc) @@ -188,15 +259,19 @@ static int proc_init_fs_context(struct fs_context *fc) static void proc_kill_sb(struct super_block *sb) { - struct pid_namespace *ns; + struct proc_fs_info *fs_info = proc_sb_info(sb); + + if (!fs_info) { + kill_anon_super(sb); + return; + } + + dput(fs_info->proc_self); + dput(fs_info->proc_thread_self); - ns = (struct pid_namespace *)sb->s_fs_info; - if (ns->proc_self) - dput(ns->proc_self); - if (ns->proc_thread_self) - dput(ns->proc_thread_self); kill_anon_super(sb); - put_pid_ns(ns); + put_pid_ns(fs_info->pid_ns); + kfree(fs_info); } static struct file_system_type proc_fs_type = { @@ -227,13 +302,19 @@ void __init proc_root_init(void) proc_mkdir("bus", NULL); proc_sys_init(); + /* + * Last things last. It is not like userspace processes eager + * to open /proc files exist at this point but register last + * anyway. + */ register_filesystem(&proc_fs_type); } -static int proc_root_getattr(const struct path *path, struct kstat *stat, +static int proc_root_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - generic_fillattr(d_inode(path->dentry), stat); + generic_fillattr(&init_user_ns, d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } @@ -292,39 +373,3 @@ struct proc_dir_entry proc_root = { .subdir = RB_ROOT, .name = "/proc", }; - -int pid_ns_prepare_proc(struct pid_namespace *ns) -{ - struct proc_fs_context *ctx; - struct fs_context *fc; - struct vfsmount *mnt; - - fc = fs_context_for_mount(&proc_fs_type, SB_KERNMOUNT); - if (IS_ERR(fc)) - return PTR_ERR(fc); - - if (fc->user_ns != ns->user_ns) { - put_user_ns(fc->user_ns); - fc->user_ns = get_user_ns(ns->user_ns); - } - - ctx = fc->fs_private; - if (ctx->pid_ns != ns) { - put_pid_ns(ctx->pid_ns); - get_pid_ns(ns); - ctx->pid_ns = ns; - } - - mnt = fc_mount(fc); - put_fs_context(fc); - if (IS_ERR(mnt)) - return PTR_ERR(mnt); - - ns->proc_mnt = mnt; - return 0; -} - -void pid_ns_release_proc(struct pid_namespace *ns) -{ - kern_unmount(ns->proc_mnt); -} diff --git a/fs/proc/self.c b/fs/proc/self.c index 57c0a1047250..72cd69bcaf4a 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 = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; @@ -36,14 +36,14 @@ 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 = proc_pid_ns(root_inode); + struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *self; int ret = -ENOMEM; - + inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); if (self) { - struct inode *inode = new_inode_pseudo(s); + struct inode *inode = new_inode(s); if (inode) { inode->i_ino = self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); @@ -62,7 +62,7 @@ int proc_setup_self(struct super_block *s) if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); else - ns->proc_self = self; + fs_info->proc_self = self; return ret; } diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 12901dcf57e2..f4616083faef 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -3,6 +3,7 @@ #include <linux/kernel_stat.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include "internal.h" /* * /proc/softirqs ... display the number of softirqs @@ -27,7 +28,10 @@ static int show_softirqs(struct seq_file *p, void *v) static int __init proc_softirqs_init(void) { - proc_create_single("softirqs", 0, NULL, show_softirqs); + struct proc_dir_entry *pde; + + pde = proc_create_single("softirqs", 0, NULL, show_softirqs); + pde_make_permanent(pde); return 0; } fs_initcall(proc_softirqs_init); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 0449edf460f5..4fb8729a68d4 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -10,6 +10,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/time.h> +#include <linux/time_namespace.h> #include <linux/irqnr.h> #include <linux/sched/cputime.h> #include <linux/tick.h> @@ -23,7 +24,7 @@ #ifdef arch_idle_time -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; @@ -45,7 +46,7 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) #else -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -118,6 +119,8 @@ static int show_stat(struct seq_file *p, void *v) irq = softirq = steal = 0; guest = guest_nice = 0; getboottime64(&boottime); + /* shift boot timestamp according to the timens offset */ + timens_sub_boottime(&boottime); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; @@ -197,8 +200,8 @@ static int show_stat(struct seq_file *p, void *v) "\nctxt %llu\n" "btime %llu\n" "processes %lu\n" - "procs_running %lu\n" - "procs_blocked %lu\n", + "procs_running %u\n" + "procs_blocked %u\n", nr_context_switches(), (unsigned long long)boottime.tv_sec, total_forks, @@ -224,8 +227,9 @@ static int stat_open(struct inode *inode, struct file *file) } static const struct proc_ops stat_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = stat_open, - .proc_read = seq_read, + .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3ba9ae83bff5..8a74cdcc9af0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/pagewalk.h> -#include <linux/vmacache.h> +#include <linux/mm_inline.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -123,38 +123,28 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif -static void vma_stop(struct proc_maps_private *priv) +static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, + loff_t *ppos) { - struct mm_struct *mm = priv->mm; - - release_task_mempolicy(priv); - up_read(&mm->mmap_sem); - mmput(mm); -} + struct vm_area_struct *vma = vma_next(&priv->iter); -static struct vm_area_struct * -m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma) -{ - if (vma == priv->tail_vma) - return NULL; - return vma->vm_next ?: priv->tail_vma; -} + if (vma) { + *ppos = vma->vm_start; + } else { + *ppos = -2UL; + vma = get_gate_vma(priv->mm); + } -static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma) -{ - if (m->count < m->size) /* vma is copied successfully */ - m->version = m_next_vma(m->private, vma) ? vma->vm_end : -1UL; + return vma; } static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; - unsigned long last_addr = m->version; + unsigned long last_addr = *ppos; struct mm_struct *mm; - struct vm_area_struct *vma; - unsigned int pos = *ppos; - /* See m_cache_vma(). Zero at the start or after lseek. */ + /* See m_next(). Zero at the start or after lseek. */ if (last_addr == -1UL) return NULL; @@ -163,64 +153,49 @@ static void *m_start(struct seq_file *m, loff_t *ppos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } - if (down_read_killable(&mm->mmap_sem)) { + if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } + vma_iter_init(&priv->iter, mm, last_addr); hold_task_mempolicy(priv); - priv->tail_vma = get_gate_vma(mm); - - if (last_addr) { - vma = find_vma(mm, last_addr - 1); - if (vma && vma->vm_start <= last_addr) - vma = m_next_vma(priv, vma); - if (vma) - return vma; - } - - m->version = 0; - if (pos < mm->map_count) { - for (vma = mm->mmap; pos; pos--) { - m->version = vma->vm_start; - vma = vma->vm_next; - } - return vma; - } + if (last_addr == -2UL) + return get_gate_vma(mm); - /* we do not bother to update m->version in this case */ - if (pos == mm->map_count && priv->tail_vma) - return priv->tail_vma; - - vma_stop(priv); - return NULL; + return proc_get_vma(priv, ppos); } -static void *m_next(struct seq_file *m, void *v, loff_t *pos) +static void *m_next(struct seq_file *m, void *v, loff_t *ppos) { - struct proc_maps_private *priv = m->private; - struct vm_area_struct *next; - - (*pos)++; - next = m_next_vma(priv, v); - if (!next) - vma_stop(priv); - return next; + if (*ppos == -2UL) { + *ppos = -1UL; + return NULL; + } + return proc_get_vma(m->private, ppos); } static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(v)) - vma_stop(priv); - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + release_task_mempolicy(priv); + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } static int proc_maps_open(struct inode *inode, struct file *file, @@ -337,6 +312,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { + struct anon_vma_name *anon_name; + if (!mm) { name = "[vdso]"; goto done; @@ -348,8 +325,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + anon_name = anon_vma_name(vma); + if (anon_name) { + seq_pad(m, ' '); + seq_printf(m, "[anon:%s]", anon_name->name); + } } done: @@ -363,7 +348,6 @@ done: static int show_map(struct seq_file *m, void *v) { show_map_vma(m, v); - m_cache_vma(m, v); return 0; } @@ -425,9 +409,9 @@ struct mem_size_stats { u64 pss_anon; u64 pss_file; u64 pss_shmem; + u64 pss_dirty; u64 pss_locked; u64 swap_pss; - bool check_shmem_swap; }; static void smaps_page_accumulate(struct mem_size_stats *mss, @@ -447,6 +431,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, mss->pss_locked += pss; if (dirty || PageDirty(page)) { + mss->pss_dirty += pss; if (private) mss->private_dirty += size; else @@ -460,7 +445,8 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, } static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty, bool locked) + bool compound, bool young, bool dirty, bool locked, + bool migration) { int i, nr = compound ? compound_nr(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -487,8 +473,15 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * page_count(page) == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate * page_count(). + * + * The page_mapcount() is called to get a snapshot of the mapcount. + * Without holding the page lock this snapshot can be slightly wrong as + * we cannot always read the mapcount atomically. It is not safe to + * call page_mapcount() even with PTL held if the page is not mapped, + * especially for migration entries. Treat regular migration entries + * as mapcount == 1. */ - if (page_count(page) == 1) { + if ((page_count(page) == 1) || migration) { smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty, locked, true); return; @@ -508,9 +501,11 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end, __always_unused int depth, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = walk->vma; - mss->swap += shmem_partial_swap_usage( - walk->vma->vm_file->f_mapping, addr, end); + mss->swap += shmem_partial_swap_usage(walk->vma->vm_file->f_mapping, + linear_page_index(vma, addr), + linear_page_index(vma, end)); return 0; } @@ -518,6 +513,16 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end, #define smaps_pte_hole NULL #endif /* CONFIG_SHMEM */ +static void smaps_pte_hole_lookup(unsigned long addr, struct mm_walk *walk) +{ +#ifdef CONFIG_SHMEM + if (walk->ops->pte_hole) { + /* depth is not used */ + smaps_pte_hole(addr, addr + PAGE_SIZE, 0, walk); + } +#endif +} + static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct mm_walk *walk) { @@ -525,9 +530,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -544,29 +552,20 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } else { mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; } - } else if (is_migration_entry(swpent)) - page = migration_entry_to_page(swpent); - else if (is_device_private_entry(swpent)) - page = device_private_entry_to_page(swpent); - } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap - && pte_none(*pte))) { - page = find_get_entry(vma->vm_file->f_mapping, - linear_page_index(vma, addr)); - if (!page) - return; - - if (xa_is_value(page)) - mss->swap += PAGE_SIZE; - else - put_page(page); - + } else if (is_pfn_swap_entry(swpent)) { + if (is_migration_entry(swpent)) + migration = true; + page = pfn_swap_entry_to_page(swpent); + } + } else { + smaps_pte_hole_lookup(addr, walk); return; } if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -576,10 +575,20 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); - struct page *page; + struct page *page = NULL; + bool migration = false; + + if (pmd_present(*pmd)) { + /* FOLL_DUMP will return -EFAULT on huge zero page */ + page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP); + } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) { + swp_entry_t entry = pmd_to_swp_entry(*pmd); - /* FOLL_DUMP will return -EFAULT on huge zero page */ - page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP); + if (is_migration_entry(entry)) { + migration = true; + page = pfn_swap_entry_to_page(entry); + } + } if (IS_ERR_OR_NULL(page)) return; if (PageAnon(page)) @@ -590,7 +599,9 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else mss->file_thp += HPAGE_PMD_SIZE; - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); + + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), + locked, migration); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -608,8 +619,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { - if (pmd_present(*pmd)) - smaps_pmd_entry(pmd, addr, walk); + smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); goto out; } @@ -617,7 +627,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (pmd_trans_unstable(pmd)) goto out; /* - * The mmap_sem held all the way back in m_start() is what + * The mmap_lock held all the way back in m_start() is what * keeps khugepaged out of here and from collapsing things * in here. */ @@ -651,10 +661,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_MAYSHARE)] = "ms", [ilog2(VM_GROWSDOWN)] = "gd", [ilog2(VM_PFNMAP)] = "pf", - [ilog2(VM_DENYWRITE)] = "dw", -#ifdef CONFIG_X86_INTEL_MPX - [ilog2(VM_MPX)] = "mp", -#endif [ilog2(VM_LOCKED)] = "lo", [ilog2(VM_IO)] = "io", [ilog2(VM_SEQ_READ)] = "sr", @@ -668,6 +674,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_WIPEONFORK)] = "wf", [ilog2(VM_DONTDUMP)] = "dd", +#ifdef CONFIG_ARM64_BTI + [ilog2(VM_ARM64_BTI)] = "bt", +#endif #ifdef CONFIG_MEM_SOFT_DIRTY [ilog2(VM_SOFTDIRTY)] = "sd", #endif @@ -677,6 +686,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_MERGEABLE)] = "mg", [ilog2(VM_UFFD_MISSING)]= "um", [ilog2(VM_UFFD_WP)] = "uw", +#ifdef CONFIG_ARM64_MTE + [ilog2(VM_MTE)] = "mt", + [ilog2(VM_MTE_ALLOWED)] = "", +#endif #ifdef CONFIG_ARCH_HAS_PKEYS /* These come out via ProtectionKey: */ [ilog2(VM_PKEY_BIT0)] = "", @@ -687,6 +700,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_PKEY_BIT4)] = "", #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR + [ilog2(VM_UFFD_MINOR)] = "ui", +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ }; size_t i; @@ -717,10 +733,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); - if (is_migration_entry(swpent)) - page = migration_entry_to_page(swpent); - else if (is_device_private_entry(swpent)) - page = device_private_entry_to_page(swpent); + if (is_pfn_swap_entry(swpent)) + page = pfn_swap_entry_to_page(swpent); } if (page) { int mapcount = page_mapcount(page); @@ -747,12 +761,22 @@ static const struct mm_walk_ops smaps_shmem_walk_ops = { .pte_hole = smaps_pte_hole, }; +/* + * Gather mem stats from @vma with the indicated beginning + * address @start, and keep them in @mss. + * + * Use vm_start of @vma as the beginning address if @start is 0. + */ static void smap_gather_stats(struct vm_area_struct *vma, - struct mem_size_stats *mss) + struct mem_size_stats *mss, unsigned long start) { + const struct mm_walk_ops *ops = &smaps_walk_ops; + + /* Invalid start */ + if (start >= vma->vm_end) + return; + #ifdef CONFIG_SHMEM - /* In case of smaps_rollup, reset the value from previous vma */ - mss->check_shmem_swap = false; if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { /* * For shared or readonly shmem mappings we know that all @@ -766,18 +790,19 @@ static void smap_gather_stats(struct vm_area_struct *vma, */ unsigned long shmem_swapped = shmem_swap_usage(vma); - if (!shmem_swapped || (vma->vm_flags & VM_SHARED) || - !(vma->vm_flags & VM_WRITE)) { + if (!start && (!shmem_swapped || (vma->vm_flags & VM_SHARED) || + !(vma->vm_flags & VM_WRITE))) { mss->swap += shmem_swapped; } else { - mss->check_shmem_swap = true; - walk_page_vma(vma, &smaps_shmem_walk_ops, mss); - return; + ops = &smaps_shmem_walk_ops; } } #endif - /* mmap_sem is held in m_start */ - walk_page_vma(vma, &smaps_walk_ops, mss); + /* mmap_lock is held in m_start */ + if (!start) + walk_page_vma(vma, ops, mss); + else + walk_page_range(vma->vm_mm, start, vma->vm_end, ops, mss); } #define SEQ_PUT_DEC(str, val) \ @@ -789,6 +814,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Dirty: ", mss->pss_dirty >> PSS_SHIFT); if (rollup_mode) { /* * These are meaningful only for smaps_rollup, otherwise two of @@ -810,7 +836,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); - SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp); + SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp); SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", mss->private_hugetlb >> 10, 7); @@ -829,7 +855,7 @@ static int show_smap(struct seq_file *m, void *v) memset(&mss, 0, sizeof(mss)); - smap_gather_stats(vma, &mss); + smap_gather_stats(vma, &mss, 0); show_map_vma(m, vma); @@ -840,15 +866,13 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); - seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_enabled(vma)); + seq_printf(m, "THPeligible: %d\n", + hugepage_vma_check(vma, vma->vm_flags, true, false, true)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); show_smap_vma_flags(m, vma); - m_cache_vma(m, vma); - return 0; } @@ -856,16 +880,16 @@ static int show_smaps_rollup(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; struct mem_size_stats mss; - struct mm_struct *mm; + struct mm_struct *mm = priv->mm; struct vm_area_struct *vma; - unsigned long last_vma_end = 0; + unsigned long vma_start = 0, last_vma_end = 0; int ret = 0; + MA_STATE(mas, &mm->mm_mt, 0, 0); priv->task = get_proc_task(priv->inode); if (!priv->task) return -ESRCH; - mm = priv->mm; if (!mm || !mmget_not_zero(mm)) { ret = -ESRCH; goto out_put_task; @@ -873,26 +897,95 @@ static int show_smaps_rollup(struct seq_file *m, void *v) memset(&mss, 0, sizeof(mss)); - ret = down_read_killable(&mm->mmap_sem); + ret = mmap_read_lock_killable(mm); if (ret) goto out_put_mm; hold_task_mempolicy(priv); + vma = mas_find(&mas, ULONG_MAX); + + if (unlikely(!vma)) + goto empty_set; - for (vma = priv->mm->mmap; vma; vma = vma->vm_next) { - smap_gather_stats(vma, &mss); + vma_start = vma->vm_start; + do { + smap_gather_stats(vma, &mss, 0); last_vma_end = vma->vm_end; - } - show_vma_header_prefix(m, priv->mm->mmap->vm_start, - last_vma_end, 0, 0, 0, 0); + /* + * Release mmap_lock temporarily if someone wants to + * access it for write request. + */ + if (mmap_lock_is_contended(mm)) { + mas_pause(&mas); + mmap_read_unlock(mm); + ret = mmap_read_lock_killable(mm); + if (ret) { + release_task_mempolicy(priv); + goto out_put_mm; + } + + /* + * After dropping the lock, there are four cases to + * consider. See the following example for explanation. + * + * +------+------+-----------+ + * | VMA1 | VMA2 | VMA3 | + * +------+------+-----------+ + * | | | | + * 4k 8k 16k 400k + * + * Suppose we drop the lock after reading VMA2 due to + * contention, then we get: + * + * last_vma_end = 16k + * + * 1) VMA2 is freed, but VMA3 exists: + * + * find_vma(mm, 16k - 1) will return VMA3. + * In this case, just continue from VMA3. + * + * 2) VMA2 still exists: + * + * find_vma(mm, 16k - 1) will return VMA2. + * Iterate the loop like the original one. + * + * 3) No more VMAs can be found: + * + * find_vma(mm, 16k - 1) will return NULL. + * No more things to do, just break. + * + * 4) (last_vma_end - 1) is the middle of a vma (VMA'): + * + * find_vma(mm, 16k - 1) will return VMA' whose range + * contains last_vma_end. + * Iterate VMA' from last_vma_end. + */ + vma = mas_find(&mas, ULONG_MAX); + /* Case 3 above */ + if (!vma) + break; + + /* Case 1 above */ + if (vma->vm_start >= last_vma_end) + continue; + + /* Case 4 above */ + if (vma->vm_end > last_vma_end) + smap_gather_stats(vma, &mss, last_vma_end); + } + /* Case 2 above */ + } while ((vma = mas_find(&mas, ULONG_MAX)) != NULL); + +empty_set: + show_vma_header_prefix(m, vma_start, last_vma_end, 0, 0, 0, 0); seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); __show_smap(m, &mss, true); release_task_mempolicy(priv); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); out_put_mm: mmput(mm); @@ -985,6 +1078,23 @@ struct clear_refs_private { }; #ifdef CONFIG_MEM_SOFT_DIRTY + +static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +{ + struct page *page; + + if (!pte_write(pte)) + return false; + if (!is_cow_mapping(vma->vm_flags)) + return false; + if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))) + return false; + page = vm_normal_page(vma, addr, pte); + if (!page) + return false; + return page_maybe_dma_pinned(page); +} + static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { @@ -999,6 +1109,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, if (pte_present(ptent)) { pte_t old_pte; + if (pte_is_pinned(vma, addr, ptent)) + return; old_pte = ptep_modify_prot_start(vma, addr, pte); ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); @@ -1139,7 +1251,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, struct mm_struct *mm; struct vm_area_struct *vma; enum clear_refs_types type; - struct mmu_gather tlb; int itype; int rv; @@ -1160,76 +1271,46 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { + MA_STATE(mas, &mm->mm_mt, 0, 0); struct mmu_notifier_range range; struct clear_refs_private cp = { .type = type, }; + if (mmap_write_lock_killable(mm)) { + count = -EINTR; + goto out_mm; + } if (type == CLEAR_REFS_MM_HIWATER_RSS) { - if (down_write_killable(&mm->mmap_sem)) { - count = -EINTR; - goto out_mm; - } - /* * Writing 5 to /proc/pid/clear_refs resets the peak * resident set size to this mm's current rss value. */ reset_mm_hiwater_rss(mm); - up_write(&mm->mmap_sem); - goto out_mm; + goto out_unlock; } - if (down_read_killable(&mm->mmap_sem)) { - count = -EINTR; - goto out_mm; - } - tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { - for (vma = mm->mmap; vma; vma = vma->vm_next) { + mas_for_each(&mas, vma, ULONG_MAX) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; - up_read(&mm->mmap_sem); - if (down_write_killable(&mm->mmap_sem)) { - count = -EINTR; - goto out_mm; - } - /* - * Avoid to modify vma->vm_flags - * without locked ops while the - * coredump reads the vm_flags. - */ - if (!mmget_still_valid(mm)) { - /* - * Silently return "count" - * like if get_task_mm() - * failed. FIXME: should this - * function have returned - * -ESRCH if get_task_mm() - * failed like if - * get_proc_task() fails? - */ - up_write(&mm->mmap_sem); - goto out_mm; - } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - vma->vm_flags &= ~VM_SOFTDIRTY; - vma_set_page_prot(vma); - } - downgrade_write(&mm->mmap_sem); - break; + vma->vm_flags &= ~VM_SOFTDIRTY; + vma_set_page_prot(vma); } + inc_tlb_flush_pending(mm); mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, 0, NULL, mm, 0, -1UL); mmu_notifier_invalidate_range_start(&range); } - walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops, - &cp); - if (type == CLEAR_REFS_SOFT_DIRTY) + walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp); + if (type == CLEAR_REFS_SOFT_DIRTY) { mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb, 0, -1); - up_read(&mm->mmap_sem); + flush_tlb_mm(mm); + dec_tlb_flush_pending(mm); + } +out_unlock: + mmap_write_unlock(mm); out_mm: mmput(mm); } @@ -1261,6 +1342,7 @@ struct pagemapread { #define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0) #define PM_SOFT_DIRTY BIT_ULL(55) #define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_UFFD_WP BIT_ULL(57) #define PM_FILE BIT_ULL(61) #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) @@ -1326,6 +1408,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, { u64 frame = 0, flags = 0; struct page *page = NULL; + bool migration = false; if (pte_present(pte)) { if (pm->show_pfn) @@ -1334,25 +1417,39 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, page = vm_normal_page(vma, addr, pte); if (pte_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; + if (pte_uffd_wp(pte)) + flags |= PM_UFFD_WP; } else if (is_swap_pte(pte)) { swp_entry_t entry; if (pte_swp_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; + if (pte_swp_uffd_wp(pte)) + flags |= PM_UFFD_WP; entry = pte_to_swp_entry(pte); - if (pm->show_pfn) + if (pm->show_pfn) { + pgoff_t offset; + /* + * For PFN swap offsets, keeping the offset field + * to be PFN only to be compatible with old smaps. + */ + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + (offset << MAX_SWAPFILES_SHIFT); + } flags |= PM_SWAP; - if (is_migration_entry(entry)) - page = migration_entry_to_page(entry); - - if (is_device_private_entry(entry)) - page = device_private_entry_to_page(entry); + migration = is_migration_entry(entry); + if (is_pfn_swap_entry(entry)) + page = pfn_swap_entry_to_page(entry); + if (pte_marker_entry_uffd_wp(entry)) + flags |= PM_UFFD_WP; } if (page && !PageAnon(page)) flags |= PM_FILE; - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; @@ -1368,8 +1465,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, spinlock_t *ptl; pte_t *pte, *orig_pte; int err = 0; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool migration = false; + ptl = pmd_trans_huge_lock(pmdp, vma); if (ptl) { u64 flags = 0, frame = 0; @@ -1385,6 +1483,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, flags |= PM_PRESENT; if (pmd_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; + if (pmd_uffd_wp(pmd)) + flags |= PM_UFFD_WP; if (pm->show_pfn) frame = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); @@ -1395,7 +1495,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned long offset; if (pm->show_pfn) { - offset = swp_offset(entry) + + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); + offset = offset + ((addr & ~PMD_MASK) >> PAGE_SHIFT); frame = swp_type(entry) | (offset << MAX_SWAPFILES_SHIFT); @@ -1403,12 +1507,15 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, flags |= PM_SWAP; if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; + if (pmd_swp_uffd_wp(pmd)) + flags |= PM_UFFD_WP; VM_BUG_ON(!is_pmd_migration_entry(pmd)); - page = migration_entry_to_page(entry); + migration = is_migration_entry(entry); + page = pfn_swap_entry_to_page(entry); } #endif - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; for (; addr != end; addr += PAGE_SIZE) { @@ -1477,10 +1584,15 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, if (page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; + if (huge_pte_uffd_wp(pte)) + flags |= PM_UFFD_WP; + flags |= PM_PRESENT; if (pm->show_pfn) frame = pte_pfn(pte) + ((addr & ~hmask) >> PAGE_SHIFT); + } else if (pte_swp_uffd_wp_any(pte)) { + flags |= PM_UFFD_WP; } for (; addr != end; addr += PAGE_SIZE) { @@ -1518,7 +1630,8 @@ static const struct mm_walk_ops pagemap_ops = { * Bits 5-54 swap offset if swapped * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst) * Bit 56 page exclusively mapped - * Bits 57-60 zero + * Bit 57 pte is uffd-wp write-protected + * Bits 58-60 zero * Bit 61 page is file-page or shared-anon * Bit 62 page swapped * Bit 63 page present @@ -1567,11 +1680,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; - start_vaddr = svpfn << PAGE_SHIFT; end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > mm->task_size >> PAGE_SHIFT) + start_vaddr = end_vaddr; + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) + start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + + /* Ensure the address is inside the task */ + if (start_vaddr > mm->task_size) start_vaddr = end_vaddr; /* @@ -1590,11 +1707,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, /* overflow ? */ if (end < start_vaddr || end > end_vaddr) end = end_vaddr; - ret = down_read_killable(&mm->mmap_sem); + ret = mmap_read_lock_killable(mm); if (ret) goto out_free; ret = walk_page_range(mm, start_vaddr, end, &pagemap_ops, &pm); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); start_vaddr = end; len = min(count, PM_ENTRY_BYTES * pm.pos); @@ -1701,7 +1818,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL; page = vm_normal_page(vma, addr, pte); - if (!page) + if (!page || is_zone_device_page(page)) return NULL; if (PageReserved(page)) @@ -1789,8 +1906,6 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, return 0; page = pte_page(huge_pte); - if (!page) - return 0; md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); @@ -1853,7 +1968,7 @@ static int show_numa_map(struct seq_file *m, void *v) if (is_vm_hugetlb_page(vma)) seq_puts(m, " huge"); - /* mmap_sem is held by m_start */ + /* mmap_lock is held by m_start */ walk_page_vma(vma, &show_numa_ops, md); if (!md->pages) @@ -1887,7 +2002,6 @@ static int show_numa_map(struct seq_file *m, void *v) seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10); out: seq_putc(m, '\n'); - m_cache_vma(m, vma); return 0; } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 7907e6419e57..2fd06f52b6a4 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -20,15 +20,13 @@ */ void task_mem(struct seq_file *m, struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; struct vm_region *region; - struct rb_node *p; unsigned long bytes = 0, sbytes = 0, slack = 0, size; - - down_read(&mm->mmap_sem); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + mmap_read_lock(mm); + for_each_vma(vmi, vma) { bytes += kobjsize(vma); region = vma->vm_region; @@ -77,21 +75,19 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "Shared:\t%8lu bytes\n", bytes, slack, sbytes); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); } unsigned long task_vsize(struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; - struct rb_node *p; unsigned long vsize = 0; - down_read(&mm->mmap_sem); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + mmap_read_lock(mm); + for_each_vma(vmi, vma) vsize += vma->vm_end - vma->vm_start; - } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); return vsize; } @@ -99,14 +95,13 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; struct vm_region *region; - struct rb_node *p; unsigned long size = kobjsize(mm); - down_read(&mm->mmap_sem); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + mmap_read_lock(mm); + for_each_vma(vmi, vma) { size += kobjsize(vma); region = vma->vm_region; if (region) { @@ -119,7 +114,7 @@ unsigned long task_statm(struct mm_struct *mm, >> PAGE_SHIFT; *data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK)) >> PAGE_SHIFT; - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); size >>= PAGE_SHIFT; size += *text + *data; *resident = size; @@ -190,17 +185,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) */ static int show_map(struct seq_file *m, void *_p) { - struct rb_node *p = _p; - - return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb)); + return nommu_vma_show(m, _p); } static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_maps_private *priv = m->private; struct mm_struct *mm; - struct rb_node *p; - loff_t n = *pos; + struct vm_area_struct *vma; + unsigned long addr = *pos; + + /* See m_next(). Zero at the start or after lseek. */ + if (addr == -1UL) + return NULL; /* pin the task and mm whilst we play with them */ priv->task = get_proc_task(priv->inode); @@ -211,17 +208,17 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!mm || !mmget_not_zero(mm)) return NULL; - if (down_read_killable(&mm->mmap_sem)) { + if (mmap_read_lock_killable(mm)) { mmput(mm); return ERR_PTR(-EINTR); } - /* start from the Nth VMA */ - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) - if (n-- == 0) - return p; + /* start the next element from addr */ + vma = find_vma(mm, addr); + if (vma) + return vma; - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); mmput(mm); return NULL; } @@ -231,7 +228,7 @@ static void m_stop(struct seq_file *m, void *_vml) struct proc_maps_private *priv = m->private; if (!IS_ERR_OR_NULL(_vml)) { - up_read(&priv->mm->mmap_sem); + mmap_read_unlock(priv->mm); mmput(priv->mm); } if (priv->task) { @@ -242,10 +239,10 @@ static void m_stop(struct seq_file *m, void *_vml) static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - struct rb_node *p = _p; + struct vm_area_struct *vma = _p; - (*pos)++; - return p ? rb_next(p) : NULL; + *pos = vma->vm_end; + return find_vma(vma->vm_mm, vma->vm_end); } static const struct seq_operations proc_pid_maps_ops = { diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index f61ae53533f5..a553273fbd41 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 = proc_pid_ns(inode); + struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; @@ -36,14 +36,14 @@ 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 = proc_pid_ns(root_inode); + struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *thread_self; int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { - struct inode *inode = new_inode_pseudo(s); + struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); @@ -60,9 +60,9 @@ int proc_setup_thread_self(struct super_block *s) inode_unlock(root_inode); if (ret) - pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); + pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); else - ns->proc_thread_self = thread_self; + fs_info->proc_thread_self = thread_self; return ret; } diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 5a1b228964fb..b5343d209381 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -7,23 +7,28 @@ #include <linux/time.h> #include <linux/time_namespace.h> #include <linux/kernel_stat.h> +#include "internal.h" static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec64 uptime; struct timespec64 idle; - u64 nsec; + u64 idle_nsec; u32 rem; int i; - nsec = 0; - for_each_possible_cpu(i) - nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; + idle_nsec = 0; + for_each_possible_cpu(i) { + struct kernel_cpustat kcs; + + kcpustat_cpu_fetch(&kcs, i); + idle_nsec += get_idle_time(&kcs, i); + } ktime_get_boottime_ts64(&uptime); timens_add_boottime(&uptime); - idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem); idle.tv_nsec = rem; seq_printf(m, "%lu.%02lu %lu.%02lu\n", (unsigned long) uptime.tv_sec, @@ -35,7 +40,10 @@ static int uptime_proc_show(struct seq_file *m, void *v) static int __init proc_uptime_init(void) { - proc_create_single("uptime", 0, NULL, uptime_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("uptime", 0, NULL, uptime_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c index b449f186577f..02e3c3cd4a9a 100644 --- a/fs/proc/version.c +++ b/fs/proc/version.c @@ -5,6 +5,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/utsname.h> +#include "internal.h" static int version_proc_show(struct seq_file *m, void *v) { @@ -17,7 +18,10 @@ static int version_proc_show(struct seq_file *m, void *v) static int __init proc_version_init(void) { - proc_create_single("version", 0, NULL, version_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("version", 0, NULL, version_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_version_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 7dc800cce354..f2aa86c421f2 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -25,9 +25,8 @@ #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> -#include <linux/uaccess.h> -#include <linux/mem_encrypt.h> -#include <asm/pgtable.h> +#include <linux/uio.h> +#include <linux/cc_platform.h> #include <asm/io.h> #include "internal.h" @@ -63,54 +62,79 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0); /* Device Dump Size */ static size_t vmcoredd_orig_sz; -/* - * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error - * The called function has to take care of module refcounting. - */ -static int (*oldmem_pfn_is_ram)(unsigned long pfn); +static DEFINE_SPINLOCK(vmcore_cb_lock); +DEFINE_STATIC_SRCU(vmcore_cb_srcu); +/* List of registered vmcore callbacks. */ +static LIST_HEAD(vmcore_cb_list); +/* Whether the vmcore has been opened once. */ +static bool vmcore_opened; -int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)) +void register_vmcore_cb(struct vmcore_cb *cb) { - if (oldmem_pfn_is_ram) - return -EBUSY; - oldmem_pfn_is_ram = fn; - return 0; + INIT_LIST_HEAD(&cb->next); + spin_lock(&vmcore_cb_lock); + list_add_tail(&cb->next, &vmcore_cb_list); + /* + * Registering a vmcore callback after the vmcore was opened is + * very unusual (e.g., manual driver loading). + */ + if (vmcore_opened) + pr_warn_once("Unexpected vmcore callback registration\n"); + spin_unlock(&vmcore_cb_lock); } -EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram); +EXPORT_SYMBOL_GPL(register_vmcore_cb); -void unregister_oldmem_pfn_is_ram(void) +void unregister_vmcore_cb(struct vmcore_cb *cb) { - oldmem_pfn_is_ram = NULL; - wmb(); + spin_lock(&vmcore_cb_lock); + list_del_rcu(&cb->next); + /* + * Unregistering a vmcore callback after the vmcore was opened is + * very unusual (e.g., forced driver removal), but we cannot stop + * unregistering. + */ + if (vmcore_opened) + pr_warn_once("Unexpected vmcore callback unregistration\n"); + spin_unlock(&vmcore_cb_lock); + + synchronize_srcu(&vmcore_cb_srcu); } -EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram); +EXPORT_SYMBOL_GPL(unregister_vmcore_cb); -static int pfn_is_ram(unsigned long pfn) +static bool pfn_is_ram(unsigned long pfn) { - int (*fn)(unsigned long pfn); - /* pfn is ram unless fn() checks pagetype */ - int ret = 1; + struct vmcore_cb *cb; + bool ret = true; - /* - * Ask hypervisor if the pfn is really ram. - * A ballooned page contains no data and reading from such a page - * will cause high load in the hypervisor. - */ - fn = oldmem_pfn_is_ram; - if (fn) - ret = fn(pfn); + list_for_each_entry_srcu(cb, &vmcore_cb_list, next, + srcu_read_lock_held(&vmcore_cb_srcu)) { + if (unlikely(!cb->pfn_is_ram)) + continue; + ret = cb->pfn_is_ram(cb, pfn); + if (!ret) + break; + } return ret; } +static int open_vmcore(struct inode *inode, struct file *file) +{ + spin_lock(&vmcore_cb_lock); + vmcore_opened = true; + spin_unlock(&vmcore_cb_lock); + + return 0; +} + /* Reads a page from the oldmem device from given offset. */ -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { unsigned long pfn, offset; size_t nr_bytes; ssize_t read = 0, tmp; + int idx; if (!count) return 0; @@ -118,6 +142,7 @@ ssize_t read_from_oldmem(char *buf, size_t count, offset = (unsigned long)(*ppos % PAGE_SIZE); pfn = (unsigned long)(*ppos / PAGE_SIZE); + idx = srcu_read_lock(&vmcore_cb_srcu); do { if (count > (PAGE_SIZE - offset)) nr_bytes = PAGE_SIZE - offset; @@ -125,28 +150,29 @@ ssize_t read_from_oldmem(char *buf, size_t count, nr_bytes = count; /* If pfn is not ram, return zeros for sparse dump files */ - if (pfn_is_ram(pfn) == 0) - memset(buf, 0, nr_bytes); - else { + if (!pfn_is_ram(pfn)) { + tmp = iov_iter_zero(nr_bytes, iter); + } else { if (encrypted) - tmp = copy_oldmem_page_encrypted(pfn, buf, + tmp = copy_oldmem_page_encrypted(iter, pfn, nr_bytes, - offset, - userbuf); + offset); else - tmp = copy_oldmem_page(pfn, buf, nr_bytes, - offset, userbuf); - - if (tmp < 0) - return tmp; + tmp = copy_oldmem_page(iter, pfn, nr_bytes, + offset); + } + if (tmp < nr_bytes) { + srcu_read_unlock(&vmcore_cb_srcu, idx); + return -EFAULT; } + *ppos += nr_bytes; count -= nr_bytes; - buf += nr_bytes; read += nr_bytes; ++pfn; offset = 0; } while (count); + srcu_read_unlock(&vmcore_cb_srcu, idx); return read; } @@ -170,7 +196,12 @@ void __weak elfcorehdr_free(unsigned long long addr) */ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, false); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, false); } /* @@ -178,7 +209,13 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) */ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, mem_encrypt_active()); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, + cc_platform_has(CC_ATTR_MEM_ENCRYPT)); } /* @@ -195,29 +232,14 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, /* * Architectures which support memory encryption override this. */ -ssize_t __weak -copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, - unsigned long offset, int userbuf) +ssize_t __weak copy_oldmem_page_encrypted(struct iov_iter *iter, + unsigned long pfn, size_t csize, unsigned long offset) { - return copy_oldmem_page(pfn, buf, csize, offset, userbuf); -} - -/* - * Copy to either kernel or user space - */ -static int copy_to(void *target, void *src, size_t size, int userbuf) -{ - if (userbuf) { - if (copy_to_user((char __user *) target, src, size)) - return -EFAULT; - } else { - memcpy(target, src, size); - } - return 0; + return copy_oldmem_page(iter, pfn, csize, offset); } #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP -static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf) +static int vmcoredd_copy_dumps(struct iov_iter *iter, u64 start, size_t size) { struct vmcoredd_node *dump; u64 offset = 0; @@ -230,14 +252,13 @@ static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf) if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; - if (copy_to(dst, buf, tsz, userbuf)) { + if (copy_to_iter(buf, tsz, iter) < tsz) { ret = -EFAULT; goto out_unlock; } size -= tsz; start += tsz; - dst += tsz; /* Leave now if buffer filled already */ if (!size) @@ -266,7 +287,8 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst, if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; - if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) { + if (remap_vmalloc_range_partial(vma, dst, buf, 0, + tsz)) { ret = -EFAULT; goto out_unlock; } @@ -292,33 +314,28 @@ out_unlock: /* Read from the ELF header and then the crash dump. On error, negative value is * returned otherwise number of bytes read are returned. */ -static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, - int userbuf) +static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) { ssize_t acc = 0, tmp; size_t tsz; u64 start; struct vmcore *m = NULL; - if (buflen == 0 || *fpos >= vmcore_size) + if (!iov_iter_count(iter) || *fpos >= vmcore_size) return 0; - /* trim buflen to not go beyond EOF */ - if (buflen > vmcore_size - *fpos) - buflen = vmcore_size - *fpos; + iov_iter_truncate(iter, vmcore_size - *fpos); /* Read ELF core header */ if (*fpos < elfcorebuf_sz) { - tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen); - if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf)) + tsz = min(elfcorebuf_sz - (size_t)*fpos, iov_iter_count(iter)); + if (copy_to_iter(elfcorebuf + *fpos, tsz, iter) < tsz) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } @@ -339,35 +356,32 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, /* Read device dumps */ if (*fpos < elfcorebuf_sz + vmcoredd_orig_sz) { tsz = min(elfcorebuf_sz + vmcoredd_orig_sz - - (size_t)*fpos, buflen); + (size_t)*fpos, iov_iter_count(iter)); start = *fpos - elfcorebuf_sz; - if (vmcoredd_copy_dumps(buffer, start, tsz, userbuf)) + if (vmcoredd_copy_dumps(iter, start, tsz)) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (!buflen) + if (!iov_iter_count(iter)) return acc; } #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ /* Read remaining elf notes */ - tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, + iov_iter_count(iter)); kaddr = elfnotes_buf + *fpos - elfcorebuf_sz - vmcoredd_orig_sz; - if (copy_to(buffer, kaddr, tsz, userbuf)) + if (copy_to_iter(kaddr, tsz, iter) < tsz) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } @@ -375,19 +389,17 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, if (*fpos < m->offset + m->size) { tsz = (size_t)min_t(unsigned long long, m->offset + m->size - *fpos, - buflen); + iov_iter_count(iter)); start = m->paddr + *fpos - m->offset; - tmp = read_from_oldmem(buffer, tsz, &start, - userbuf, mem_encrypt_active()); + tmp = read_from_oldmem(iter, tsz, &start, + cc_platform_has(CC_ATTR_MEM_ENCRYPT)); if (tmp < 0) return tmp; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } } @@ -395,15 +407,14 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, return acc; } -static ssize_t read_vmcore(struct file *file, char __user *buffer, - size_t buflen, loff_t *fpos) +static ssize_t read_vmcore(struct kiocb *iocb, struct iov_iter *iter) { - return __read_vmcore((__force char *) buffer, buflen, fpos, 1); + return __read_vmcore(iter, &iocb->ki_pos); } /* * The vmcore fault handler uses the page cache and fills data using the - * standard __vmcore_read() function. + * standard __read_vmcore() function. * * On s390 the fault handler is used for memory regions that can't be mapped * directly with remap_pfn_range(). @@ -413,9 +424,10 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) #ifdef CONFIG_S390 struct address_space *mapping = vmf->vma->vm_file->f_mapping; pgoff_t index = vmf->pgoff; + struct iov_iter iter; + struct kvec kvec; struct page *page; loff_t offset; - char *buf; int rc; page = find_or_create_page(mapping, index, GFP_KERNEL); @@ -423,8 +435,11 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) return VM_FAULT_OOM; if (!PageUptodate(page)) { offset = (loff_t) index << PAGE_SHIFT; - buf = __va((page_to_pfn(page) << PAGE_SHIFT)); - rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0); + kvec.iov_base = page_address(page); + kvec.iov_len = PAGE_SIZE; + iov_iter_kvec(&iter, READ, &kvec, 1, PAGE_SIZE); + + rc = __read_vmcore(&iter, &offset); if (rc < 0) { unlock_page(page); put_page(page); @@ -446,7 +461,7 @@ static const struct vm_operations_struct vmcore_mmap_ops = { /** * vmcore_alloc_buf - allocate buffer in vmalloc memory - * @sizez: size of buffer + * @size: size of buffer * * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap * the buffer to user-space by means of remap_vmalloc_range(). @@ -537,14 +552,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot) { + int ret, idx; + /* - * Check if oldmem_pfn_is_ram was registered to avoid - * looping over all pages without a reason. + * Check if a callback was registered to avoid looping over all + * pages without a reason. */ - if (oldmem_pfn_is_ram) - return remap_oldmem_pfn_checked(vma, from, pfn, size, prot); + idx = srcu_read_lock(&vmcore_cb_srcu); + if (!list_empty(&vmcore_cb_list)) + ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot); else - return remap_oldmem_pfn_range(vma, from, pfn, size, prot); + ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot); + srcu_read_unlock(&vmcore_cb_srcu, idx); + return ret; } static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) @@ -624,7 +644,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz; if (remap_vmalloc_range_partial(vma, vma->vm_start + len, - kaddr, tsz)) + kaddr, 0, tsz)) goto fail; size -= tsz; @@ -668,7 +688,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) #endif static const struct proc_ops vmcore_proc_ops = { - .proc_read = read_vmcore, + .proc_open = open_vmcore, + .proc_read_iter = read_vmcore, .proc_lseek = default_llseek, .proc_mmap = mmap_vmcore, }; @@ -1503,11 +1524,8 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) return 0; out_err: - if (buf) - vfree(buf); - - if (dump) - vfree(dump); + vfree(buf); + vfree(dump); return ret; } |