diff options
Diffstat (limited to 'fs/proc')
37 files changed, 10587 insertions, 4298 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig new file mode 100644 index 00000000000..2183fcf41d5 --- /dev/null +++ b/fs/proc/Kconfig @@ -0,0 +1,73 @@ +config PROC_FS + bool "/proc file system support" if EXPERT + default y + help + This is a virtual file system providing information about the status + of the system. "Virtual" means that it doesn't take up any space on + your hard disk: the files are created on the fly by the kernel when + you try to access them. Also, you cannot read the files with older + version of the program less: you need to use more or cat. + + It's totally cool; for example, "cat /proc/interrupts" gives + information about what the different IRQs are used for at the moment + (there is a small number of Interrupt ReQuest lines in your computer + that are used by the attached devices to gain the CPU's attention -- + often a source of trouble if two devices are mistakenly configured + to use the same IRQ). The program procinfo to display some + information about your system gathered from the /proc file system. + + Before you can use the /proc file system, it has to be mounted, + meaning it has to be given a location in the directory hierarchy. + That location should be /proc. A command such as "mount -t proc proc + /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 + ("man 5 proc"). + + This option will enlarge your kernel by about 67 KB. Several + programs depend on this, so everyone should say Y here. + +config PROC_KCORE + bool "/proc/kcore support" if !ARM + depends on PROC_FS && MMU + help + Provides a virtual ELF core file of the live kernel. This can + be read with gdb and other ELF tools. No modifications can be + made using this mechanism. + +config PROC_VMCORE + bool "/proc/vmcore support" + depends on PROC_FS && CRASH_DUMP + default y + help + Exports the dump image of crashed kernel in ELF format. + +config PROC_SYSCTL + bool "Sysctl support (/proc/sys)" if EXPERT + depends on PROC_FS + select SYSCTL + default y + ---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 + interface is through /proc/sys. If you say Y here a tree of + modifiable sysctl entries will be generated beneath the + /proc/sys directory. They are explained in the files + in <file:Documentation/sysctl/>. Note that enabling this + option will enlarge the kernel by at least 8 KB. + + As it is generally a good thing, you should say Y here unless + building a kernel for install/rescue disks or your system is very + limited in memory. + +config PROC_PAGE_MONITOR + default y + depends on PROC_FS && MMU + bool "Enable /proc page monitoring" if EXPERT + help + Various /proc files exist to monitor process memory utilization: + /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap, + /proc/kpagecount, and /proc/kpageflags. Disabling these + interfaces will reduce the size of the kernel by approximately 4kb. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 7431d7ba2d0..239493ec718 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -2,14 +2,30 @@ # Makefile for the Linux proc filesystem routines. # -obj-$(CONFIG_PROC_FS) += proc.o +obj-y += proc.o proc-y := nommu.o task_nommu.o -proc-$(CONFIG_MMU) := mmu.o task_mmu.o +proc-$(CONFIG_MMU) := task_mmu.o proc-y += inode.o root.o base.o generic.o array.o \ - kmsg.o proc_tty.o proc_misc.o - + fd.o +proc-$(CONFIG_TTY) += proc_tty.o +proc-y += cmdline.o +proc-y += consoles.o +proc-y += cpuinfo.o +proc-y += devices.o +proc-y += interrupts.o +proc-y += loadavg.o +proc-y += meminfo.o +proc-y += stat.o +proc-y += uptime.o +proc-y += version.o +proc-y += softirqs.o +proc-y += namespaces.o +proc-y += self.o +proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o +proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o -proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o +proc-$(CONFIG_PRINTK) += kmsg.o +proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o diff --git a/fs/proc/array.c b/fs/proc/array.c index 7eb1bd7f800..64db2bceac5 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -40,7 +40,7 @@ * * * Alan Cox : security fixes. - * <Alan.Cox@linux.org> + * <alan@lxorguk.ukuu.org.uk> * * Al Viro : safe handling of mm_struct * @@ -52,7 +52,6 @@ * : base.c too. */ -#include <linux/config.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/time.h> @@ -63,42 +62,46 @@ #include <linux/mman.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> #include <linux/pagemap.h> #include <linux/swap.h> -#include <linux/slab.h> #include <linux/smp.h> #include <linux/signal.h> #include <linux/highmem.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/times.h> #include <linux/cpuset.h> #include <linux/rcupdate.h> +#include <linux/delayacct.h> +#include <linux/seq_file.h> +#include <linux/pid_namespace.h> +#include <linux/ptrace.h> +#include <linux/tracehook.h> +#include <linux/user_namespace.h> -#include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm/io.h> #include <asm/processor.h> #include "internal.h" -/* Gcc optimizes away "strlen(x)" for constant x */ -#define ADDBUF(buffer, string) \ -do { memcpy(buffer, string, strlen(string)); \ - buffer += strlen(string); } while (0) - -static inline char * task_name(struct task_struct *p, char * buf) +static inline void task_name(struct seq_file *m, struct task_struct *p) { int i; - char * name; + char *buf, *end; + char *name; char tcomm[sizeof(p->comm)]; get_task_comm(tcomm, p); - ADDBUF(buf, "Name:\t"); + seq_puts(m, "Name:\t"); + end = m->buf + m->size; + buf = m->buf + m->count; name = tcomm; i = sizeof(tcomm); - do { + while (i && (buf < end)) { unsigned char c = *name; name++; i--; @@ -106,20 +109,21 @@ static inline char * task_name(struct task_struct *p, char * buf) if (!c) break; if (c == '\\') { - buf[1] = c; - buf += 2; + buf++; + if (buf < end) + *buf++ = c; continue; } if (c == '\n') { - buf[0] = '\\'; - buf[1] = 'n'; - buf += 2; + *buf++ = '\\'; + if (buf < end) + *buf++ = 'n'; continue; } buf++; - } while (i); - *buf = '\n'; - return buf+1; + } + m->count = buf - m->buf; + seq_putc(m, '\n'); } /* @@ -128,87 +132,94 @@ static inline char * task_name(struct task_struct *p, char * buf) * you can test for combinations of others with * simple bit tests. */ -static const char *task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "T (tracing stop)", /* 8 */ - "Z (zombie)", /* 16 */ - "X (dead)" /* 32 */ +static const char * const task_state_array[] = { + "R (running)", /* 0 */ + "S (sleeping)", /* 1 */ + "D (disk sleep)", /* 2 */ + "T (stopped)", /* 4 */ + "t (tracing stop)", /* 8 */ + "X (dead)", /* 16 */ + "Z (zombie)", /* 32 */ }; -static inline const char * get_task_state(struct task_struct *tsk) +static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state & (TASK_RUNNING | - TASK_INTERRUPTIBLE | - TASK_UNINTERRUPTIBLE | - TASK_STOPPED | - TASK_TRACED)) | - (tsk->exit_state & (EXIT_ZOMBIE | - EXIT_DEAD)); - const char **p = &task_state_array[0]; - - while (state) { - p++; - state >>= 1; - } - return *p; + unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; + + BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); + + return task_state_array[fls(state)]; } -static inline char * task_state(struct task_struct *p, char *buffer) +static inline void task_state(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *p) { + struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; int g; struct fdtable *fdt = NULL; + const struct cred *cred; + pid_t ppid, tpid; - read_lock(&tasklist_lock); - buffer += sprintf(buffer, + rcu_read_lock(); + ppid = pid_alive(p) ? + task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; + tpid = 0; + if (pid_alive(p)) { + struct task_struct *tracer = ptrace_parent(p); + if (tracer) + tpid = task_pid_nr_ns(tracer, ns); + } + cred = get_task_cred(p); + seq_printf(m, "State:\t%s\n" - "SleepAVG:\t%lu%%\n" "Tgid:\t%d\n" + "Ngid:\t%d\n" "Pid:\t%d\n" "PPid:\t%d\n" "TracerPid:\t%d\n" "Uid:\t%d\t%d\t%d\t%d\n" "Gid:\t%d\t%d\t%d\t%d\n", get_task_state(p), - (p->sleep_avg/1024)*100/(1020000000/1024), - p->tgid, - p->pid, pid_alive(p) ? p->group_leader->real_parent->tgid : 0, - pid_alive(p) && p->ptrace ? p->parent->pid : 0, - p->uid, p->euid, p->suid, p->fsuid, - p->gid, p->egid, p->sgid, p->fsgid); - read_unlock(&tasklist_lock); + task_tgid_nr_ns(p, ns), + task_numa_group_id(p), + pid_nr_ns(pid, ns), + ppid, tpid, + from_kuid_munged(user_ns, cred->uid), + from_kuid_munged(user_ns, cred->euid), + from_kuid_munged(user_ns, cred->suid), + from_kuid_munged(user_ns, cred->fsuid), + from_kgid_munged(user_ns, cred->gid), + from_kgid_munged(user_ns, cred->egid), + from_kgid_munged(user_ns, cred->sgid), + from_kgid_munged(user_ns, cred->fsgid)); + task_lock(p); - rcu_read_lock(); if (p->files) fdt = files_fdtable(p->files); - buffer += sprintf(buffer, + seq_printf(m, "FDSize:\t%d\n" "Groups:\t", fdt ? fdt->max_fds : 0); rcu_read_unlock(); - group_info = p->group_info; - get_group_info(group_info); + group_info = cred->group_info; task_unlock(p); - for (g = 0; g < min(group_info->ngroups,NGROUPS_SMALL); g++) - buffer += sprintf(buffer, "%d ", GROUP_AT(group_info,g)); - put_group_info(group_info); + for (g = 0; g < group_info->ngroups; g++) + seq_printf(m, "%d ", + from_kgid_munged(user_ns, GROUP_AT(group_info, g))); + put_cred(cred); - buffer += sprintf(buffer, "\n"); - return buffer; + seq_putc(m, '\n'); } -static char * render_sigset_t(const char *header, sigset_t *set, char *buffer) +void render_sigset_t(struct seq_file *m, const char *header, + sigset_t *set) { - int i, len; + int i; - len = strlen(header); - memcpy(buffer, header, len); - buffer += len; + seq_puts(m, header); i = _NSIG; do { @@ -219,12 +230,10 @@ static char * render_sigset_t(const char *header, sigset_t *set, char *buffer) if (sigismember(set, i+2)) x |= 2; if (sigismember(set, i+3)) x |= 4; if (sigismember(set, i+4)) x |= 8; - *buffer++ = (x < 10 ? '0' : 'a' - 10) + x; + seq_printf(m, "%x", x); } while (i >= 4); - *buffer++ = '\n'; - *buffer = 0; - return buffer; + seq_putc(m, '\n'); } static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, @@ -242,8 +251,9 @@ static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign, } } -static inline char * task_sig(struct task_struct *p, char *buffer) +static inline void task_sig(struct seq_file *m, struct task_struct *p) { + unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; unsigned long qsize = 0; @@ -255,149 +265,207 @@ static inline char * task_sig(struct task_struct *p, char *buffer) sigemptyset(&ignored); sigemptyset(&caught); - /* Gather all the data with the appropriate locks held */ - read_lock(&tasklist_lock); - if (p->sighand) { - spin_lock_irq(&p->sighand->siglock); + if (lock_task_sighand(p, &flags)) { pending = p->pending.signal; shpending = p->signal->shared_pending.signal; blocked = p->blocked; collect_sigign_sigcatch(p, &ignored, &caught); - num_threads = atomic_read(&p->signal->count); - qsize = atomic_read(&p->user->sigpending); - qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur; - spin_unlock_irq(&p->sighand->siglock); + num_threads = get_nr_threads(p); + rcu_read_lock(); /* FIXME: is this correct? */ + qsize = atomic_read(&__task_cred(p)->user->sigpending); + rcu_read_unlock(); + qlim = task_rlimit(p, RLIMIT_SIGPENDING); + unlock_task_sighand(p, &flags); } - read_unlock(&tasklist_lock); - buffer += sprintf(buffer, "Threads:\t%d\n", num_threads); - buffer += sprintf(buffer, "SigQ:\t%lu/%lu\n", qsize, qlim); + seq_printf(m, "Threads:\t%d\n", num_threads); + seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim); /* render them all */ - buffer = render_sigset_t("SigPnd:\t", &pending, buffer); - buffer = render_sigset_t("ShdPnd:\t", &shpending, buffer); - buffer = render_sigset_t("SigBlk:\t", &blocked, buffer); - buffer = render_sigset_t("SigIgn:\t", &ignored, buffer); - buffer = render_sigset_t("SigCgt:\t", &caught, buffer); + render_sigset_t(m, "SigPnd:\t", &pending); + render_sigset_t(m, "ShdPnd:\t", &shpending); + render_sigset_t(m, "SigBlk:\t", &blocked); + render_sigset_t(m, "SigIgn:\t", &ignored); + render_sigset_t(m, "SigCgt:\t", &caught); +} + +static void render_cap_t(struct seq_file *m, const char *header, + kernel_cap_t *a) +{ + unsigned __capi; - return buffer; + seq_puts(m, header); + CAP_FOR_EACH_U32(__capi) { + seq_printf(m, "%08x", + a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]); + } + seq_putc(m, '\n'); } -static inline char *task_cap(struct task_struct *p, char *buffer) +/* Remove non-existent capabilities */ +#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \ + CAP_TO_MASK(CAP_LAST_CAP + 1) - 1) + +static inline void task_cap(struct seq_file *m, struct task_struct *p) { - return buffer + sprintf(buffer, "CapInh:\t%016x\n" - "CapPrm:\t%016x\n" - "CapEff:\t%016x\n", - cap_t(p->cap_inheritable), - cap_t(p->cap_permitted), - cap_t(p->cap_effective)); + const struct cred *cred; + kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset; + + rcu_read_lock(); + cred = __task_cred(p); + cap_inheritable = cred->cap_inheritable; + cap_permitted = cred->cap_permitted; + cap_effective = cred->cap_effective; + cap_bset = cred->cap_bset; + rcu_read_unlock(); + + NORM_CAPS(cap_inheritable); + NORM_CAPS(cap_permitted); + NORM_CAPS(cap_effective); + NORM_CAPS(cap_bset); + + render_cap_t(m, "CapInh:\t", &cap_inheritable); + render_cap_t(m, "CapPrm:\t", &cap_permitted); + render_cap_t(m, "CapEff:\t", &cap_effective); + render_cap_t(m, "CapBnd:\t", &cap_bset); +} + +static inline void task_seccomp(struct seq_file *m, struct task_struct *p) +{ +#ifdef CONFIG_SECCOMP + seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode); +#endif +} + +static inline void task_context_switch_counts(struct seq_file *m, + struct task_struct *p) +{ + seq_printf(m, "voluntary_ctxt_switches:\t%lu\n" + "nonvoluntary_ctxt_switches:\t%lu\n", + p->nvcsw, + p->nivcsw); +} + +static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_puts(m, "Cpus_allowed:\t"); + seq_cpumask(m, &task->cpus_allowed); + seq_putc(m, '\n'); + seq_puts(m, "Cpus_allowed_list:\t"); + seq_cpumask_list(m, &task->cpus_allowed); + seq_putc(m, '\n'); } -int proc_pid_status(struct task_struct *task, char * buffer) +int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - char * orig = buffer; struct mm_struct *mm = get_task_mm(task); - buffer = task_name(task, buffer); - buffer = task_state(task, buffer); - + task_name(m, task); + task_state(m, ns, pid, task); + if (mm) { - buffer = task_mem(mm, buffer); + task_mem(m, mm); mmput(mm); } - buffer = task_sig(task, buffer); - buffer = task_cap(task, buffer); - buffer = cpuset_task_status_allowed(task, buffer); -#if defined(CONFIG_S390) - buffer = task_show_regs(task, buffer); -#endif - return buffer - orig; + task_sig(m, task); + task_cap(m, task); + task_seccomp(m, task); + task_cpus_allowed(m, task); + cpuset_task_status_allowed(m, task); + task_context_switch_counts(m, task); + return 0; } -static int do_task_stat(struct task_struct *task, char * buffer, int whole) +static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task, int whole) { unsigned long vsize, eip, esp, wchan = ~0UL; - long priority, nice; + int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; char state; - int res; - pid_t ppid, pgid = -1, sid = -1; + pid_t ppid = 0, pgid = -1, sid = -1; int num_threads = 0; + int permitted; struct mm_struct *mm; unsigned long long start_time; unsigned long cmin_flt = 0, cmaj_flt = 0; unsigned long min_flt = 0, maj_flt = 0; cputime_t cutime, cstime, utime, stime; + cputime_t cgtime, gtime; unsigned long rsslim = 0; - DEFINE_KTIME(it_real_value); - struct task_struct *t; char tcomm[sizeof(task->comm)]; + unsigned long flags; state = *get_task_state(task); vsize = eip = esp = 0; + permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); - eip = KSTK_EIP(task); - esp = KSTK_ESP(task); + if (permitted) { + eip = KSTK_EIP(task); + esp = KSTK_ESP(task); + } } get_task_comm(tcomm, task); sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = cputime_zero; - read_lock(&tasklist_lock); - if (task->sighand) { - spin_lock_irq(&task->sighand->siglock); - num_threads = atomic_read(&task->signal->count); + cutime = cstime = utime = stime = 0; + cgtime = gtime = 0; + + if (lock_task_sighand(task, &flags)) { + struct signal_struct *sig = task->signal; + + if (sig->tty) { + struct pid *pgrp = tty_get_pgrp(sig->tty); + tty_pgrp = pid_nr_ns(pgrp, ns); + put_pid(pgrp); + tty_nr = new_encode_dev(tty_devnum(sig->tty)); + } + + num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch); + cmin_flt = sig->cmin_flt; + cmaj_flt = sig->cmaj_flt; + cutime = sig->cutime; + cstime = sig->cstime; + cgtime = sig->cgtime; + rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); + /* add up live thread stats at the group level */ if (whole) { - t = task; + struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != task); - } + gtime += task_gtime(t); + } while_each_thread(task, t); - spin_unlock_irq(&task->sighand->siglock); - } - if (task->signal) { - if (task->signal->tty) { - tty_pgrp = task->signal->tty->pgrp; - tty_nr = new_encode_dev(tty_devnum(task->signal->tty)); + min_flt += sig->min_flt; + maj_flt += sig->maj_flt; + thread_group_cputime_adjusted(task, &utime, &stime); + gtime += sig->gtime; } - pgid = process_group(task); - sid = task->signal->session; - cmin_flt = task->signal->cmin_flt; - cmaj_flt = task->signal->cmaj_flt; - cutime = task->signal->cutime; - cstime = task->signal->cstime; - rsslim = task->signal->rlim[RLIMIT_RSS].rlim_cur; - if (whole) { - min_flt += task->signal->min_flt; - maj_flt += task->signal->maj_flt; - utime = cputime_add(utime, task->signal->utime); - stime = cputime_add(stime, task->signal->stime); - } - it_real_value = task->signal->real_timer.expires; + + sid = task_session_nr_ns(task, ns); + ppid = task_tgid_nr_ns(task->real_parent, ns); + pgid = task_pgrp_nr_ns(task, ns); + + unlock_task_sighand(task, &flags); } - ppid = pid_alive(task) ? task->group_leader->real_parent->tgid : 0; - read_unlock(&tasklist_lock); - if (!whole || num_threads<2) + if (permitted && (!whole || num_threads < 2)) wchan = get_wchan(task); if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - utime = task->utime; - stime = task->stime; + task_cputime_adjusted(task, &utime, &stime); + gtime = task_gtime(task); } /* scale priority and nice values from timeslices to -20..20 */ @@ -407,84 +475,240 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) /* Temporary variable needed for gcc-2.96 */ /* convert timespec -> nsec*/ - start_time = (unsigned long long)task->start_time.tv_sec * NSEC_PER_SEC - + task->start_time.tv_nsec; + start_time = + (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC + + task->real_start_time.tv_nsec; /* convert nsec -> ticks */ start_time = nsec_to_clock_t(start_time); - res = sprintf(buffer,"%d (%s) %c %d %d %d %d %d %lu %lu \ -%lu %lu %lu %lu %lu %ld %ld %ld %ld %d %ld %llu %lu %ld %lu %lu %lu %lu %lu \ -%lu %lu %lu %lu %lu %lu %lu %lu %d %d %lu %lu\n", - task->pid, - tcomm, - state, - ppid, - pgid, - sid, - tty_nr, - tty_pgrp, - task->flags, - min_flt, - cmin_flt, - maj_flt, - cmaj_flt, - cputime_to_clock_t(utime), - cputime_to_clock_t(stime), - cputime_to_clock_t(cutime), - cputime_to_clock_t(cstime), - priority, - nice, - num_threads, - (long) ktime_to_clock_t(it_real_value), - start_time, - vsize, - mm ? get_mm_rss(mm) : 0, - rsslim, - mm ? mm->start_code : 0, - mm ? mm->end_code : 0, - mm ? mm->start_stack : 0, - esp, - eip, - /* The signal information here is obsolete. - * It must be decimal for Linux 2.0 compatibility. - * Use /proc/#/status for real-time signals. - */ - task->pending.signal.sig[0] & 0x7fffffffUL, - task->blocked.sig[0] & 0x7fffffffUL, - sigign .sig[0] & 0x7fffffffUL, - sigcatch .sig[0] & 0x7fffffffUL, - wchan, - 0UL, - 0UL, - task->exit_signal, - task_cpu(task), - task->rt_priority, - task->policy); - if(mm) + seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); + seq_put_decimal_ll(m, ' ', ppid); + seq_put_decimal_ll(m, ' ', pgid); + seq_put_decimal_ll(m, ' ', sid); + seq_put_decimal_ll(m, ' ', tty_nr); + seq_put_decimal_ll(m, ' ', tty_pgrp); + seq_put_decimal_ull(m, ' ', task->flags); + seq_put_decimal_ull(m, ' ', min_flt); + seq_put_decimal_ull(m, ' ', cmin_flt); + seq_put_decimal_ull(m, ' ', maj_flt); + seq_put_decimal_ull(m, ' ', cmaj_flt); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(utime)); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(stime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cutime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cstime)); + seq_put_decimal_ll(m, ' ', priority); + seq_put_decimal_ll(m, ' ', nice); + seq_put_decimal_ll(m, ' ', num_threads); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, ' ', start_time); + seq_put_decimal_ull(m, ' ', vsize); + seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0); + seq_put_decimal_ull(m, ' ', rsslim); + seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0); + seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0); + seq_put_decimal_ull(m, ' ', (permitted && mm) ? mm->start_stack : 0); + seq_put_decimal_ull(m, ' ', esp); + seq_put_decimal_ull(m, ' ', eip); + /* The signal information here is obsolete. + * It must be decimal for Linux 2.0 compatibility. + * Use /proc/#/status for real-time signals. + */ + seq_put_decimal_ull(m, ' ', task->pending.signal.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); + seq_put_decimal_ull(m, ' ', wchan); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ull(m, ' ', 0); + seq_put_decimal_ll(m, ' ', task->exit_signal); + seq_put_decimal_ll(m, ' ', task_cpu(task)); + seq_put_decimal_ull(m, ' ', task->rt_priority); + seq_put_decimal_ull(m, ' ', task->policy); + seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task)); + seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime)); + seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime)); + + if (mm && permitted) { + seq_put_decimal_ull(m, ' ', mm->start_data); + seq_put_decimal_ull(m, ' ', mm->end_data); + seq_put_decimal_ull(m, ' ', mm->start_brk); + seq_put_decimal_ull(m, ' ', mm->arg_start); + seq_put_decimal_ull(m, ' ', mm->arg_end); + seq_put_decimal_ull(m, ' ', mm->env_start); + seq_put_decimal_ull(m, ' ', mm->env_end); + } else + seq_printf(m, " 0 0 0 0 0 0 0"); + + if (permitted) + seq_put_decimal_ll(m, ' ', task->exit_code); + else + seq_put_decimal_ll(m, ' ', 0); + + seq_putc(m, '\n'); + if (mm) mmput(mm); - return res; + return 0; } -int proc_tid_stat(struct task_struct *task, char * buffer) +int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - return do_task_stat(task, buffer, 0); + return do_task_stat(m, ns, pid, task, 0); } -int proc_tgid_stat(struct task_struct *task, char * buffer) +int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - return do_task_stat(task, buffer, 1); + return do_task_stat(m, ns, pid, task, 1); } -int proc_pid_statm(struct task_struct *task, char *buffer) +int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0; + unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0; struct mm_struct *mm = get_task_mm(task); - + if (mm) { 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, 0, 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'); + + return 0; +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +static struct pid * +get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos) +{ + struct task_struct *start, *task; + struct pid *pid = NULL; + + read_lock(&tasklist_lock); + + start = pid_task(proc_pid(inode), PIDTYPE_PID); + if (!start) + goto out; + + /* + * Lets try to continue searching first, this gives + * us significant speedup on children-rich processes. + */ + if (pid_prev) { + task = pid_task(pid_prev, PIDTYPE_PID); + if (task && task->real_parent == start && + !(list_empty(&task->sibling))) { + if (list_is_last(&task->sibling, &start->children)) + goto out; + task = list_first_entry(&task->sibling, + struct task_struct, sibling); + pid = get_pid(task_pid(task)); + goto out; + } + } + + /* + * Slow search case. + * + * We might miss some children here if children + * are exited while we were not holding the lock, + * but it was never promised to be accurate that + * much. + * + * "Just suppose that the parent sleeps, but N children + * exit after we printed their tids. Now the slow paths + * skips N extra children, we miss N tasks." (c) + * + * So one need to stop or freeze the leader and all + * its children to get a precise result. + */ + list_for_each_entry(task, &start->children, sibling) { + if (pos-- == 0) { + pid = get_pid(task_pid(task)); + break; + } + } + +out: + read_unlock(&tasklist_lock); + return pid; +} + +static int children_seq_show(struct seq_file *seq, void *v) +{ + struct inode *inode = seq->private; + pid_t pid; + + pid = pid_nr_ns(v, inode->i_sb->s_fs_info); + return seq_printf(seq, "%d ", pid); +} + +static void *children_seq_start(struct seq_file *seq, loff_t *pos) +{ + return get_children_pid(seq->private, NULL, *pos); +} + +static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct pid *pid; - return sprintf(buffer,"%d %d %d %d %d %d %d\n", - size, resident, shared, text, lib, data, 0); + pid = get_children_pid(seq->private, v, *pos + 1); + put_pid(v); + + ++*pos; + return pid; +} + +static void children_seq_stop(struct seq_file *seq, void *v) +{ + put_pid(v); } + +static const struct seq_operations children_seq_ops = { + .start = children_seq_start, + .next = children_seq_next, + .stop = children_seq_stop, + .show = children_seq_show, +}; + +static int children_seq_open(struct inode *inode, struct file *file) +{ + struct seq_file *m; + int ret; + + ret = seq_open(file, &children_seq_ops); + if (ret) + return ret; + + m = file->private_data; + m->private = inode; + + return ret; +} + +int children_seq_release(struct inode *inode, struct file *file) +{ + seq_release(inode, file); + return 0; +} + +const struct file_operations proc_tid_children_operations = { + .open = children_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = children_seq_release, +}; +#endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 20feb7568de..2d696b0c93b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -49,424 +49,171 @@ #include <asm/uaccess.h> -#include <linux/config.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> +#include <linux/task_io_accounting_ops.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> -#include <linux/namespace.h> +#include <linux/mnt_namespace.h> #include <linux/mm.h> -#include <linux/smp_lock.h> +#include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> +#include <linux/stacktrace.h> +#include <linux/resource.h> +#include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> -#include <linux/seccomp.h> +#include <linux/tracehook.h> +#include <linux/printk.h> +#include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> +#include <linux/nsproxy.h> +#include <linux/oom.h> +#include <linux/elf.h> +#include <linux/pid_namespace.h> +#include <linux/user_namespace.h> +#include <linux/fs_struct.h> +#include <linux/slab.h> +#include <linux/flex_array.h> +#include <linux/posix-timers.h> +#ifdef CONFIG_HARDWALL +#include <asm/hardwall.h> +#endif +#include <trace/events/oom.h> #include "internal.h" +#include "fd.h" -/* - * For hysterical raisins we keep the same inumbers as in the old procfs. - * Feel free to change the macro below - just keep the range distinct from - * inumbers of the rest of procfs (currently those are in 0x0000--0xffff). - * As soon as we'll get a separate superblock we will be able to forget - * about magical ranges too. +/* NOTE: + * Implementing inode permission operations in /proc is almost + * certainly an error. Permission checks need to happen during + * each system call not at open time. The reason is that most of + * what we wish to check for permissions in /proc varies at runtime. + * + * The classic example of a problem is opening file descriptors + * in /proc for a task before it execs a suid executable. */ -#define fake_ino(pid,ino) (((pid)<<16)|(ino)) - -enum pid_directory_inos { - PROC_TGID_INO = 2, - PROC_TGID_TASK, - PROC_TGID_STATUS, - PROC_TGID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TGID_SECCOMP, -#endif - PROC_TGID_CWD, - PROC_TGID_ROOT, - PROC_TGID_EXE, - PROC_TGID_FD, - PROC_TGID_ENVIRON, - PROC_TGID_AUXV, - PROC_TGID_CMDLINE, - PROC_TGID_STAT, - PROC_TGID_STATM, - PROC_TGID_MAPS, - PROC_TGID_NUMA_MAPS, - PROC_TGID_MOUNTS, - PROC_TGID_WCHAN, -#ifdef CONFIG_MMU - PROC_TGID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TGID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TGID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TGID_ATTR, - PROC_TGID_ATTR_CURRENT, - PROC_TGID_ATTR_PREV, - PROC_TGID_ATTR_EXEC, - PROC_TGID_ATTR_FSCREATE, -#endif -#ifdef CONFIG_AUDITSYSCALL - PROC_TGID_LOGINUID, -#endif - PROC_TGID_OOM_SCORE, - PROC_TGID_OOM_ADJUST, - PROC_TID_INO, - PROC_TID_STATUS, - PROC_TID_MEM, -#ifdef CONFIG_SECCOMP - PROC_TID_SECCOMP, -#endif - PROC_TID_CWD, - PROC_TID_ROOT, - PROC_TID_EXE, - PROC_TID_FD, - PROC_TID_ENVIRON, - PROC_TID_AUXV, - PROC_TID_CMDLINE, - PROC_TID_STAT, - PROC_TID_STATM, - PROC_TID_MAPS, - PROC_TID_NUMA_MAPS, - PROC_TID_MOUNTS, - PROC_TID_WCHAN, -#ifdef CONFIG_MMU - PROC_TID_SMAPS, -#endif -#ifdef CONFIG_SCHEDSTATS - PROC_TID_SCHEDSTAT, -#endif -#ifdef CONFIG_CPUSETS - PROC_TID_CPUSET, -#endif -#ifdef CONFIG_SECURITY - PROC_TID_ATTR, - PROC_TID_ATTR_CURRENT, - PROC_TID_ATTR_PREV, - PROC_TID_ATTR_EXEC, - PROC_TID_ATTR_FSCREATE, -#endif -#ifdef CONFIG_AUDITSYSCALL - PROC_TID_LOGINUID, -#endif - PROC_TID_OOM_SCORE, - PROC_TID_OOM_ADJUST, - - /* Add new entries before this */ - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ -}; - struct pid_entry { - int type; - int len; char *name; - mode_t mode; -}; - -#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)} - -static struct pid_entry tgid_base_stuff[] = { - E(PROC_TGID_TASK, "task", S_IFDIR|S_IRUGO|S_IXUGO), - E(PROC_TGID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TGID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TGID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TGID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TGID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TGID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), -#ifdef CONFIG_MMU - E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TGID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TGID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; -static struct pid_entry tid_base_stuff[] = { - E(PROC_TID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), - E(PROC_TID_ENVIRON, "environ", S_IFREG|S_IRUSR), - E(PROC_TID_AUXV, "auxv", S_IFREG|S_IRUSR), - E(PROC_TID_STATUS, "status", S_IFREG|S_IRUGO), - E(PROC_TID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), - E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), - E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), - E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), -#ifdef CONFIG_NUMA - E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), -#ifdef CONFIG_SECCOMP - E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), -#endif - E(PROC_TID_CWD, "cwd", S_IFLNK|S_IRWXUGO), - E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), - E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), - E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), -#ifdef CONFIG_MMU - E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SECURITY - E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), -#endif -#ifdef CONFIG_KALLSYMS - E(PROC_TID_WCHAN, "wchan", S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_SCHEDSTATS - E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO), -#endif -#ifdef CONFIG_CPUSETS - E(PROC_TID_CPUSET, "cpuset", S_IFREG|S_IRUGO), -#endif - E(PROC_TID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), - E(PROC_TID_OOM_ADJUST, "oom_adj", S_IFREG|S_IRUGO|S_IWUSR), -#ifdef CONFIG_AUDITSYSCALL - E(PROC_TID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), -#endif - {0,0,NULL,0} -}; - -#ifdef CONFIG_SECURITY -static struct pid_entry tgid_attr_stuff[] = { - E(PROC_TGID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TGID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} -}; -static struct pid_entry tid_attr_stuff[] = { - E(PROC_TID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), - E(PROC_TID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), - E(PROC_TID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), - {0,0,NULL,0} + int len; + umode_t mode; + const struct inode_operations *iop; + const struct file_operations *fop; + union proc_op op; }; -#endif -#undef E +#define NOD(NAME, MODE, IOP, FOP, OP) { \ + .name = (NAME), \ + .len = sizeof(NAME) - 1, \ + .mode = MODE, \ + .iop = IOP, \ + .fop = FOP, \ + .op = OP, \ +} + +#define DIR(NAME, MODE, iops, fops) \ + NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) +#define LNK(NAME, get_link) \ + NOD(NAME, (S_IFLNK|S_IRWXUGO), \ + &proc_pid_link_inode_operations, NULL, \ + { .proc_get_link = get_link } ) +#define REG(NAME, MODE, fops) \ + NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) +#define INF(NAME, MODE, read) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_info_file_operations, \ + { .proc_read = read } ) +#define ONE(NAME, MODE, show) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_single_file_operations, \ + { .proc_show = show } ) -static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +/* + * Count the number of hardlinks for the pid_entry table, excluding the . + * and .. links. + */ +static unsigned int pid_entry_count_dirs(const struct pid_entry *entries, + unsigned int n) { - struct task_struct *task = proc_task(inode); - struct files_struct *files; - struct file *file; - int fd = proc_type(inode) - PROC_TID_FD_DIR; + unsigned int i; + unsigned int count; - files = get_files_struct(task); - if (files) { - rcu_read_lock(); - file = fcheck_files(files, fd); - if (file) { - *mnt = mntget(file->f_vfsmnt); - *dentry = dget(file->f_dentry); - rcu_read_unlock(); - put_files_struct(files); - return 0; - } - rcu_read_unlock(); - put_files_struct(files); + count = 0; + for (i = 0; i < n; ++i) { + if (S_ISDIR(entries[i].mode)) + ++count; } - return -ENOENT; -} -static struct fs_struct *get_fs_struct(struct task_struct *task) -{ - struct fs_struct *fs; - task_lock(task); - fs = task->fs; - if(fs) - atomic_inc(&fs->count); - task_unlock(task); - return fs; + return count; } -static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +static int get_task_root(struct task_struct *task, struct path *root) { - struct fs_struct *fs = get_fs_struct(proc_task(inode)); int result = -ENOENT; - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->pwdmnt); - *dentry = dget(fs->pwd); - read_unlock(&fs->lock); - result = 0; - put_fs_struct(fs); - } - return result; -} -static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) -{ - struct fs_struct *fs = get_fs_struct(proc_task(inode)); - int result = -ENOENT; - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->rootmnt); - *dentry = dget(fs->root); - read_unlock(&fs->lock); + task_lock(task); + if (task->fs) { + get_fs_root(task->fs, root); result = 0; - put_fs_struct(fs); } + task_unlock(task); return result; } - -/* Same as proc_root_link, but this addionally tries to get fs from other - * threads in the group */ -static int proc_task_root_link(struct inode *inode, struct dentry **dentry, - struct vfsmount **mnt) +static int proc_cwd_link(struct dentry *dentry, struct path *path) { - struct fs_struct *fs; + struct task_struct *task = get_proc_task(dentry->d_inode); int result = -ENOENT; - struct task_struct *leader = proc_task(inode); - task_lock(leader); - fs = leader->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(leader); - } else { - /* Try to get fs from other threads */ - task_unlock(leader); - read_lock(&tasklist_lock); - if (pid_alive(leader)) { - struct task_struct *task = leader; - - while ((task = next_thread(task)) != leader) { - task_lock(task); - fs = task->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(task); - break; - } - task_unlock(task); - } + if (task) { + task_lock(task); + if (task->fs) { + get_fs_pwd(task->fs, path); + result = 0; } - read_unlock(&tasklist_lock); - } - - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->rootmnt); - *dentry = dget(fs->root); - read_unlock(&fs->lock); - result = 0; - put_fs_struct(fs); + task_unlock(task); + put_task_struct(task); } return result; } - -#define MAY_PTRACE(task) \ - (task == current || \ - (task->parent == current && \ - (task->ptrace & PT_PTRACED) && \ - (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ - security_ptrace(current,task) == 0)) - -static int proc_pid_environ(struct task_struct *task, char * buffer) +static int proc_root_link(struct dentry *dentry, struct path *path) { - int res = 0; - struct mm_struct *mm = get_task_mm(task); - if (mm) { - unsigned int len = mm->env_end - mm->env_start; - if (len > PAGE_SIZE) - len = PAGE_SIZE; - res = access_process_vm(task, mm->env_start, buffer, len, 0); - if (!ptrace_may_attach(task)) - res = -ESRCH; - mmput(mm); + struct task_struct *task = get_proc_task(dentry->d_inode); + int result = -ENOENT; + + if (task) { + result = get_task_root(task, path); + put_task_struct(task); } - return res; + return result; } -static int proc_pid_cmdline(struct task_struct *task, char * buffer) +static int proc_pid_cmdline(struct task_struct *task, char *buffer) { - int res = 0; - unsigned int len; - struct mm_struct *mm = get_task_mm(task); - if (!mm) - goto out; - if (!mm->arg_end) - goto out_mm; /* Shh! No looking before we're done */ - - len = mm->arg_end - mm->arg_start; - - if (len > PAGE_SIZE) - len = PAGE_SIZE; - - res = access_process_vm(task, mm->arg_start, buffer, len, 0); - - // If the nul at the end of args has been overwritten, then - // assume application is using setproctitle(3). - if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) { - len = strnlen(buffer, res); - if (len < res) { - res = len; - } else { - len = mm->env_end - mm->env_start; - if (len > PAGE_SIZE - res) - len = PAGE_SIZE - res; - res += access_process_vm(task, mm->env_start, buffer+res, len, 0); - res = strnlen(buffer, res); - } - } -out_mm: - mmput(mm); -out: - return res; + return get_cmdline(task, buffer, PAGE_SIZE); } static int proc_pid_auxv(struct task_struct *task, char *buffer) { - int res = 0; - struct mm_struct *mm = get_task_mm(task); - if (mm) { + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + int res = PTR_ERR(mm); + if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; - do + do { nwords += 2; - while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ + } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ res = nwords * sizeof(mm->saved_auxv[0]); if (res > PAGE_SIZE) res = PAGE_SIZE; @@ -484,252 +231,371 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer) */ static int proc_pid_wchan(struct task_struct *task, char *buffer) { - char *modname; - const char *sym_name; - unsigned long wchan, size, offset; - char namebuf[KSYM_NAME_LEN+1]; + unsigned long wchan; + char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); - sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf); - if (sym_name) - return sprintf(buffer, "%s", sym_name); - return sprintf(buffer, "%lu", wchan); + if (lookup_symbol_name(wchan, symname) < 0) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + return 0; + else + return sprintf(buffer, "%lu", wchan); + else + return sprintf(buffer, "%s", symname); } #endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_SCHEDSTATS -/* - * Provides /proc/PID/schedstat - */ -static int proc_pid_schedstat(struct task_struct *task, char *buffer) +static int lock_trace(struct task_struct *task) { - return sprintf(buffer, "%lu %lu %lu\n", - task->sched_info.cpu_time, - task->sched_info.run_delay, - task->sched_info.pcnt); + int err = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (err) + return err; + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + mutex_unlock(&task->signal->cred_guard_mutex); + return -EPERM; + } + return 0; } -#endif -/* The badness from the OOM killer */ -unsigned long badness(struct task_struct *p, unsigned long uptime); -static int proc_oom_score(struct task_struct *task, char *buffer) +static void unlock_trace(struct task_struct *task) { - unsigned long points; - struct timespec uptime; - - do_posix_clock_monotonic_gettime(&uptime); - points = badness(task, uptime.tv_sec); - return sprintf(buffer, "%lu\n", points); + mutex_unlock(&task->signal->cred_guard_mutex); } -/************************************************************************/ -/* Here the fs part begins */ -/************************************************************************/ +#ifdef CONFIG_STACKTRACE -/* permission checks */ +#define MAX_STACK_TRACE_DEPTH 64 -/* If the process being read is separated by chroot from the reading process, - * don't let the reader access the threads. - */ -static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt) +static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - struct dentry *de, *base; - struct vfsmount *our_vfsmnt, *mnt; - int res = 0; - read_lock(¤t->fs->lock); - our_vfsmnt = mntget(current->fs->rootmnt); - base = dget(current->fs->root); - read_unlock(¤t->fs->lock); + struct stack_trace trace; + unsigned long *entries; + int err; + int i; - spin_lock(&vfsmount_lock); - de = root; - mnt = vfsmnt; + entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); + if (!entries) + return -ENOMEM; - while (vfsmnt != our_vfsmnt) { - if (vfsmnt == vfsmnt->mnt_parent) - goto out; - de = vfsmnt->mnt_mountpoint; - vfsmnt = vfsmnt->mnt_parent; - } + trace.nr_entries = 0; + trace.max_entries = MAX_STACK_TRACE_DEPTH; + trace.entries = entries; + trace.skip = 0; - if (!is_subdir(de, base)) - goto out; - spin_unlock(&vfsmount_lock); + err = lock_trace(task); + if (!err) { + save_stack_trace_tsk(task, &trace); -exit: - dput(base); - mntput(our_vfsmnt); - dput(root); - mntput(mnt); - return res; -out: - spin_unlock(&vfsmount_lock); - res = -EACCES; - goto exit; -} - -static int proc_check_root(struct inode *inode) -{ - struct dentry *root; - struct vfsmount *vfsmnt; + for (i = 0; i < trace.nr_entries; i++) { + seq_printf(m, "[<%pK>] %pS\n", + (void *)entries[i], (void *)entries[i]); + } + unlock_trace(task); + } + kfree(entries); - if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ - return -ENOENT; - return proc_check_chroot(root, vfsmnt); + return err; } +#endif -static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) +#ifdef CONFIG_SCHEDSTATS +/* + * Provides /proc/PID/schedstat + */ +static int proc_pid_schedstat(struct task_struct *task, char *buffer) { - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; - return proc_check_root(inode); + return sprintf(buffer, "%llu %llu %lu\n", + (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)task->sched_info.run_delay, + task->sched_info.pcount); } +#endif -static int proc_task_permission(struct inode *inode, int mask, struct nameidata *nd) +#ifdef CONFIG_LATENCYTOP +static int lstats_show_proc(struct seq_file *m, void *v) { - struct dentry *root; - struct vfsmount *vfsmnt; + int i; + struct inode *inode = m->private; + struct task_struct *task = get_proc_task(inode); - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; + if (!task) + return -ESRCH; + seq_puts(m, "Latency Top version : v0.1\n"); + for (i = 0; i < 32; i++) { + struct latency_record *lr = &task->latency_record[i]; + if (lr->backtrace[0]) { + int q; + seq_printf(m, "%i %li %li", + lr->count, lr->time, lr->max); + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { + unsigned long bt = lr->backtrace[q]; + if (!bt) + break; + if (bt == ULONG_MAX) + break; + seq_printf(m, " %ps", (void *)bt); + } + seq_putc(m, '\n'); + } - if (proc_task_root_link(inode, &root, &vfsmnt)) - return -ENOENT; + } + put_task_struct(task); + return 0; +} - return proc_check_chroot(root, vfsmnt); +static int lstats_open(struct inode *inode, struct file *file) +{ + return single_open(file, lstats_show_proc, inode); } -extern struct seq_operations proc_pid_maps_op; -static int maps_open(struct inode *inode, struct file *file) +static ssize_t lstats_write(struct file *file, const char __user *buf, + size_t count, loff_t *offs) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; + struct task_struct *task = get_proc_task(file_inode(file)); + + if (!task) + return -ESRCH; + clear_all_latency_tracing(task); + put_task_struct(task); + + return count; } -static struct file_operations proc_maps_operations = { - .open = maps_open, +static const struct file_operations proc_lstats_operations = { + .open = lstats_open, .read = seq_read, + .write = lstats_write, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; -#ifdef CONFIG_NUMA -extern struct seq_operations proc_pid_numa_maps_op; -static int numa_maps_open(struct inode *inode, struct file *file) +#endif + +#ifdef CONFIG_CGROUPS +static int cgroup_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_numa_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; + struct pid *pid = PROC_I(inode)->pid; + return single_open(file, proc_cgroup_show, pid); } -static struct file_operations proc_numa_maps_operations = { - .open = numa_maps_open, +static const struct file_operations proc_cgroup_operations = { + .open = cgroup_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; #endif -#ifdef CONFIG_MMU -extern struct seq_operations proc_pid_smaps_op; -static int smaps_open(struct inode *inode, struct file *file) +#ifdef CONFIG_PROC_PID_CPUSET + +static int cpuset_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_smaps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; + struct pid *pid = PROC_I(inode)->pid; + return single_open(file, proc_cpuset_show, pid); } -static struct file_operations proc_smaps_operations = { - .open = smaps_open, +static const struct file_operations proc_cpuset_operations = { + .open = cpuset_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; #endif -extern struct seq_operations mounts_op; -struct proc_mounts { - struct seq_file m; - int event; +static int proc_oom_score(struct task_struct *task, char *buffer) +{ + unsigned long totalpages = totalram_pages + total_swap_pages; + unsigned long points = 0; + + read_lock(&tasklist_lock); + if (pid_alive(task)) + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; + read_unlock(&tasklist_lock); + return sprintf(buffer, "%lu\n", points); +} + +struct limit_names { + char *name; + char *unit; }; -static int mounts_open(struct inode *inode, struct file *file) +static const struct limit_names lnames[RLIM_NLIMITS] = { + [RLIMIT_CPU] = {"Max cpu time", "seconds"}, + [RLIMIT_FSIZE] = {"Max file size", "bytes"}, + [RLIMIT_DATA] = {"Max data size", "bytes"}, + [RLIMIT_STACK] = {"Max stack size", "bytes"}, + [RLIMIT_CORE] = {"Max core file size", "bytes"}, + [RLIMIT_RSS] = {"Max resident set", "bytes"}, + [RLIMIT_NPROC] = {"Max processes", "processes"}, + [RLIMIT_NOFILE] = {"Max open files", "files"}, + [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, + [RLIMIT_AS] = {"Max address space", "bytes"}, + [RLIMIT_LOCKS] = {"Max file locks", "locks"}, + [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, + [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, + [RLIMIT_NICE] = {"Max nice priority", NULL}, + [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, + [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, +}; + +/* Display limits for a process */ +static int proc_pid_limits(struct task_struct *task, char *buffer) { - struct task_struct *task = proc_task(inode); - struct namespace *namespace; - struct proc_mounts *p; - int ret = -EINVAL; + unsigned int i; + int count = 0; + unsigned long flags; + char *bufptr = buffer; - task_lock(task); - namespace = task->namespace; - if (namespace) - get_namespace(namespace); - task_unlock(task); + struct rlimit rlim[RLIM_NLIMITS]; - if (namespace) { - ret = -ENOMEM; - p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); - if (p) { - file->private_data = &p->m; - ret = seq_open(file, &mounts_op); - if (!ret) { - p->m.private = namespace; - p->event = namespace->event; - return 0; - } - kfree(p); - } - put_namespace(namespace); + if (!lock_task_sighand(task, &flags)) + return 0; + memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); + unlock_task_sighand(task, &flags); + + /* + * print the file header + */ + count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n", + "Limit", "Soft Limit", "Hard Limit", "Units"); + + for (i = 0; i < RLIM_NLIMITS; i++) { + if (rlim[i].rlim_cur == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-25s %-20s ", + lnames[i].name, "unlimited"); + else + count += sprintf(&bufptr[count], "%-25s %-20lu ", + lnames[i].name, rlim[i].rlim_cur); + + if (rlim[i].rlim_max == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-20s ", "unlimited"); + else + count += sprintf(&bufptr[count], "%-20lu ", + rlim[i].rlim_max); + + if (lnames[i].unit) + count += sprintf(&bufptr[count], "%-10s\n", + lnames[i].unit); + else + count += sprintf(&bufptr[count], "\n"); } - return ret; + + return count; } -static int mounts_release(struct inode *inode, struct file *file) +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK +static int proc_pid_syscall(struct task_struct *task, char *buffer) { - struct seq_file *m = file->private_data; - struct namespace *namespace = m->private; - put_namespace(namespace); - return seq_release(inode, file); + long nr; + unsigned long args[6], sp, pc; + int res = lock_trace(task); + if (res) + return res; + + if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + res = sprintf(buffer, "running\n"); + else if (nr < 0) + res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else + res = sprintf(buffer, + "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", + nr, + args[0], args[1], args[2], args[3], args[4], args[5], + sp, pc); + unlock_trace(task); + return res; +} +#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ + +/************************************************************************/ +/* Here the fs part begins */ +/************************************************************************/ + +/* permission checks */ +static int proc_fd_access_allowed(struct inode *inode) +{ + struct task_struct *task; + int allowed = 0; + /* 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. + */ + task = get_proc_task(inode); + if (task) { + allowed = ptrace_may_access(task, PTRACE_MODE_READ); + put_task_struct(task); + } + return allowed; } -static unsigned mounts_poll(struct file *file, poll_table *wait) +int proc_setattr(struct dentry *dentry, struct iattr *attr) { - struct proc_mounts *p = file->private_data; - struct namespace *ns = p->m.private; - unsigned res = 0; + int error; + struct inode *inode = dentry->d_inode; - poll_wait(file, &ns->poll, wait); + if (attr->ia_valid & ATTR_MODE) + return -EPERM; - spin_lock(&vfsmount_lock); - if (p->event != ns->event) { - p->event = ns->event; - res = POLLERR; - } - spin_unlock(&vfsmount_lock); + error = inode_change_ok(inode, attr); + if (error) + return error; - return res; + setattr_copy(inode, attr); + mark_inode_dirty(inode); + return 0; } -static struct file_operations proc_mounts_operations = { - .open = mounts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, - .poll = mounts_poll, +/* + * 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, + struct task_struct *task, + int hide_pid_min) +{ + if (pid->hide_pid < hide_pid_min) + return true; + if (in_group_p(pid->pid_gid)) + return true; + return ptrace_may_access(task, PTRACE_MODE_READ); +} + + +static int proc_pid_permission(struct inode *inode, int mask) +{ + struct pid_namespace *pid = inode->i_sb->s_fs_info; + struct task_struct *task; + bool has_perms; + + task = get_proc_task(inode); + if (!task) + return -ESRCH; + has_perms = has_pid_permissions(pid, task, 1); + put_task_struct(task); + + if (!has_perms) { + if (pid->hide_pid == 2) { + /* + * Let's make getdents(), stat(), and open() + * consistent with each other. If a process + * may not stat() a file, it shouldn't be seen + * in procfs at all. + */ + return -ENOENT; + } + + return -EPERM; + } + return generic_permission(inode, mask); +} + + + +static const struct inode_operations proc_def_inode_operations = { + .setattr = proc_setattr, }; #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ @@ -737,140 +603,171 @@ static struct file_operations proc_mounts_operations = { static ssize_t proc_info_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; + struct inode * inode = file_inode(file); unsigned long page; ssize_t length; - struct task_struct *task = proc_task(inode); + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; if (count > PROC_BLOCK_SIZE) count = PROC_BLOCK_SIZE; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + + length = -ENOMEM; + if (!(page = __get_free_page(GFP_TEMPORARY))) + goto out; length = PROC_I(inode)->op.proc_read(task, (char*)page); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); free_page(page); +out: + put_task_struct(task); +out_no_task: return length; } -static struct file_operations proc_info_file_operations = { +static const struct file_operations proc_info_file_operations = { .read = proc_info_read, + .llseek = generic_file_llseek, }; -static int mem_open(struct inode* inode, struct file* file) +static int proc_single_show(struct seq_file *m, void *v) { - file->private_data = (void*)((long)current->self_exec_id); - return 0; + struct inode *inode = m->private; + struct pid_namespace *ns; + struct pid *pid; + struct task_struct *task; + int ret; + + ns = inode->i_sb->s_fs_info; + pid = proc_pid(inode); + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return -ESRCH; + + ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); + + put_task_struct(task); + return ret; } -static ssize_t mem_read(struct file * file, char __user * buf, - size_t count, loff_t *ppos) +static int proc_single_open(struct inode *inode, struct file *filp) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char *page; - unsigned long src = *ppos; - int ret = -ESRCH; + return single_open(filp, proc_single_show, inode); +} + +static const struct file_operations proc_single_file_operations = { + .open = proc_single_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) +{ + struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) - goto out; + if (!task) + return -ESRCH; - ret = -ENOMEM; - page = (char *)__get_free_page(GFP_USER); - if (!page) - goto out; + mm = mm_access(task, mode); + put_task_struct(task); - ret = 0; - - mm = get_task_mm(task); - if (!mm) - goto out_free; + if (IS_ERR(mm)) + return PTR_ERR(mm); - ret = -EIO; - - if (file->private_data != (void*)((long)current->self_exec_id)) - goto out_put; + if (mm) { + /* ensure this mm_struct can't be freed */ + atomic_inc(&mm->mm_count); + /* but do not pin its memory */ + mmput(mm); + } - ret = 0; - - while (count > 0) { - int this_len, retval; + file->private_data = mm; - this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; - retval = access_process_vm(task, src, page, this_len, 0); - if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) { - if (!ret) - ret = -EIO; - break; - } + return 0; +} - if (copy_to_user(buf, page, retval)) { - ret = -EFAULT; - break; - } - - ret += retval; - src += retval; - buf += retval; - count -= retval; - } - *ppos = src; +static int mem_open(struct inode *inode, struct file *file) +{ + int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH); + + /* OK to pass negative loff_t, we can catch out-of-range */ + file->f_mode |= FMODE_UNSIGNED_OFFSET; -out_put: - mmput(mm); -out_free: - free_page((unsigned long) page); -out: return ret; } -#define mem_write NULL - -#ifndef mem_write -/* This is a security hazard */ -static ssize_t mem_write(struct file * file, const char * buf, - size_t count, loff_t *ppos) +static ssize_t mem_rw(struct file *file, char __user *buf, + size_t count, loff_t *ppos, int write) { - int copied = 0; + struct mm_struct *mm = file->private_data; + unsigned long addr = *ppos; + ssize_t copied; char *page; - struct task_struct *task = proc_task(file->f_dentry->d_inode); - unsigned long dst = *ppos; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) - return -ESRCH; + if (!mm) + return 0; - page = (char *)__get_free_page(GFP_USER); + page = (char *)__get_free_page(GFP_TEMPORARY); if (!page) return -ENOMEM; + copied = 0; + if (!atomic_inc_not_zero(&mm->mm_users)) + goto free; + while (count > 0) { - int this_len, retval; + int this_len = min_t(int, count, PAGE_SIZE); - this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; - if (copy_from_user(page, buf, this_len)) { + if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } - retval = access_process_vm(task, dst, page, this_len, 1); - if (!retval) { + + this_len = access_remote_vm(mm, addr, page, this_len, write); + if (!this_len) { if (!copied) copied = -EIO; break; } - copied += retval; - buf += retval; - dst += retval; - count -= retval; + + if (!write && copy_to_user(buf, page, this_len)) { + copied = -EFAULT; + break; + } + + buf += this_len; + addr += this_len; + copied += this_len; + count -= this_len; } - *ppos = dst; + *ppos = addr; + + mmput(mm); +free: free_page((unsigned long) page); return copied; } -#endif -static loff_t mem_lseek(struct file * file, loff_t offset, int orig) +static ssize_t mem_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + return mem_rw(file, buf, count, ppos, 0); +} + +static ssize_t mem_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return mem_rw(file, (char __user*)buf, count, ppos, 1); +} + +loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: @@ -886,65 +783,284 @@ static loff_t mem_lseek(struct file * file, loff_t offset, int orig) return file->f_pos; } -static struct file_operations proc_mem_operations = { +static int mem_release(struct inode *inode, struct file *file) +{ + struct mm_struct *mm = file->private_data; + if (mm) + mmdrop(mm); + return 0; +} + +static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, + .release = mem_release, }; -static ssize_t oom_adjust_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +static int environ_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char buffer[8]; - size_t len; - int oom_adjust = task->oomkilladj; - loff_t __ppos = *ppos; + return __mem_open(inode, file, PTRACE_MODE_READ); +} + +static ssize_t environ_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + char *page; + unsigned long src = *ppos; + int ret = 0; + struct mm_struct *mm = file->private_data; - len = sprintf(buffer, "%i\n", oom_adjust); - if (__ppos >= len) + if (!mm) return 0; - if (count > len-__ppos) - count = len-__ppos; - if (copy_to_user(buf, buffer + __ppos, count)) - return -EFAULT; - *ppos = __ppos + count; - return count; + + page = (char *)__get_free_page(GFP_TEMPORARY); + if (!page) + return -ENOMEM; + + ret = 0; + if (!atomic_inc_not_zero(&mm->mm_users)) + goto free; + while (count > 0) { + size_t this_len, max_len; + int retval; + + if (src >= (mm->env_end - mm->env_start)) + break; + + this_len = mm->env_end - (mm->env_start + src); + + max_len = min_t(size_t, PAGE_SIZE, count); + this_len = min(max_len, this_len); + + retval = access_remote_vm(mm, (mm->env_start + src), + page, this_len, 0); + + if (retval <= 0) { + ret = retval; + break; + } + + if (copy_to_user(buf, page, retval)) { + ret = -EFAULT; + break; + } + + ret += retval; + src += retval; + buf += retval; + count -= retval; + } + *ppos = src; + mmput(mm); + +free: + free_page((unsigned long) page); + return ret; } -static ssize_t oom_adjust_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static const struct file_operations proc_environ_operations = { + .open = environ_open, + .read = environ_read, + .llseek = generic_file_llseek, + .release = mem_release, +}; + +static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char buffer[8], *end; - int oom_adjust; + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; - if (!capable(CAP_SYS_RESOURCE)) - return -EPERM; - memset(buffer, 0, 8); - if (count > 6) - count = 6; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; - oom_adjust = simple_strtol(buffer, &end, 0); - if ((oom_adjust < -16 || oom_adjust > 15) && oom_adjust != OOM_DISABLE) - return -EINVAL; - if (*end == '\n') - end++; - task->oomkilladj = oom_adjust; - if (end - buffer == 0) - return -EIO; - return end - buffer; + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); } -static struct file_operations proc_oom_adjust_operations = { - .read = oom_adjust_read, - .write = oom_adjust_write, +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file_inode(file)); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, }; -static struct inode_operations proc_mem_inode_operations = { - .permission = proc_permission, +static ssize_t oom_score_adj_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; + short oom_score_adj = OOM_SCORE_ADJ_MIN; + unsigned long flags; + size_t len; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + oom_score_adj = task->signal->oom_score_adj; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + unsigned long flags; + int oom_score_adj; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); + if (err) + goto out; + if (oom_score_adj < OOM_SCORE_ADJ_MIN || + oom_score_adj > OOM_SCORE_ADJ_MAX) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file_inode(file)); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + if ((short)oom_score_adj < task->signal->oom_score_adj_min && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + task->signal->oom_score_adj = (short)oom_score_adj; + if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) + task->signal->oom_score_adj_min = (short)oom_score_adj; + trace_oom_score_adj_update(task); + +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_score_adj_operations = { + .read = oom_score_adj_read, + .write = oom_score_adj_write, + .llseek = default_llseek, }; #ifdef CONFIG_AUDITSYSCALL @@ -952,52 +1068,70 @@ static struct inode_operations proc_mem_inode_operations = { static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; - struct task_struct *task = proc_task(inode); + struct inode * inode = file_inode(file); + struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; + if (!task) + return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", - audit_get_loginuid(task->audit_context)); + from_kuid(file->f_cred->user_ns, + audit_get_loginuid(task))); + put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { - struct inode * inode = file->f_dentry->d_inode; + struct inode * inode = file_inode(file); char *page, *tmp; ssize_t length; - struct task_struct *task = proc_task(inode); uid_t loginuid; + kuid_t kloginuid; - if (!capable(CAP_AUDIT_CONTROL)) + rcu_read_lock(); + if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); - if (current != task) - return -EPERM; - - if (count > PAGE_SIZE) - count = PAGE_SIZE; + if (count >= PAGE_SIZE) + count = PAGE_SIZE - 1; if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } - page = (char*)__get_free_page(GFP_USER); + page = (char*)__get_free_page(GFP_TEMPORARY); if (!page) return -ENOMEM; length = -EFAULT; if (copy_from_user(page, buf, count)) goto out_free_page; + page[count] = '\0'; loginuid = simple_strtoul(page, &tmp, 10); if (tmp == page) { length = -EINVAL; goto out_free_page; } - length = audit_set_loginuid(task, loginuid); + + /* is userspace tring to explicitly UNSET the loginuid? */ + if (loginuid == AUDIT_UID_UNSET) { + kloginuid = INVALID_UID; + } else { + kloginuid = make_kuid(file->f_cred->user_ns, loginuid); + if (!uid_valid(kloginuid)) { + length = -EINVAL; + goto out_free_page; + } + } + + length = audit_set_loginuid(kloginuid); if (likely(length == 0)) length = count; @@ -1006,107 +1140,335 @@ out_free_page: return length; } -static struct file_operations proc_loginuid_operations = { +static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, + .llseek = generic_file_llseek, +}; + +static ssize_t proc_sessionid_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + struct task_struct *task = get_proc_task(inode); + ssize_t length; + char tmpbuf[TMPBUFLEN]; + + if (!task) + return -ESRCH; + length = scnprintf(tmpbuf, TMPBUFLEN, "%u", + audit_get_sessionid(task)); + put_task_struct(task); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + +static const struct file_operations proc_sessionid_operations = { + .read = proc_sessionid_read, + .llseek = generic_file_llseek, }; #endif -#ifdef CONFIG_SECCOMP -static ssize_t seccomp_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +#ifdef CONFIG_FAULT_INJECTION +static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) { - struct task_struct *tsk = proc_task(file->f_dentry->d_inode); - char __buf[20]; - loff_t __ppos = *ppos; + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; size_t len; + int make_it_fail; - /* no need to print the trailing zero, so use only len */ - len = sprintf(__buf, "%u\n", tsk->seccomp.mode); - if (__ppos >= len) - return 0; - if (count > len - __ppos) - count = len - __ppos; - if (copy_to_user(buf, __buf + __ppos, count)) + if (!task) + return -ESRCH; + make_it_fail = task->make_it_fail; + put_task_struct(task); + + len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); + + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t proc_fault_inject_write(struct file * file, + const char __user * buf, size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF], *end; + int make_it_fail; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) return -EFAULT; - *ppos = __ppos + count; + make_it_fail = simple_strtol(strstrip(buffer), &end, 0); + if (*end) + return -EINVAL; + if (make_it_fail < 0 || make_it_fail > 1) + return -EINVAL; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + task->make_it_fail = make_it_fail; + put_task_struct(task); + return count; } -static ssize_t seccomp_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static const struct file_operations proc_fault_inject_operations = { + .read = proc_fault_inject_read, + .write = proc_fault_inject_write, + .llseek = generic_file_llseek, +}; +#endif + + +#ifdef CONFIG_SCHED_DEBUG +/* + * Print out various scheduling related per-task fields: + */ +static int sched_show(struct seq_file *m, void *v) { - struct task_struct *tsk = proc_task(file->f_dentry->d_inode); - char __buf[20], *end; - unsigned int seccomp_mode; + struct inode *inode = m->private; + struct task_struct *p; - /* can set it only once to be even more secure */ - if (unlikely(tsk->seccomp.mode)) - return -EPERM; + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_set_task(p); + + put_task_struct(p); + + return count; +} + +static int sched_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_show, inode); +} + +static const struct file_operations proc_pid_sched_operations = { + .open = sched_open, + .read = seq_read, + .write = sched_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif + +#ifdef CONFIG_SCHED_AUTOGROUP +/* + * Print out autogroup related information: + */ +static int sched_autogroup_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; - memset(__buf, 0, sizeof(__buf)); - count = min(count, sizeof(__buf) - 1); - if (copy_from_user(__buf, buf, count)) + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_autogroup_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_autogroup_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + char buffer[PROC_NUMBUF]; + int nice; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) return -EFAULT; - seccomp_mode = simple_strtoul(__buf, &end, 0); - if (*end == '\n') - end++; - if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) { - tsk->seccomp.mode = seccomp_mode; - set_tsk_thread_flag(tsk, TIF_SECCOMP); - } else - return -EINVAL; - if (unlikely(!(end - __buf))) - return -EIO; - return end - __buf; + + err = kstrtoint(strstrip(buffer), 0, &nice); + if (err < 0) + return err; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + err = proc_sched_autogroup_set_nice(p, nice); + if (err) + count = err; + + put_task_struct(p); + + return count; +} + +static int sched_autogroup_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_autogroup_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; } -static struct file_operations proc_seccomp_operations = { - .read = seccomp_read, - .write = seccomp_write, +static const struct file_operations proc_pid_sched_autogroup_operations = { + .open = sched_autogroup_open, + .read = seq_read, + .write = sched_autogroup_write, + .llseek = seq_lseek, + .release = single_release, }; -#endif /* CONFIG_SECCOMP */ + +#endif /* CONFIG_SCHED_AUTOGROUP */ + +static ssize_t comm_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + char buffer[TASK_COMM_LEN]; + const size_t maxlen = sizeof(buffer) - 1; + + memset(buffer, 0, sizeof(buffer)); + if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) + return -EFAULT; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + if (same_thread_group(current, p)) + set_task_comm(p, buffer); + else + count = -EINVAL; + + put_task_struct(p); + + return count; +} + +static int comm_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + task_lock(p); + seq_printf(m, "%s\n", p->comm); + task_unlock(p); + + put_task_struct(p); + + return 0; +} + +static int comm_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, comm_show, inode); +} + +static const struct file_operations proc_pid_set_comm_operations = { + .open = comm_open, + .read = seq_read, + .write = comm_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int proc_exe_link(struct dentry *dentry, struct path *exe_path) +{ + struct task_struct *task; + struct mm_struct *mm; + struct file *exe_file; + + task = get_proc_task(dentry->d_inode); + if (!task) + return -ENOENT; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + return -ENOENT; + exe_file = get_mm_exe_file(mm); + mmput(mm); + if (exe_file) { + *exe_path = exe_file->f_path; + path_get(&exe_file->f_path); + fput(exe_file); + return 0; + } else + return -ENOENT; +} static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; + struct path path; int error = -EACCES; - /* We don't need a base pointer in the /proc filesystem */ - path_release(nd); - - if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; - error = proc_check_root(inode); + + error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt); - nd->last_type = LAST_BIND; + nd_jump_link(nd, &path); + return NULL; out: return ERR_PTR(error); } -static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt, - char __user *buffer, int buflen) +static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) { - struct inode * inode; - char *tmp = (char*)__get_free_page(GFP_KERNEL), *path; + char *tmp = (char*)__get_free_page(GFP_TEMPORARY); + char *pathname; int len; if (!tmp) return -ENOMEM; - - inode = dentry->d_inode; - path = d_path(dentry, mnt, tmp, PAGE_SIZE); - len = PTR_ERR(path); - if (IS_ERR(path)) + + pathname = d_path(path, tmp, PAGE_SIZE); + len = PTR_ERR(pathname); + if (IS_ERR(pathname)) goto out; - len = tmp + PAGE_SIZE - 1 - path; + len = tmp + PAGE_SIZE - 1 - pathname; if (len > buflen) len = buflen; - if (copy_to_user(buffer, path, len)) + if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: free_page((unsigned long)tmp); @@ -1117,218 +1479,62 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b { int error = -EACCES; struct inode *inode = dentry->d_inode; - struct dentry *de; - struct vfsmount *mnt = NULL; - - lock_kernel(); + struct path path; - if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) - goto out; - error = proc_check_root(inode); - if (error) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt); + error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; - error = do_proc_readlink(de, mnt, buffer, buflen); - dput(de); - mntput(mnt); + error = do_proc_readlink(&path, buffer, buflen); + path_put(&path); out: - unlock_kernel(); return error; } -static struct inode_operations proc_pid_link_inode_operations = { +const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_pid_follow_link + .follow_link = proc_pid_follow_link, + .setattr = proc_setattr, }; -#define NUMBUF 10 - -static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) -{ - struct inode *inode = filp->f_dentry->d_inode; - struct task_struct *p = proc_task(inode); - unsigned int fd, tid, ino; - int retval; - char buf[NUMBUF]; - struct files_struct * files; - struct fdtable *fdt; - - retval = -ENOENT; - if (!pid_alive(p)) - goto out; - retval = 0; - tid = p->pid; - - fd = filp->f_pos; - switch (fd) { - case 0: - if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - case 1: - ino = fake_ino(tid, PROC_TID_INO); - if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - default: - files = get_files_struct(p); - if (!files) - goto out; - rcu_read_lock(); - fdt = files_fdtable(files); - for (fd = filp->f_pos-2; - fd < fdt->max_fds; - fd++, filp->f_pos++) { - unsigned int i,j; - - if (!fcheck_files(files, fd)) - continue; - rcu_read_unlock(); - - j = NUMBUF; - i = fd; - do { - j--; - buf[j] = '0' + (i % 10); - i /= 10; - } while (i); - - ino = fake_ino(tid, PROC_TID_FD_DIR + fd); - if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) { - rcu_read_lock(); - break; - } - rcu_read_lock(); - } - rcu_read_unlock(); - put_files_struct(files); - } -out: - return retval; -} - -static int proc_pident_readdir(struct file *filp, - void *dirent, filldir_t filldir, - struct pid_entry *ents, unsigned int nents) -{ - int i; - int pid; - struct dentry *dentry = filp->f_dentry; - struct inode *inode = dentry->d_inode; - struct pid_entry *p; - ino_t ino; - int ret; - - ret = -ENOENT; - if (!pid_alive(proc_task(inode))) - goto out; - - ret = 0; - pid = proc_task(inode)->pid; - i = filp->f_pos; - switch (i) { - case 0: - ino = inode->i_ino; - if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - default: - i -= 2; - if (i >= nents) { - ret = 1; - goto out; - } - p = ents + i; - while (p->name) { - if (filldir(dirent, p->name, p->len, filp->f_pos, - fake_ino(pid, p->type), p->mode >> 12) < 0) - goto out; - filp->f_pos++; - p++; - } - } - - ret = 1; -out: - return ret; -} - -static int proc_tgid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); -} - -static int proc_tid_base_readdir(struct file * filp, - void * dirent, filldir_t filldir) -{ - return proc_pident_readdir(filp,dirent,filldir, - tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); -} /* building an inode */ -static int task_dumpable(struct task_struct *task) -{ - int dumpable = 0; - struct mm_struct *mm; - - task_lock(task); - mm = task->mm; - if (mm) - dumpable = mm->dumpable; - task_unlock(task); - if(dumpable == 1) - return 1; - return 0; -} - - -static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino) +struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; struct proc_inode *ei; + const struct cred *cred; /* We need a new inode */ - + inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); - ei->task = NULL; + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(task->pid, ino); - - if (!pid_alive(task)) - goto out_unlock; + inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ - get_task_struct(task); - ei->task = task; - ei->type = ino; - inode->i_uid = 0; - inode->i_gid = 0; - if (ino == PROC_TGID_INO || ino == PROC_TID_INO || task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; + ei->pid = get_task_pid(task, PIDTYPE_PID); + if (!ei->pid) + goto out_unlock; + + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); } security_task_to_inode(task, inode); @@ -1336,11 +1542,43 @@ out: return inode; out_unlock: - ei->pde = NULL; iput(inode); return NULL; } +int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task; + const struct cred *cred; + struct pid_namespace *pid = dentry->d_sb->s_fs_info; + + generic_fillattr(inode, stat); + + rcu_read_lock(); + stat->uid = GLOBAL_ROOT_UID; + stat->gid = GLOBAL_ROOT_GID; + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + if (!has_pid_permissions(pid, task, 2)) { + rcu_read_unlock(); + /* + * This doesn't prevent learning whether PID exists, + * it only makes getattr() consistent with readdir(). + */ + return -ENOENT; + } + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + cred = __task_cred(task); + stat->uid = cred->euid; + stat->gid = cred->egid; + } + } + rcu_read_unlock(); + return 0; +} + /* dentry stuff */ /* @@ -1350,912 +1588,1615 @@ out_unlock: * * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. + * + * Before the /proc/pid/status file was created the only way to read + * the effective uid of a /process was to stat /proc/pid. Reading + * /proc/pid/status is slow enough that procps and other packages + * kept stating /proc/pid. To keep the rules in /proc simple I have + * made this apply to all per process world readable and executable + * directories. */ -static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +int pid_revalidate(struct dentry *dentry, unsigned int flags) { - struct inode *inode = dentry->d_inode; - struct task_struct *task = proc_task(inode); - if (pid_alive(task)) { - if (proc_type(inode) == PROC_TGID_INO || proc_type(inode) == PROC_TID_INO || task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; - } else { - inode->i_uid = 0; - inode->i_gid = 0; - } - security_task_to_inode(task, inode); - return 1; - } - d_drop(dentry); - return 0; -} + struct inode *inode; + struct task_struct *task; + const struct cred *cred; -static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - struct inode *inode = dentry->d_inode; - struct task_struct *task = proc_task(inode); - int fd = proc_type(inode) - PROC_TID_FD_DIR; - struct files_struct *files; + if (flags & LOOKUP_RCU) + return -ECHILD; - files = get_files_struct(task); - if (files) { - rcu_read_lock(); - if (fcheck_files(files, fd)) { + inode = dentry->d_inode; + task = get_proc_task(inode); + + if (task) { + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; rcu_read_unlock(); - put_files_struct(files); - if (task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; - } else { - inode->i_uid = 0; - inode->i_gid = 0; - } - security_task_to_inode(task, inode); - return 1; + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } - rcu_read_unlock(); - put_files_struct(files); + inode->i_mode &= ~(S_ISUID | S_ISGID); + security_task_to_inode(task, inode); + put_task_struct(task); + return 1; } d_drop(dentry); return 0; } -static void pid_base_iput(struct dentry *dentry, struct inode *inode) +static inline bool proc_inode_is_dead(struct inode *inode) { - struct task_struct *task = proc_task(inode); - spin_lock(&task->proc_lock); - if (task->proc_dentry == dentry) - task->proc_dentry = NULL; - spin_unlock(&task->proc_lock); - iput(inode); + return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } -static int pid_delete_dentry(struct dentry * dentry) +int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ - return !pid_alive(proc_task(dentry->d_inode)); + return proc_inode_is_dead(dentry->d_inode); } -static struct dentry_operations tid_fd_dentry_operations = +const struct dentry_operations pid_dentry_operations = { - .d_revalidate = tid_fd_revalidate, + .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; -static struct dentry_operations pid_dentry_operations = +/* Lookups */ + +/* + * Fill a directory entry. + * + * If possible create the dcache entry and derive our inode number and + * 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 + * the dcache entry in readdir is necessary to keep the inode numbers + * reported by readdir in sync with the inode numbers reported + * by stat. + */ +bool proc_fill_cache(struct file *file, struct dir_context *ctx, + const char *name, int len, + instantiate_t instantiate, struct task_struct *task, const void *ptr) { - .d_revalidate = pid_revalidate, - .d_delete = pid_delete_dentry, -}; + struct dentry *child, *dir = file->f_path.dentry; + struct qstr qname = QSTR_INIT(name, len); + struct inode *inode; + unsigned type; + ino_t ino; + + child = d_hash_and_lookup(dir, &qname); + if (!child) { + child = d_alloc(dir, &qname); + if (!child) + goto end_instantiate; + if (instantiate(dir->d_inode, child, task, ptr) < 0) { + dput(child); + goto end_instantiate; + } + } + inode = child->d_inode; + ino = inode->i_ino; + type = inode->i_mode >> 12; + dput(child); + return dir_emit(ctx, name, len, ino, type); + +end_instantiate: + return dir_emit(ctx, name, len, 1, DT_UNKNOWN); +} -static struct dentry_operations pid_base_dentry_operations = +#ifdef CONFIG_CHECKPOINT_RESTORE + +/* + * dname_to_vma_addr - maps a dentry name into two unsigned longs + * which represent vma start and end addresses. + */ +static int dname_to_vma_addr(struct dentry *dentry, + unsigned long *start, unsigned long *end) { - .d_revalidate = pid_revalidate, - .d_iput = pid_base_iput, - .d_delete = pid_delete_dentry, -}; + if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2) + return -EINVAL; -/* Lookups */ + return 0; +} -static unsigned name_to_int(struct dentry *dentry) +static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) { - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; - unsigned n = 0; + unsigned long vm_start, vm_end; + bool exact_vma_exists = false; + struct mm_struct *mm = NULL; + struct task_struct *task; + const struct cred *cred; + struct inode *inode; + int status = 0; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (!capable(CAP_SYS_ADMIN)) { + status = -EPERM; + goto out_notask; + } - if (len > 1 && *name == '0') + inode = dentry->d_inode; + task = get_proc_task(inode); + if (!task) + goto out_notask; + + mm = mm_access(task, PTRACE_MODE_READ); + if (IS_ERR_OR_NULL(mm)) goto out; - while (len-- > 0) { - unsigned c = *name++ - '0'; - if (c > 9) - goto out; - if (n >= (~0U-9)/10) - goto out; - n *= 10; - n += c; - } - return n; + + if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { + down_read(&mm->mmap_sem); + exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); + up_read(&mm->mmap_sem); + } + + mmput(mm); + + if (exact_vma_exists) { + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } + security_task_to_inode(task, inode); + status = 1; + } + out: - return ~0U; + put_task_struct(task); + +out_notask: + if (status <= 0) + d_drop(dentry); + + return status; } -/* SMP-safe */ -static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static const struct dentry_operations tid_map_files_dentry_operations = { + .d_revalidate = map_files_d_revalidate, + .d_delete = pid_delete_dentry, +}; + +static int proc_map_files_get_link(struct dentry *dentry, struct path *path) { - struct task_struct *task = proc_task(dir); - unsigned fd = name_to_int(dentry); - struct file * file; - struct files_struct * files; - struct inode *inode; - struct proc_inode *ei; + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + int rc; - if (fd == ~0U) + rc = -ENOENT; + task = get_proc_task(dentry->d_inode); + if (!task) goto out; - if (!pid_alive(task)) + + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) goto out; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd); + rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); + if (rc) + goto out_mmput; + + rc = -ENOENT; + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (vma && vma->vm_file) { + *path = vma->vm_file->f_path; + path_get(path); + rc = 0; + } + up_read(&mm->mmap_sem); + +out_mmput: + mmput(mm); +out: + return rc; +} + +struct map_files_info { + fmode_t mode; + unsigned long len; + unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */ +}; + +static int +proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + fmode_t mode = (fmode_t)(unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) - goto out; + return -ENOENT; + ei = PROC_I(inode); - files = get_files_struct(task); - if (!files) - goto out_unlock; - inode->i_mode = S_IFLNK; - rcu_read_lock(); - file = fcheck_files(files, fd); - if (!file) - goto out_unlock2; - if (file->f_mode & 1) - inode->i_mode |= S_IRUSR | S_IXUSR; - if (file->f_mode & 2) - inode->i_mode |= S_IWUSR | S_IXUSR; - rcu_read_unlock(); - put_files_struct(files); + ei->op.proc_get_link = proc_map_files_get_link; + inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; - ei->op.proc_get_link = proc_fd_link; - dentry->d_op = &tid_fd_dentry_operations; + inode->i_mode = S_IFLNK; + + if (mode & FMODE_READ) + inode->i_mode |= S_IRUSR; + if (mode & FMODE_WRITE) + inode->i_mode |= S_IWUSR; + + d_set_d_op(dentry, &tid_map_files_dentry_operations); d_add(dentry, inode); - return NULL; -out_unlock2: - rcu_read_unlock(); - put_files_struct(files); -out_unlock: - iput(inode); -out: - return ERR_PTR(-ENOENT); + return 0; } -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir); -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd); +static struct dentry *proc_map_files_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + int result; + struct mm_struct *mm; -static struct file_operations proc_fd_operations = { - .read = generic_read_dir, - .readdir = proc_readfd, -}; + result = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out; -static struct file_operations proc_task_operations = { - .read = generic_read_dir, - .readdir = proc_task_readdir, + result = -ENOENT; + task = get_proc_task(dir); + if (!task) + goto out; + + result = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + result = -ENOENT; + if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) + goto out_put_task; + + mm = get_task_mm(task); + if (!mm) + goto out_put_task; + + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (!vma) + goto out_no_vma; + + if (vma->vm_file) + result = proc_map_files_instantiate(dir, dentry, task, + (void *)(unsigned long)vma->vm_file->f_mode); + +out_no_vma: + up_read(&mm->mmap_sem); + mmput(mm); +out_put_task: + put_task_struct(task); +out: + return ERR_PTR(result); +} + +static const struct inode_operations proc_map_files_inode_operations = { + .lookup = proc_map_files_lookup, + .permission = proc_fd_permission, + .setattr = proc_setattr, }; -/* - * proc directories can do almost nothing.. - */ -static struct inode_operations proc_fd_inode_operations = { - .lookup = proc_lookupfd, - .permission = proc_permission, +static int +proc_map_files_readdir(struct file *file, struct dir_context *ctx) +{ + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + unsigned long nr_files, pos, i; + struct flex_array *fa = NULL; + struct map_files_info info; + struct map_files_info *p; + int ret; + + ret = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out; + + ret = -ENOENT; + task = get_proc_task(file_inode(file)); + if (!task) + goto out; + + ret = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + ret = 0; + if (!dir_emit_dots(file, ctx)) + goto out_put_task; + + mm = get_task_mm(task); + if (!mm) + goto out_put_task; + down_read(&mm->mmap_sem); + + nr_files = 0; + + /* + * We need two passes here: + * + * 1) Collect vmas of mapped files with mmap_sem taken + * 2) Release mmap_sem and instantiate entries + * + * otherwise we get lockdep complained, since filldir() + * routine might require mmap_sem taken in might_fault(). + */ + + for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { + if (vma->vm_file && ++pos > ctx->pos) + nr_files++; + } + + if (nr_files) { + fa = flex_array_alloc(sizeof(info), nr_files, + GFP_KERNEL); + if (!fa || flex_array_prealloc(fa, 0, nr_files, + GFP_KERNEL)) { + ret = -ENOMEM; + if (fa) + flex_array_free(fa); + up_read(&mm->mmap_sem); + mmput(mm); + goto out_put_task; + } + for (i = 0, vma = mm->mmap, pos = 2; vma; + vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (++pos <= ctx->pos) + continue; + + info.mode = vma->vm_file->f_mode; + info.len = snprintf(info.name, + sizeof(info.name), "%lx-%lx", + vma->vm_start, vma->vm_end); + if (flex_array_put(fa, i++, &info, GFP_KERNEL)) + BUG(); + } + } + up_read(&mm->mmap_sem); + + for (i = 0; i < nr_files; i++) { + p = flex_array_get(fa, i); + if (!proc_fill_cache(file, ctx, + p->name, p->len, + proc_map_files_instantiate, + task, + (void *)(unsigned long)p->mode)) + break; + ctx->pos++; + } + if (fa) + flex_array_free(fa); + mmput(mm); + +out_put_task: + put_task_struct(task); +out: + return ret; +} + +static const struct file_operations proc_map_files_operations = { + .read = generic_read_dir, + .iterate = proc_map_files_readdir, + .llseek = default_llseek, }; -static struct inode_operations proc_task_inode_operations = { - .lookup = proc_task_lookup, - .permission = proc_task_permission, +struct timers_private { + struct pid *pid; + struct task_struct *task; + struct sighand_struct *sighand; + struct pid_namespace *ns; + unsigned long flags; }; -#ifdef CONFIG_SECURITY -static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, - size_t count, loff_t *ppos) +static void *timers_start(struct seq_file *m, loff_t *pos) { - struct inode * inode = file->f_dentry->d_inode; - unsigned long page; - ssize_t length; - struct task_struct *task = proc_task(inode); + struct timers_private *tp = m->private; - if (count > PAGE_SIZE) - count = PAGE_SIZE; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + tp->task = get_pid_task(tp->pid, PIDTYPE_PID); + if (!tp->task) + return ERR_PTR(-ESRCH); - length = security_getprocattr(task, - (char*)file->f_dentry->d_name.name, - (void*)page, count); - if (length >= 0) - length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); - free_page(page); - return length; + tp->sighand = lock_task_sighand(tp->task, &tp->flags); + if (!tp->sighand) + return ERR_PTR(-ESRCH); + + return seq_list_start(&tp->task->signal->posix_timers, *pos); } -static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) -{ - struct inode * inode = file->f_dentry->d_inode; - char *page; - ssize_t length; - struct task_struct *task = proc_task(inode); - - if (count > PAGE_SIZE) - count = PAGE_SIZE; - if (*ppos != 0) { - /* No partial writes. */ - return -EINVAL; +static void *timers_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct timers_private *tp = m->private; + return seq_list_next(v, &tp->task->signal->posix_timers, pos); +} + +static void timers_stop(struct seq_file *m, void *v) +{ + struct timers_private *tp = m->private; + + if (tp->sighand) { + unlock_task_sighand(tp->task, &tp->flags); + tp->sighand = NULL; + } + + if (tp->task) { + put_task_struct(tp->task); + tp->task = NULL; } - page = (char*)__get_free_page(GFP_USER); - if (!page) +} + +static int show_timer(struct seq_file *m, void *v) +{ + struct k_itimer *timer; + struct timers_private *tp = m->private; + int notify; + static char *nstr[] = { + [SIGEV_SIGNAL] = "signal", + [SIGEV_NONE] = "none", + [SIGEV_THREAD] = "thread", + }; + + timer = list_entry((struct list_head *)v, struct k_itimer, list); + notify = timer->it_sigev_notify; + + seq_printf(m, "ID: %d\n", timer->it_id); + seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo, + timer->sigq->info.si_value.sival_ptr); + seq_printf(m, "notify: %s/%s.%d\n", + nstr[notify & ~SIGEV_THREAD_ID], + (notify & SIGEV_THREAD_ID) ? "tid" : "pid", + pid_nr_ns(timer->it_pid, tp->ns)); + seq_printf(m, "ClockID: %d\n", timer->it_clock); + + return 0; +} + +static const struct seq_operations proc_timers_seq_ops = { + .start = timers_start, + .next = timers_next, + .stop = timers_stop, + .show = show_timer, +}; + +static int proc_timers_open(struct inode *inode, struct file *file) +{ + struct timers_private *tp; + + tp = __seq_open_private(file, &proc_timers_seq_ops, + sizeof(struct timers_private)); + if (!tp) return -ENOMEM; - length = -EFAULT; - if (copy_from_user(page, buf, count)) - goto out; - length = security_setprocattr(task, - (char*)file->f_dentry->d_name.name, - (void*)page, count); -out: - free_page((unsigned long) page); - return length; -} + tp->pid = proc_pid(inode); + tp->ns = inode->i_sb->s_fs_info; + return 0; +} -static struct file_operations proc_pid_attr_operations = { - .read = proc_pid_attr_read, - .write = proc_pid_attr_write, +static const struct file_operations proc_timers_operations = { + .open = proc_timers_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, }; +#endif /* CONFIG_CHECKPOINT_RESTORE */ -static struct file_operations proc_tid_attr_operations; -static struct inode_operations proc_tid_attr_inode_operations; -static struct file_operations proc_tgid_attr_operations; -static struct inode_operations proc_tgid_attr_inode_operations; -#endif +static int proc_pident_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, const void *ptr) +{ + const struct pid_entry *p = ptr; + struct inode *inode; + struct proc_inode *ei; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; -static int get_tid_list(int index, unsigned int *tids, struct inode *dir); + ei = PROC_I(inode); + inode->i_mode = p->mode; + if (S_ISDIR(inode->i_mode)) + set_nlink(inode, 2); /* Use getattr to fix if necessary */ + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + d_set_d_op(dentry, &pid_dentry_operations); + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; +out: + return -ENOENT; +} -/* SMP-safe */ static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, - struct pid_entry *ents) + const struct pid_entry *ents, + unsigned int nents) { - struct inode *inode; int error; - struct task_struct *task = proc_task(dir); - struct pid_entry *p; - struct proc_inode *ei; + struct task_struct *task = get_proc_task(dir); + const struct pid_entry *p, *last; error = -ENOENT; - inode = NULL; - if (!pid_alive(task)) - goto out; + if (!task) + goto out_no_task; - for (p = ents; p->name; p++) { + /* + * Yes, it does not scale. And it should not. Don't add + * new entries into /proc/<tgid>/ without very good reasons. + */ + last = &ents[nents - 1]; + for (p = ents; p <= last; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) break; } - if (!p->name) + if (p > last) goto out; - error = -EINVAL; - inode = proc_pid_make_inode(dir->i_sb, task, p->type); - if (!inode) + error = proc_pident_instantiate(dir, dentry, task, p); +out: + put_task_struct(task); +out_no_task: + return ERR_PTR(error); +} + +static int proc_pident_readdir(struct file *file, struct dir_context *ctx, + const struct pid_entry *ents, unsigned int nents) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + const struct pid_entry *p; + + if (!task) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) goto out; - ei = PROC_I(inode); - inode->i_mode = p->mode; - /* - * Yes, it does not scale. And it should not. Don't add - * new entries into /proc/<tgid>/ without very good reasons. - */ - switch(p->type) { - case PROC_TGID_TASK: - inode->i_nlink = 2 + get_tid_list(2, NULL, dir); - inode->i_op = &proc_task_inode_operations; - inode->i_fop = &proc_task_operations; - break; - case PROC_TID_FD: - case PROC_TGID_FD: - inode->i_nlink = 2; - inode->i_op = &proc_fd_inode_operations; - inode->i_fop = &proc_fd_operations; - break; - case PROC_TID_EXE: - case PROC_TGID_EXE: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_exe_link; - break; - case PROC_TID_CWD: - case PROC_TGID_CWD: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_cwd_link; - break; - case PROC_TID_ROOT: - case PROC_TGID_ROOT: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_root_link; - break; - case PROC_TID_ENVIRON: - case PROC_TGID_ENVIRON: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_environ; - break; - case PROC_TID_AUXV: - case PROC_TGID_AUXV: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_auxv; - break; - case PROC_TID_STATUS: - case PROC_TGID_STATUS: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_status; - break; - case PROC_TID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tid_stat; - break; - case PROC_TGID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tgid_stat; - break; - case PROC_TID_CMDLINE: - case PROC_TGID_CMDLINE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_cmdline; - break; - case PROC_TID_STATM: - case PROC_TGID_STATM: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_statm; - break; - case PROC_TID_MAPS: - case PROC_TGID_MAPS: - inode->i_fop = &proc_maps_operations; - break; -#ifdef CONFIG_NUMA - case PROC_TID_NUMA_MAPS: - case PROC_TGID_NUMA_MAPS: - inode->i_fop = &proc_numa_maps_operations; - break; -#endif - case PROC_TID_MEM: - case PROC_TGID_MEM: - inode->i_op = &proc_mem_inode_operations; - inode->i_fop = &proc_mem_operations; - break; -#ifdef CONFIG_SECCOMP - case PROC_TID_SECCOMP: - case PROC_TGID_SECCOMP: - inode->i_fop = &proc_seccomp_operations; - break; -#endif /* CONFIG_SECCOMP */ - case PROC_TID_MOUNTS: - case PROC_TGID_MOUNTS: - inode->i_fop = &proc_mounts_operations; - break; -#ifdef CONFIG_MMU - case PROC_TID_SMAPS: - case PROC_TGID_SMAPS: - inode->i_fop = &proc_smaps_operations; - break; -#endif -#ifdef CONFIG_SECURITY - case PROC_TID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tid_attr_inode_operations; - inode->i_fop = &proc_tid_attr_operations; - break; - case PROC_TGID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tgid_attr_inode_operations; - inode->i_fop = &proc_tgid_attr_operations; - break; - case PROC_TID_ATTR_CURRENT: - case PROC_TGID_ATTR_CURRENT: - case PROC_TID_ATTR_PREV: - case PROC_TGID_ATTR_PREV: - case PROC_TID_ATTR_EXEC: - case PROC_TGID_ATTR_EXEC: - case PROC_TID_ATTR_FSCREATE: - case PROC_TGID_ATTR_FSCREATE: - inode->i_fop = &proc_pid_attr_operations; - break; -#endif -#ifdef CONFIG_KALLSYMS - case PROC_TID_WCHAN: - case PROC_TGID_WCHAN: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_wchan; - break; -#endif -#ifdef CONFIG_SCHEDSTATS - case PROC_TID_SCHEDSTAT: - case PROC_TGID_SCHEDSTAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_schedstat; - break; -#endif -#ifdef CONFIG_CPUSETS - case PROC_TID_CPUSET: - case PROC_TGID_CPUSET: - inode->i_fop = &proc_cpuset_operations; - break; -#endif - case PROC_TID_OOM_SCORE: - case PROC_TGID_OOM_SCORE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_oom_score; - break; - case PROC_TID_OOM_ADJUST: - case PROC_TGID_OOM_ADJUST: - inode->i_fop = &proc_oom_adjust_operations; - break; -#ifdef CONFIG_AUDITSYSCALL - case PROC_TID_LOGINUID: - case PROC_TGID_LOGINUID: - inode->i_fop = &proc_loginuid_operations; + if (ctx->pos >= nents + 2) + goto out; + + for (p = ents + (ctx->pos - 2); p <= ents + nents - 1; p++) { + if (!proc_fill_cache(file, ctx, p->name, p->len, + proc_pident_instantiate, task, p)) break; -#endif - default: - printk("procfs: impossible type (%d)",p->type); - iput(inode); - return ERR_PTR(-EINVAL); + ctx->pos++; } - dentry->d_op = &pid_dentry_operations; - d_add(dentry, inode); - return NULL; - out: - return ERR_PTR(error); + put_task_struct(task); + return 0; } -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tgid_base_stuff); +#ifdef CONFIG_SECURITY +static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + char *p = NULL; + ssize_t length; + struct task_struct *task = get_proc_task(inode); + + if (!task) + return -ESRCH; + + length = security_getprocattr(task, + (char*)file->f_path.dentry->d_name.name, + &p); + put_task_struct(task); + if (length > 0) + length = simple_read_from_buffer(buf, count, ppos, p, length); + kfree(p); + return length; } -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tid_base_stuff); +static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + char *page; + ssize_t length; + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; + if (count > PAGE_SIZE) + count = PAGE_SIZE; + + /* No partial writes. */ + length = -EINVAL; + if (*ppos != 0) + goto out; + + length = -ENOMEM; + page = (char*)__get_free_page(GFP_TEMPORARY); + if (!page) + goto out; + + length = -EFAULT; + if (copy_from_user(page, buf, count)) + goto out_free; + + /* Guard against adverse ptrace interaction */ + length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + if (length < 0) + goto out_free; + + length = security_setprocattr(task, + (char*)file->f_path.dentry->d_name.name, + (void*)page, count); + mutex_unlock(&task->signal->cred_guard_mutex); +out_free: + free_page((unsigned long) page); +out: + put_task_struct(task); +out_no_task: + return length; } -static struct file_operations proc_tgid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_base_readdir, +static const struct file_operations proc_pid_attr_operations = { + .read = proc_pid_attr_read, + .write = proc_pid_attr_write, + .llseek = generic_file_llseek, }; -static struct file_operations proc_tid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tid_base_readdir, +static const struct pid_entry attr_dir_stuff[] = { + REG("current", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("prev", S_IRUGO, proc_pid_attr_operations), + REG("exec", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("fscreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("keycreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), }; -static struct inode_operations proc_tgid_base_inode_operations = { - .lookup = proc_tgid_base_lookup, +static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) +{ + return proc_pident_readdir(file, ctx, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static const struct file_operations proc_attr_dir_operations = { + .read = generic_read_dir, + .iterate = proc_attr_dir_readdir, + .llseek = default_llseek, }; -static struct inode_operations proc_tid_base_inode_operations = { - .lookup = proc_tid_base_lookup, +static struct dentry *proc_attr_dir_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + return proc_pident_lookup(dir, dentry, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static const struct inode_operations proc_attr_dir_inode_operations = { + .lookup = proc_attr_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, }; -#ifdef CONFIG_SECURITY -static int proc_tgid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +#endif + +#ifdef CONFIG_ELF_CORE +static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - return proc_pident_readdir(filp,dirent,filldir, - tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff)); + struct task_struct *task = get_proc_task(file_inode(file)); + struct mm_struct *mm; + char buffer[PROC_NUMBUF]; + size_t len; + int ret; + + if (!task) + return -ESRCH; + + ret = 0; + mm = get_task_mm(task); + if (mm) { + len = snprintf(buffer, sizeof(buffer), "%08lx\n", + ((mm->flags & MMF_DUMP_FILTER_MASK) >> + MMF_DUMP_FILTER_SHIFT)); + mmput(mm); + ret = simple_read_from_buffer(buf, count, ppos, buffer, len); + } + + put_task_struct(task); + + return ret; } -static int proc_tid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +static ssize_t proc_coredump_filter_write(struct file *file, + const char __user *buf, + size_t count, + loff_t *ppos) { - return proc_pident_readdir(filp,dirent,filldir, - tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff)); + struct task_struct *task; + struct mm_struct *mm; + char buffer[PROC_NUMBUF], *end; + unsigned int val; + int ret; + int i; + unsigned long mask; + + ret = -EFAULT; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + goto out_no_task; + + ret = -EINVAL; + val = (unsigned int)simple_strtoul(buffer, &end, 0); + if (*end == '\n') + end++; + if (end - buffer == 0) + goto out_no_task; + + ret = -ESRCH; + task = get_proc_task(file_inode(file)); + if (!task) + goto out_no_task; + + ret = end - buffer; + mm = get_task_mm(task); + if (!mm) + goto out_no_mm; + + for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { + if (val & mask) + set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + else + clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + } + + mmput(mm); + out_no_mm: + put_task_struct(task); + out_no_task: + return ret; } -static struct file_operations proc_tgid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_attr_readdir, +static const struct file_operations proc_coredump_filter_operations = { + .read = proc_coredump_filter_read, + .write = proc_coredump_filter_write, + .llseek = generic_file_llseek, }; +#endif -static struct file_operations proc_tid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tid_attr_readdir, -}; +#ifdef CONFIG_TASK_IO_ACCOUNTING +static int do_io_accounting(struct task_struct *task, char *buffer, int whole) +{ + struct task_io_accounting acct = task->ioac; + unsigned long flags; + int result; -static struct dentry *proc_tgid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + result = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (result) + return result; + + if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + result = -EACCES; + goto out_unlock; + } + + if (whole && lock_task_sighand(task, &flags)) { + struct task_struct *t = task; + + task_io_accounting_add(&acct, &task->signal->ioac); + while_each_thread(task, t) + task_io_accounting_add(&acct, &t->ioac); + + unlock_task_sighand(task, &flags); + } + result = sprintf(buffer, + "rchar: %llu\n" + "wchar: %llu\n" + "syscr: %llu\n" + "syscw: %llu\n" + "read_bytes: %llu\n" + "write_bytes: %llu\n" + "cancelled_write_bytes: %llu\n", + (unsigned long long)acct.rchar, + (unsigned long long)acct.wchar, + (unsigned long long)acct.syscr, + (unsigned long long)acct.syscw, + (unsigned long long)acct.read_bytes, + (unsigned long long)acct.write_bytes, + (unsigned long long)acct.cancelled_write_bytes); +out_unlock: + mutex_unlock(&task->signal->cred_guard_mutex); + return result; +} + +static int proc_tid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 0); +} + +static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 1); +} +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +#ifdef CONFIG_USER_NS +static int proc_id_map_open(struct inode *inode, struct file *file, + struct seq_operations *seq_ops) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + struct seq_file *seq; + int ret = -EINVAL; + + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + ret = seq_open(file, seq_ops); + if (ret) + goto err_put_ns; + + seq = file->private_data; + seq->private = ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_id_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + put_user_ns(ns); + return seq_release(inode, file); +} + +static int proc_uid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_uid_seq_operations); +} + +static int proc_gid_map_open(struct inode *inode, struct file *file) { - return proc_pident_lookup(dir, dentry, tgid_attr_stuff); + return proc_id_map_open(inode, file, &proc_gid_seq_operations); } -static struct dentry *proc_tid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) +static int proc_projid_map_open(struct inode *inode, struct file *file) { - return proc_pident_lookup(dir, dentry, tid_attr_stuff); + return proc_id_map_open(inode, file, &proc_projid_seq_operations); } -static struct inode_operations proc_tgid_attr_inode_operations = { - .lookup = proc_tgid_attr_lookup, +static const struct file_operations proc_uid_map_operations = { + .open = proc_uid_map_open, + .write = proc_uid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, }; -static struct inode_operations proc_tid_attr_inode_operations = { - .lookup = proc_tid_attr_lookup, +static const struct file_operations proc_gid_map_operations = { + .open = proc_gid_map_open, + .write = proc_gid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, }; -#endif + +static const struct file_operations proc_projid_map_operations = { + .open = proc_projid_map_open, + .write = proc_projid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; +#endif /* CONFIG_USER_NS */ + +static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + int err = lock_trace(task); + if (!err) { + seq_printf(m, "%08x\n", task->personality); + unlock_trace(task); + } + return err; +} /* - * /proc/self: + * Thread groups */ -static int proc_self_readlink(struct dentry *dentry, char __user *buffer, - int buflen) +static const struct file_operations proc_task_operations; +static const struct inode_operations proc_task_inode_operations; + +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), +#ifdef CONFIG_CHECKPOINT_RESTORE + DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), +#endif + DIR("fdinfo", S_IRUSR|S_IXUSR, 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), +#endif + REG("environ", S_IRUSR, proc_environ_operations), + INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("status", S_IRUGO, proc_pid_status), + ONE("personality", S_IRUSR, proc_pid_personality), + INF("limits", S_IRUGO, proc_pid_limits), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif +#ifdef CONFIG_SCHED_AUTOGROUP + REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), +#endif + REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + INF("syscall", S_IRUSR, proc_pid_syscall), +#endif + INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("stat", S_IRUGO, proc_tgid_stat), + ONE("statm", S_IRUGO, proc_pid_statm), + REG("maps", S_IRUGO, proc_pid_maps_operations), +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), +#endif + REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), + LNK("cwd", proc_cwd_link), + LNK("root", proc_root_link), + LNK("exe", proc_exe_link), + REG("mounts", S_IRUGO, proc_mounts_operations), + REG("mountinfo", S_IRUGO, proc_mountinfo_operations), + REG("mountstats", S_IRUSR, proc_mountstats_operations), +#ifdef CONFIG_PROC_PAGE_MONITOR + REG("clear_refs", S_IWUSR, proc_clear_refs_operations), + REG("smaps", S_IRUGO, proc_pid_smaps_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), +#endif +#ifdef CONFIG_SECURITY + DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, proc_pid_wchan), +#endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), +#endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, proc_pid_schedstat), +#endif +#ifdef CONFIG_LATENCYTOP + REG("latency", S_IRUGO, proc_lstats_operations), +#endif +#ifdef CONFIG_PROC_PID_CPUSET + REG("cpuset", S_IRUGO, proc_cpuset_operations), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, proc_cgroup_operations), +#endif + INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), + REG("sessionid", S_IRUGO, proc_sessionid_operations), +#endif +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), +#endif +#ifdef CONFIG_ELF_CORE + REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUSR, proc_tgid_io_accounting), +#endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), + REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), +#endif +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("timers", S_IRUGO, proc_timers_operations), +#endif +}; + +static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { - char tmp[30]; - sprintf(tmp, "%d", current->tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); + return proc_pident_readdir(file, ctx, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } -static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) +static const struct file_operations proc_tgid_base_operations = { + .read = generic_read_dir, + .iterate = proc_tgid_base_readdir, + .llseek = default_llseek, +}; + +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - char tmp[30]; - sprintf(tmp, "%d", current->tgid); - return ERR_PTR(vfs_follow_link(nd,tmp)); -} + return proc_pident_lookup(dir, dentry, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); +} -static struct inode_operations proc_self_inode_operations = { - .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, +static const struct inode_operations proc_tgid_base_inode_operations = { + .lookup = proc_tgid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, + .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[PROC_NUMBUF]; + struct qstr name; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", pid); + /* no ->d_hash() rejects on procfs */ + dentry = d_hash_and_lookup(mnt->mnt_root, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", 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), "%d", pid); + dentry = d_hash_and_lookup(dir, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + dput(dir); +out_put_leader: + dput(leader); +out: + return; +} + /** - * proc_pid_unhash - Unhash /proc/@pid entry from the dcache. - * @p: task that should be flushed. + * 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. + * + * 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. * - * Drops the /proc/@pid dcache entry from the hash chains. + * 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. * - * Dropping /proc/@pid entries and detach_pid must be synchroneous, - * otherwise e.g. /proc/@pid/exe might point to the wrong executable, - * if the pid value is immediately reused. This is enforced by - * - caller must acquire spin_lock(p->proc_lock) - * - must be called before detach_pid() - * - proc_pid_lookup acquires proc_lock, and checks that - * the target is not dead by looking at the attach count - * of PIDTYPE_PID. + * 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. */ -struct dentry *proc_pid_unhash(struct task_struct *p) +void proc_flush_task(struct task_struct *task) { - struct dentry *proc_dentry; + int i; + struct pid *pid, *tgid; + struct upid *upid; - proc_dentry = p->proc_dentry; - if (proc_dentry != NULL) { + pid = task_pid(task); + tgid = task_tgid(task); - spin_lock(&dcache_lock); - spin_lock(&proc_dentry->d_lock); - if (!d_unhashed(proc_dentry)) { - dget_locked(proc_dentry); - __d_drop(proc_dentry); - spin_unlock(&proc_dentry->d_lock); - } else { - spin_unlock(&proc_dentry->d_lock); - proc_dentry = NULL; - } - spin_unlock(&dcache_lock); + 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); } - return proc_dentry; } -/** - * proc_pid_flush - recover memory used by stale /proc/@pid/x entries - * @proc_dentry: directoy to prune. - * - * Shrink the /proc directory that was used by the just killed thread. - */ - -void proc_pid_flush(struct dentry *proc_dentry) +static int proc_pid_instantiate(struct inode *dir, + struct dentry * dentry, + struct task_struct *task, const void *ptr) { - might_sleep(); - if(proc_dentry != NULL) { - shrink_dcache_parent(proc_dentry); - dput(proc_dentry); - } + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tgid_base_inode_operations; + inode->i_fop = &proc_tgid_base_operations; + inode->i_flags|=S_IMMUTABLE; + + set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff, + ARRAY_SIZE(tgid_base_stuff))); + + d_set_d_op(dentry, &pid_dentry_operations); + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; +out: + return -ENOENT; } -/* SMP-safe */ -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { + int result = 0; struct task_struct *task; - struct inode *inode; - struct proc_inode *ei; unsigned tgid; - int died; - - if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) { - inode = new_inode(dir->i_sb); - if (!inode) - return ERR_PTR(-ENOMEM); - ei = PROC_I(inode); - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(0, PROC_TGID_INO); - ei->pde = NULL; - inode->i_mode = S_IFLNK|S_IRWXUGO; - inode->i_uid = inode->i_gid = 0; - inode->i_size = 64; - inode->i_op = &proc_self_inode_operations; - d_add(dentry, inode); - return NULL; - } + struct pid_namespace *ns; + tgid = name_to_int(dentry); if (tgid == ~0U) goto out; - read_lock(&tasklist_lock); - task = find_task_by_pid(tgid); + ns = dentry->d_sb->s_fs_info; + rcu_read_lock(); + task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!task) goto out; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO); + result = proc_pid_instantiate(dir, dentry, task, NULL); + put_task_struct(task); +out: + return ERR_PTR(result); +} + +/* + * Find the first task with tgid >= tgid + * + */ +struct tgid_iter { + unsigned int tgid; + struct task_struct *task; +}; +static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) +{ + struct pid *pid; + if (iter.task) + put_task_struct(iter.task); + rcu_read_lock(); +retry: + iter.task = NULL; + 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.tgid += 1; + goto retry; + } + get_task_struct(iter.task); + } + rcu_read_unlock(); + return iter; +} - if (!inode) { - put_task_struct(task); - goto out; +#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1) + +/* for the /proc/ directory itself, after non-process stuff has been done */ +int proc_pid_readdir(struct file *file, struct dir_context *ctx) +{ + struct tgid_iter iter; + struct pid_namespace *ns = file->f_dentry->d_sb->s_fs_info; + loff_t pos = ctx->pos; + + if (pos >= PID_MAX_LIMIT + TGID_OFFSET) + return 0; + + if (pos == TGID_OFFSET - 1) { + struct inode *inode = ns->proc_self->d_inode; + if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) + return 0; + iter.tgid = 0; + } else { + iter.tgid = pos - TGID_OFFSET; } - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tgid_base_inode_operations; - inode->i_fop = &proc_tgid_base_operations; - inode->i_flags|=S_IMMUTABLE; + iter.task = NULL; + for (iter = next_tgid(ns, iter); + iter.task; + iter.tgid += 1, iter = next_tgid(ns, iter)) { + char name[PROC_NUMBUF]; + int len; + if (!has_pid_permissions(ns, iter.task, 2)) + continue; + + len = snprintf(name, sizeof(name), "%d", iter.tgid); + ctx->pos = iter.tgid + TGID_OFFSET; + if (!proc_fill_cache(file, ctx, name, len, + proc_pid_instantiate, iter.task, NULL)) { + put_task_struct(iter.task); + return 0; + } + } + ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; + return 0; +} + +/* + * Tasks + */ +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("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), + REG("environ", S_IRUSR, proc_environ_operations), + INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("status", S_IRUGO, proc_pid_status), + ONE("personality", S_IRUSR, proc_pid_personality), + INF("limits", S_IRUGO, proc_pid_limits), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif + REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + INF("syscall", S_IRUSR, proc_pid_syscall), +#endif + INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("stat", S_IRUGO, proc_tid_stat), + ONE("statm", S_IRUGO, proc_pid_statm), + REG("maps", S_IRUGO, proc_tid_maps_operations), +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("children", S_IRUGO, proc_tid_children_operations), +#endif +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations), +#endif + REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), + LNK("cwd", proc_cwd_link), + LNK("root", proc_root_link), + LNK("exe", proc_exe_link), + REG("mounts", S_IRUGO, proc_mounts_operations), + REG("mountinfo", S_IRUGO, proc_mountinfo_operations), +#ifdef CONFIG_PROC_PAGE_MONITOR + REG("clear_refs", S_IWUSR, proc_clear_refs_operations), + REG("smaps", S_IRUGO, proc_tid_smaps_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), +#endif #ifdef CONFIG_SECURITY - inode->i_nlink = 5; -#else - inode->i_nlink = 4; + DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, proc_pid_wchan), +#endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), #endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, proc_pid_schedstat), +#endif +#ifdef CONFIG_LATENCYTOP + REG("latency", S_IRUGO, proc_lstats_operations), +#endif +#ifdef CONFIG_PROC_PID_CPUSET + REG("cpuset", S_IRUGO, proc_cpuset_operations), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, proc_cgroup_operations), +#endif + INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), + REG("sessionid", S_IRUGO, proc_sessionid_operations), +#endif +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUSR, proc_tid_io_accounting), +#endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), + REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), +#endif +}; - dentry->d_op = &pid_base_dentry_operations; +static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) +{ + return proc_pident_readdir(file, ctx, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); +} - died = 0; - d_add(dentry, inode); - spin_lock(&task->proc_lock); - task->proc_dentry = dentry; - if (!pid_alive(task)) { - dentry = proc_pid_unhash(task); - died = 1; - } - spin_unlock(&task->proc_lock); +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + return proc_pident_lookup(dir, dentry, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); +} - put_task_struct(task); - if (died) { - proc_pid_flush(dentry); +static const struct file_operations proc_tid_base_operations = { + .read = generic_read_dir, + .iterate = proc_tid_base_readdir, + .llseek = default_llseek, +}; + +static const struct inode_operations proc_tid_base_inode_operations = { + .lookup = proc_tid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + +static int proc_task_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, const void *ptr) +{ + struct inode *inode; + inode = proc_pid_make_inode(dir->i_sb, task); + + if (!inode) goto out; - } - return NULL; + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tid_base_inode_operations; + inode->i_fop = &proc_tid_base_operations; + inode->i_flags|=S_IMMUTABLE; + + set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff, + ARRAY_SIZE(tid_base_stuff))); + + d_set_d_op(dentry, &pid_dentry_operations); + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; out: - return ERR_PTR(-ENOENT); + return -ENOENT; } -/* SMP-safe */ -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { + int result = -ENOENT; struct task_struct *task; - struct task_struct *leader = proc_task(dir); - struct inode *inode; + struct task_struct *leader = get_proc_task(dir); unsigned tid; + struct pid_namespace *ns; + + if (!leader) + goto out_no_task; tid = name_to_int(dentry); if (tid == ~0U) goto out; - read_lock(&tasklist_lock); - task = find_task_by_pid(tid); + ns = dentry->d_sb->s_fs_info; + rcu_read_lock(); + task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!task) goto out; - if (leader->tgid != task->tgid) + if (!same_thread_group(leader, task)) goto out_drop_task; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO); - - - if (!inode) - goto out_drop_task; - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tid_base_inode_operations; - inode->i_fop = &proc_tid_base_operations; - inode->i_flags|=S_IMMUTABLE; -#ifdef CONFIG_SECURITY - inode->i_nlink = 4; -#else - inode->i_nlink = 3; -#endif - - dentry->d_op = &pid_base_dentry_operations; - - d_add(dentry, inode); - - put_task_struct(task); - return NULL; + result = proc_task_instantiate(dir, dentry, task, NULL); out_drop_task: put_task_struct(task); out: - return ERR_PTR(-ENOENT); + put_task_struct(leader); +out_no_task: + return ERR_PTR(result); } -#define PROC_NUMBUF 10 -#define PROC_MAXPIDS 20 - /* - * Get a few tgid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the first tid of a thread group to return to user space. + * + * Usually this is just the thread group leader, but if the users + * buffer was too small or there was a seek into the middle of the + * directory we have more work todo. + * + * In the case of a short read we start with find_task_by_pid. + * + * In the case of a seek we start with the leader and walk nr + * threads past it. */ -static int get_tgid_list(int index, unsigned long version, unsigned int *tgids) +static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, + struct pid_namespace *ns) { - struct task_struct *p; - int nr_tgids = 0; + struct task_struct *pos, *task; + unsigned long nr = f_pos; - index--; - read_lock(&tasklist_lock); - p = NULL; - if (version) { - p = find_task_by_pid(version); - if (p && !thread_group_leader(p)) - p = NULL; - } + if (nr != f_pos) /* 32bit overflow? */ + return NULL; - if (p) - index = 0; - else - p = next_task(&init_task); + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + if (!task) + goto fail; - for ( ; p != &init_task; p = next_task(p)) { - int tgid = p->pid; - if (!pid_alive(p)) - continue; - if (--index >= 0) - continue; - tgids[nr_tgids] = tgid; - nr_tgids++; - if (nr_tgids >= PROC_MAXPIDS) - break; + /* Attempt to start with the tid of a thread */ + if (tid && nr) { + pos = find_task_by_pid_ns(tid, ns); + if (pos && same_thread_group(pos, task)) + goto found; } - read_unlock(&tasklist_lock); - return nr_tgids; + + /* If nr exceeds the number of threads there is nothing todo */ + if (nr >= get_nr_threads(task)) + goto fail; + + /* If we haven't found our starting place yet start + * with the leader and walk nr threads forward. + */ + pos = task = task->group_leader; + do { + if (!nr--) + goto found; + } while_each_thread(task, pos); +fail: + pos = NULL; + goto out; +found: + get_task_struct(pos); +out: + rcu_read_unlock(); + return pos; } /* - * Get a few tid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the next thread in the thread list. + * Return NULL if there is an error or no next thread. + * + * The reference to the input task_struct is released. */ -static int get_tid_list(int index, unsigned int *tids, struct inode *dir) +static struct task_struct *next_tid(struct task_struct *start) { - struct task_struct *leader_task = proc_task(dir); - struct task_struct *task = leader_task; - int nr_tids = 0; - - index -= 2; - read_lock(&tasklist_lock); - /* - * The starting point task (leader_task) might be an already - * unlinked task, which cannot be used to access the task-list - * via next_thread(). - */ - if (pid_alive(task)) do { - int tid = task->pid; - - if (--index >= 0) - continue; - if (tids != NULL) - tids[nr_tids] = tid; - nr_tids++; - if (nr_tids >= PROC_MAXPIDS) - break; - } while ((task = next_thread(task)) != leader_task); - read_unlock(&tasklist_lock); - return nr_tids; + struct task_struct *pos = NULL; + rcu_read_lock(); + if (pid_alive(start)) { + pos = next_thread(start); + if (thread_group_leader(pos)) + pos = NULL; + else + get_task_struct(pos); + } + rcu_read_unlock(); + put_task_struct(start); + return pos; } -/* for the /proc/ directory itself, after non-process stuff has been done */ -int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) +/* for the /proc/TGID/task/ directories */ +static int proc_task_readdir(struct file *file, struct dir_context *ctx) { - unsigned int tgid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; - unsigned int nr_tgids, i; - int next_tgid; + struct inode *inode = file_inode(file); + struct task_struct *task; + struct pid_namespace *ns; + int tid; - if (!nr) { - ino_t ino = fake_ino(0,PROC_TGID_INO); - if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0) - return 0; - filp->f_pos++; - nr++; - } + if (proc_inode_is_dead(inode)) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) + return 0; /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - next_tgid = filp->f_version; - filp->f_version = 0; - for (;;) { - nr_tgids = get_tgid_list(nr, next_tgid, tgid_array); - if (!nr_tgids) { - /* no more entries ! */ + ns = file->f_dentry->d_sb->s_fs_info; + tid = (int)file->f_version; + file->f_version = 0; + for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); + task; + task = next_tid(task), ctx->pos++) { + char name[PROC_NUMBUF]; + int len; + tid = task_pid_nr_ns(task, ns); + len = snprintf(name, sizeof(name), "%d", tid); + if (!proc_fill_cache(file, ctx, name, len, + proc_task_instantiate, task, NULL)) { + /* returning this tgid failed, save it as the first + * pid for the next readir call */ + file->f_version = (u64)tid; + put_task_struct(task); break; } - next_tgid = 0; - - /* do not use the last found pid, reserve it for next_tgid */ - if (nr_tgids == PROC_MAXPIDS) { - nr_tgids--; - next_tgid = tgid_array[nr_tgids]; - } - - for (i=0;i<nr_tgids;i++) { - int tgid = tgid_array[i]; - ino_t ino = fake_ino(tgid,PROC_TGID_INO); - unsigned long j = PROC_NUMBUF; - - do - buf[--j] = '0' + (tgid % 10); - while ((tgid /= 10) != 0); - - if (filldir(dirent, buf+j, PROC_NUMBUF-j, filp->f_pos, ino, DT_DIR) < 0) { - /* returning this tgid failed, save it as the first - * pid for the next readir call */ - filp->f_version = tgid_array[i]; - goto out; - } - filp->f_pos++; - nr++; - } } -out: + return 0; } -/* for the /proc/TGID/task/ directories */ -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir) +static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { - unsigned int tid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr_tids, i; - struct dentry *dentry = filp->f_dentry; struct inode *inode = dentry->d_inode; - int retval = -ENOENT; - ino_t ino; - unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ + struct task_struct *p = get_proc_task(inode); + generic_fillattr(inode, stat); - if (!pid_alive(proc_task(inode))) - goto out; - retval = 0; - - switch (pos) { - case 0: - ino = inode->i_ino; - if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0) - goto out; - pos++; - /* fall through */ - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0) - goto out; - pos++; - /* fall through */ + if (p) { + stat->nlink += get_nr_threads(p); + put_task_struct(p); } - nr_tids = get_tid_list(pos, tid_array, inode); - inode->i_nlink = pos + nr_tids; - - for (i = 0; i < nr_tids; i++) { - unsigned long j = PROC_NUMBUF; - int tid = tid_array[i]; - - ino = fake_ino(tid,PROC_TID_INO); + return 0; +} - do - buf[--j] = '0' + (tid % 10); - while ((tid /= 10) != 0); +static const struct inode_operations proc_task_inode_operations = { + .lookup = proc_task_lookup, + .getattr = proc_task_getattr, + .setattr = proc_setattr, + .permission = proc_pid_permission, +}; - if (filldir(dirent, buf+j, PROC_NUMBUF-j, pos, ino, DT_DIR) < 0) - break; - pos++; - } -out: - filp->f_pos = pos; - return retval; -} +static const struct file_operations proc_task_operations = { + .read = generic_read_dir, + .iterate = proc_task_readdir, + .llseek = default_llseek, +}; diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c new file mode 100644 index 00000000000..cbd82dff7e8 --- /dev/null +++ b/fs/proc/cmdline.c @@ -0,0 +1,29 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +static int cmdline_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s\n", saved_command_line); + return 0; +} + +static int cmdline_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, cmdline_proc_show, NULL); +} + +static const struct file_operations cmdline_proc_fops = { + .open = cmdline_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_cmdline_init(void) +{ + proc_create("cmdline", 0, NULL, &cmdline_proc_fops); + return 0; +} +fs_initcall(proc_cmdline_init); diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c new file mode 100644 index 00000000000..290ba85cb90 --- /dev/null +++ b/fs/proc/consoles.c @@ -0,0 +1,112 @@ +/* + * Copyright (c) 2010 Werner Fink, Jiri Slaby + * + * Licensed under GPLv2 + */ + +#include <linux/console.h> +#include <linux/kernel.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/tty_driver.h> + +/* + * This is handler for /proc/consoles + */ +static int show_console_dev(struct seq_file *m, void *v) +{ + static const struct { + short flag; + char name; + } con_flags[] = { + { CON_ENABLED, 'E' }, + { CON_CONSDEV, 'C' }, + { CON_BOOT, 'B' }, + { CON_PRINTBUFFER, 'p' }, + { CON_BRL, 'b' }, + { CON_ANYTIME, 'a' }, + }; + char flags[ARRAY_SIZE(con_flags) + 1]; + struct console *con = v; + unsigned int a; + dev_t dev = 0; + + if (con->device) { + const struct tty_driver *driver; + int index; + driver = con->device(con, &index); + if (driver) { + dev = MKDEV(driver->major, driver->minor_start); + dev += index; + } + } + + for (a = 0; a < ARRAY_SIZE(con_flags); a++) + flags[a] = (con->flags & con_flags[a].flag) ? + con_flags[a].name : ' '; + flags[a] = 0; + + seq_setwidth(m, 21 - 1); + seq_printf(m, "%s%d", con->name, con->index); + seq_pad(m, ' '); + seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-', + con->write ? 'W' : '-', con->unblank ? 'U' : '-', + flags); + if (dev) + seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev)); + + seq_printf(m, "\n"); + + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + struct console *con; + loff_t off = 0; + + console_lock(); + for_each_console(con) + if (off++ == *pos) + break; + + return con; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct console *con = v; + ++*pos; + return con->next; +} + +static void c_stop(struct seq_file *m, void *v) +{ + console_unlock(); +} + +static const struct seq_operations consoles_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = show_console_dev +}; + +static int consoles_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &consoles_op); +} + +static const struct file_operations proc_consoles_operations = { + .open = consoles_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_consoles_init(void) +{ + proc_create("consoles", 0, NULL, &proc_consoles_operations); + return 0; +} +fs_initcall(proc_consoles_init); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c new file mode 100644 index 00000000000..06f4d31e039 --- /dev/null +++ b/fs/proc/cpuinfo.c @@ -0,0 +1,24 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +extern const struct seq_operations cpuinfo_op; +static int cpuinfo_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &cpuinfo_op); +} + +static const struct file_operations proc_cpuinfo_operations = { + .open = cpuinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_cpuinfo_init(void) +{ + proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); + return 0; +} +fs_initcall(proc_cpuinfo_init); diff --git a/fs/proc/devices.c b/fs/proc/devices.c new file mode 100644 index 00000000000..50493edc30e --- /dev/null +++ b/fs/proc/devices.c @@ -0,0 +1,70 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +static int devinfo_show(struct seq_file *f, void *v) +{ + int i = *(loff_t *) v; + + if (i < CHRDEV_MAJOR_HASH_SIZE) { + if (i == 0) + seq_puts(f, "Character devices:\n"); + chrdev_show(f, i); + } +#ifdef CONFIG_BLOCK + else { + i -= CHRDEV_MAJOR_HASH_SIZE; + if (i == 0) + seq_puts(f, "\nBlock devices:\n"); + blkdev_show(f, i); + } +#endif + return 0; +} + +static void *devinfo_start(struct seq_file *f, loff_t *pos) +{ + if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + return pos; + return NULL; +} + +static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) +{ + (*pos)++; + if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + return NULL; + return pos; +} + +static void devinfo_stop(struct seq_file *f, void *v) +{ + /* Nothing to do */ +} + +static const struct seq_operations devinfo_ops = { + .start = devinfo_start, + .next = devinfo_next, + .stop = devinfo_stop, + .show = devinfo_show +}; + +static int devinfo_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &devinfo_ops); +} + +static const struct file_operations proc_devinfo_operations = { + .open = devinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_devices_init(void) +{ + proc_create("devices", 0, NULL, &proc_devinfo_operations); + return 0; +} +fs_initcall(proc_devices_init); diff --git a/fs/proc/fd.c b/fs/proc/fd.c new file mode 100644 index 00000000000..0788d093f5d --- /dev/null +++ b/fs/proc/fd.c @@ -0,0 +1,351 @@ +#include <linux/sched.h> +#include <linux/errno.h> +#include <linux/dcache.h> +#include <linux/path.h> +#include <linux/fdtable.h> +#include <linux/namei.h> +#include <linux/pid.h> +#include <linux/security.h> +#include <linux/file.h> +#include <linux/seq_file.h> + +#include <linux/proc_fs.h> + +#include "../mount.h" +#include "internal.h" +#include "fd.h" + +static int seq_show(struct seq_file *m, void *v) +{ + struct files_struct *files = NULL; + int f_flags = 0, ret = -ENOENT; + struct file *file = NULL; + struct task_struct *task; + + task = get_proc_task(m->private); + if (!task) + return -ENOENT; + + files = get_files_struct(task); + put_task_struct(task); + + if (files) { + int fd = proc_fd(m->private); + + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (file) { + struct fdtable *fdt = files_fdtable(files); + + f_flags = file->f_flags; + if (close_on_exec(fd, fdt)) + f_flags |= O_CLOEXEC; + + get_file(file); + ret = 0; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + + if (!ret) { + seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", + (long long)file->f_pos, f_flags, + real_mount(file->f_path.mnt)->mnt_id); + if (file->f_op->show_fdinfo) + ret = file->f_op->show_fdinfo(m, file); + fput(file); + } + + return ret; +} + +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, seq_show, inode); +} + +static const struct file_operations proc_fdinfo_file_operations = { + .open = seq_fdinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct files_struct *files; + struct task_struct *task; + const struct cred *cred; + struct inode *inode; + int fd; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + inode = dentry->d_inode; + task = get_proc_task(inode); + fd = proc_fd(inode); + + if (task) { + files = get_files_struct(task); + if (files) { + struct file *file; + + rcu_read_lock(); + file = fcheck_files(files, fd); + if (file) { + unsigned f_mode = file->f_mode; + + rcu_read_unlock(); + put_files_struct(files); + + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } + + if (S_ISLNK(inode->i_mode)) { + unsigned i_mode = S_IFLNK; + if (f_mode & FMODE_READ) + i_mode |= S_IRUSR | S_IXUSR; + if (f_mode & FMODE_WRITE) + i_mode |= S_IWUSR | S_IXUSR; + inode->i_mode = i_mode; + } + + security_task_to_inode(task, inode); + put_task_struct(task); + return 1; + } + rcu_read_unlock(); + put_files_struct(files); + } + put_task_struct(task); + } + + d_drop(dentry); + return 0; +} + +static const struct dentry_operations tid_fd_dentry_operations = { + .d_revalidate = tid_fd_revalidate, + .d_delete = pid_delete_dentry, +}; + +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(dentry->d_inode); + if (task) { + files = get_files_struct(task); + put_task_struct(task); + } + + if (files) { + int fd = proc_fd(dentry->d_inode); + struct file *fd_file; + + spin_lock(&files->file_lock); + fd_file = fcheck_files(files, fd); + if (fd_file) { + *path = fd_file->f_path; + path_get(&fd_file->f_path); + ret = 0; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + + return ret; +} + +static int +proc_fd_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + unsigned fd = (unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + ei->fd = fd; + + inode->i_mode = S_IFLNK; + inode->i_op = &proc_pid_link_inode_operations; + inode->i_size = 64; + + ei->op.proc_get_link = proc_fd_link; + + d_set_d_op(dentry, &tid_fd_dentry_operations); + d_add(dentry, inode); + + /* Close the race of the process dying before we return the dentry */ + if (tid_fd_revalidate(dentry, 0)) + return 0; + out: + return -ENOENT; +} + +static struct dentry *proc_lookupfd_common(struct inode *dir, + struct dentry *dentry, + instantiate_t instantiate) +{ + struct task_struct *task = get_proc_task(dir); + int result = -ENOENT; + unsigned fd = name_to_int(dentry); + + if (!task) + goto out_no_task; + if (fd == ~0U) + goto out; + + result = instantiate(dir, dentry, task, (void *)(unsigned long)fd); +out: + put_task_struct(task); +out_no_task: + return ERR_PTR(result); +} + +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) + return -ENOENT; + + 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++) { + char name[PROC_NUMBUF]; + int len; + + if (!fcheck_files(files, fd)) + continue; + rcu_read_unlock(); + + len = snprintf(name, sizeof(name), "%d", fd); + if (!proc_fill_cache(file, ctx, + name, len, instantiate, p, + (void *)(unsigned long)fd)) + goto out_fd_loop; + rcu_read_lock(); + } + rcu_read_unlock(); +out_fd_loop: + put_files_struct(files); +out: + put_task_struct(p); + return 0; +} + +static int proc_readfd(struct file *file, struct dir_context *ctx) +{ + return proc_readfd_common(file, ctx, proc_fd_instantiate); +} + +const struct file_operations proc_fd_operations = { + .read = generic_read_dir, + .iterate = proc_readfd, + .llseek = default_llseek, +}; + +static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + return proc_lookupfd_common(dir, dentry, proc_fd_instantiate); +} + +/* + * /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 rv = generic_permission(inode, mask); + if (rv == 0) + return 0; + if (task_tgid(current) == proc_pid(inode)) + rv = 0; + return rv; +} + +const struct inode_operations proc_fd_inode_operations = { + .lookup = proc_lookupfd, + .permission = proc_fd_permission, + .setattr = proc_setattr, +}; + +static int +proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + unsigned fd = (unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + ei->fd = fd; + + inode->i_mode = S_IFREG | S_IRUSR; + inode->i_fop = &proc_fdinfo_file_operations; + + d_set_d_op(dentry, &tid_fd_dentry_operations); + d_add(dentry, inode); + + /* Close the race of the process dying before we return the dentry */ + if (tid_fd_revalidate(dentry, 0)) + return 0; + out: + return -ENOENT; +} + +static struct dentry * +proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); +} + +static int proc_readfdinfo(struct file *file, struct dir_context *ctx) +{ + return proc_readfd_common(file, ctx, + proc_fdinfo_instantiate); +} + +const struct inode_operations proc_fdinfo_inode_operations = { + .lookup = proc_lookupfdinfo, + .setattr = proc_setattr, +}; + +const struct file_operations proc_fdinfo_operations = { + .read = generic_read_dir, + .iterate = proc_readfdinfo, + .llseek = default_llseek, +}; diff --git a/fs/proc/fd.h b/fs/proc/fd.h new file mode 100644 index 00000000000..7c047f256ae --- /dev/null +++ b/fs/proc/fd.h @@ -0,0 +1,19 @@ +#ifndef __PROCFS_FD_H__ +#define __PROCFS_FD_H__ + +#include <linux/fs.h> + +extern const struct file_operations proc_fd_operations; +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); + +static inline int proc_fd(struct inode *inode) +{ + return PROC_I(inode)->fd; +} + +#endif /* __PROCFS_FD_H__ */ diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 20e5c4509a4..b7f268eb5f4 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -12,223 +12,30 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> +#include <linux/mm.h> #include <linux/module.h> +#include <linux/slab.h> +#include <linux/printk.h> #include <linux/mount.h> -#include <linux/smp_lock.h> #include <linux/init.h> #include <linux/idr.h> #include <linux/namei.h> #include <linux/bitops.h> +#include <linux/spinlock.h> +#include <linux/completion.h> #include <asm/uaccess.h> #include "internal.h" -static ssize_t proc_file_read(struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos); -static ssize_t proc_file_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos); -static loff_t proc_file_lseek(struct file *, loff_t, int); +DEFINE_SPINLOCK(proc_subdir_lock); -int proc_match(int len, const char *name, struct proc_dir_entry *de) +static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de) { if (de->namelen != len) return 0; return !memcmp(name, de->name, len); } -static struct file_operations proc_file_operations = { - .llseek = proc_file_lseek, - .read = proc_file_read, - .write = proc_file_write, -}; - -/* buffer size is one page but our output routines use some slack for overruns */ -#define PROC_BLOCK_SIZE (PAGE_SIZE - 1024) - -static ssize_t -proc_file_read(struct file *file, char __user *buf, size_t nbytes, - loff_t *ppos) -{ - struct inode * inode = file->f_dentry->d_inode; - char *page; - ssize_t retval=0; - int eof=0; - ssize_t n, count; - char *start; - struct proc_dir_entry * dp; - unsigned long long pos; - - /* - * Gaah, please just use "seq_file" instead. The legacy /proc - * interfaces cut loff_t down to off_t for reads, and ignore - * the offset entirely for writes.. - */ - pos = *ppos; - if (pos > MAX_NON_LFS) - return 0; - if (nbytes > MAX_NON_LFS - pos) - nbytes = MAX_NON_LFS - pos; - - dp = PDE(inode); - if (!(page = (char*) __get_free_page(GFP_KERNEL))) - return -ENOMEM; - - while ((nbytes > 0) && !eof) { - count = min_t(size_t, PROC_BLOCK_SIZE, nbytes); - - start = NULL; - if (dp->get_info) { - /* Handle old net routines */ - n = dp->get_info(page, &start, *ppos, count); - if (n < count) - eof = 1; - } else if (dp->read_proc) { - /* - * How to be a proc read function - * ------------------------------ - * Prototype: - * int f(char *buffer, char **start, off_t offset, - * int count, int *peof, void *dat) - * - * Assume that the buffer is "count" bytes in size. - * - * If you know you have supplied all the data you - * have, set *peof. - * - * You have three ways to return data: - * 0) Leave *start = NULL. (This is the default.) - * Put the data of the requested offset at that - * offset within the buffer. Return the number (n) - * of bytes there are from the beginning of the - * buffer up to the last byte of data. If the - * number of supplied bytes (= n - offset) is - * greater than zero and you didn't signal eof - * and the reader is prepared to take more data - * you will be called again with the requested - * offset advanced by the number of bytes - * absorbed. This interface is useful for files - * no larger than the buffer. - * 1) Set *start = an unsigned long value less than - * the buffer address but greater than zero. - * Put the data of the requested offset at the - * beginning of the buffer. Return the number of - * bytes of data placed there. If this number is - * greater than zero and you didn't signal eof - * and the reader is prepared to take more data - * you will be called again with the requested - * offset advanced by *start. This interface is - * useful when you have a large file consisting - * of a series of blocks which you want to count - * and return as wholes. - * (Hack by Paul.Russell@rustcorp.com.au) - * 2) Set *start = an address within the buffer. - * Put the data of the requested offset at *start. - * Return the number of bytes of data placed there. - * If this number is greater than zero and you - * didn't signal eof and the reader is prepared to - * take more data you will be called again with the - * requested offset advanced by the number of bytes - * absorbed. - */ - n = dp->read_proc(page, &start, *ppos, - count, &eof, dp->data); - } else - break; - - if (n == 0) /* end of file */ - break; - if (n < 0) { /* error */ - if (retval == 0) - retval = n; - break; - } - - if (start == NULL) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); - n = PAGE_SIZE; - } - n -= *ppos; - if (n <= 0) - break; - if (n > count) - n = count; - start = page + *ppos; - } else if (start < page) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); - n = PAGE_SIZE; - } - if (n > count) { - /* - * Don't reduce n because doing so might - * cut off part of a data block. - */ - printk(KERN_WARNING - "proc_file_read: Read count exceeded\n"); - } - } else /* start >= page */ { - unsigned long startoff = (unsigned long)(start - page); - if (n > (PAGE_SIZE - startoff)) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); - n = PAGE_SIZE - startoff; - } - if (n > count) - n = count; - } - - n -= copy_to_user(buf, start < page ? page : start, n); - if (n == 0) { - if (retval == 0) - retval = -EFAULT; - break; - } - - *ppos += start < page ? (unsigned long)start : n; - nbytes -= n; - buf += n; - retval += n; - } - free_page((unsigned long) page); - return retval; -} - -static ssize_t -proc_file_write(struct file *file, const char __user *buffer, - size_t count, loff_t *ppos) -{ - struct inode *inode = file->f_dentry->d_inode; - struct proc_dir_entry * dp; - - dp = PDE(inode); - - if (!dp->write_proc) - return -EIO; - - /* FIXME: does this routine need ppos? probably... */ - return dp->write_proc(file, buffer, count, dp->data); -} - - -static loff_t -proc_file_lseek(struct file *file, loff_t offset, int orig) -{ - loff_t retval = -EINVAL; - switch (orig) { - case 1: - offset += file->f_pos; - /* fallthrough */ - case 0: - if (offset < 0 || offset > MAX_NON_LFS) - break; - file->f_pos = retval = offset; - } - return retval; -} - static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = dentry->d_inode; @@ -237,17 +44,14 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) error = inode_change_ok(inode, iattr); if (error) - goto out; + return error; - error = inode_setattr(inode, iattr); - if (error) - goto out; - - de->uid = inode->i_uid; - de->gid = inode->i_gid; + setattr_copy(inode, iattr); + mark_inode_dirty(inode); + + proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; -out: - return error; + return 0; } static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -256,13 +60,13 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry, struct inode *inode = dentry->d_inode; struct proc_dir_entry *de = PROC_I(inode)->pde; if (de && de->nlink) - inode->i_nlink = de->nlink; + set_nlink(inode, de->nlink); generic_fillattr(inode, stat); return 0; } -static struct inode_operations proc_file_inode_operations = { +static const struct inode_operations proc_file_inode_operations = { .setattr = proc_notify_change, }; @@ -271,14 +75,17 @@ static struct inode_operations proc_file_inode_operations = { * returns the struct proc_dir_entry for "/proc/tty/driver", and * returns "serial" in residual. */ -static int xlate_proc_name(const char *name, - struct proc_dir_entry **ret, const char **residual) +static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, + const char **residual) { const char *cp = name, *next; struct proc_dir_entry *de; - int len; + unsigned int len; + + de = *ret; + if (!de) + de = &proc_root; - de = &proc_root; while (1) { next = strchr(cp, '/'); if (!next) @@ -289,8 +96,10 @@ static int xlate_proc_name(const char *name, if (proc_match(len, cp, de)) break; } - if (!de) + if (!de) { + WARN(1, "name '%s'\n", name); return -ENOENT; + } cp += len + 1; } *residual = cp; @@ -298,110 +107,104 @@ static int xlate_proc_name(const char *name, return 0; } -static DEFINE_IDR(proc_inum_idr); +static int xlate_proc_name(const char *name, struct proc_dir_entry **ret, + const char **residual) +{ + int rv; + + spin_lock(&proc_subdir_lock); + rv = __xlate_proc_name(name, ret, residual); + spin_unlock(&proc_subdir_lock); + return rv; +} + +static DEFINE_IDA(proc_inum_ida); static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */ -#define PROC_DYNAMIC_FIRST 0xF0000000UL +#define PROC_DYNAMIC_FIRST 0xF0000000U /* * Return an inode number between PROC_DYNAMIC_FIRST and * 0xffffffff, or zero on failure. */ -static unsigned int get_inode_number(void) +int proc_alloc_inum(unsigned int *inum) { - int i, inum = 0; + unsigned int i; int error; retry: - if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0) - return 0; + if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL)) + return -ENOMEM; - spin_lock(&proc_inum_lock); - error = idr_get_new(&proc_inum_idr, NULL, &i); - spin_unlock(&proc_inum_lock); + spin_lock_irq(&proc_inum_lock); + error = ida_get_new(&proc_inum_ida, &i); + spin_unlock_irq(&proc_inum_lock); if (error == -EAGAIN) goto retry; else if (error) - return 0; - - inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST; - - /* inum will never be more than 0xf0ffffff, so no check - * for overflow. - */ + return error; - return inum; + if (i > UINT_MAX - PROC_DYNAMIC_FIRST) { + spin_lock_irq(&proc_inum_lock); + ida_remove(&proc_inum_ida, i); + spin_unlock_irq(&proc_inum_lock); + return -ENOSPC; + } + *inum = PROC_DYNAMIC_FIRST + i; + return 0; } -static void release_inode_number(unsigned int inum) +void proc_free_inum(unsigned int inum) { - int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK; - - spin_lock(&proc_inum_lock); - idr_remove(&proc_inum_idr, id); - spin_unlock(&proc_inum_lock); + unsigned long flags; + spin_lock_irqsave(&proc_inum_lock, flags); + ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); + spin_unlock_irqrestore(&proc_inum_lock, flags); } static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd) { - nd_set_link(nd, PDE(dentry->d_inode)->data); + nd_set_link(nd, __PDE_DATA(dentry->d_inode)); return NULL; } -static struct inode_operations proc_link_inode_operations = { +static const struct inode_operations proc_link_inode_operations = { .readlink = generic_readlink, .follow_link = proc_follow_link, }; /* - * As some entries in /proc are volatile, we want to - * get rid of unused dentries. This could be made - * smarter: we could keep a "volatile" flag in the - * inode to indicate which ones to keep. - */ -static int proc_delete_dentry(struct dentry * dentry) -{ - return 1; -} - -static struct dentry_operations proc_dentry_operations = -{ - .d_delete = proc_delete_dentry, -}; - -/* * Don't create negative dentries here, return -ENOENT by hand * instead. */ -struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, + struct dentry *dentry) { - struct inode *inode = NULL; - struct proc_dir_entry * de; - int error = -ENOENT; + struct inode *inode; - lock_kernel(); - de = PDE(dir); - if (de) { - for (de = de->subdir; de ; de = de->next) { - if (de->namelen != dentry->d_name.len) - continue; - if (!memcmp(dentry->d_name.name, de->name, de->namelen)) { - unsigned int ino = de->low_ino; - - error = -EINVAL; - inode = proc_get_inode(dir->i_sb, ino, de); - break; - } + spin_lock(&proc_subdir_lock); + for (de = de->subdir; de ; de = de->next) { + if (de->namelen != dentry->d_name.len) + continue; + if (!memcmp(dentry->d_name.name, de->name, de->namelen)) { + pde_get(de); + spin_unlock(&proc_subdir_lock); + inode = proc_get_inode(dir->i_sb, de); + if (!inode) + return ERR_PTR(-ENOMEM); + d_set_d_op(dentry, &simple_dentry_operations); + d_add(dentry, inode); + return NULL; } } - unlock_kernel(); + spin_unlock(&proc_subdir_lock); + return ERR_PTR(-ENOENT); +} - if (inode) { - dentry->d_op = &proc_dentry_operations; - d_add(dentry, inode); - return NULL; - } - return ERR_PTR(error); +struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + return proc_lookup_de(PDE(dir), dir, dentry); } /* @@ -413,64 +216,52 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam * value of the readdir() call, as long as it's non-negative * for success.. */ -int proc_readdir(struct file * filp, - void * dirent, filldir_t filldir) +int proc_readdir_de(struct proc_dir_entry *de, struct file *file, + struct dir_context *ctx) { - struct proc_dir_entry * de; - unsigned int ino; int i; - struct inode *inode = filp->f_dentry->d_inode; - int ret = 0; - lock_kernel(); + if (!dir_emit_dots(file, ctx)) + return 0; - ino = inode->i_ino; - de = PDE(inode); - if (!de) { - ret = -EINVAL; - goto out; + spin_lock(&proc_subdir_lock); + de = de->subdir; + i = ctx->pos - 2; + for (;;) { + if (!de) { + spin_unlock(&proc_subdir_lock); + return 0; + } + if (!i) + break; + de = de->next; + i--; } - i = filp->f_pos; - switch (i) { - case 0: - if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - case 1: - if (filldir(dirent, "..", 2, i, - parent_ino(filp->f_dentry), - DT_DIR) < 0) - goto out; - i++; - filp->f_pos++; - /* fall through */ - default: - de = de->subdir; - i -= 2; - for (;;) { - if (!de) { - ret = 1; - goto out; - } - if (!i) - break; - de = de->next; - i--; - } - do { - if (filldir(dirent, de->name, de->namelen, filp->f_pos, - de->low_ino, de->mode >> 12) < 0) - goto out; - filp->f_pos++; - de = de->next; - } while (de); - } - ret = 1; -out: unlock_kernel(); - return ret; + do { + struct proc_dir_entry *next; + pde_get(de); + spin_unlock(&proc_subdir_lock); + if (!dir_emit(ctx, de->name, de->namelen, + de->low_ino, de->mode >> 12)) { + pde_put(de); + return 0; + } + spin_lock(&proc_subdir_lock); + ctx->pos++; + next = de->next; + pde_put(de); + de = next; + } while (de); + spin_unlock(&proc_subdir_lock); + return 1; +} + +int proc_readdir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + + return proc_readdir_de(PDE(inode), file, ctx); } /* @@ -478,15 +269,16 @@ out: unlock_kernel(); * use the in-memory "struct proc_dir_entry" tree to parse * the /proc directory. */ -static struct file_operations proc_dir_operations = { +static const struct file_operations proc_dir_operations = { + .llseek = generic_file_llseek, .read = generic_read_dir, - .readdir = proc_readdir, + .iterate = proc_readdir, }; /* * proc directories can do almost nothing.. */ -static struct inode_operations proc_dir_inode_operations = { +static const struct inode_operations proc_dir_inode_operations = { .lookup = proc_lookup, .getattr = proc_getattr, .setattr = proc_notify_change, @@ -494,76 +286,58 @@ static struct inode_operations proc_dir_inode_operations = { static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp) { - unsigned int i; + struct proc_dir_entry *tmp; + int ret; - i = get_inode_number(); - if (i == 0) - return -EAGAIN; - dp->low_ino = i; - dp->next = dir->subdir; - dp->parent = dir; - dir->subdir = dp; + ret = proc_alloc_inum(&dp->low_ino); + if (ret) + return ret; + if (S_ISDIR(dp->mode)) { - if (dp->proc_iops == NULL) { - dp->proc_fops = &proc_dir_operations; - dp->proc_iops = &proc_dir_inode_operations; - } + dp->proc_fops = &proc_dir_operations; + dp->proc_iops = &proc_dir_inode_operations; dir->nlink++; } else if (S_ISLNK(dp->mode)) { - if (dp->proc_iops == NULL) - dp->proc_iops = &proc_link_inode_operations; + dp->proc_iops = &proc_link_inode_operations; } else if (S_ISREG(dp->mode)) { - if (dp->proc_fops == NULL) - dp->proc_fops = &proc_file_operations; - if (dp->proc_iops == NULL) - dp->proc_iops = &proc_file_inode_operations; + BUG_ON(dp->proc_fops == NULL); + dp->proc_iops = &proc_file_inode_operations; + } else { + WARN_ON(1); + return -EINVAL; } - return 0; -} -/* - * Kill an inode that got unregistered.. - */ -static void proc_kill_inodes(struct proc_dir_entry *de) -{ - struct list_head *p; - struct super_block *sb = proc_mnt->mnt_sb; - - /* - * Actually it's a partial revoke(). - */ - file_list_lock(); - list_for_each(p, &sb->s_files) { - struct file * filp = list_entry(p, struct file, f_u.fu_list); - struct dentry * dentry = filp->f_dentry; - struct inode * inode; - struct file_operations *fops; - - if (dentry->d_op != &proc_dentry_operations) - continue; - inode = dentry->d_inode; - if (PDE(inode) != de) - continue; - fops = filp->f_op; - filp->f_op = NULL; - fops_put(fops); - } - file_list_unlock(); + spin_lock(&proc_subdir_lock); + + for (tmp = dir->subdir; tmp; tmp = tmp->next) + if (strcmp(tmp->name, dp->name) == 0) { + WARN(1, "proc_dir_entry '%s/%s' already registered\n", + dir->name, dp->name); + break; + } + + dp->next = dir->subdir; + dp->parent = dir; + dir->subdir = dp; + spin_unlock(&proc_subdir_lock); + + return 0; } -static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, +static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, const char *name, - mode_t mode, + umode_t mode, nlink_t nlink) { struct proc_dir_entry *ent = NULL; const char *fn = name; - int len; + unsigned int len; /* make sure name is valid */ - if (!name || !strlen(name)) goto out; + if (!name || !strlen(name)) + goto out; - if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0) + if (xlate_proc_name(name, parent, &fn) != 0) goto out; /* At this point there must not be any '/' characters beyond *fn */ @@ -572,16 +346,18 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, len = strlen(fn); - ent = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL); - if (!ent) goto out; + ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL); + if (!ent) + goto out; - memset(ent, 0, sizeof(struct proc_dir_entry)); - memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1); - ent->name = ((char *) ent) + sizeof(*ent); + memcpy(ent->name, fn, len + 1); ent->namelen = len; ent->mode = mode; ent->nlink = nlink; - out: + atomic_set(&ent->count, 1); + spin_lock_init(&ent->pde_unload_lock); + INIT_LIST_HEAD(&ent->pde_openers); +out: return ent; } @@ -590,7 +366,7 @@ struct proc_dir_entry *proc_symlink(const char *name, { struct proc_dir_entry *ent; - ent = proc_create(&parent,name, + ent = __proc_create(&parent, name, (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1); if (ent) { @@ -609,17 +385,19 @@ struct proc_dir_entry *proc_symlink(const char *name, } return ent; } +EXPORT_SYMBOL(proc_symlink); -struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode, - struct proc_dir_entry *parent) +struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data) { struct proc_dir_entry *ent; - ent = proc_create(&parent, name, S_IFDIR | mode, 2); - if (ent) { - ent->proc_fops = &proc_dir_operations; - ent->proc_iops = &proc_dir_inode_operations; + if (mode == 0) + mode = S_IRUGO | S_IXUGO; + ent = __proc_create(&parent, name, S_IFDIR | mode, 2); + if (ent) { + ent->data = data; if (proc_register(parent, ent) < 0) { kfree(ent); ent = NULL; @@ -627,93 +405,194 @@ struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode, } return ent; } +EXPORT_SYMBOL_GPL(proc_mkdir_data); + +struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, + struct proc_dir_entry *parent) +{ + return proc_mkdir_data(name, mode, parent, NULL); +} +EXPORT_SYMBOL(proc_mkdir_mode); struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) { - return proc_mkdir_mode(name, S_IRUGO | S_IXUGO, parent); + return proc_mkdir_data(name, 0, parent, NULL); } +EXPORT_SYMBOL(proc_mkdir); -struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode, - struct proc_dir_entry *parent) +struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct file_operations *proc_fops, + void *data) { - struct proc_dir_entry *ent; - nlink_t nlink; + struct proc_dir_entry *pde; + if ((mode & S_IFMT) == 0) + mode |= S_IFREG; - if (S_ISDIR(mode)) { - if ((mode & S_IALLUGO) == 0) - mode |= S_IRUGO | S_IXUGO; - nlink = 2; - } else { - if ((mode & S_IFMT) == 0) - mode |= S_IFREG; - if ((mode & S_IALLUGO) == 0) - mode |= S_IRUGO; - nlink = 1; + if (!S_ISREG(mode)) { + WARN_ON(1); /* use proc_mkdir() */ + return NULL; } - ent = proc_create(&parent,name,mode,nlink); - if (ent) { - if (S_ISDIR(mode)) { - ent->proc_fops = &proc_dir_operations; - ent->proc_iops = &proc_dir_inode_operations; - } - if (proc_register(parent, ent) < 0) { - kfree(ent); - ent = NULL; - } - } - return ent; + if ((mode & S_IALLUGO) == 0) + mode |= S_IRUGO; + pde = __proc_create(&parent, name, mode, 1); + if (!pde) + goto out; + pde->proc_fops = proc_fops; + pde->data = data; + if (proc_register(parent, pde) < 0) + goto out_free; + return pde; +out_free: + kfree(pde); +out: + return NULL; } - -void free_proc_entry(struct proc_dir_entry *de) +EXPORT_SYMBOL(proc_create_data); + +void proc_set_size(struct proc_dir_entry *de, loff_t size) { - unsigned int ino = de->low_ino; + de->size = size; +} +EXPORT_SYMBOL(proc_set_size); - if (ino < PROC_DYNAMIC_FIRST) - return; +void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) +{ + de->uid = uid; + de->gid = gid; +} +EXPORT_SYMBOL(proc_set_user); - release_inode_number(ino); +static void free_proc_entry(struct proc_dir_entry *de) +{ + proc_free_inum(de->low_ino); - if (S_ISLNK(de->mode) && de->data) + if (S_ISLNK(de->mode)) kfree(de->data); kfree(de); } +void pde_put(struct proc_dir_entry *pde) +{ + if (atomic_dec_and_test(&pde->count)) + free_proc_entry(pde); +} + /* * Remove a /proc entry and free it if it's not currently in use. - * If it is in use, we set the 'deleted' flag. */ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) { struct proc_dir_entry **p; - struct proc_dir_entry *de; + struct proc_dir_entry *de = NULL; const char *fn = name; - int len; + unsigned int len; - if (!parent && xlate_proc_name(name, &parent, &fn) != 0) - goto out; + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return; + } len = strlen(fn); + for (p = &parent->subdir; *p; p=&(*p)->next ) { - if (!proc_match(len, fn, *p)) + if (proc_match(len, fn, *p)) { + de = *p; + *p = de->next; + de->next = NULL; + break; + } + } + spin_unlock(&proc_subdir_lock); + if (!de) { + WARN(1, "name '%s'\n", name); + return; + } + + proc_entry_rundown(de); + + if (S_ISDIR(de->mode)) + parent->nlink--; + de->nlink = 0; + WARN(de->subdir, "%s: removing non-empty directory " + "'%s/%s', leaking at least '%s'\n", __func__, + de->parent->name, de->name, de->subdir->name); + pde_put(de); +} +EXPORT_SYMBOL(remove_proc_entry); + +int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) +{ + struct proc_dir_entry **p; + struct proc_dir_entry *root = NULL, *de, *next; + const char *fn = name; + unsigned int len; + + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + len = strlen(fn); + + for (p = &parent->subdir; *p; p=&(*p)->next ) { + if (proc_match(len, fn, *p)) { + root = *p; + *p = root->next; + root->next = NULL; + break; + } + } + if (!root) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + de = root; + while (1) { + next = de->subdir; + if (next) { + de->subdir = next->next; + next->next = NULL; + de = next; continue; - de = *p; - *p = de->next; - de->next = NULL; + } + spin_unlock(&proc_subdir_lock); + + proc_entry_rundown(de); + next = de->parent; if (S_ISDIR(de->mode)) - parent->nlink--; - proc_kill_inodes(de); + next->nlink--; de->nlink = 0; - WARN_ON(de->subdir); - if (!atomic_read(&de->count)) - free_proc_entry(de); - else { - de->deleted = 1; - printk("remove_proc_entry: %s/%s busy, count=%d\n", - parent->name, de->name, atomic_read(&de->count)); - } - break; + if (de == root) + break; + pde_put(de); + + spin_lock(&proc_subdir_lock); + de = next; } -out: - return; + pde_put(root); + return 0; +} +EXPORT_SYMBOL(remove_proc_subtree); + +void *proc_get_parent_data(const struct inode *inode) +{ + struct proc_dir_entry *de = PDE(inode); + return de->parent->data; +} +EXPORT_SYMBOL_GPL(proc_get_parent_data); + +void proc_remove(struct proc_dir_entry *de) +{ + if (de) + remove_proc_subtree(de->name, de->parent); +} +EXPORT_SYMBOL(proc_remove); + +void *PDE_DATA(const struct inode *inode) +{ + return __PDE_DATA(inode); } +EXPORT_SYMBOL(PDE_DATA); diff --git a/fs/proc/inode-alloc.txt b/fs/proc/inode-alloc.txt deleted file mode 100644 index 77212f938c2..00000000000 --- a/fs/proc/inode-alloc.txt +++ /dev/null @@ -1,14 +0,0 @@ -Current inode allocations in the proc-fs (hex-numbers): - - 00000000 reserved - 00000001-00000fff static entries (goners) - 001 root-ino - - 00001000-00001fff unused - 0001xxxx-7fffxxxx pid-dir entries for pid 1-7fff - 80000000-efffffff unused - f0000000-ffffffff dynamic entries - -Goal: - a) once we'll split the thing into several virtual filesystems we - will get rid of magical ranges (and this file, BTW). diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 6573f31f1fd..0adbc02d60e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -7,164 +7,409 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/kernel.h> +#include <linux/pid_namespace.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> +#include <linux/completion.h> +#include <linux/poll.h> +#include <linux/printk.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/smp_lock.h> +#include <linux/sysctl.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/mount.h> +#include <linux/magic.h> -#include <asm/system.h> #include <asm/uaccess.h> #include "internal.h" -static inline struct proc_dir_entry * de_get(struct proc_dir_entry *de) -{ - if (de) - atomic_inc(&de->count); - return de; -} - -/* - * Decrements the use count and checks for deferred deletion. - */ -static void de_put(struct proc_dir_entry *de) -{ - if (de) { - lock_kernel(); - if (!atomic_read(&de->count)) { - printk("de_put: entry %s already free!\n", de->name); - unlock_kernel(); - return; - } - - if (atomic_dec_and_test(&de->count)) { - if (de->deleted) { - printk("de_put: deferred delete of %s\n", - de->name); - free_proc_entry(de); - } - } - unlock_kernel(); - } -} - -/* - * Decrement the use count of the proc_dir_entry. - */ -static void proc_delete_inode(struct inode *inode) +static void proc_evict_inode(struct inode *inode) { struct proc_dir_entry *de; - struct task_struct *tsk; + struct ctl_table_header *head; + const struct proc_ns_operations *ns_ops; + void *ns; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); - /* Let go of any associated process */ - tsk = PROC_I(inode)->task; - if (tsk) - put_task_struct(tsk); + /* Stop tracking associated processes */ + put_pid(PROC_I(inode)->pid); /* Let go of any associated proc directory entry */ de = PROC_I(inode)->pde; - if (de) { - if (de->owner) - module_put(de->owner); - de_put(de); + if (de) + pde_put(de); + head = PROC_I(inode)->sysctl; + if (head) { + RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); + sysctl_head_put(head); } - clear_inode(inode); -} - -struct vfsmount *proc_mnt; - -static void proc_read_inode(struct inode * inode) -{ - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + /* Release any associated namespace */ + ns_ops = PROC_I(inode)->ns.ns_ops; + ns = PROC_I(inode)->ns.ns; + if (ns_ops && ns) + ns_ops->put(ns); } -static kmem_cache_t * proc_inode_cachep; +static struct kmem_cache * proc_inode_cachep; static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; struct inode *inode; - ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, SLAB_KERNEL); + ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL); if (!ei) return NULL; - ei->task = NULL; - ei->type = 0; + ei->pid = NULL; + ei->fd = 0; ei->op.proc_get_link = NULL; ei->pde = NULL; + ei->sysctl = NULL; + ei->sysctl_entry = NULL; + ei->ns.ns = NULL; + ei->ns.ns_ops = NULL; inode = &ei->vfs_inode; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; return inode; } -static void proc_destroy_inode(struct inode *inode) +static void proc_i_callback(struct rcu_head *head) { + struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } -static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) +static void proc_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, proc_i_callback); +} + +static void init_once(void *foo) { struct proc_inode *ei = (struct proc_inode *) foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) - inode_init_once(&ei->vfs_inode); + inode_init_once(&ei->vfs_inode); } - -int __init proc_init_inodecache(void) + +void __init proc_init_inodecache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), - 0, SLAB_RECLAIM_ACCOUNT, - init_once, NULL); - if (proc_inode_cachep == NULL) - return -ENOMEM; - return 0; + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD|SLAB_PANIC), + init_once); } -static int proc_remount(struct super_block *sb, int *flags, char *data) +static int proc_show_options(struct seq_file *seq, struct dentry *root) { - *flags |= MS_NODIRATIME; + struct super_block *sb = root->d_sb; + struct pid_namespace *pid = sb->s_fs_info; + + 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 != 0) + seq_printf(seq, ",hidepid=%u", pid->hide_pid); + return 0; } -static struct super_operations proc_sops = { +static const struct super_operations proc_sops = { .alloc_inode = proc_alloc_inode, .destroy_inode = proc_destroy_inode, - .read_inode = proc_read_inode, .drop_inode = generic_delete_inode, - .delete_inode = proc_delete_inode, + .evict_inode = proc_evict_inode, .statfs = simple_statfs, .remount_fs = proc_remount, + .show_options = proc_show_options, }; -struct inode *proc_get_inode(struct super_block *sb, unsigned int ino, - struct proc_dir_entry *de) +enum {BIAS = -1U<<31}; + +static inline int use_pde(struct proc_dir_entry *pde) +{ + return atomic_inc_unless_negative(&pde->in_use); +} + +static void unuse_pde(struct proc_dir_entry *pde) +{ + if (atomic_dec_return(&pde->in_use) == BIAS) + complete(pde->pde_unload_completion); +} + +/* pde is locked */ +static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) +{ + if (pdeo->closing) { + /* somebody else is doing that, just wait */ + DECLARE_COMPLETION_ONSTACK(c); + pdeo->c = &c; + spin_unlock(&pde->pde_unload_lock); + wait_for_completion(&c); + spin_lock(&pde->pde_unload_lock); + } else { + struct file *file; + pdeo->closing = 1; + spin_unlock(&pde->pde_unload_lock); + file = pdeo->file; + pde->proc_fops->release(file_inode(file), file); + spin_lock(&pde->pde_unload_lock); + list_del_init(&pdeo->lh); + if (pdeo->c) + complete(pdeo->c); + kfree(pdeo); + } +} + +void proc_entry_rundown(struct proc_dir_entry *de) +{ + DECLARE_COMPLETION_ONSTACK(c); + /* Wait until all existing callers into module are done. */ + de->pde_unload_completion = &c; + if (atomic_add_return(BIAS, &de->in_use) != BIAS) + wait_for_completion(&c); + + spin_lock(&de->pde_unload_lock); + while (!list_empty(&de->pde_openers)) { + struct pde_opener *pdeo; + pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); + close_pdeo(de, pdeo); + } + spin_unlock(&de->pde_unload_lock); +} + +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)) { + loff_t (*llseek)(struct file *, loff_t, int); + llseek = pde->proc_fops->llseek; + if (!llseek) + llseek = default_llseek; + rv = llseek(file, offset, whence); + unuse_pde(pde); + } + return rv; +} + +static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + ssize_t (*read)(struct file *, char __user *, size_t, loff_t *); + struct proc_dir_entry *pde = PDE(file_inode(file)); + ssize_t rv = -EIO; + if (use_pde(pde)) { + read = pde->proc_fops->read; + if (read) + rv = read(file, buf, count, ppos); + unuse_pde(pde); + } + return rv; +} + +static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +{ + ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *); + struct proc_dir_entry *pde = PDE(file_inode(file)); + ssize_t rv = -EIO; + if (use_pde(pde)) { + write = pde->proc_fops->write; + if (write) + rv = write(file, buf, count, ppos); + unuse_pde(pde); + } + return rv; +} + +static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts) { - struct inode * inode; + struct proc_dir_entry *pde = PDE(file_inode(file)); + unsigned int rv = DEFAULT_POLLMASK; + unsigned int (*poll)(struct file *, struct poll_table_struct *); + if (use_pde(pde)) { + poll = pde->proc_fops->poll; + if (poll) + rv = poll(file, pts); + unuse_pde(pde); + } + return rv; +} + +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; + long (*ioctl)(struct file *, unsigned int, unsigned long); + if (use_pde(pde)) { + ioctl = pde->proc_fops->unlocked_ioctl; + if (ioctl) + rv = ioctl(file, cmd, arg); + unuse_pde(pde); + } + return rv; +} + +#ifdef CONFIG_COMPAT +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; + long (*compat_ioctl)(struct file *, unsigned int, unsigned long); + if (use_pde(pde)) { + compat_ioctl = pde->proc_fops->compat_ioctl; + if (compat_ioctl) + rv = compat_ioctl(file, cmd, arg); + unuse_pde(pde); + } + return rv; +} +#endif + +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; + int (*mmap)(struct file *, struct vm_area_struct *); + if (use_pde(pde)) { + mmap = pde->proc_fops->mmap; + if (mmap) + rv = mmap(file, vma); + unuse_pde(pde); + } + return rv; +} + +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 (use_pde(pde)) { + typeof(proc_reg_get_unmapped_area) *get_area; + + get_area = pde->proc_fops->get_unmapped_area; +#ifdef CONFIG_MMU + if (!get_area) + get_area = current->mm->get_unmapped_area; +#endif + + if (get_area) + rv = get_area(file, orig_addr, len, pgoff, flags); + else + rv = orig_addr; + unuse_pde(pde); + } + return rv; +} + +static int proc_reg_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + int rv = 0; + int (*open)(struct inode *, struct file *); + int (*release)(struct inode *, struct file *); + struct pde_opener *pdeo; /* - * Increment the use count so the dir entry can't disappear. + * What for, you ask? Well, we can have open, rmmod, remove_proc_entry + * sequence. ->release won't be called because ->proc_fops will be + * cleared. Depending on complexity of ->release, consequences vary. + * + * We can't wait for mercy when close will be done for real, it's + * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release + * by hand in remove_proc_entry(). For this, save opener's credentials + * for later. */ - de_get(de); + pdeo = kzalloc(sizeof(struct pde_opener), GFP_KERNEL); + if (!pdeo) + return -ENOMEM; - WARN_ON(de && de->deleted); + if (!use_pde(pde)) { + kfree(pdeo); + return -ENOENT; + } + open = pde->proc_fops->open; + release = pde->proc_fops->release; - if (de != NULL && !try_module_get(de->owner)) - goto out_mod; + if (open) + rv = open(inode, file); - inode = iget(sb, ino); - if (!inode) - goto out_ino; + if (rv == 0 && release) { + /* To know what to release. */ + pdeo->file = file; + /* Strictly for "too late" ->release in proc_reg_release(). */ + spin_lock(&pde->pde_unload_lock); + list_add(&pdeo->lh, &pde->pde_openers); + spin_unlock(&pde->pde_unload_lock); + } else + kfree(pdeo); + + unuse_pde(pde); + return rv; +} + +static int proc_reg_release(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + struct pde_opener *pdeo; + spin_lock(&pde->pde_unload_lock); + list_for_each_entry(pdeo, &pde->pde_openers, lh) { + if (pdeo->file == file) { + close_pdeo(pde, pdeo); + break; + } + } + spin_unlock(&pde->pde_unload_lock); + return 0; +} + +static const struct file_operations proc_reg_file_ops = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .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, +}; + +#ifdef CONFIG_COMPAT +static const struct file_operations proc_reg_file_ops_no_compat = { + .llseek = proc_reg_llseek, + .read = proc_reg_read, + .write = proc_reg_write, + .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, + .release = proc_reg_release, +}; +#endif + +struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) +{ + struct inode *inode = new_inode_pseudo(sb); + + if (inode) { + inode->i_ino = de->low_ino; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + PROC_I(inode)->pde = de; - PROC_I(inode)->pde = de; - if (de) { if (de->mode) { inode->i_mode = de->mode; inode->i_uid = de->uid; @@ -173,51 +418,50 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino, if (de->size) inode->i_size = de->size; if (de->nlink) - inode->i_nlink = de->nlink; - if (de->proc_iops) - inode->i_op = de->proc_iops; - if (de->proc_fops) - inode->i_fop = de->proc_fops; - } - + set_nlink(inode, de->nlink); + WARN_ON(!de->proc_iops); + inode->i_op = de->proc_iops; + if (de->proc_fops) { + if (S_ISREG(inode->i_mode)) { +#ifdef CONFIG_COMPAT + if (!de->proc_fops->compat_ioctl) + inode->i_fop = + &proc_reg_file_ops_no_compat; + else +#endif + inode->i_fop = &proc_reg_file_ops; + } else { + inode->i_fop = de->proc_fops; + } + } + } else + pde_put(de); return inode; +} -out_ino: - if (de != NULL) - module_put(de->owner); -out_mod: - de_put(de); - return NULL; -} - -int proc_fill_super(struct super_block *s, void *data, int silent) +int proc_fill_super(struct super_block *s) { - struct inode * root_inode; + struct inode *root_inode; - s->s_flags |= MS_NODIRATIME; + s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; - root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root); - if (!root_inode) - goto out_no_root; - /* - * Fixup the root inode's nlink value - */ - root_inode->i_nlink += nr_processes(); - root_inode->i_uid = 0; - root_inode->i_gid = 0; - s->s_root = d_alloc_root(root_inode); - if (!s->s_root) - goto out_no_root; - return 0; + pde_get(&proc_root); + root_inode = proc_get_inode(s, &proc_root); + if (!root_inode) { + pr_err("proc_fill_super: get root inode failed\n"); + return -ENOMEM; + } + + s->s_root = d_make_root(root_inode); + if (!s->s_root) { + pr_err("proc_fill_super: allocate dentry failed\n"); + return -ENOMEM; + } -out_no_root: - printk("proc_read_super: get root inode failed\n"); - iput(root_inode); - return -ENOMEM; + return proc_setup_self(s); } -MODULE_LICENSE("GPL"); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 95a1cf32b83..3ab6d14e71c 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -1,4 +1,4 @@ -/* internal.h: internal procfs definitions +/* Internal procfs definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -10,43 +10,282 @@ */ #include <linux/proc_fs.h> +#include <linux/proc_ns.h> +#include <linux/spinlock.h> +#include <linux/atomic.h> +#include <linux/binfmts.h> -struct vmalloc_info { - unsigned long used; - unsigned long largest_chunk; +struct ctl_table_header; +struct mempolicy; + +/* + * This is not completely implemented yet. The idea is to + * create an in-memory tree (like the actual /proc filesystem + * tree) of these proc_dir_entries, so that we can dynamically + * add new files to /proc. + * + * The "next" pointer creates a linked list of one /proc directory, + * while parent/subdir create the directory structure (every + * /proc file has a parent, but "subdir" is NULL for all + * non-directory entries). + */ +struct proc_dir_entry { + unsigned int low_ino; + umode_t mode; + nlink_t nlink; + kuid_t uid; + kgid_t gid; + loff_t size; + const struct inode_operations *proc_iops; + const struct file_operations *proc_fops; + struct proc_dir_entry *next, *parent, *subdir; + void *data; + atomic_t count; /* use count */ + atomic_t in_use; /* number of callers into module in progress; */ + /* negative -> it's going away RSN */ + struct completion *pde_unload_completion; + struct list_head pde_openers; /* who did ->open, but not ->release */ + spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ + u8 namelen; + char name[]; }; -#ifdef CONFIG_MMU -#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -extern void get_vmalloc_info(struct vmalloc_info *vmi); -#else +union proc_op { + int (*proc_get_link)(struct dentry *, struct path *); + int (*proc_read)(struct task_struct *task, char *page); + int (*proc_show)(struct seq_file *m, + struct pid_namespace *ns, struct pid *pid, + struct task_struct *task); +}; -#define VMALLOC_TOTAL 0UL -#define get_vmalloc_info(vmi) \ -do { \ - (vmi)->used = 0; \ - (vmi)->largest_chunk = 0; \ -} while(0) +struct proc_inode { + struct pid *pid; + int fd; + union proc_op op; + struct proc_dir_entry *pde; + struct ctl_table_header *sysctl; + struct ctl_table *sysctl_entry; + struct proc_ns ns; + struct inode vfs_inode; +}; -#endif +/* + * General functions + */ +static inline struct proc_inode *PROC_I(const struct inode *inode) +{ + return container_of(inode, struct proc_inode, vfs_inode); +} -extern void create_seq_entry(char *name, mode_t mode, struct file_operations *f); -extern int proc_exe_link(struct inode *, struct dentry **, struct vfsmount **); -extern int proc_tid_stat(struct task_struct *, char *); -extern int proc_tgid_stat(struct task_struct *, char *); -extern int proc_pid_status(struct task_struct *, char *); -extern int proc_pid_statm(struct task_struct *, char *); +static inline struct proc_dir_entry *PDE(const struct inode *inode) +{ + return PROC_I(inode)->pde; +} -void free_proc_entry(struct proc_dir_entry *de); +static inline void *__PDE_DATA(const struct inode *inode) +{ + return PDE(inode)->data; +} -int proc_init_inodecache(void); +static inline struct pid *proc_pid(struct inode *inode) +{ + return PROC_I(inode)->pid; +} -static inline struct task_struct *proc_task(struct inode *inode) +static inline struct task_struct *get_proc_task(struct inode *inode) { - return PROC_I(inode)->task; + return get_pid_task(proc_pid(inode), PIDTYPE_PID); } -static inline int proc_type(struct inode *inode) +static inline int task_dumpable(struct task_struct *task) +{ + int dumpable = 0; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) + dumpable = get_dumpable(mm); + task_unlock(task); + if (dumpable == SUID_DUMP_USER) + return 1; + return 0; +} + +static inline unsigned name_to_int(struct dentry *dentry) +{ + const char *name = dentry->d_name.name; + int len = dentry->d_name.len; + unsigned n = 0; + + if (len > 1 && *name == '0') + goto out; + while (len-- > 0) { + unsigned c = *name++ - '0'; + if (c > 9) + goto out; + if (n >= (~0U-9)/10) + goto out; + n *= 10; + n += c; + } + return n; +out: + return ~0U; +} + +/* + * Offset of the first process in the /proc root directory.. + */ +#define FIRST_PROCESS_ENTRY 256 + +/* Worst case buffer size needed for holding an integer. */ +#define PROC_NUMBUF 13 + +/* + * array.c + */ +extern const struct file_operations proc_tid_children_operations; + +extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, + struct pid *, struct task_struct *); +extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, + struct pid *, struct task_struct *); +extern int proc_pid_status(struct seq_file *, struct pid_namespace *, + struct pid *, struct task_struct *); +extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, + struct pid *, struct task_struct *); + +/* + * base.c + */ +extern const struct dentry_operations pid_dentry_operations; +extern int pid_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int proc_setattr(struct dentry *, struct iattr *); +extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *); +extern int pid_revalidate(struct dentry *, unsigned int); +extern int pid_delete_dentry(const struct dentry *); +extern int proc_pid_readdir(struct file *, struct dir_context *); +extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); +extern loff_t mem_lseek(struct file *, loff_t, int); + +/* Lookups */ +typedef int instantiate_t(struct inode *, struct dentry *, + struct task_struct *, const void *); +extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int, + instantiate_t, struct task_struct *, const void *); + +/* + * generic.c + */ +extern spinlock_t proc_subdir_lock; + +extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); +extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *, + struct dentry *); +extern int proc_readdir(struct file *, struct dir_context *); +extern int proc_readdir_de(struct proc_dir_entry *, struct file *, struct dir_context *); + +static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) { - return PROC_I(inode)->type; + atomic_inc(&pde->count); + return pde; } +extern void pde_put(struct proc_dir_entry *); + +/* + * inode.c + */ +struct pde_opener { + struct file *file; + struct list_head lh; + int closing; + struct completion *c; +}; + +extern const struct inode_operations proc_pid_link_inode_operations; + +extern void proc_init_inodecache(void); +extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); +extern int proc_fill_super(struct super_block *); +extern void proc_entry_rundown(struct proc_dir_entry *); + +/* + * proc_namespaces.c + */ +extern const struct inode_operations proc_ns_dir_inode_operations; +extern const struct file_operations proc_ns_dir_operations; + +/* + * proc_net.c + */ +extern const struct file_operations proc_net_operations; +extern const struct inode_operations proc_net_inode_operations; + +#ifdef CONFIG_NET +extern int proc_net_init(void); +#else +static inline int proc_net_init(void) { return 0; } +#endif + +/* + * proc_self.c + */ +extern int proc_setup_self(struct super_block *); + +/* + * proc_sysctl.c + */ +#ifdef CONFIG_PROC_SYSCTL +extern int proc_sys_init(void); +extern void sysctl_head_put(struct ctl_table_header *); +#else +static inline void proc_sys_init(void) { } +static inline void sysctl_head_put(struct ctl_table_header *head) { } +#endif + +/* + * proc_tty.c + */ +#ifdef CONFIG_TTY +extern void proc_tty_init(void); +#else +static inline void proc_tty_init(void) {} +#endif + +/* + * root.c + */ +extern struct proc_dir_entry proc_root; + +extern void proc_self_init(void); +extern int proc_remount(struct super_block *, int *, char *); + +/* + * task_[no]mmu.c + */ +struct proc_maps_private { + struct pid *pid; + struct task_struct *task; +#ifdef CONFIG_MMU + struct vm_area_struct *tail_vma; +#endif +#ifdef CONFIG_NUMA + struct mempolicy *task_mempolicy; +#endif +}; + +extern const struct file_operations proc_pid_maps_operations; +extern const struct file_operations proc_tid_maps_operations; +extern const struct file_operations proc_pid_numa_maps_operations; +extern const struct file_operations proc_tid_numa_maps_operations; +extern const struct file_operations proc_pid_smaps_operations; +extern const struct file_operations proc_tid_smaps_operations; +extern const struct file_operations proc_clear_refs_operations; +extern const struct file_operations proc_pagemap_operations; + +extern unsigned long task_vsize(struct mm_struct *); +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 *); diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c new file mode 100644 index 00000000000..a352d5703b4 --- /dev/null +++ b/fs/proc/interrupts.c @@ -0,0 +1,53 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irqnr.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +/* + * /proc/interrupts + */ +static void *int_seq_start(struct seq_file *f, loff_t *pos) +{ + return (*pos <= nr_irqs) ? pos : NULL; +} + +static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos) +{ + (*pos)++; + if (*pos > nr_irqs) + return NULL; + return pos; +} + +static void int_seq_stop(struct seq_file *f, void *v) +{ + /* Nothing to do */ +} + +static const struct seq_operations int_seq_ops = { + .start = int_seq_start, + .next = int_seq_next, + .stop = int_seq_stop, + .show = show_interrupts +}; + +static int interrupts_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &int_seq_ops); +} + +static const struct file_operations proc_interrupts_operations = { + .open = interrupts_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_interrupts_init(void) +{ + proc_create("interrupts", 0, NULL, &proc_interrupts_operations); + return 0; +} +fs_initcall(proc_interrupts_init); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index adc2cd95169..39e6ef32f0b 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -9,32 +9,36 @@ * Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com> */ -#include <linux/config.h> #include <linux/mm.h> #include <linux/proc_fs.h> +#include <linux/kcore.h> #include <linux/user.h> -#include <linux/a.out.h> #include <linux/capability.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/notifier.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/printk.h> +#include <linux/bootmem.h> #include <linux/init.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <asm/io.h> +#include <linux/list.h> +#include <linux/ioport.h> +#include <linux/memory.h> +#include <asm/sections.h> +#include "internal.h" +#define CORE_STR "CORE" -static int open_kcore(struct inode * inode, struct file * filp) -{ - return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; -} +#ifndef ELF_CORE_EFLAGS +#define ELF_CORE_EFLAGS 0 +#endif -static ssize_t read_kcore(struct file *, char __user *, size_t, loff_t *); +static struct proc_dir_entry *proc_root_kcore; -struct file_operations proc_kcore_operations = { - .read = read_kcore, - .open = open_kcore, -}; #ifndef kc_vaddr_to_offset #define kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET) @@ -43,8 +47,6 @@ struct file_operations proc_kcore_operations = { #define kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET) #endif -#define roundup(x, y) ((((x)+((y)-1))/(y))*(y)) - /* An ELF note in memory */ struct memelfnote { @@ -54,18 +56,19 @@ struct memelfnote void *data; }; -static struct kcore_list *kclist; +static LIST_HEAD(kclist_head); static DEFINE_RWLOCK(kclist_lock); +static int kcore_need_update = 1; void -kclist_add(struct kcore_list *new, void *addr, size_t size) +kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { new->addr = (unsigned long)addr; new->size = size; + new->type = type; write_lock(&kclist_lock); - new->next = kclist; - kclist = new; + list_add_tail(&new->list, &kclist_head); write_unlock(&kclist_lock); } @@ -77,7 +80,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) *nphdr = 1; /* PT_NOTE */ size = 0; - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { try = kc_vaddr_to_offset((size_t)m->addr + m->size); if (try > size) size = try; @@ -85,14 +88,187 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) } *elf_buflen = sizeof(struct elfhdr) + (*nphdr + 2)*sizeof(struct elf_phdr) + - 3 * (sizeof(struct elf_note) + 4) + - sizeof(struct elf_prstatus) + - sizeof(struct elf_prpsinfo) + - sizeof(struct task_struct); + 3 * ((sizeof(struct elf_note)) + + roundup(sizeof(CORE_STR), 4)) + + roundup(sizeof(struct elf_prstatus), 4) + + roundup(sizeof(struct elf_prpsinfo), 4) + + roundup(sizeof(struct task_struct), 4); *elf_buflen = PAGE_ALIGN(*elf_buflen); return size + *elf_buflen; } +static void free_kclist_ents(struct list_head *head) +{ + struct kcore_list *tmp, *pos; + + list_for_each_entry_safe(pos, tmp, head, list) { + list_del(&pos->list); + kfree(pos); + } +} +/* + * Replace all KCORE_RAM/KCORE_VMEMMAP information with passed list. + */ +static void __kcore_update_ram(struct list_head *list) +{ + int nphdr; + size_t size; + struct kcore_list *tmp, *pos; + LIST_HEAD(garbage); + + write_lock(&kclist_lock); + if (kcore_need_update) { + list_for_each_entry_safe(pos, tmp, &kclist_head, list) { + if (pos->type == KCORE_RAM + || pos->type == KCORE_VMEMMAP) + list_move(&pos->list, &garbage); + } + list_splice_tail(list, &kclist_head); + } else + list_splice(list, &garbage); + kcore_need_update = 0; + proc_root_kcore->size = get_kcore_size(&nphdr, &size); + write_unlock(&kclist_lock); + + free_kclist_ents(&garbage); +} + + +#ifdef CONFIG_HIGHMEM +/* + * If no highmem, we can assume [0...max_low_pfn) continuous range of memory + * because memory hole is not as big as !HIGHMEM case. + * (HIGHMEM is special because part of memory is _invisible_ from the kernel.) + */ +static int kcore_update_ram(void) +{ + LIST_HEAD(head); + struct kcore_list *ent; + int ret = 0; + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->addr = (unsigned long)__va(0); + ent->size = max_low_pfn << PAGE_SHIFT; + ent->type = KCORE_RAM; + list_add(&ent->list, &head); + __kcore_update_ram(&head); + return ret; +} + +#else /* !CONFIG_HIGHMEM */ + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* calculate vmemmap's address from given system ram pfn and register it */ +static int +get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT; + unsigned long nr_pages = ent->size >> PAGE_SHIFT; + unsigned long start, end; + struct kcore_list *vmm, *tmp; + + + start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK; + end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1; + end = ALIGN(end, PAGE_SIZE); + /* overlap check (because we have to align page */ + list_for_each_entry(tmp, head, list) { + if (tmp->type != KCORE_VMEMMAP) + continue; + if (start < tmp->addr + tmp->size) + if (end > tmp->addr) + end = tmp->addr; + } + if (start < end) { + vmm = kmalloc(sizeof(*vmm), GFP_KERNEL); + if (!vmm) + return 0; + vmm->addr = start; + vmm->size = end - start; + vmm->type = KCORE_VMEMMAP; + list_add_tail(&vmm->list, head); + } + return 1; + +} +#else +static int +get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + return 1; +} + +#endif + +static int +kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) +{ + struct list_head *head = (struct list_head *)arg; + struct kcore_list *ent; + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT)); + ent->size = nr_pages << PAGE_SHIFT; + + /* Sanity check: Can happen in 32bit arch...maybe */ + if (ent->addr < (unsigned long) __va(0)) + goto free_out; + + /* cut not-mapped area. ....from ppc-32 code. */ + if (ULONG_MAX - ent->addr < ent->size) + ent->size = ULONG_MAX - ent->addr; + + /* cut when vmalloc() area is higher than direct-map area */ + if (VMALLOC_START > (unsigned long)__va(0)) { + if (ent->addr > VMALLOC_START) + goto free_out; + if (VMALLOC_START - ent->addr < ent->size) + ent->size = VMALLOC_START - ent->addr; + } + + ent->type = KCORE_RAM; + list_add_tail(&ent->list, head); + + if (!get_sparsemem_vmemmap_info(ent, head)) { + list_del(&ent->list); + goto free_out; + } + + return 0; +free_out: + kfree(ent); + return 1; +} + +static int kcore_update_ram(void) +{ + int nid, ret; + unsigned long end_pfn; + LIST_HEAD(head); + + /* Not inialized....update now */ + /* find out "max pfn" */ + end_pfn = 0; + for_each_node_state(nid, N_MEMORY) { + unsigned long node_end; + node_end = node_end_pfn(nid); + if (end_pfn < node_end) + end_pfn = node_end; + } + /* scan 0 to max_pfn */ + ret = walk_system_ram_range(0, end_pfn, &head, kclist_add_private); + if (ret) { + free_kclist_ents(&head); + return -ENOMEM; + } + __kcore_update_ram(&head); + return ret; +} +#endif /* CONFIG_HIGHMEM */ /*****************************************************************************/ /* @@ -103,7 +279,7 @@ static int notesize(struct memelfnote *en) int sz; sz = sizeof(struct elf_note); - sz += roundup(strlen(en->name), 4); + sz += roundup((strlen(en->name) + 1), 4); sz += roundup(en->datasz, 4); return sz; @@ -119,7 +295,7 @@ static char *storenote(struct memelfnote *men, char *bufp) #define DUMP_WRITE(addr,nr) do { memcpy(bufp,addr,nr); bufp += nr; } while(0) - en.n_namesz = strlen(men->name); + en.n_namesz = strlen(men->name) + 1; en.n_descsz = men->datasz; en.n_type = men->type; @@ -166,11 +342,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) elf->e_entry = 0; elf->e_phoff = sizeof(struct elfhdr); elf->e_shoff = 0; -#if defined(CONFIG_H8300) - elf->e_flags = ELF_FLAGS; -#else - elf->e_flags = 0; -#endif + elf->e_flags = ELF_CORE_EFLAGS; elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize= sizeof(struct elf_phdr); elf->e_phnum = nphdr; @@ -192,7 +364,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) nhdr->p_align = 0; /* setup ELF PT_LOAD program header for every area */ - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { phdr = (struct elf_phdr *) bufp; bufp += sizeof(struct elf_phdr); offset += sizeof(struct elf_phdr); @@ -213,7 +385,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) nhdr->p_offset = offset; /* set up the process status */ - notes[0].name = "CORE"; + notes[0].name = CORE_STR; notes[0].type = NT_PRSTATUS; notes[0].datasz = sizeof(struct elf_prstatus); notes[0].data = &prstatus; @@ -224,7 +396,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) bufp = storenote(¬es[0], bufp); /* set up the process info */ - notes[1].name = "CORE"; + notes[1].name = CORE_STR; notes[1].type = NT_PRPSINFO; notes[1].datasz = sizeof(struct elf_prpsinfo); notes[1].data = &prpsinfo; @@ -235,13 +407,13 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) prpsinfo.pr_zomb = 0; strcpy(prpsinfo.pr_fname, "vmlinux"); - strncpy(prpsinfo.pr_psargs, saved_command_line, ELF_PRARGSZ); + strlcpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs)); nhdr->p_filesz += notesize(¬es[1]); bufp = storenote(¬es[1], bufp); /* set up the task structure */ - notes[2].name = "CORE"; + notes[2].name = CORE_STR; notes[2].type = NT_TASKSTRUCT; notes[2].datasz = sizeof(struct task_struct); notes[2].data = current; @@ -265,7 +437,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) unsigned long start; read_lock(&kclist_lock); - proc_root_kcore->size = size = get_kcore_size(&nphdr, &elf_buflen); + size = get_kcore_size(&nphdr, &elf_buflen); + if (buflen == 0 || *fpos >= size) { read_unlock(&kclist_lock); return 0; @@ -282,12 +455,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) tsz = elf_buflen - *fpos; if (buflen < tsz) tsz = buflen; - elf_buf = kmalloc(elf_buflen, GFP_ATOMIC); + elf_buf = kzalloc(elf_buflen, GFP_ATOMIC); if (!elf_buf) { read_unlock(&kclist_lock); return -ENOMEM; } - memset(elf_buf, 0, elf_buflen); elf_kcore_store_hdr(elf_buf, nphdr, elf_buflen); read_unlock(&kclist_lock); if (copy_to_user(buffer, elf_buf + *fpos, tsz)) { @@ -318,55 +490,23 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) struct kcore_list *m; read_lock(&kclist_lock); - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { if (start >= m->addr && start < (m->addr+m->size)) break; } read_unlock(&kclist_lock); - if (m == NULL) { + if (&m->list == &kclist_head) { if (clear_user(buffer, tsz)) return -EFAULT; - } else if ((start >= VMALLOC_START) && (start < VMALLOC_END)) { + } else if (is_vmalloc_or_module_addr((void *)start)) { char * elf_buf; - struct vm_struct *m; - unsigned long curstart = start; - unsigned long cursize = tsz; - elf_buf = kmalloc(tsz, GFP_KERNEL); + elf_buf = kzalloc(tsz, GFP_KERNEL); if (!elf_buf) return -ENOMEM; - memset(elf_buf, 0, tsz); - - read_lock(&vmlist_lock); - for (m=vmlist; m && cursize; m=m->next) { - unsigned long vmstart; - unsigned long vmsize; - unsigned long msize = m->size - PAGE_SIZE; - - if (((unsigned long)m->addr + msize) < - curstart) - continue; - if ((unsigned long)m->addr > (curstart + - cursize)) - break; - vmstart = (curstart < (unsigned long)m->addr ? - (unsigned long)m->addr : curstart); - if (((unsigned long)m->addr + msize) > - (curstart + cursize)) - vmsize = curstart + cursize - vmstart; - else - vmsize = (unsigned long)m->addr + - msize - vmstart; - curstart = vmstart + vmsize; - cursize -= vmsize; - /* don't dump ioremap'd stuff! (TA) */ - if (m->flags & VM_IOREMAP) - continue; - memcpy(elf_buf + (vmstart - start), - (char *)vmstart, vmsize); - } - read_unlock(&vmlist_lock); + vread(elf_buf, (char *)start, tsz); + /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, elf_buf, tsz)) { kfree(elf_buf); return -EFAULT; @@ -378,14 +518,14 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) n = copy_to_user(buffer, (char *)start, tsz); /* - * We cannot distingush between fault on source + * We cannot distinguish between fault on source * and fault on destination. When this happens * we clear too and hope it will trigger the * EFAULT again. */ if (n) { if (clear_user(buffer + tsz - n, - tsz - n)) + n)) return -EFAULT; } } else { @@ -403,3 +543,100 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return acc; } + + +static int open_kcore(struct inode *inode, struct file *filp) +{ + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + if (kcore_need_update) + kcore_update_ram(); + if (i_size_read(inode) != proc_root_kcore->size) { + mutex_lock(&inode->i_mutex); + i_size_write(inode, proc_root_kcore->size); + mutex_unlock(&inode->i_mutex); + } + return 0; +} + + +static const struct file_operations proc_kcore_operations = { + .read = read_kcore, + .open = open_kcore, + .llseek = default_llseek, +}; + +/* just remember that we have to update kcore */ +static int __meminit kcore_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + switch (action) { + case MEM_ONLINE: + case MEM_OFFLINE: + write_lock(&kclist_lock); + kcore_need_update = 1; + write_unlock(&kclist_lock); + } + return NOTIFY_OK; +} + +static struct notifier_block kcore_callback_nb __meminitdata = { + .notifier_call = kcore_callback, + .priority = 0, +}; + +static struct kcore_list kcore_vmalloc; + +#ifdef CONFIG_ARCH_PROC_KCORE_TEXT +static struct kcore_list kcore_text; +/* + * If defined, special segment is used for mapping kernel text instead of + * direct-map area. We need to create special TEXT section. + */ +static void __init proc_kcore_text_init(void) +{ + kclist_add(&kcore_text, _text, _end - _text, KCORE_TEXT); +} +#else +static void __init proc_kcore_text_init(void) +{ +} +#endif + +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) +/* + * MODULES_VADDR has no intersection with VMALLOC_ADDR. + */ +struct kcore_list kcore_modules; +static void __init add_modules_range(void) +{ + kclist_add(&kcore_modules, (void *)MODULES_VADDR, + MODULES_END - MODULES_VADDR, KCORE_VMALLOC); +} +#else +static void __init add_modules_range(void) +{ +} +#endif + +static int __init proc_kcore_init(void) +{ + proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, + &proc_kcore_operations); + if (!proc_root_kcore) { + pr_err("couldn't create /proc/kcore\n"); + return 0; /* Always returns 0. */ + } + /* Store text area if it's special */ + proc_kcore_text_init(); + /* Store vmalloc area */ + kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, + VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); + add_modules_range(); + /* Store direct-map area from physical memory map */ + kcore_update_ram(); + register_hotmemory_notifier(&kcore_callback_nb); + + return 0; +} +fs_initcall(proc_kcore_init); diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 10d37bf2520..05f8dcdb086 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -10,46 +10,55 @@ #include <linux/time.h> #include <linux/kernel.h> #include <linux/poll.h> +#include <linux/proc_fs.h> #include <linux/fs.h> +#include <linux/syslog.h> #include <asm/uaccess.h> #include <asm/io.h> extern wait_queue_head_t log_wait; -extern int do_syslog(int type, char __user *bug, int count); - static int kmsg_open(struct inode * inode, struct file * file) { - return do_syslog(1,NULL,0); + return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC); } static int kmsg_release(struct inode * inode, struct file * file) { - (void) do_syslog(0,NULL,0); + (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC); return 0; } static ssize_t kmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - if ((file->f_flags & O_NONBLOCK) && !do_syslog(9, NULL, 0)) + if ((file->f_flags & O_NONBLOCK) && + !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return -EAGAIN; - return do_syslog(2, buf, count); + return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC); } static unsigned int kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); - if (do_syslog(9, NULL, 0)) + if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return POLLIN | POLLRDNORM; return 0; } -struct file_operations proc_kmsg_operations = { +static const struct file_operations proc_kmsg_operations = { .read = kmsg_read, .poll = kmsg_poll, .open = kmsg_open, .release = kmsg_release, + .llseek = generic_file_llseek, }; + +static int __init proc_kmsg_init(void) +{ + proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); + return 0; +} +fs_initcall(proc_kmsg_init); diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c new file mode 100644 index 00000000000..aec66e6c206 --- /dev/null +++ b/fs/proc/loadavg.c @@ -0,0 +1,45 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/pid_namespace.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/seqlock.h> +#include <linux/time.h> + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) + +static int loadavg_proc_show(struct seq_file *m, void *v) +{ + unsigned long avnrun[3]; + + get_avenrun(avnrun, FIXED_1/200, 0); + + seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%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]), + nr_running(), nr_threads, + task_active_pid_ns(current)->last_pid); + return 0; +} + +static int loadavg_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, loadavg_proc_show, NULL); +} + +static const struct file_operations loadavg_proc_fops = { + .open = loadavg_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_loadavg_init(void) +{ + proc_create("loadavg", 0, NULL, &loadavg_proc_fops); + return 0; +} +fs_initcall(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c new file mode 100644 index 00000000000..7445af0b1aa --- /dev/null +++ b/fs/proc/meminfo.c @@ -0,0 +1,223 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/mman.h> +#include <linux/mmzone.h> +#include <linux/proc_fs.h> +#include <linux/quicklist.h> +#include <linux/seq_file.h> +#include <linux/swap.h> +#include <linux/vmstat.h> +#include <linux/atomic.h> +#include <linux/vmalloc.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include "internal.h" + +void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) +{ +} + +static int meminfo_proc_show(struct seq_file *m, void *v) +{ + struct sysinfo i; + unsigned long committed; + struct vmalloc_info vmi; + long cached; + long available; + unsigned long pagecache; + unsigned long wmark_low = 0; + unsigned long pages[NR_LRU_LISTS]; + struct zone *zone; + int lru; + +/* + * display in kilobytes. + */ +#define K(x) ((x) << (PAGE_SHIFT - 10)) + si_meminfo(&i); + si_swapinfo(&i); + committed = percpu_counter_read_positive(&vm_committed_as); + + cached = global_page_state(NR_FILE_PAGES) - + total_swapcache_pages() - i.bufferram; + if (cached < 0) + cached = 0; + + get_vmalloc_info(&vmi); + + for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) + pages[lru] = global_page_state(NR_LRU_BASE + lru); + + for_each_zone(zone) + wmark_low += zone->watermark[WMARK_LOW]; + + /* + * Estimate the amount of memory available for userspace allocations, + * without causing swapping. + * + * Free memory cannot be taken below the low watermark, before the + * system starts swapping. + */ + available = i.freeram - wmark_low; + + /* + * Not all the page cache can be freed, otherwise the system will + * start swapping. Assume at least half of the page cache, or the + * low watermark worth of cache, needs to stay. + */ + pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; + pagecache -= min(pagecache / 2, wmark_low); + available += pagecache; + + /* + * Part of the reclaimable slab consists of items that are in use, + * and cannot be freed. Cap this estimate at the low watermark. + */ + available += global_page_state(NR_SLAB_RECLAIMABLE) - + min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low); + + if (available < 0) + available = 0; + + /* + * Tagged format, for easy grepping and expansion. + */ + seq_printf(m, + "MemTotal: %8lu kB\n" + "MemFree: %8lu kB\n" + "MemAvailable: %8lu kB\n" + "Buffers: %8lu kB\n" + "Cached: %8lu kB\n" + "SwapCached: %8lu kB\n" + "Active: %8lu kB\n" + "Inactive: %8lu kB\n" + "Active(anon): %8lu kB\n" + "Inactive(anon): %8lu kB\n" + "Active(file): %8lu kB\n" + "Inactive(file): %8lu kB\n" + "Unevictable: %8lu kB\n" + "Mlocked: %8lu kB\n" +#ifdef CONFIG_HIGHMEM + "HighTotal: %8lu kB\n" + "HighFree: %8lu kB\n" + "LowTotal: %8lu kB\n" + "LowFree: %8lu kB\n" +#endif +#ifndef CONFIG_MMU + "MmapCopy: %8lu kB\n" +#endif + "SwapTotal: %8lu kB\n" + "SwapFree: %8lu kB\n" + "Dirty: %8lu kB\n" + "Writeback: %8lu kB\n" + "AnonPages: %8lu kB\n" + "Mapped: %8lu kB\n" + "Shmem: %8lu kB\n" + "Slab: %8lu kB\n" + "SReclaimable: %8lu kB\n" + "SUnreclaim: %8lu kB\n" + "KernelStack: %8lu kB\n" + "PageTables: %8lu kB\n" +#ifdef CONFIG_QUICKLIST + "Quicklists: %8lu kB\n" +#endif + "NFS_Unstable: %8lu kB\n" + "Bounce: %8lu kB\n" + "WritebackTmp: %8lu kB\n" + "CommitLimit: %8lu kB\n" + "Committed_AS: %8lu kB\n" + "VmallocTotal: %8lu kB\n" + "VmallocUsed: %8lu kB\n" + "VmallocChunk: %8lu kB\n" +#ifdef CONFIG_MEMORY_FAILURE + "HardwareCorrupted: %5lu kB\n" +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + "AnonHugePages: %8lu kB\n" +#endif + , + K(i.totalram), + K(i.freeram), + K(available), + K(i.bufferram), + K(cached), + K(total_swapcache_pages()), + K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), + K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), + K(pages[LRU_ACTIVE_ANON]), + K(pages[LRU_INACTIVE_ANON]), + K(pages[LRU_ACTIVE_FILE]), + K(pages[LRU_INACTIVE_FILE]), + K(pages[LRU_UNEVICTABLE]), + K(global_page_state(NR_MLOCK)), +#ifdef CONFIG_HIGHMEM + K(i.totalhigh), + K(i.freehigh), + K(i.totalram-i.totalhigh), + K(i.freeram-i.freehigh), +#endif +#ifndef CONFIG_MMU + K((unsigned long) atomic_long_read(&mmap_pages_allocated)), +#endif + K(i.totalswap), + K(i.freeswap), + K(global_page_state(NR_FILE_DIRTY)), + K(global_page_state(NR_WRITEBACK)), + K(global_page_state(NR_ANON_PAGES)), + K(global_page_state(NR_FILE_MAPPED)), + K(global_page_state(NR_SHMEM)), + K(global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)), + K(global_page_state(NR_SLAB_RECLAIMABLE)), + K(global_page_state(NR_SLAB_UNRECLAIMABLE)), + global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024, + K(global_page_state(NR_PAGETABLE)), +#ifdef CONFIG_QUICKLIST + K(quicklist_total_size()), +#endif + K(global_page_state(NR_UNSTABLE_NFS)), + K(global_page_state(NR_BOUNCE)), + K(global_page_state(NR_WRITEBACK_TEMP)), + K(vm_commit_limit()), + K(committed), + (unsigned long)VMALLOC_TOTAL >> 10, + vmi.used >> 10, + vmi.largest_chunk >> 10 +#ifdef CONFIG_MEMORY_FAILURE + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * + HPAGE_PMD_NR) +#endif + ); + + hugetlb_report_meminfo(m); + + arch_report_meminfo(m); + + return 0; +#undef K +} + +static int meminfo_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, meminfo_proc_show, NULL); +} + +static const struct file_operations meminfo_proc_fops = { + .open = meminfo_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_meminfo_init(void) +{ + proc_create("meminfo", 0, NULL, &meminfo_proc_fops); + return 0; +} +fs_initcall(proc_meminfo_init); diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c deleted file mode 100644 index 25d2d9c6e32..00000000000 --- a/fs/proc/mmu.c +++ /dev/null @@ -1,77 +0,0 @@ -/* mmu.c: mmu memory info files - * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/mman.h> -#include <linux/proc_fs.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/pagemap.h> -#include <linux/swap.h> -#include <linux/slab.h> -#include <linux/smp.h> -#include <linux/seq_file.h> -#include <linux/hugetlb.h> -#include <linux/vmalloc.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/tlb.h> -#include <asm/div64.h> -#include "internal.h" - -void get_vmalloc_info(struct vmalloc_info *vmi) -{ - struct vm_struct *vma; - unsigned long free_area_size; - unsigned long prev_end; - - vmi->used = 0; - - if (!vmlist) { - vmi->largest_chunk = VMALLOC_TOTAL; - } - else { - vmi->largest_chunk = 0; - - prev_end = VMALLOC_START; - - read_lock(&vmlist_lock); - - for (vma = vmlist; vma; vma = vma->next) { - unsigned long addr = (unsigned long) vma->addr; - - /* - * Some archs keep another range for modules in vmlist - */ - if (addr < VMALLOC_START) - continue; - if (addr >= VMALLOC_END) - break; - - vmi->used += vma->size; - - free_area_size = addr - prev_end; - if (vmi->largest_chunk < free_area_size) - vmi->largest_chunk = free_area_size; - - prev_end = vma->size + addr; - } - - if (VMALLOC_END - prev_end > vmi->largest_chunk) - vmi->largest_chunk = VMALLOC_END - prev_end; - - read_unlock(&vmlist_lock); - } -} diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c new file mode 100644 index 00000000000..89026095f2b --- /dev/null +++ b/fs/proc/namespaces.c @@ -0,0 +1,297 @@ +#include <linux/proc_fs.h> +#include <linux/nsproxy.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/fs_struct.h> +#include <linux/mount.h> +#include <linux/path.h> +#include <linux/namei.h> +#include <linux/file.h> +#include <linux/utsname.h> +#include <net/net_namespace.h> +#include <linux/ipc_namespace.h> +#include <linux/pid_namespace.h> +#include <linux/user_namespace.h> +#include "internal.h" + + +static const struct proc_ns_operations *ns_entries[] = { +#ifdef CONFIG_NET_NS + &netns_operations, +#endif +#ifdef CONFIG_UTS_NS + &utsns_operations, +#endif +#ifdef CONFIG_IPC_NS + &ipcns_operations, +#endif +#ifdef CONFIG_PID_NS + &pidns_operations, +#endif +#ifdef CONFIG_USER_NS + &userns_operations, +#endif + &mntns_operations, +}; + +static const struct file_operations ns_file_operations = { + .llseek = no_llseek, +}; + +static const struct inode_operations ns_inode_operations = { + .setattr = proc_setattr, +}; + +static char *ns_dname(struct dentry *dentry, char *buffer, int buflen) +{ + struct inode *inode = dentry->d_inode; + const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops; + + return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]", + ns_ops->name, inode->i_ino); +} + +const struct dentry_operations ns_dentry_operations = +{ + .d_delete = always_delete_dentry, + .d_dname = ns_dname, +}; + +static struct dentry *proc_ns_get_dentry(struct super_block *sb, + struct task_struct *task, const struct proc_ns_operations *ns_ops) +{ + struct dentry *dentry, *result; + struct inode *inode; + struct proc_inode *ei; + struct qstr qname = { .name = "", }; + void *ns; + + ns = ns_ops->get(task); + if (!ns) + return ERR_PTR(-ENOENT); + + dentry = d_alloc_pseudo(sb, &qname); + if (!dentry) { + ns_ops->put(ns); + return ERR_PTR(-ENOMEM); + } + + inode = iget_locked(sb, ns_ops->inum(ns)); + if (!inode) { + dput(dentry); + ns_ops->put(ns); + return ERR_PTR(-ENOMEM); + } + + ei = PROC_I(inode); + if (inode->i_state & I_NEW) { + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_op = &ns_inode_operations; + inode->i_mode = S_IFREG | S_IRUGO; + inode->i_fop = &ns_file_operations; + ei->ns.ns_ops = ns_ops; + ei->ns.ns = ns; + unlock_new_inode(inode); + } else { + ns_ops->put(ns); + } + + d_set_d_op(dentry, &ns_dentry_operations); + result = d_instantiate_unique(dentry, inode); + if (result) { + dput(dentry); + dentry = result; + } + + return dentry; +} + +static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct super_block *sb = inode->i_sb; + struct proc_inode *ei = PROC_I(inode); + struct task_struct *task; + struct path ns_path; + void *error = ERR_PTR(-EACCES); + + task = get_proc_task(inode); + if (!task) + goto out; + + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops); + if (IS_ERR(ns_path.dentry)) { + error = ERR_CAST(ns_path.dentry); + goto out_put_task; + } + + ns_path.mnt = mntget(nd->path.mnt); + nd_jump_link(nd, &ns_path); + error = NULL; + +out_put_task: + put_task_struct(task); +out: + return error; +} + +static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen) +{ + struct inode *inode = dentry->d_inode; + struct proc_inode *ei = PROC_I(inode); + const struct proc_ns_operations *ns_ops = ei->ns.ns_ops; + struct task_struct *task; + void *ns; + char name[50]; + int res = -EACCES; + + task = get_proc_task(inode); + if (!task) + goto out; + + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + res = -ENOENT; + ns = ns_ops->get(task); + if (!ns) + goto out_put_task; + + snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns)); + res = readlink_copy(buffer, buflen, name); + ns_ops->put(ns); +out_put_task: + put_task_struct(task); +out: + return res; +} + +static const struct inode_operations proc_ns_link_inode_operations = { + .readlink = proc_ns_readlink, + .follow_link = proc_ns_follow_link, + .setattr = proc_setattr, +}; + +static int proc_ns_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, const void *ptr) +{ + const struct proc_ns_operations *ns_ops = ptr; + struct inode *inode; + struct proc_inode *ei; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + inode->i_mode = S_IFLNK|S_IRWXUGO; + inode->i_op = &proc_ns_link_inode_operations; + ei->ns.ns_ops = ns_ops; + + d_set_d_op(dentry, &pid_dentry_operations); + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; +out: + return -ENOENT; +} + +static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + const struct proc_ns_operations **entry, **last; + + if (!task) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) + goto out; + if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries)) + goto out; + entry = ns_entries + (ctx->pos - 2); + last = &ns_entries[ARRAY_SIZE(ns_entries) - 1]; + while (entry <= last) { + const struct proc_ns_operations *ops = *entry; + if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name), + proc_ns_instantiate, task, ops)) + break; + ctx->pos++; + entry++; + } +out: + put_task_struct(task); + return 0; +} + +const struct file_operations proc_ns_dir_operations = { + .read = generic_read_dir, + .iterate = proc_ns_dir_readdir, +}; + +static struct dentry *proc_ns_dir_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + int error; + struct task_struct *task = get_proc_task(dir); + const struct proc_ns_operations **entry, **last; + unsigned int len = dentry->d_name.len; + + error = -ENOENT; + + if (!task) + goto out_no_task; + + last = &ns_entries[ARRAY_SIZE(ns_entries)]; + for (entry = ns_entries; entry < last; entry++) { + if (strlen((*entry)->name) != len) + continue; + if (!memcmp(dentry->d_name.name, (*entry)->name, len)) + break; + } + if (entry == last) + goto out; + + error = proc_ns_instantiate(dir, dentry, task, *entry); +out: + put_task_struct(task); +out_no_task: + return ERR_PTR(error); +} + +const struct inode_operations proc_ns_dir_inode_operations = { + .lookup = proc_ns_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + +struct file *proc_ns_fget(int fd) +{ + struct file *file; + + file = fget(fd); + if (!file) + return ERR_PTR(-EBADF); + + if (file->f_op != &ns_file_operations) + goto out_invalid; + + return file; + +out_invalid: + fput(file); + return ERR_PTR(-EINVAL); +} + +struct proc_ns *get_proc_ns(struct inode *inode) +{ + return &PROC_I(inode)->ns; +} + +bool proc_ns_inode(struct inode *inode) +{ + return inode->i_fop == &ns_file_operations; +} diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index cff10ab1af6..d4a35746cab 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -21,7 +21,6 @@ #include <linux/mmzone.h> #include <linux/pagemap.h> #include <linux/swap.h> -#include <linux/slab.h> #include <linux/smp.h> #include <linux/seq_file.h> #include <linux/hugetlb.h> @@ -33,95 +32,94 @@ #include "internal.h" /* - * display a list of all the VMAs the kernel knows about - * - nommu kernals have a single flat list + * display a single region to a sequenced file */ -static int nommu_vma_list_show(struct seq_file *m, void *v) +static int nommu_region_show(struct seq_file *m, struct vm_region *region) { - struct vm_area_struct *vma; unsigned long ino = 0; struct file *file; dev_t dev = 0; - int flags, len; + int flags; - vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); - - flags = vma->vm_flags; - file = vma->vm_file; + flags = region->vm_flags; + file = region->vm_file; if (file) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(region->vm_file); dev = inode->i_sb->s_dev; ino = inode->i_ino; } + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); seq_printf(m, - "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", - vma->vm_start, - vma->vm_end, + "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", + region->vm_start, + region->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - vma->vm_pgoff << PAGE_SHIFT, - MAJOR(dev), MINOR(dev), ino, &len); + ((loff_t)region->vm_pgoff) << PAGE_SHIFT, + MAJOR(dev), MINOR(dev), ino); if (file) { - len = 25 + sizeof(void *) * 6 - len; - if (len < 1) - len = 1; - seq_printf(m, "%*c", len, ' '); - seq_path(m, file->f_vfsmnt, file->f_dentry, ""); + seq_pad(m, ' '); + seq_path(m, &file->f_path, ""); } seq_putc(m, '\n'); return 0; } -static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) +/* + * display a list of all the REGIONs the kernel knows about + * - nommu kernels have a single flat list + */ +static int nommu_region_list_show(struct seq_file *m, void *_p) { - struct rb_node *_rb; - loff_t pos = *_pos; - void *next = NULL; + struct rb_node *p = _p; - down_read(&nommu_vma_sem); + return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb)); +} - for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) { - if (pos == 0) { - next = _rb; - break; - } - pos--; - } +static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos) +{ + struct rb_node *p; + loff_t pos = *_pos; + + down_read(&nommu_region_sem); - return next; + for (p = rb_first(&nommu_region_tree); p; p = rb_next(p)) + if (pos-- == 0) + return p; + return NULL; } -static void nommu_vma_list_stop(struct seq_file *m, void *v) +static void nommu_region_list_stop(struct seq_file *m, void *v) { - up_read(&nommu_vma_sem); + up_read(&nommu_region_sem); } -static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos) +static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos) { (*pos)++; return rb_next((struct rb_node *) v); } -static struct seq_operations proc_nommu_vma_list_seqop = { - .start = nommu_vma_list_start, - .next = nommu_vma_list_next, - .stop = nommu_vma_list_stop, - .show = nommu_vma_list_show +static const struct seq_operations proc_nommu_region_list_seqop = { + .start = nommu_region_list_start, + .next = nommu_region_list_next, + .stop = nommu_region_list_stop, + .show = nommu_region_list_show }; -static int proc_nommu_vma_list_open(struct inode *inode, struct file *file) +static int proc_nommu_region_list_open(struct inode *inode, struct file *file) { - return seq_open(file, &proc_nommu_vma_list_seqop); + return seq_open(file, &proc_nommu_region_list_seqop); } -static struct file_operations proc_nommu_vma_list_operations = { - .open = proc_nommu_vma_list_open, +static const struct file_operations proc_nommu_region_list_operations = { + .open = proc_nommu_region_list_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, @@ -129,8 +127,8 @@ static struct file_operations proc_nommu_vma_list_operations = { static int __init proc_nommu_init(void) { - create_seq_entry("maps", S_IRUGO, &proc_nommu_vma_list_operations); + proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations); return 0; } -module_init(proc_nommu_init); +fs_initcall(proc_nommu_init); diff --git a/fs/proc/page.c b/fs/proc/page.c new file mode 100644 index 00000000000..e647c55275d --- /dev/null +++ b/fs/proc/page.c @@ -0,0 +1,221 @@ +#include <linux/bootmem.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/ksm.h> +#include <linux/mm.h> +#include <linux/mmzone.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/hugetlb.h> +#include <linux/kernel-page-flags.h> +#include <asm/uaccess.h> +#include "internal.h" + +#define KPMSIZE sizeof(u64) +#define KPMMASK (KPMSIZE - 1) + +/* /proc/kpagecount - an array exposing page counts + * + * Each entry is a u64 representing the corresponding + * physical page count. + */ +static ssize_t kpagecount_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + u64 pcount; + + pfn = src / KPMSIZE; + count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EINVAL; + + while (count > 0) { + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + else + ppage = NULL; + if (!ppage || PageSlab(ppage)) + pcount = 0; + else + pcount = page_mapcount(ppage); + + if (put_user(pcount, out)) { + ret = -EFAULT; + break; + } + + pfn++; + out++; + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static const struct file_operations proc_kpagecount_operations = { + .llseek = mem_lseek, + .read = kpagecount_read, +}; + +/* /proc/kpageflags - an array exposing page flags + * + * Each entry is a u64 representing the corresponding + * physical page flags. + */ + +static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit) +{ + return ((kflags >> kbit) & 1) << ubit; +} + +u64 stable_page_flags(struct page *page) +{ + u64 k; + u64 u; + + /* + * pseudo flag: KPF_NOPAGE + * it differentiates a memory hole from a page with no flags + */ + if (!page) + return 1 << KPF_NOPAGE; + + k = page->flags; + u = 0; + + /* + * pseudo flags for the well known (anonymous) memory mapped pages + * + * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the + * simple test in page_mapped() is not enough. + */ + if (!PageSlab(page) && page_mapped(page)) + u |= 1 << KPF_MMAP; + if (PageAnon(page)) + u |= 1 << KPF_ANON; + if (PageKsm(page)) + u |= 1 << KPF_KSM; + + /* + * compound pages: export both head/tail info + * they together define a compound page's start/end pos and order + */ + if (PageHead(page)) + u |= 1 << KPF_COMPOUND_HEAD; + if (PageTail(page)) + u |= 1 << KPF_COMPOUND_TAIL; + if (PageHuge(page)) + u |= 1 << KPF_HUGE; + /* + * PageTransCompound can be true for non-huge compound pages (slab + * pages or pages allocated by drivers with __GFP_COMP) because it + * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon + * to make sure a given page is a thp, not a non-huge compound page. + */ + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) + u |= 1 << KPF_THP; + + /* + * Caveats on high order pages: page->_count will only be set + * -1 on the head page; SLUB/SLQB do the same for PG_slab; + * SLOB won't set PG_slab at all on compound pages. + */ + if (PageBuddy(page)) + u |= 1 << KPF_BUDDY; + + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); + + u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); + + u |= kpf_copy_bit(k, KPF_ERROR, PG_error); + u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); + u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate); + u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback); + + u |= kpf_copy_bit(k, KPF_LRU, PG_lru); + u |= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced); + u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active); + u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim); + + u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache); + u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked); + + u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable); + u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked); + +#ifdef CONFIG_MEMORY_FAILURE + u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison); +#endif + +#ifdef CONFIG_ARCH_USES_PG_UNCACHED + u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached); +#endif + + u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved); + u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk); + u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private); + 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); + + return u; +}; + +static ssize_t kpageflags_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + + pfn = src / KPMSIZE; + count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EINVAL; + + while (count > 0) { + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + else + ppage = NULL; + + if (put_user(stable_page_flags(ppage), out)) { + ret = -EFAULT; + break; + } + + pfn++; + out++; + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static const struct file_operations proc_kpageflags_operations = { + .llseek = mem_lseek, + .read = kpageflags_read, +}; + +static int __init proc_page_init(void) +{ + proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations); + proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); + return 0; +} +fs_initcall(proc_page_init); diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c deleted file mode 100644 index 9bdd077d6f5..00000000000 --- a/fs/proc/proc_devtree.c +++ /dev/null @@ -1,173 +0,0 @@ -/* - * proc_devtree.c - handles /proc/device-tree - * - * Copyright 1997 Paul Mackerras - */ -#include <linux/errno.h> -#include <linux/time.h> -#include <linux/proc_fs.h> -#include <linux/stat.h> -#include <linux/string.h> -#include <asm/prom.h> -#include <asm/uaccess.h> - -#ifndef HAVE_ARCH_DEVTREE_FIXUPS -static inline void set_node_proc_entry(struct device_node *np, - struct proc_dir_entry *de) -{ -} -#endif - -static struct proc_dir_entry *proc_device_tree; - -/* - * Supply data on a read from /proc/device-tree/node/property. - */ -static int property_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - struct property *pp = data; - int n; - - if (off >= pp->length) { - *eof = 1; - return 0; - } - n = pp->length - off; - if (n > count) - n = count; - else - *eof = 1; - memcpy(page, pp->value + off, n); - *start = page; - return n; -} - -/* - * For a node with a name like "gc@10", we make symlinks called "gc" - * and "@10" to it. - */ - -/* - * Add a property to a node - */ -static struct proc_dir_entry * -__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp) -{ - struct proc_dir_entry *ent; - - /* - * Unfortunately proc_register puts each new entry - * at the beginning of the list. So we rearrange them. - */ - ent = create_proc_read_entry(pp->name, - strncmp(pp->name, "security-", 9) - ? S_IRUGO : S_IRUSR, de, - property_read_proc, pp); - if (ent == NULL) - return NULL; - - if (!strncmp(pp->name, "security-", 9)) - ent->size = 0; /* don't leak number of password chars */ - else - ent->size = pp->length; - - return ent; -} - - -void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop) -{ - __proc_device_tree_add_prop(pde, prop); -} - -void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop) -{ - remove_proc_entry(prop->name, pde); -} - -void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop) -{ - struct proc_dir_entry *ent; - - for (ent = pde->subdir; ent != NULL; ent = ent->next) - if (ent->data == oldprop) - break; - if (ent == NULL) { - printk(KERN_WARNING "device-tree: property \"%s\" " - " does not exist\n", oldprop->name); - } else { - ent->data = newprop; - ent->size = newprop->length; - } -} - -/* - * Process a node, adding entries for its children and its properties. - */ -void proc_device_tree_add_node(struct device_node *np, - struct proc_dir_entry *de) -{ - struct property *pp; - struct proc_dir_entry *ent; - struct device_node *child; - const char *p; - - set_node_proc_entry(np, de); - for (child = NULL; (child = of_get_next_child(np, child));) { - p = strrchr(child->full_name, '/'); - if (!p) - p = child->full_name; - else - ++p; - ent = proc_mkdir(p, de); - if (ent == 0) - break; - proc_device_tree_add_node(child, ent); - } - of_node_put(child); - for (pp = np->properties; pp != 0; pp = pp->next) { - /* - * Yet another Apple device-tree bogosity: on some machines, - * they have properties & nodes with the same name. Those - * properties are quite unimportant for us though, thus we - * simply "skip" them here, but we do have to check. - */ - for (ent = de->subdir; ent != NULL; ent = ent->next) - if (!strcmp(ent->name, pp->name)) - break; - if (ent != NULL) { - printk(KERN_WARNING "device-tree: property \"%s\" name" - " conflicts with node in %s\n", pp->name, - np->full_name); - continue; - } - - ent = __proc_device_tree_add_prop(de, pp); - if (ent == 0) - break; - } -} - -/* - * Called on initialization to set up the /proc/device-tree subtree - */ -void proc_device_tree_init(void) -{ - struct device_node *root; - if ( !have_of ) - return; - proc_device_tree = proc_mkdir("device-tree", NULL); - if (proc_device_tree == 0) - return; - root = of_find_node_by_path("/"); - if (root == 0) { - printk(KERN_ERR "/proc/device-tree: can't find root\n"); - return; - } - proc_device_tree_add_node(root, proc_device_tree); - of_node_put(root); -} diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c deleted file mode 100644 index 8f8014285a3..00000000000 --- a/fs/proc/proc_misc.c +++ /dev/null @@ -1,776 +0,0 @@ -/* - * linux/fs/proc/proc_misc.c - * - * linux/fs/proc/array.c - * Copyright (C) 1992 by Linus Torvalds - * based on ideas by Darren Senn - * - * This used to be the part of array.c. See the rest of history and credits - * there. I took this into a separate file and switched the thing to generic - * proc_file_inode_operations, leaving in array.c only per-process stuff. - * Inumbers allocation made dynamic (via create_proc_entry()). AV, May 1999. - * - * Changes: - * Fulton Green : Encapsulated position metric calculations. - * <kernel@FultonGreen.com> - */ - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/kernel_stat.h> -#include <linux/fs.h> -#include <linux/tty.h> -#include <linux/string.h> -#include <linux/mman.h> -#include <linux/proc_fs.h> -#include <linux/ioport.h> -#include <linux/config.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/pagemap.h> -#include <linux/swap.h> -#include <linux/slab.h> -#include <linux/smp.h> -#include <linux/signal.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/smp_lock.h> -#include <linux/seq_file.h> -#include <linux/times.h> -#include <linux/profile.h> -#include <linux/blkdev.h> -#include <linux/hugetlb.h> -#include <linux/jiffies.h> -#include <linux/sysrq.h> -#include <linux/vmalloc.h> -#include <linux/crash_dump.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/io.h> -#include <asm/tlb.h> -#include <asm/div64.h> -#include "internal.h" - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -/* - * Warning: stuff below (imported functions) assumes that its output will fit - * into one page. For some of those functions it may be wrong. Moreover, we - * have a way to deal with that gracefully. Right now I used straightforward - * wrappers, but this needs further analysis wrt potential overflows. - */ -extern int get_hardware_list(char *); -extern int get_stram_list(char *); -extern int get_filesystem_list(char *); -extern int get_exec_domain_list(char *); -extern int get_dma_list(char *); -extern int get_locks_status (char *, char **, off_t, int); - -static int proc_calc_metrics(char *page, char **start, off_t off, - int count, int *eof, int len) -{ - if (len <= off+count) *eof = 1; - *start = page + off; - len -= off; - if (len>count) len = count; - if (len<0) len = 0; - return len; -} - -static int loadavg_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int a, b, c; - int len; - - a = avenrun[0] + (FIXED_1/200); - b = avenrun[1] + (FIXED_1/200); - c = avenrun[2] + (FIXED_1/200); - len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n", - LOAD_INT(a), LOAD_FRAC(a), - LOAD_INT(b), LOAD_FRAC(b), - LOAD_INT(c), LOAD_FRAC(c), - nr_running(), nr_threads, last_pid); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int uptime_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - struct timespec uptime; - struct timespec idle; - int len; - cputime_t idletime = cputime_add(init_task.utime, init_task.stime); - - do_posix_clock_monotonic_gettime(&uptime); - cputime_to_timespec(idletime, &idle); - len = sprintf(page,"%lu.%02lu %lu.%02lu\n", - (unsigned long) uptime.tv_sec, - (uptime.tv_nsec / (NSEC_PER_SEC / 100)), - (unsigned long) idle.tv_sec, - (idle.tv_nsec / (NSEC_PER_SEC / 100))); - - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int meminfo_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - struct sysinfo i; - int len; - struct page_state ps; - unsigned long inactive; - unsigned long active; - unsigned long free; - unsigned long committed; - unsigned long allowed; - struct vmalloc_info vmi; - long cached; - - get_page_state(&ps); - get_zone_counts(&active, &inactive, &free); - -/* - * display in kilobytes. - */ -#define K(x) ((x) << (PAGE_SHIFT - 10)) - si_meminfo(&i); - si_swapinfo(&i); - committed = atomic_read(&vm_committed_space); - allowed = ((totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100) + total_swap_pages; - - cached = get_page_cache_size() - total_swapcache_pages - i.bufferram; - if (cached < 0) - cached = 0; - - get_vmalloc_info(&vmi); - - /* - * Tagged format, for easy grepping and expansion. - */ - len = sprintf(page, - "MemTotal: %8lu kB\n" - "MemFree: %8lu kB\n" - "Buffers: %8lu kB\n" - "Cached: %8lu kB\n" - "SwapCached: %8lu kB\n" - "Active: %8lu kB\n" - "Inactive: %8lu kB\n" - "HighTotal: %8lu kB\n" - "HighFree: %8lu kB\n" - "LowTotal: %8lu kB\n" - "LowFree: %8lu kB\n" - "SwapTotal: %8lu kB\n" - "SwapFree: %8lu kB\n" - "Dirty: %8lu kB\n" - "Writeback: %8lu kB\n" - "Mapped: %8lu kB\n" - "Slab: %8lu kB\n" - "CommitLimit: %8lu kB\n" - "Committed_AS: %8lu kB\n" - "PageTables: %8lu kB\n" - "VmallocTotal: %8lu kB\n" - "VmallocUsed: %8lu kB\n" - "VmallocChunk: %8lu kB\n", - K(i.totalram), - K(i.freeram), - K(i.bufferram), - K(cached), - K(total_swapcache_pages), - K(active), - K(inactive), - K(i.totalhigh), - K(i.freehigh), - K(i.totalram-i.totalhigh), - K(i.freeram-i.freehigh), - K(i.totalswap), - K(i.freeswap), - K(ps.nr_dirty), - K(ps.nr_writeback), - K(ps.nr_mapped), - K(ps.nr_slab), - K(allowed), - K(committed), - K(ps.nr_page_table_pages), - (unsigned long)VMALLOC_TOTAL >> 10, - vmi.used >> 10, - vmi.largest_chunk >> 10 - ); - - len += hugetlb_report_meminfo(page + len); - - return proc_calc_metrics(page, start, off, count, eof, len); -#undef K -} - -extern struct seq_operations fragmentation_op; -static int fragmentation_open(struct inode *inode, struct file *file) -{ - (void)inode; - return seq_open(file, &fragmentation_op); -} - -static struct file_operations fragmentation_file_operations = { - .open = fragmentation_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -extern struct seq_operations zoneinfo_op; -static int zoneinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &zoneinfo_op); -} - -static struct file_operations proc_zoneinfo_file_operations = { - .open = zoneinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int version_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len; - - strcpy(page, linux_banner); - len = strlen(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -extern struct seq_operations cpuinfo_op; -static int cpuinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &cpuinfo_op); -} - -enum devinfo_states { - CHR_HDR, - CHR_LIST, - BLK_HDR, - BLK_LIST, - DEVINFO_DONE -}; - -struct devinfo_state { - void *chrdev; - void *blkdev; - unsigned int num_records; - unsigned int cur_record; - enum devinfo_states state; -}; - -static void *devinfo_start(struct seq_file *f, loff_t *pos) -{ - struct devinfo_state *info = f->private; - - if (*pos) { - if ((info) && (*pos <= info->num_records)) - return info; - return NULL; - } - info = kmalloc(sizeof(*info), GFP_KERNEL); - f->private = info; - info->chrdev = acquire_chrdev_list(); - info->blkdev = acquire_blkdev_list(); - info->state = CHR_HDR; - info->num_records = count_chrdev_list(); - info->num_records += count_blkdev_list(); - info->num_records += 2; /* Character and Block headers */ - *pos = 1; - info->cur_record = *pos; - return info; -} - -static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) -{ - int idummy; - char *ndummy; - struct devinfo_state *info = f->private; - - switch (info->state) { - case CHR_HDR: - info->state = CHR_LIST; - (*pos)++; - /*fallthrough*/ - case CHR_LIST: - if (get_chrdev_info(info->chrdev,&idummy,&ndummy)) { - /* - * The character dev list is complete - */ - info->state = BLK_HDR; - } else { - info->chrdev = get_next_chrdev(info->chrdev); - } - (*pos)++; - break; - case BLK_HDR: - info->state = BLK_LIST; - (*pos)++; - break; - case BLK_LIST: - if (get_blkdev_info(info->blkdev,&idummy,&ndummy)) { - /* - * The block dev list is complete - */ - info->state = DEVINFO_DONE; - } else { - info->blkdev = get_next_blkdev(info->blkdev); - } - (*pos)++; - break; - case DEVINFO_DONE: - (*pos)++; - info->cur_record = *pos; - info = NULL; - break; - default: - break; - } - if (info) - info->cur_record = *pos; - return info; -} - -static void devinfo_stop(struct seq_file *f, void *v) -{ - struct devinfo_state *info = f->private; - - if (info) { - release_chrdev_list(info->chrdev); - release_blkdev_list(info->blkdev); - f->private = NULL; - kfree(info); - } -} - -static int devinfo_show(struct seq_file *f, void *arg) -{ - int major; - char *name; - struct devinfo_state *info = f->private; - - switch(info->state) { - case CHR_HDR: - seq_printf(f,"Character devices:\n"); - /* fallthrough */ - case CHR_LIST: - if (!get_chrdev_info(info->chrdev,&major,&name)) - seq_printf(f,"%3d %s\n",major,name); - break; - case BLK_HDR: - seq_printf(f,"\nBlock devices:\n"); - /* fallthrough */ - case BLK_LIST: - if (!get_blkdev_info(info->blkdev,&major,&name)) - seq_printf(f,"%3d %s\n",major,name); - break; - default: - break; - } - - return 0; -} - -static struct seq_operations devinfo_op = { - .start = devinfo_start, - .next = devinfo_next, - .stop = devinfo_stop, - .show = devinfo_show, -}; - -static int devinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &devinfo_op); -} - -static struct file_operations proc_devinfo_operations = { - .open = devinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static struct file_operations proc_cpuinfo_operations = { - .open = cpuinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -extern struct seq_operations vmstat_op; -static int vmstat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &vmstat_op); -} -static struct file_operations proc_vmstat_file_operations = { - .open = vmstat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#ifdef CONFIG_PROC_HARDWARE -static int hardware_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_hardware_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} -#endif - -#ifdef CONFIG_STRAM_PROC -static int stram_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_stram_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} -#endif - -extern struct seq_operations partitions_op; -static int partitions_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &partitions_op); -} -static struct file_operations proc_partitions_operations = { - .open = partitions_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -extern struct seq_operations diskstats_op; -static int diskstats_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &diskstats_op); -} -static struct file_operations proc_diskstats_operations = { - .open = diskstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#ifdef CONFIG_MODULES -extern struct seq_operations modules_op; -static int modules_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &modules_op); -} -static struct file_operations proc_modules_operations = { - .open = modules_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - -#ifdef CONFIG_SLAB -extern struct seq_operations slabinfo_op; -extern ssize_t slabinfo_write(struct file *, const char __user *, size_t, loff_t *); -static int slabinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &slabinfo_op); -} -static struct file_operations proc_slabinfo_operations = { - .open = slabinfo_open, - .read = seq_read, - .write = slabinfo_write, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - -static int show_stat(struct seq_file *p, void *v) -{ - int i; - unsigned long jif; - cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; - u64 sum = 0; - - user = nice = system = idle = iowait = - irq = softirq = steal = cputime64_zero; - jif = - wall_to_monotonic.tv_sec; - if (wall_to_monotonic.tv_nsec) - --jif; - - for_each_cpu(i) { - int j; - - user = cputime64_add(user, kstat_cpu(i).cpustat.user); - nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); - system = cputime64_add(system, kstat_cpu(i).cpustat.system); - idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle); - iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait); - irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); - softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); - steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); - for (j = 0 ; j < NR_IRQS ; j++) - sum += kstat_cpu(i).irqs[j]; - } - - seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu\n", - (unsigned long long)cputime64_to_clock_t(user), - (unsigned long long)cputime64_to_clock_t(nice), - (unsigned long long)cputime64_to_clock_t(system), - (unsigned long long)cputime64_to_clock_t(idle), - (unsigned long long)cputime64_to_clock_t(iowait), - (unsigned long long)cputime64_to_clock_t(irq), - (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal)); - for_each_online_cpu(i) { - - /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kstat_cpu(i).cpustat.user; - nice = kstat_cpu(i).cpustat.nice; - system = kstat_cpu(i).cpustat.system; - idle = kstat_cpu(i).cpustat.idle; - iowait = kstat_cpu(i).cpustat.iowait; - irq = kstat_cpu(i).cpustat.irq; - softirq = kstat_cpu(i).cpustat.softirq; - steal = kstat_cpu(i).cpustat.steal; - seq_printf(p, "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu\n", - i, - (unsigned long long)cputime64_to_clock_t(user), - (unsigned long long)cputime64_to_clock_t(nice), - (unsigned long long)cputime64_to_clock_t(system), - (unsigned long long)cputime64_to_clock_t(idle), - (unsigned long long)cputime64_to_clock_t(iowait), - (unsigned long long)cputime64_to_clock_t(irq), - (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal)); - } - seq_printf(p, "intr %llu", (unsigned long long)sum); - -#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) - for (i = 0; i < NR_IRQS; i++) - seq_printf(p, " %u", kstat_irqs(i)); -#endif - - seq_printf(p, - "\nctxt %llu\n" - "btime %lu\n" - "processes %lu\n" - "procs_running %lu\n" - "procs_blocked %lu\n", - nr_context_switches(), - (unsigned long)jif, - total_forks, - nr_running(), - nr_iowait()); - - return 0; -} - -static int stat_open(struct inode *inode, struct file *file) -{ - unsigned size = 4096 * (1 + num_possible_cpus() / 32); - char *buf; - struct seq_file *m; - int res; - - /* don't ask for more than the kmalloc() max size, currently 128 KB */ - if (size > 128 * 1024) - size = 128 * 1024; - buf = kmalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - res = single_open(file, show_stat, NULL); - if (!res) { - m = file->private_data; - m->buf = buf; - m->size = size; - } else - kfree(buf); - return res; -} -static struct file_operations proc_stat_operations = { - .open = stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -/* - * /proc/interrupts - */ -static void *int_seq_start(struct seq_file *f, loff_t *pos) -{ - return (*pos <= NR_IRQS) ? pos : NULL; -} - -static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos) -{ - (*pos)++; - if (*pos > NR_IRQS) - return NULL; - return pos; -} - -static void int_seq_stop(struct seq_file *f, void *v) -{ - /* Nothing to do */ -} - - -extern int show_interrupts(struct seq_file *f, void *v); /* In arch code */ -static struct seq_operations int_seq_ops = { - .start = int_seq_start, - .next = int_seq_next, - .stop = int_seq_stop, - .show = show_interrupts -}; - -static int interrupts_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &int_seq_ops); -} - -static struct file_operations proc_interrupts_operations = { - .open = interrupts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int filesystems_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_filesystem_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int cmdline_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len; - - len = sprintf(page, "%s\n", saved_command_line); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int locks_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_locks_status(page, start, off, count); - - if (len < count) - *eof = 1; - return len; -} - -static int execdomains_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_exec_domain_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -#ifdef CONFIG_MAGIC_SYSRQ -/* - * writing 'C' to /proc/sysrq-trigger is like sysrq-C - */ -static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - if (count) { - char c; - - if (get_user(c, buf)) - return -EFAULT; - __handle_sysrq(c, NULL, NULL, 0); - } - return count; -} - -static struct file_operations proc_sysrq_trigger_operations = { - .write = write_sysrq_trigger, -}; -#endif - -struct proc_dir_entry *proc_root_kcore; - -void create_seq_entry(char *name, mode_t mode, struct file_operations *f) -{ - struct proc_dir_entry *entry; - entry = create_proc_entry(name, mode, NULL); - if (entry) - entry->proc_fops = f; -} - -void __init proc_misc_init(void) -{ - struct proc_dir_entry *entry; - static struct { - char *name; - int (*read_proc)(char*,char**,off_t,int,int*,void*); - } *p, simple_ones[] = { - {"loadavg", loadavg_read_proc}, - {"uptime", uptime_read_proc}, - {"meminfo", meminfo_read_proc}, - {"version", version_read_proc}, -#ifdef CONFIG_PROC_HARDWARE - {"hardware", hardware_read_proc}, -#endif -#ifdef CONFIG_STRAM_PROC - {"stram", stram_read_proc}, -#endif - {"filesystems", filesystems_read_proc}, - {"cmdline", cmdline_read_proc}, - {"locks", locks_read_proc}, - {"execdomains", execdomains_read_proc}, - {NULL,} - }; - for (p = simple_ones; p->name; p++) - create_proc_read_entry(p->name, 0, NULL, p->read_proc, NULL); - - proc_symlink("mounts", NULL, "self/mounts"); - - /* And now for trickier ones */ - entry = create_proc_entry("kmsg", S_IRUSR, &proc_root); - if (entry) - entry->proc_fops = &proc_kmsg_operations; - create_seq_entry("devices", 0, &proc_devinfo_operations); - create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations); - create_seq_entry("partitions", 0, &proc_partitions_operations); - create_seq_entry("stat", 0, &proc_stat_operations); - create_seq_entry("interrupts", 0, &proc_interrupts_operations); -#ifdef CONFIG_SLAB - create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations); -#endif - create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations); - create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations); - create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations); - create_seq_entry("diskstats", 0, &proc_diskstats_operations); -#ifdef CONFIG_MODULES - create_seq_entry("modules", 0, &proc_modules_operations); -#endif -#ifdef CONFIG_SCHEDSTATS - create_seq_entry("schedstat", 0, &proc_schedstat_operations); -#endif -#ifdef CONFIG_PROC_KCORE - proc_root_kcore = create_proc_entry("kcore", S_IRUSR, NULL); - if (proc_root_kcore) { - proc_root_kcore->proc_fops = &proc_kcore_operations; - proc_root_kcore->size = - (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE; - } -#endif -#ifdef CONFIG_PROC_VMCORE - proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL); - if (proc_vmcore) - proc_vmcore->proc_fops = &proc_vmcore_operations; -#endif -#ifdef CONFIG_MAGIC_SYSRQ - entry = create_proc_entry("sysrq-trigger", S_IWUSR, NULL); - if (entry) - entry->proc_fops = &proc_sysrq_trigger_operations; -#endif -} diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c new file mode 100644 index 00000000000..4677bb7dc7c --- /dev/null +++ b/fs/proc/proc_net.c @@ -0,0 +1,230 @@ +/* + * linux/fs/proc/net.c + * + * Copyright (C) 2007 + * + * Author: Eric Biederman <ebiederm@xmission.com> + * + * proc net directory handling functions + */ + +#include <asm/uaccess.h> + +#include <linux/errno.h> +#include <linux/time.h> +#include <linux/proc_fs.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/bitops.h> +#include <linux/mount.h> +#include <linux/nsproxy.h> +#include <net/net_namespace.h> +#include <linux/seq_file.h> + +#include "internal.h" + +static inline struct net *PDE_NET(struct proc_dir_entry *pde) +{ + return pde->parent->data; +} + +static struct net *get_proc_net(const struct inode *inode) +{ + return maybe_get_net(PDE_NET(PDE(inode))); +} + +int seq_open_net(struct inode *ino, struct file *f, + const struct seq_operations *ops, int size) +{ + struct net *net; + struct seq_net_private *p; + + BUG_ON(size < sizeof(*p)); + + net = get_proc_net(ino); + if (net == NULL) + return -ENXIO; + + p = __seq_open_private(f, ops, size); + if (p == NULL) { + put_net(net); + return -ENOMEM; + } +#ifdef CONFIG_NET_NS + p->net = net; +#endif + return 0; +} +EXPORT_SYMBOL_GPL(seq_open_net); + +int single_open_net(struct inode *inode, struct file *file, + int (*show)(struct seq_file *, void *)) +{ + int err; + struct net *net; + + err = -ENXIO; + net = get_proc_net(inode); + if (net == NULL) + goto err_net; + + err = single_open(file, show, net); + if (err < 0) + goto err_open; + + return 0; + +err_open: + put_net(net); +err_net: + return err; +} +EXPORT_SYMBOL_GPL(single_open_net); + +int seq_release_net(struct inode *ino, struct file *f) +{ + struct seq_file *seq; + + seq = f->private_data; + + put_net(seq_file_net(seq)); + seq_release_private(ino, f); + return 0; +} +EXPORT_SYMBOL_GPL(seq_release_net); + +int single_release_net(struct inode *ino, struct file *f) +{ + struct seq_file *seq = f->private_data; + put_net(seq->private); + return single_release(ino, f); +} +EXPORT_SYMBOL_GPL(single_release_net); + +static struct net *get_proc_task_net(struct inode *dir) +{ + struct task_struct *task; + struct nsproxy *ns; + struct net *net = NULL; + + rcu_read_lock(); + task = pid_task(proc_pid(dir), PIDTYPE_PID); + if (task != NULL) { + ns = task_nsproxy(task); + if (ns != NULL) + net = get_net(ns->net_ns); + } + rcu_read_unlock(); + + return net; +} + +static struct dentry *proc_tgid_net_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + struct dentry *de; + struct net *net; + + de = ERR_PTR(-ENOENT); + net = get_proc_task_net(dir); + if (net != NULL) { + de = proc_lookup_de(net->proc_net, dir, dentry); + put_net(net); + } + return de; +} + +static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct net *net; + + net = get_proc_task_net(inode); + + generic_fillattr(inode, stat); + + if (net != NULL) { + stat->nlink = net->proc_net->nlink; + put_net(net); + } + + return 0; +} + +const struct inode_operations proc_net_inode_operations = { + .lookup = proc_tgid_net_lookup, + .getattr = proc_tgid_net_getattr, +}; + +static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) +{ + int ret; + struct net *net; + + ret = -EINVAL; + net = get_proc_task_net(file_inode(file)); + if (net != NULL) { + ret = proc_readdir_de(net->proc_net, file, ctx); + put_net(net); + } + return ret; +} + +const struct file_operations proc_net_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = proc_tgid_net_readdir, +}; + +static __net_init int proc_net_ns_init(struct net *net) +{ + struct proc_dir_entry *netd, *net_statd; + int err; + + err = -ENOMEM; + netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL); + if (!netd) + goto out; + + netd->data = net; + netd->nlink = 2; + netd->namelen = 3; + netd->parent = &proc_root; + memcpy(netd->name, "net", 4); + + err = -EEXIST; + net_statd = proc_net_mkdir(net, "stat", netd); + if (!net_statd) + goto free_net; + + net->proc_net = netd; + net->proc_net_stat = net_statd; + return 0; + +free_net: + kfree(netd); +out: + return err; +} + +static __net_exit void proc_net_ns_exit(struct net *net) +{ + remove_proc_entry("stat", net->proc_net); + kfree(net->proc_net); +} + +static struct pernet_operations __net_initdata proc_net_ns_ops = { + .init = proc_net_ns_init, + .exit = proc_net_ns_exit, +}; + +int __init proc_net_init(void) +{ + proc_symlink("net", NULL, "self/net"); + + return register_pernet_subsys(&proc_net_ns_ops); +} diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c new file mode 100644 index 00000000000..71290463a1d --- /dev/null +++ b/fs/proc/proc_sysctl.c @@ -0,0 +1,1582 @@ +/* + * /proc/sys support + */ +#include <linux/init.h> +#include <linux/sysctl.h> +#include <linux/poll.h> +#include <linux/proc_fs.h> +#include <linux/printk.h> +#include <linux/security.h> +#include <linux/sched.h> +#include <linux/namei.h> +#include <linux/mm.h> +#include <linux/module.h> +#include "internal.h" + +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; + +void proc_sys_poll_notify(struct ctl_table_poll *poll) +{ + if (!poll) + return; + + atomic_inc(&poll->event); + wake_up_interruptible(&poll->wait); +} + +static struct ctl_table root_table[] = { + { + .procname = "", + .mode = S_IFDIR|S_IRUGO|S_IXUGO, + }, + { } +}; +static struct ctl_table_root sysctl_table_root = { + .default_set.dir.header = { + {{.count = 1, + .nreg = 1, + .ctl_table = root_table }}, + .ctl_table_arg = root_table, + .root = &sysctl_table_root, + .set = &sysctl_table_root.default_set, + }, +}; + +static DEFINE_SPINLOCK(sysctl_lock); + +static void drop_sysctl_table(struct ctl_table_header *header); +static int sysctl_follow_link(struct ctl_table_header **phead, + struct ctl_table **pentry, struct nsproxy *namespaces); +static int insert_links(struct ctl_table_header *head); +static void put_links(struct ctl_table_header *header); + +static void sysctl_print_dir(struct ctl_dir *dir) +{ + if (dir->header.parent) + sysctl_print_dir(dir->header.parent); + pr_cont("%s/", dir->header.ctl_table[0].procname); +} + +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); + if (cmp == 0) + cmp = len1 - len2; + return cmp; +} + +/* Called under sysctl_lock */ +static struct ctl_table *find_entry(struct ctl_table_header **phead, + struct ctl_dir *dir, const char *name, int namelen) +{ + struct ctl_table_header *head; + struct ctl_table *entry; + struct rb_node *node = dir->root.rb_node; + + while (node) + { + struct ctl_node *ctl_node; + const char *procname; + int cmp; + + ctl_node = rb_entry(node, struct ctl_node, node); + head = ctl_node->header; + entry = &head->ctl_table[ctl_node - head->node]; + procname = entry->procname; + + cmp = namecmp(name, namelen, procname, strlen(procname)); + if (cmp < 0) + node = node->rb_left; + else if (cmp > 0) + node = node->rb_right; + else { + *phead = head; + return entry; + } + } + return NULL; +} + +static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) +{ + struct rb_node *node = &head->node[entry - head->ctl_table].node; + struct rb_node **p = &head->parent->root.rb_node; + struct rb_node *parent = NULL; + const char *name = entry->procname; + int namelen = strlen(name); + + while (*p) { + struct ctl_table_header *parent_head; + struct ctl_table *parent_entry; + struct ctl_node *parent_node; + const char *parent_name; + int cmp; + + parent = *p; + parent_node = rb_entry(parent, struct ctl_node, node); + parent_head = parent_node->header; + parent_entry = &parent_head->ctl_table[parent_node - parent_head->node]; + parent_name = parent_entry->procname; + + cmp = namecmp(name, namelen, parent_name, strlen(parent_name)); + if (cmp < 0) + p = &(*p)->rb_left; + else if (cmp > 0) + p = &(*p)->rb_right; + else { + pr_err("sysctl duplicate entry: "); + sysctl_print_dir(head->parent); + pr_cont("/%s\n", entry->procname); + return -EEXIST; + } + } + + rb_link_node(node, parent, p); + rb_insert_color(node, &head->parent->root); + return 0; +} + +static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry) +{ + struct rb_node *node = &head->node[entry - head->ctl_table].node; + + rb_erase(node, &head->parent->root); +} + +static void init_header(struct ctl_table_header *head, + struct ctl_table_root *root, struct ctl_table_set *set, + struct ctl_node *node, struct ctl_table *table) +{ + head->ctl_table = table; + head->ctl_table_arg = table; + head->used = 0; + head->count = 1; + head->nreg = 1; + head->unregistering = NULL; + head->root = root; + head->set = set; + head->parent = NULL; + head->node = node; + if (node) { + struct ctl_table *entry; + for (entry = table; entry->procname; entry++, node++) + node->header = head; + } +} + +static void erase_header(struct ctl_table_header *head) +{ + struct ctl_table *entry; + for (entry = head->ctl_table; entry->procname; entry++) + erase_entry(head, entry); +} + +static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) +{ + struct ctl_table *entry; + int err; + + dir->header.nreg++; + header->parent = dir; + err = insert_links(header); + if (err) + goto fail_links; + for (entry = header->ctl_table; entry->procname; entry++) { + err = insert_entry(header, entry); + if (err) + goto fail; + } + return 0; +fail: + erase_header(header); + put_links(header); +fail_links: + header->parent = NULL; + drop_sysctl_table(&dir->header); + return err; +} + +/* called under sysctl_lock */ +static int use_table(struct ctl_table_header *p) +{ + if (unlikely(p->unregistering)) + return 0; + p->used++; + return 1; +} + +/* called under sysctl_lock */ +static void unuse_table(struct ctl_table_header *p) +{ + if (!--p->used) + if (unlikely(p->unregistering)) + complete(p->unregistering); +} + +/* called under sysctl_lock, will reacquire if has to wait */ +static void start_unregistering(struct ctl_table_header *p) +{ + /* + * if p->used is 0, nobody will ever touch that entry again; + * we'll eliminate all paths to it before dropping sysctl_lock + */ + if (unlikely(p->used)) { + struct completion wait; + init_completion(&wait); + p->unregistering = &wait; + spin_unlock(&sysctl_lock); + wait_for_completion(&wait); + spin_lock(&sysctl_lock); + } else { + /* anything non-NULL; we'll never dereference it */ + p->unregistering = ERR_PTR(-EINVAL); + } + /* + * do not remove from the list until nobody holds it; walking the + * list in do_sysctl() relies on that. + */ + erase_header(p); +} + +static void sysctl_head_get(struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + head->count++; + spin_unlock(&sysctl_lock); +} + +void sysctl_head_put(struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + if (!--head->count) + kfree_rcu(head, rcu); + spin_unlock(&sysctl_lock); +} + +static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) +{ + BUG_ON(!head); + spin_lock(&sysctl_lock); + if (!use_table(head)) + head = ERR_PTR(-ENOENT); + spin_unlock(&sysctl_lock); + return head; +} + +static void sysctl_head_finish(struct ctl_table_header *head) +{ + if (!head) + return; + spin_lock(&sysctl_lock); + unuse_table(head); + spin_unlock(&sysctl_lock); +} + +static struct ctl_table_set * +lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces) +{ + struct ctl_table_set *set = &root->default_set; + if (root->lookup) + set = root->lookup(root, namespaces); + return set; +} + +static struct ctl_table *lookup_entry(struct ctl_table_header **phead, + struct ctl_dir *dir, + const char *name, int namelen) +{ + struct ctl_table_header *head; + struct ctl_table *entry; + + spin_lock(&sysctl_lock); + entry = find_entry(&head, dir, name, namelen); + if (entry && use_table(head)) + *phead = head; + else + entry = NULL; + spin_unlock(&sysctl_lock); + return entry; +} + +static struct ctl_node *first_usable_entry(struct rb_node *node) +{ + struct ctl_node *ctl_node; + + for (;node; node = rb_next(node)) { + ctl_node = rb_entry(node, struct ctl_node, node); + if (use_table(ctl_node->header)) + return ctl_node; + } + return NULL; +} + +static void first_entry(struct ctl_dir *dir, + struct ctl_table_header **phead, struct ctl_table **pentry) +{ + struct ctl_table_header *head = NULL; + struct ctl_table *entry = NULL; + struct ctl_node *ctl_node; + + spin_lock(&sysctl_lock); + ctl_node = first_usable_entry(rb_first(&dir->root)); + spin_unlock(&sysctl_lock); + if (ctl_node) { + head = ctl_node->header; + entry = &head->ctl_table[ctl_node - head->node]; + } + *phead = head; + *pentry = entry; +} + +static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry) +{ + struct ctl_table_header *head = *phead; + struct ctl_table *entry = *pentry; + struct ctl_node *ctl_node = &head->node[entry - head->ctl_table]; + + spin_lock(&sysctl_lock); + unuse_table(head); + + ctl_node = first_usable_entry(rb_next(&ctl_node->node)); + spin_unlock(&sysctl_lock); + head = NULL; + if (ctl_node) { + head = ctl_node->header; + entry = &head->ctl_table[ctl_node - head->node]; + } + *phead = head; + *pentry = entry; +} + +void register_sysctl_root(struct ctl_table_root *root) +{ +} + +/* + * sysctl_perm does NOT grant the superuser all rights automatically, because + * some sysctl variables are readonly even to root. + */ + +static int test_perm(int mode, int op) +{ + if (uid_eq(current_euid(), GLOBAL_ROOT_UID)) + mode >>= 6; + else if (in_egroup_p(GLOBAL_ROOT_GID)) + mode >>= 3; + if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) + return 0; + return -EACCES; +} + +static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op) +{ + struct ctl_table_root *root = head->root; + int mode; + + if (root->permissions) + mode = root->permissions(head, table); + else + mode = table->mode; + + return test_perm(mode, op); +} + +static struct inode *proc_sys_make_inode(struct super_block *sb, + struct ctl_table_header *head, struct ctl_table *table) +{ + struct inode *inode; + struct proc_inode *ei; + + inode = new_inode(sb); + if (!inode) + goto out; + + inode->i_ino = get_next_ino(); + + sysctl_head_get(head); + ei = PROC_I(inode); + ei->sysctl = head; + ei->sysctl_entry = table; + + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_mode = table->mode; + if (!S_ISDIR(table->mode)) { + inode->i_mode |= S_IFREG; + inode->i_op = &proc_sys_inode_operations; + inode->i_fop = &proc_sys_file_operations; + } else { + inode->i_mode |= S_IFDIR; + inode->i_op = &proc_sys_dir_operations; + inode->i_fop = &proc_sys_dir_file_operations; + } +out: + return inode; +} + +static struct ctl_table_header *grab_header(struct inode *inode) +{ + struct ctl_table_header *head = PROC_I(inode)->sysctl; + if (!head) + head = &sysctl_table_root.default_set.dir.header; + return sysctl_head_grab(head); +} + +static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct ctl_table_header *head = grab_header(dir); + struct ctl_table_header *h = NULL; + struct qstr *name = &dentry->d_name; + struct ctl_table *p; + struct inode *inode; + struct dentry *err = ERR_PTR(-ENOENT); + struct ctl_dir *ctl_dir; + int ret; + + if (IS_ERR(head)) + return ERR_CAST(head); + + ctl_dir = container_of(head, struct ctl_dir, header); + + p = lookup_entry(&h, ctl_dir, name->name, name->len); + if (!p) + goto out; + + if (S_ISLNK(p->mode)) { + ret = sysctl_follow_link(&h, &p, current->nsproxy); + err = ERR_PTR(ret); + if (ret) + goto out; + } + + err = ERR_PTR(-ENOMEM); + inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p); + if (!inode) + goto out; + + err = NULL; + d_set_d_op(dentry, &proc_sys_dentry_operations); + d_add(dentry, inode); + +out: + if (h) + sysctl_head_finish(h); + sysctl_head_finish(head); + return err; +} + +static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, + size_t count, loff_t *ppos, int write) +{ + struct inode *inode = file_inode(filp); + struct ctl_table_header *head = grab_header(inode); + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + ssize_t error; + size_t res; + + if (IS_ERR(head)) + return PTR_ERR(head); + + /* + * At this point we know that the sysctl was not unregistered + * and won't be until we finish. + */ + error = -EPERM; + if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ)) + goto out; + + /* if that can happen at all, it should be -EINVAL, not -EISDIR */ + error = -EINVAL; + if (!table->proc_handler) + goto out; + + /* careful: calling conventions are nasty here */ + res = count; + error = table->proc_handler(table, write, buf, &res, ppos); + if (!error) + error = res; +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) +{ + return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0); +} + +static ssize_t proc_sys_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1); +} + +static int proc_sys_open(struct inode *inode, struct file *filp) +{ + struct ctl_table_header *head = grab_header(inode); + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + + /* sysctl was unregistered */ + if (IS_ERR(head)) + return PTR_ERR(head); + + if (table->poll) + filp->private_data = proc_sys_poll_event(table->poll); + + sysctl_head_finish(head); + + return 0; +} + +static unsigned int proc_sys_poll(struct file *filp, poll_table *wait) +{ + struct inode *inode = file_inode(filp); + struct ctl_table_header *head = grab_header(inode); + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + unsigned int ret = DEFAULT_POLLMASK; + unsigned long event; + + /* sysctl was unregistered */ + if (IS_ERR(head)) + return POLLERR | POLLHUP; + + if (!table->proc_handler) + goto out; + + if (!table->poll) + goto out; + + event = (unsigned long)filp->private_data; + poll_wait(filp, &table->poll->wait, wait); + + if (event != atomic_read(&table->poll->event)) { + filp->private_data = proc_sys_poll_event(table->poll); + ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI; + } + +out: + sysctl_head_finish(head); + + return ret; +} + +static bool proc_sys_fill_cache(struct file *file, + struct dir_context *ctx, + struct ctl_table_header *head, + struct ctl_table *table) +{ + struct dentry *child, *dir = file->f_path.dentry; + struct inode *inode; + struct qstr qname; + ino_t ino = 0; + unsigned type = DT_UNKNOWN; + + qname.name = table->procname; + qname.len = strlen(table->procname); + qname.hash = full_name_hash(qname.name, qname.len); + + child = d_lookup(dir, &qname); + if (!child) { + child = d_alloc(dir, &qname); + if (child) { + inode = proc_sys_make_inode(dir->d_sb, head, table); + if (!inode) { + dput(child); + return false; + } else { + d_set_d_op(child, &proc_sys_dentry_operations); + d_add(child, inode); + } + } else { + return false; + } + } + inode = child->d_inode; + ino = inode->i_ino; + type = inode->i_mode >> 12; + dput(child); + return dir_emit(ctx, qname.name, qname.len, ino, type); +} + +static bool proc_sys_link_fill_cache(struct file *file, + struct dir_context *ctx, + struct ctl_table_header *head, + struct ctl_table *table) +{ + bool ret = true; + head = sysctl_head_grab(head); + + if (S_ISLNK(table->mode)) { + /* It is not an error if we can not follow the link ignore it */ + int err = sysctl_follow_link(&head, &table, current->nsproxy); + if (err) + goto out; + } + + ret = proc_sys_fill_cache(file, ctx, head, table); +out: + sysctl_head_finish(head); + return ret; +} + +static int scan(struct ctl_table_header *head, ctl_table *table, + unsigned long *pos, struct file *file, + struct dir_context *ctx) +{ + bool res; + + if ((*pos)++ < ctx->pos) + return true; + + if (unlikely(S_ISLNK(table->mode))) + res = proc_sys_link_fill_cache(file, ctx, head, table); + else + res = proc_sys_fill_cache(file, ctx, head, table); + + if (res) + ctx->pos = *pos; + + return res; +} + +static int proc_sys_readdir(struct file *file, struct dir_context *ctx) +{ + struct ctl_table_header *head = grab_header(file_inode(file)); + struct ctl_table_header *h = NULL; + struct ctl_table *entry; + struct ctl_dir *ctl_dir; + unsigned long pos; + + if (IS_ERR(head)) + return PTR_ERR(head); + + ctl_dir = container_of(head, struct ctl_dir, header); + + if (!dir_emit_dots(file, ctx)) + return 0; + + pos = 2; + + for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) { + if (!scan(h, entry, &pos, file, ctx)) { + sysctl_head_finish(h); + break; + } + } + sysctl_head_finish(head); + return 0; +} + +static int proc_sys_permission(struct inode *inode, int mask) +{ + /* + * sysctl entries that are not writeable, + * are _NOT_ writeable, capabilities or not. + */ + struct ctl_table_header *head; + struct ctl_table *table; + int error; + + /* Executable files are not allowed under /proc/sys/ */ + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) + return -EACCES; + + head = grab_header(inode); + if (IS_ERR(head)) + return PTR_ERR(head); + + table = PROC_I(inode)->sysctl_entry; + if (!table) /* global root - r-xr-xr-x */ + error = mask & MAY_WRITE ? -EACCES : 0; + else /* Use the permissions on the sysctl table entry */ + error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK); + + sysctl_head_finish(head); + return error; +} + +static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + int error; + + if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) + return -EPERM; + + error = inode_change_ok(inode, attr); + if (error) + return error; + + setattr_copy(inode, attr); + mark_inode_dirty(inode); + return 0; +} + +static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct ctl_table_header *head = grab_header(inode); + struct ctl_table *table = PROC_I(inode)->sysctl_entry; + + if (IS_ERR(head)) + return PTR_ERR(head); + + generic_fillattr(inode, stat); + if (table) + stat->mode = (stat->mode & S_IFMT) | table->mode; + + sysctl_head_finish(head); + return 0; +} + +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, + .llseek = default_llseek, +}; + +static const struct file_operations proc_sys_dir_file_operations = { + .read = generic_read_dir, + .iterate = proc_sys_readdir, + .llseek = generic_file_llseek, +}; + +static const struct inode_operations proc_sys_inode_operations = { + .permission = proc_sys_permission, + .setattr = proc_sys_setattr, + .getattr = proc_sys_getattr, +}; + +static const struct inode_operations proc_sys_dir_operations = { + .lookup = proc_sys_lookup, + .permission = proc_sys_permission, + .setattr = proc_sys_setattr, + .getattr = proc_sys_getattr, +}; + +static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + return !PROC_I(dentry->d_inode)->sysctl->unregistering; +} + +static int proc_sys_delete(const struct dentry *dentry) +{ + return !!PROC_I(dentry->d_inode)->sysctl->unregistering; +} + +static int sysctl_is_seen(struct ctl_table_header *p) +{ + struct ctl_table_set *set = p->set; + int res; + spin_lock(&sysctl_lock); + if (p->unregistering) + res = 0; + else if (!set->is_seen) + res = 1; + else + res = set->is_seen(set); + spin_unlock(&sysctl_lock); + return res; +} + +static int proc_sys_compare(const struct dentry *parent, const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + struct ctl_table_header *head; + struct inode *inode; + + /* Although proc doesn't have negative dentries, rcu-walk means + * that inode here can be NULL */ + /* AV: can it, indeed? */ + inode = ACCESS_ONCE(dentry->d_inode); + if (!inode) + return 1; + if (name->len != len) + return 1; + if (memcmp(name->name, str, len)) + return 1; + head = rcu_dereference(PROC_I(inode)->sysctl); + return !head || !sysctl_is_seen(head); +} + +static const struct dentry_operations proc_sys_dentry_operations = { + .d_revalidate = proc_sys_revalidate, + .d_delete = proc_sys_delete, + .d_compare = proc_sys_compare, +}; + +static struct ctl_dir *find_subdir(struct ctl_dir *dir, + const char *name, int namelen) +{ + struct ctl_table_header *head; + struct ctl_table *entry; + + entry = find_entry(&head, dir, name, namelen); + if (!entry) + return ERR_PTR(-ENOENT); + if (!S_ISDIR(entry->mode)) + return ERR_PTR(-ENOTDIR); + return container_of(head, struct ctl_dir, header); +} + +static struct ctl_dir *new_dir(struct ctl_table_set *set, + const char *name, int namelen) +{ + struct ctl_table *table; + struct ctl_dir *new; + struct ctl_node *node; + char *new_name; + + new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) + + sizeof(struct ctl_table)*2 + namelen + 1, + GFP_KERNEL); + if (!new) + return NULL; + + node = (struct ctl_node *)(new + 1); + 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); + + return new; +} + +/** + * get_subdir - find or create a subdir with the specified name. + * @dir: Directory to create the subdirectory in + * @name: The name of the subdirectory to find or create + * @namelen: The length of name + * + * Takes a directory with an elevated reference count so we know that + * if we drop the lock the directory will not go away. Upon success + * the reference is moved from @dir to the returned subdirectory. + * Upon error an error code is returned and the reference on @dir is + * simply dropped. + */ +static struct ctl_dir *get_subdir(struct ctl_dir *dir, + const char *name, int namelen) +{ + struct ctl_table_set *set = dir->header.set; + struct ctl_dir *subdir, *new = NULL; + int err; + + spin_lock(&sysctl_lock); + subdir = find_subdir(dir, name, namelen); + if (!IS_ERR(subdir)) + goto found; + if (PTR_ERR(subdir) != -ENOENT) + goto failed; + + spin_unlock(&sysctl_lock); + new = new_dir(set, name, namelen); + spin_lock(&sysctl_lock); + subdir = ERR_PTR(-ENOMEM); + if (!new) + goto failed; + + /* Was the subdir added while we dropped the lock? */ + subdir = find_subdir(dir, name, namelen); + if (!IS_ERR(subdir)) + goto found; + if (PTR_ERR(subdir) != -ENOENT) + goto failed; + + /* Nope. Use the our freshly made directory entry. */ + err = insert_header(dir, &new->header); + subdir = ERR_PTR(err); + if (err) + goto failed; + subdir = new; +found: + subdir->header.nreg++; +failed: + if (unlikely(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)); + } + drop_sysctl_table(&dir->header); + if (new) + drop_sysctl_table(&new->header); + spin_unlock(&sysctl_lock); + return subdir; +} + +static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir) +{ + struct ctl_dir *parent; + const char *procname; + if (!dir->header.parent) + return &set->dir; + parent = xlate_dir(set, dir->header.parent); + if (IS_ERR(parent)) + return parent; + procname = dir->header.ctl_table[0].procname; + return find_subdir(parent, procname, strlen(procname)); +} + +static int sysctl_follow_link(struct ctl_table_header **phead, + struct ctl_table **pentry, struct nsproxy *namespaces) +{ + struct ctl_table_header *head; + struct ctl_table_root *root; + struct ctl_table_set *set; + struct ctl_table *entry; + struct ctl_dir *dir; + int ret; + + ret = 0; + spin_lock(&sysctl_lock); + root = (*pentry)->data; + set = lookup_header_set(root, namespaces); + dir = xlate_dir(set, (*phead)->parent); + if (IS_ERR(dir)) + ret = PTR_ERR(dir); + else { + const char *procname = (*pentry)->procname; + head = NULL; + entry = find_entry(&head, dir, procname, strlen(procname)); + ret = -ENOENT; + if (entry && use_table(head)) { + unuse_table(*phead); + *phead = head; + *pentry = entry; + ret = 0; + } + } + + spin_unlock(&sysctl_lock); + return ret; +} + +static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + pr_err("sysctl table check failed: %s/%s %pV\n", + path, table->procname, &vaf); + + va_end(args); + return -EINVAL; +} + +static int sysctl_check_table(const char *path, struct ctl_table *table) +{ + 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_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"); + } + if (!table->proc_handler) + err = sysctl_err(path, table, "No proc_handler"); + + if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) + err = sysctl_err(path, table, "bogus .mode 0%o", + table->mode); + } + return err; +} + +static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table, + struct ctl_table_root *link_root) +{ + struct ctl_table *link_table, *entry, *link; + struct ctl_table_header *links; + struct ctl_node *node; + char *link_name; + int nr_entries, name_bytes; + + name_bytes = 0; + nr_entries = 0; + for (entry = table; entry->procname; entry++) { + nr_entries++; + name_bytes += strlen(entry->procname) + 1; + } + + links = kzalloc(sizeof(struct ctl_table_header) + + sizeof(struct ctl_node)*nr_entries + + sizeof(struct ctl_table)*(nr_entries + 1) + + name_bytes, + GFP_KERNEL); + + if (!links) + return NULL; + + node = (struct ctl_node *)(links + 1); + link_table = (struct ctl_table *)(node + nr_entries); + link_name = (char *)&link_table[nr_entries + 1]; + + for (link = link_table, entry = table; entry->procname; link++, entry++) { + 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; + } + init_header(links, dir->header.root, dir->header.set, node, link_table); + links->nreg = nr_entries; + + return links; +} + +static bool get_links(struct ctl_dir *dir, + struct ctl_table *table, struct ctl_table_root *link_root) +{ + struct ctl_table_header *head; + struct ctl_table *entry, *link; + + /* Are there links available for every entry in table? */ + for (entry = table; entry->procname; entry++) { + const char *procname = entry->procname; + link = find_entry(&head, dir, procname, strlen(procname)); + if (!link) + return false; + if (S_ISDIR(link->mode) && S_ISDIR(entry->mode)) + continue; + if (S_ISLNK(link->mode) && (link->data == link_root)) + continue; + return false; + } + + /* The checks passed. Increase the registration count on the links */ + for (entry = table; entry->procname; entry++) { + const char *procname = entry->procname; + link = find_entry(&head, dir, procname, strlen(procname)); + head->nreg++; + } + return true; +} + +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_table_header *links; + int err; + + if (head->set == root_set) + return 0; + + core_parent = xlate_dir(root_set, head->parent); + if (IS_ERR(core_parent)) + return 0; + + if (get_links(core_parent, head->ctl_table, head->root)) + return 0; + + core_parent->header.nreg++; + spin_unlock(&sysctl_lock); + + links = new_links(core_parent, head->ctl_table, head->root); + + spin_lock(&sysctl_lock); + err = -ENOMEM; + if (!links) + goto out; + + err = 0; + if (get_links(core_parent, head->ctl_table, head->root)) { + kfree(links); + goto out; + } + + err = insert_header(core_parent, links); + if (err) + kfree(links); +out: + drop_sysctl_table(&core_parent->header); + return err; +} + +/** + * __register_sysctl_table - register a leaf sysctl table + * @set: Sysctl tree to register on + * @path: The path to the directory the sysctl table is in. + * @table: the top-level table structure + * + * Register a sysctl table hierarchy. @table should be a filled in ctl_table + * array. A completely 0 filled entry terminates the table. + * + * The members of the &struct ctl_table structure are used as follows: + * + * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not + * enter a sysctl file + * + * data - a pointer to data for use by proc_handler + * + * maxlen - the maximum size in bytes of the data + * + * mode - the file permissions for the /proc/sys file + * + * child - must be %NULL. + * + * proc_handler - the text handler routine (described below) + * + * extra1, extra2 - extra pointers usable by the proc handler routines + * + * Leaf nodes in the sysctl tree will be represented by a single file + * under /proc; non-leaf nodes will be represented by directories. + * + * There must be a proc_handler routine for any terminal nodes. + * Several default handlers are available to cover common cases - + * + * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(), + * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(), + * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax() + * + * It is the handler's job to read the input buffer from user memory + * and process it. The handler should return 0 on success. + * + * This routine returns %NULL on a failure to register, and a pointer + * to the table header on success. + */ +struct ctl_table_header *__register_sysctl_table( + struct ctl_table_set *set, + const char *path, struct ctl_table *table) +{ + struct ctl_table_root *root = set->dir.header.root; + struct ctl_table_header *header; + const char *name, *nextname; + struct ctl_dir *dir; + struct ctl_table *entry; + struct ctl_node *node; + int nr_entries = 0; + + for (entry = table; entry->procname; entry++) + nr_entries++; + + header = kzalloc(sizeof(struct ctl_table_header) + + sizeof(struct ctl_node)*nr_entries, GFP_KERNEL); + if (!header) + return NULL; + + node = (struct ctl_node *)(header + 1); + init_header(header, root, set, node, table); + if (sysctl_check_table(path, table)) + goto fail; + + spin_lock(&sysctl_lock); + dir = &set->dir; + /* Reference moved down the diretory tree get_subdir */ + dir->header.nreg++; + spin_unlock(&sysctl_lock); + + /* Find the directory for the ctl_table */ + for (name = path; name; name = nextname) { + int namelen; + nextname = strchr(name, '/'); + if (nextname) { + namelen = nextname - name; + nextname++; + } else { + namelen = strlen(name); + } + if (namelen == 0) + continue; + + dir = get_subdir(dir, name, namelen); + if (IS_ERR(dir)) + goto fail; + } + + spin_lock(&sysctl_lock); + if (insert_header(dir, header)) + goto fail_put_dir_locked; + + drop_sysctl_table(&dir->header); + spin_unlock(&sysctl_lock); + + return header; + +fail_put_dir_locked: + drop_sysctl_table(&dir->header); + spin_unlock(&sysctl_lock); +fail: + kfree(header); + dump_stack(); + return NULL; +} + +/** + * register_sysctl - register a sysctl table + * @path: The path to the directory the sysctl table is in. + * @table: the table structure + * + * Register a sysctl table. @table should be a filled in ctl_table + * array. A completely 0 filled entry terminates the table. + * + * See __register_sysctl_table for more details. + */ +struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table) +{ + return __register_sysctl_table(&sysctl_table_root.default_set, + path, table); +} +EXPORT_SYMBOL(register_sysctl); + +static char *append_path(const char *path, char *pos, const char *name) +{ + int namelen; + namelen = strlen(name); + if (((pos - path) + namelen + 2) >= PATH_MAX) + return NULL; + memcpy(pos, name, namelen); + pos[namelen] = '/'; + pos[namelen + 1] = '\0'; + pos += namelen + 1; + return pos; +} + +static int count_subheaders(struct ctl_table *table) +{ + int has_files = 0; + int nr_subheaders = 0; + struct ctl_table *entry; + + /* special case: no directory and empty directory */ + if (!table || !table->procname) + return 1; + + for (entry = table; entry->procname; entry++) { + if (entry->child) + nr_subheaders += count_subheaders(entry->child); + else + has_files = 1; + } + return nr_subheaders + has_files; +} + +static int register_leaf_sysctl_tables(const char *path, char *pos, + struct ctl_table_header ***subheader, struct ctl_table_set *set, + struct ctl_table *table) +{ + struct ctl_table *ctl_table_arg = NULL; + struct ctl_table *entry, *files; + int nr_files = 0; + int nr_dirs = 0; + int err = -ENOMEM; + + for (entry = table; entry->procname; entry++) { + if (entry->child) + nr_dirs++; + else + nr_files++; + } + + files = table; + /* If there are mixed files and directories we need a new table */ + if (nr_dirs && nr_files) { + struct ctl_table *new; + files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1), + GFP_KERNEL); + if (!files) + goto out; + + ctl_table_arg = files; + for (new = files, entry = table; entry->procname; entry++) { + if (entry->child) + continue; + *new = *entry; + new++; + } + } + + /* Register everything except a directory full of subdirectories */ + if (nr_files || !nr_dirs) { + struct ctl_table_header *header; + header = __register_sysctl_table(set, path, files); + if (!header) { + kfree(ctl_table_arg); + goto out; + } + + /* Remember if we need to free the file table */ + header->ctl_table_arg = ctl_table_arg; + **subheader = header; + (*subheader)++; + } + + /* Recurse into the subdirectories. */ + for (entry = table; entry->procname; entry++) { + char *child_pos; + + if (!entry->child) + continue; + + err = -ENAMETOOLONG; + child_pos = append_path(path, pos, entry->procname); + if (!child_pos) + goto out; + + err = register_leaf_sysctl_tables(path, child_pos, subheader, + set, entry->child); + pos[0] = '\0'; + if (err) + goto out; + } + err = 0; +out: + /* On failure our caller will unregister all registered subheaders */ + return err; +} + +/** + * __register_sysctl_paths - register a sysctl table hierarchy + * @set: Sysctl tree to register on + * @path: The path to the directory the sysctl table is in. + * @table: the top-level table structure + * + * Register a sysctl table hierarchy. @table should be a filled in ctl_table + * array. A completely 0 filled entry terminates the table. + * + * See __register_sysctl_table for more details. + */ +struct ctl_table_header *__register_sysctl_paths( + struct ctl_table_set *set, + const struct ctl_path *path, struct ctl_table *table) +{ + struct ctl_table *ctl_table_arg = table; + int nr_subheaders = count_subheaders(table); + struct ctl_table_header *header = NULL, **subheaders, **subheader; + const struct ctl_path *component; + char *new_path, *pos; + + pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL); + if (!new_path) + return NULL; + + pos[0] = '\0'; + for (component = path; component->procname; component++) { + pos = append_path(new_path, pos, component->procname); + if (!pos) + goto out; + } + while (table->procname && table->child && !table[1].procname) { + pos = append_path(new_path, pos, table->procname); + if (!pos) + goto out; + table = table->child; + } + if (nr_subheaders == 1) { + header = __register_sysctl_table(set, new_path, table); + if (header) + header->ctl_table_arg = ctl_table_arg; + } else { + header = kzalloc(sizeof(*header) + + sizeof(*subheaders)*nr_subheaders, GFP_KERNEL); + if (!header) + goto out; + + subheaders = (struct ctl_table_header **) (header + 1); + subheader = subheaders; + header->ctl_table_arg = ctl_table_arg; + + if (register_leaf_sysctl_tables(new_path, pos, &subheader, + set, table)) + goto err_register_leaves; + } + +out: + kfree(new_path); + return header; + +err_register_leaves: + while (subheader > subheaders) { + struct ctl_table_header *subh = *(--subheader); + struct ctl_table *table = subh->ctl_table_arg; + unregister_sysctl_table(subh); + kfree(table); + } + kfree(header); + header = NULL; + goto out; +} + +/** + * register_sysctl_table_path - register a sysctl table hierarchy + * @path: The path to the directory the sysctl table is in. + * @table: the top-level table structure + * + * Register a sysctl table hierarchy. @table should be a filled in ctl_table + * array. A completely 0 filled entry terminates the table. + * + * See __register_sysctl_paths for more details. + */ +struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, + struct ctl_table *table) +{ + return __register_sysctl_paths(&sysctl_table_root.default_set, + path, table); +} +EXPORT_SYMBOL(register_sysctl_paths); + +/** + * register_sysctl_table - register a sysctl table hierarchy + * @table: the top-level table structure + * + * Register a sysctl table hierarchy. @table should be a filled in ctl_table + * array. A completely 0 filled entry terminates the table. + * + * See register_sysctl_paths for more details. + */ +struct ctl_table_header *register_sysctl_table(struct ctl_table *table) +{ + static const struct ctl_path null_path[] = { {} }; + + return register_sysctl_paths(null_path, table); +} +EXPORT_SYMBOL(register_sysctl_table); + +static void put_links(struct ctl_table_header *header) +{ + struct ctl_table_set *root_set = &sysctl_table_root.default_set; + struct ctl_table_root *root = header->root; + struct ctl_dir *parent = header->parent; + struct ctl_dir *core_parent; + struct ctl_table *entry; + + if (header->set == root_set) + return; + + core_parent = xlate_dir(root_set, parent); + if (IS_ERR(core_parent)) + return; + + for (entry = header->ctl_table; entry->procname; entry++) { + struct ctl_table_header *link_head; + struct ctl_table *link; + const char *name = entry->procname; + + link = find_entry(&link_head, core_parent, name, strlen(name)); + if (link && + ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) || + (S_ISLNK(link->mode) && (link->data == root)))) { + drop_sysctl_table(link_head); + } + else { + pr_err("sysctl link missing during unregister: "); + sysctl_print_dir(parent); + pr_cont("/%s\n", name); + } + } +} + +static void drop_sysctl_table(struct ctl_table_header *header) +{ + struct ctl_dir *parent = header->parent; + + if (--header->nreg) + return; + + put_links(header); + start_unregistering(header); + if (!--header->count) + kfree_rcu(header, rcu); + + if (parent) + drop_sysctl_table(&parent->header); +} + +/** + * unregister_sysctl_table - unregister a sysctl table hierarchy + * @header: the header returned from register_sysctl_table + * + * Unregisters the sysctl table and all children. proc entries may not + * actually be removed until they are no longer used by anyone. + */ +void unregister_sysctl_table(struct ctl_table_header * header) +{ + int nr_subheaders; + might_sleep(); + + if (header == NULL) + return; + + nr_subheaders = count_subheaders(header->ctl_table_arg); + if (unlikely(nr_subheaders > 1)) { + struct ctl_table_header **subheaders; + int i; + + subheaders = (struct ctl_table_header **)(header + 1); + for (i = nr_subheaders -1; i >= 0; i--) { + struct ctl_table_header *subh = subheaders[i]; + struct ctl_table *table = subh->ctl_table_arg; + unregister_sysctl_table(subh); + kfree(table); + } + kfree(header); + return; + } + + spin_lock(&sysctl_lock); + drop_sysctl_table(header); + spin_unlock(&sysctl_lock); +} +EXPORT_SYMBOL(unregister_sysctl_table); + +void setup_sysctl_set(struct ctl_table_set *set, + struct ctl_table_root *root, + int (*is_seen)(struct ctl_table_set *)) +{ + memset(set, 0, sizeof(*set)); + set->is_seen = is_seen; + init_header(&set->dir.header, root, set, NULL, root_table); +} + +void retire_sysctl_set(struct ctl_table_set *set) +{ + WARN_ON(!RB_EMPTY_ROOT(&set->dir.root)); +} + +int __init proc_sys_init(void) +{ + struct proc_dir_entry *proc_sys_root; + + proc_sys_root = proc_mkdir("sys", NULL); + proc_sys_root->proc_iops = &proc_sys_dir_operations; + proc_sys_root->proc_fops = &proc_sys_dir_file_operations; + proc_sys_root->nlink = 0; + + return sysctl_init(); +} diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index 15c4455b09e..cb761f01030 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -5,7 +5,7 @@ */ #include <asm/uaccess.h> - +#include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/time.h> @@ -15,9 +15,6 @@ #include <linux/seq_file.h> #include <linux/bitops.h> -static int tty_ldiscs_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data); - /* * The /proc/tty directory inodes... */ @@ -39,27 +36,27 @@ static void show_tty_range(struct seq_file *m, struct tty_driver *p, } switch (p->type) { case TTY_DRIVER_TYPE_SYSTEM: - seq_printf(m, "system"); + seq_puts(m, "system"); if (p->subtype == SYSTEM_TYPE_TTY) - seq_printf(m, ":/dev/tty"); + seq_puts(m, ":/dev/tty"); else if (p->subtype == SYSTEM_TYPE_SYSCONS) - seq_printf(m, ":console"); + seq_puts(m, ":console"); else if (p->subtype == SYSTEM_TYPE_CONSOLE) - seq_printf(m, ":vtmaster"); + seq_puts(m, ":vtmaster"); break; case TTY_DRIVER_TYPE_CONSOLE: - seq_printf(m, "console"); + seq_puts(m, "console"); break; case TTY_DRIVER_TYPE_SERIAL: - seq_printf(m, "serial"); + seq_puts(m, "serial"); break; case TTY_DRIVER_TYPE_PTY: if (p->subtype == PTY_TYPE_MASTER) - seq_printf(m, "pty:master"); + seq_puts(m, "pty:master"); else if (p->subtype == PTY_TYPE_SLAVE) - seq_printf(m, "pty:slave"); + seq_puts(m, "pty:slave"); else - seq_printf(m, "pty"); + seq_puts(m, "pty"); break; default: seq_printf(m, "type:%d.%d", p->type, p->subtype); @@ -69,7 +66,7 @@ static void show_tty_range(struct seq_file *m, struct tty_driver *p, static int show_tty_driver(struct seq_file *m, void *v) { - struct tty_driver *p = v; + struct tty_driver *p = list_entry(v, struct tty_driver, tty_drivers); dev_t from = MKDEV(p->major, p->minor_start); dev_t to = from + p->num; @@ -77,19 +74,19 @@ static int show_tty_driver(struct seq_file *m, void *v) /* pseudo-drivers first */ seq_printf(m, "%-20s /dev/%-8s ", "/dev/tty", "tty"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 0); - seq_printf(m, "system:/dev/tty\n"); + seq_puts(m, "system:/dev/tty\n"); seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1); - seq_printf(m, "system:console\n"); + seq_puts(m, "system:console\n"); #ifdef CONFIG_UNIX98_PTYS seq_printf(m, "%-20s /dev/%-8s ", "/dev/ptmx", "ptmx"); seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 2); - seq_printf(m, "system\n"); + seq_puts(m, "system\n"); #endif #ifdef CONFIG_VT seq_printf(m, "%-20s /dev/%-8s ", "/dev/vc/0", "vc/0"); seq_printf(m, "%3d %7d ", TTY_MAJOR, 0); - seq_printf(m, "system:vtmaster\n"); + seq_puts(m, "system:vtmaster\n"); #endif } @@ -106,27 +103,21 @@ static int show_tty_driver(struct seq_file *m, void *v) /* iterator */ static void *t_start(struct seq_file *m, loff_t *pos) { - struct list_head *p; - loff_t l = *pos; - list_for_each(p, &tty_drivers) - if (!l--) - return list_entry(p, struct tty_driver, tty_drivers); - return NULL; + mutex_lock(&tty_mutex); + return seq_list_start(&tty_drivers, *pos); } static void *t_next(struct seq_file *m, void *v, loff_t *pos) { - struct list_head *p = ((struct tty_driver *)v)->tty_drivers.next; - (*pos)++; - return p==&tty_drivers ? NULL : - list_entry(p, struct tty_driver, tty_drivers); + return seq_list_next(v, &tty_drivers, pos); } static void t_stop(struct seq_file *m, void *v) { + mutex_unlock(&tty_mutex); } -static struct seq_operations tty_drivers_op = { +static const struct seq_operations tty_drivers_op = { .start = t_start, .next = t_next, .stop = t_stop, @@ -138,7 +129,7 @@ static int tty_drivers_open(struct inode *inode, struct file *file) return seq_open(file, &tty_drivers_op); } -static struct file_operations proc_tty_drivers_operations = { +static const struct file_operations proc_tty_drivers_operations = { .open = tty_drivers_open, .read = seq_read, .llseek = seq_lseek, @@ -146,39 +137,6 @@ static struct file_operations proc_tty_drivers_operations = { }; /* - * This is the handler for /proc/tty/ldiscs - */ -static int tty_ldiscs_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int i; - int len = 0; - off_t begin = 0; - struct tty_ldisc *ld; - - for (i=0; i < NR_LDISCS; i++) { - ld = tty_ldisc_get(i); - if (ld == NULL) - continue; - len += sprintf(page+len, "%-10s %2d\n", - ld->name ? ld->name : "???", i); - tty_ldisc_put(i); - if (len+begin > off+count) - break; - if (len+begin < off) { - begin += len; - len = 0; - } - } - if (i >= NR_LDISCS) - *eof = 1; - if (off >= len+begin) - return 0; - *start = page + (off-begin); - return ((count < begin+len-off) ? count : begin+len-off); -} - -/* * This function is called by tty_register_driver() to handle * registering the driver's /proc handler into /proc/tty/driver/<foo> */ @@ -186,19 +144,12 @@ void proc_tty_register_driver(struct tty_driver *driver) { struct proc_dir_entry *ent; - if ((!driver->read_proc && !driver->write_proc) || - !driver->driver_name || - driver->proc_entry) - return; - - ent = create_proc_entry(driver->driver_name, 0, proc_tty_driver); - if (!ent) + if (!driver->driver_name || driver->proc_entry || + !driver->ops->proc_fops) return; - ent->read_proc = driver->read_proc; - ent->write_proc = driver->write_proc; - ent->owner = driver->owner; - ent->data = driver; + ent = proc_create_data(driver->driver_name, 0, proc_tty_driver, + driver->ops->proc_fops, driver); driver->proc_entry = ent; } @@ -223,7 +174,6 @@ void proc_tty_unregister_driver(struct tty_driver *driver) */ void __init proc_tty_init(void) { - struct proc_dir_entry *entry; if (!proc_mkdir("tty", NULL)) return; proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL); @@ -233,10 +183,7 @@ void __init proc_tty_init(void) * password lengths and inter-keystroke timings during password * entry. */ - proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR | S_IXUSR, NULL); - - create_proc_read_entry("tty/ldiscs", 0, NULL, tty_ldiscs_read_proc, NULL); - entry = create_proc_entry("tty/drivers", 0, NULL); - if (entry) - entry->proc_fops = &proc_tty_drivers_operations; + proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL); + proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops); + proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations); } diff --git a/fs/proc/root.c b/fs/proc/root.c index 68896283c8a..5dbadecb234 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -12,111 +12,209 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> -#include <linux/config.h> #include <linux/init.h> +#include <linux/sched.h> #include <linux/module.h> #include <linux/bitops.h> -#include <linux/smp_lock.h> +#include <linux/user_namespace.h> +#include <linux/mount.h> +#include <linux/pid_namespace.h> +#include <linux/parser.h> #include "internal.h" -struct proc_dir_entry *proc_net, *proc_net_stat, *proc_bus, *proc_root_fs, *proc_root_driver; +static int proc_test_super(struct super_block *sb, void *data) +{ + return sb->s_fs_info == data; +} -#ifdef CONFIG_SYSCTL -struct proc_dir_entry *proc_sys_root; -#endif +static int proc_set_super(struct super_block *sb, void *data) +{ + int err = set_anon_super(sb, NULL); + if (!err) { + struct pid_namespace *ns = (struct pid_namespace *)data; + sb->s_fs_info = get_pid_ns(ns); + } + return err; +} + +enum { + Opt_gid, Opt_hidepid, Opt_err, +}; + +static const match_table_t tokens = { + {Opt_hidepid, "hidepid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_err, NULL}, +}; + +static int proc_parse_options(char *options, struct pid_namespace *pid) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + + if (!options) + return 1; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + args[0].to = args[0].from = NULL; + token = match_token(p, tokens, args); + switch (token) { + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + pid->pid_gid = make_kgid(current_user_ns(), option); + break; + case Opt_hidepid: + if (match_int(&args[0], &option)) + return 0; + if (option < 0 || option > 2) { + pr_err("proc: hidepid value must be between 0 and 2.\n"); + return 0; + } + pid->hide_pid = option; + break; + default: + pr_err("proc: unrecognized mount option \"%s\" " + "or missing value\n", p); + return 0; + } + } -static struct super_block *proc_get_sb(struct file_system_type *fs_type, + return 1; +} + +int proc_remount(struct super_block *sb, int *flags, char *data) +{ + struct pid_namespace *pid = sb->s_fs_info; + + sync_filesystem(sb); + return !proc_parse_options(data, pid); +} + +static struct dentry *proc_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, proc_fill_super); + int err; + struct super_block *sb; + struct pid_namespace *ns; + char *options; + + if (flags & MS_KERNMOUNT) { + ns = (struct pid_namespace *)data; + options = NULL; + } else { + ns = task_active_pid_ns(current); + options = data; + + if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) + return ERR_PTR(-EPERM); + + /* Does the mounter have privilege over the pid namespace? */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + } + + sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); + if (IS_ERR(sb)) + return ERR_CAST(sb); + + if (!proc_parse_options(options, ns)) { + deactivate_locked_super(sb); + return ERR_PTR(-EINVAL); + } + + if (!sb->s_root) { + err = proc_fill_super(sb); + if (err) { + deactivate_locked_super(sb); + return ERR_PTR(err); + } + + sb->s_flags |= MS_ACTIVE; + } + + return dget(sb->s_root); +} + +static void proc_kill_sb(struct super_block *sb) +{ + struct pid_namespace *ns; + + ns = (struct pid_namespace *)sb->s_fs_info; + if (ns->proc_self) + dput(ns->proc_self); + kill_anon_super(sb); + put_pid_ns(ns); } static struct file_system_type proc_fs_type = { .name = "proc", - .get_sb = proc_get_sb, - .kill_sb = kill_anon_super, + .mount = proc_mount, + .kill_sb = proc_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; void __init proc_root_init(void) { - int err = proc_init_inodecache(); - if (err) - return; + int err; + + proc_init_inodecache(); err = register_filesystem(&proc_fs_type); if (err) return; - proc_mnt = kern_mount(&proc_fs_type); - err = PTR_ERR(proc_mnt); - if (IS_ERR(proc_mnt)) { - unregister_filesystem(&proc_fs_type); - return; - } - proc_misc_init(); - proc_net = proc_mkdir("net", NULL); - proc_net_stat = proc_mkdir("net/stat", NULL); + + proc_self_init(); + proc_symlink("mounts", NULL, "self/mounts"); + + proc_net_init(); #ifdef CONFIG_SYSVIPC proc_mkdir("sysvipc", NULL); #endif -#ifdef CONFIG_SYSCTL - proc_sys_root = proc_mkdir("sys", NULL); -#endif -#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) - proc_mkdir("sys/fs", NULL); - proc_mkdir("sys/fs/binfmt_misc", NULL); -#endif - proc_root_fs = proc_mkdir("fs", NULL); - proc_root_driver = proc_mkdir("driver", NULL); + proc_mkdir("fs", NULL); + proc_mkdir("driver", NULL); proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */ #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE) /* just give it a mountpoint */ proc_mkdir("openprom", NULL); #endif proc_tty_init(); -#ifdef CONFIG_PROC_DEVICETREE - proc_device_tree_init(); -#endif - proc_bus = proc_mkdir("bus", NULL); + proc_mkdir("bus", NULL); + proc_sys_init(); } -static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat +) { - /* - * nr_threads is actually protected by the tasklist_lock; - * however, it's conventional to do reads, especially for - * reporting, without any locking whatsoever. - */ - if (dir->i_ino == PROC_ROOT_INO) /* check for safety... */ - dir->i_nlink = proc_root.nlink + nr_threads; - - if (!proc_lookup(dir, dentry, nd)) { + generic_fillattr(dentry->d_inode, stat); + stat->nlink = proc_root.nlink + nr_processes(); + return 0; +} + +static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) +{ + if (!proc_lookup(dir, dentry, flags)) return NULL; - } - return proc_pid_lookup(dir, dentry, nd); + return proc_pid_lookup(dir, dentry, flags); } -static int proc_root_readdir(struct file * filp, - void * dirent, filldir_t filldir) +static int proc_root_readdir(struct file *file, struct dir_context *ctx) { - unsigned int nr = filp->f_pos; - int ret; - - lock_kernel(); - - if (nr < FIRST_PROCESS_ENTRY) { - int error = proc_readdir(filp, dirent, filldir); - if (error <= 0) { - unlock_kernel(); + if (ctx->pos < FIRST_PROCESS_ENTRY) { + int error = proc_readdir(file, ctx); + if (unlikely(error <= 0)) return error; - } - filp->f_pos = FIRST_PROCESS_ENTRY; + ctx->pos = FIRST_PROCESS_ENTRY; } - unlock_kernel(); - ret = proc_pid_readdir(filp, dirent, filldir); - return ret; + return proc_pid_readdir(file, ctx); } /* @@ -124,16 +222,18 @@ static int proc_root_readdir(struct file * filp, * <pid> directories. Thus we don't use the generic * directory handling functions for that.. */ -static struct file_operations proc_root_operations = { +static const struct file_operations proc_root_operations = { .read = generic_read_dir, - .readdir = proc_root_readdir, + .iterate = proc_root_readdir, + .llseek = default_llseek, }; /* * proc root can do almost nothing.. */ -static struct inode_operations proc_root_inode_operations = { +static const struct inode_operations proc_root_inode_operations = { .lookup = proc_root_lookup, + .getattr = proc_root_getattr, }; /* @@ -142,21 +242,28 @@ static struct inode_operations proc_root_inode_operations = { struct proc_dir_entry proc_root = { .low_ino = PROC_ROOT_INO, .namelen = 5, - .name = "/proc", .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, + .count = ATOMIC_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_fops = &proc_root_operations, .parent = &proc_root, + .name = "/proc", }; -EXPORT_SYMBOL(proc_symlink); -EXPORT_SYMBOL(proc_mkdir); -EXPORT_SYMBOL(create_proc_entry); -EXPORT_SYMBOL(remove_proc_entry); -EXPORT_SYMBOL(proc_root); -EXPORT_SYMBOL(proc_root_fs); -EXPORT_SYMBOL(proc_net); -EXPORT_SYMBOL(proc_net_stat); -EXPORT_SYMBOL(proc_bus); -EXPORT_SYMBOL(proc_root_driver); +int pid_ns_prepare_proc(struct pid_namespace *ns) +{ + struct vfsmount *mnt; + + mnt = kern_mount_data(&proc_fs_type, ns); + 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 new file mode 100644 index 00000000000..4348bb8907c --- /dev/null +++ b/fs/proc/self.c @@ -0,0 +1,84 @@ +#include <linux/sched.h> +#include <linux/namei.h> +#include <linux/slab.h> +#include <linux/pid_namespace.h> +#include "internal.h" + +/* + * /proc/self: + */ +static int proc_self_readlink(struct dentry *dentry, char __user *buffer, + int buflen) +{ + struct pid_namespace *ns = dentry->d_sb->s_fs_info; + pid_t tgid = task_tgid_nr_ns(current, ns); + char tmp[PROC_NUMBUF]; + if (!tgid) + return -ENOENT; + sprintf(tmp, "%d", tgid); + return readlink_copy(buffer, buflen, tmp); +} + +static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct pid_namespace *ns = dentry->d_sb->s_fs_info; + pid_t tgid = task_tgid_nr_ns(current, ns); + char *name = ERR_PTR(-ENOENT); + if (tgid) { + /* 11 for max length of signed int in decimal + NULL term */ + name = kmalloc(12, GFP_KERNEL); + if (!name) + name = ERR_PTR(-ENOMEM); + else + sprintf(name, "%d", tgid); + } + nd_set_link(nd, name); + return NULL; +} + +static const struct inode_operations proc_self_inode_operations = { + .readlink = proc_self_readlink, + .follow_link = proc_self_follow_link, + .put_link = kfree_put_link, +}; + +static unsigned self_inum; + +int proc_setup_self(struct super_block *s) +{ + struct inode *root_inode = s->s_root->d_inode; + struct pid_namespace *ns = s->s_fs_info; + struct dentry *self; + + mutex_lock(&root_inode->i_mutex); + self = d_alloc_name(s->s_root, "self"); + if (self) { + struct inode *inode = new_inode_pseudo(s); + if (inode) { + inode->i_ino = self_inum; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_mode = S_IFLNK | S_IRWXUGO; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_op = &proc_self_inode_operations; + d_add(self, inode); + } else { + dput(self); + self = ERR_PTR(-ENOMEM); + } + } else { + self = ERR_PTR(-ENOMEM); + } + mutex_unlock(&root_inode->i_mutex); + if (IS_ERR(self)) { + pr_err("proc_fill_super: can't allocate /proc/self\n"); + return PTR_ERR(self); + } + ns->proc_self = self; + return 0; +} + +void __init proc_self_init(void) +{ + proc_alloc_inum(&self_inum); +} diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c new file mode 100644 index 00000000000..ad8a77f94be --- /dev/null +++ b/fs/proc/softirqs.c @@ -0,0 +1,44 @@ +#include <linux/init.h> +#include <linux/kernel_stat.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +/* + * /proc/softirqs ... display the number of softirqs + */ +static int show_softirqs(struct seq_file *p, void *v) +{ + int i, j; + + seq_puts(p, " "); + for_each_possible_cpu(i) + seq_printf(p, "CPU%-8d", i); + seq_putc(p, '\n'); + + for (i = 0; i < NR_SOFTIRQS; i++) { + seq_printf(p, "%12s:", softirq_to_name[i]); + for_each_possible_cpu(j) + seq_printf(p, " %10u", kstat_softirqs_cpu(i, j)); + seq_putc(p, '\n'); + } + return 0; +} + +static int softirqs_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_softirqs, NULL); +} + +static const struct file_operations proc_softirqs_operations = { + .open = softirqs_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_softirqs_init(void) +{ + proc_create("softirqs", 0, NULL, &proc_softirqs_operations); + return 0; +} +fs_initcall(proc_softirqs_init); diff --git a/fs/proc/stat.c b/fs/proc/stat.c new file mode 100644 index 00000000000..bf2d03f8fd3 --- /dev/null +++ b/fs/proc/stat.c @@ -0,0 +1,206 @@ +#include <linux/cpumask.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/cputime.h> +#include <linux/tick.h> + +#ifndef arch_irq_stat_cpu +#define arch_irq_stat_cpu(cpu) 0 +#endif +#ifndef arch_irq_stat +#define arch_irq_stat() 0 +#endif + +#ifdef arch_idle_time + +static cputime64_t get_idle_time(int cpu) +{ + cputime64_t idle; + + idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) + idle += arch_idle_time(cpu); + return idle; +} + +static cputime64_t get_iowait_time(int cpu) +{ + cputime64_t iowait; + + iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + if (cpu_online(cpu) && nr_iowait_cpu(cpu)) + iowait += arch_idle_time(cpu); + return iowait; +} + +#else + +static u64 get_idle_time(int cpu) +{ + u64 idle, idle_time = -1ULL; + + if (cpu_online(cpu)) + idle_time = get_cpu_idle_time_us(cpu, NULL); + + if (idle_time == -1ULL) + /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ + idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + else + idle = usecs_to_cputime64(idle_time); + + return idle; +} + +static u64 get_iowait_time(int cpu) +{ + u64 iowait, iowait_time = -1ULL; + + if (cpu_online(cpu)) + iowait_time = get_cpu_iowait_time_us(cpu, NULL); + + if (iowait_time == -1ULL) + /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ + iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + else + iowait = usecs_to_cputime64(iowait_time); + + return iowait; +} + +#endif + +static int show_stat(struct seq_file *p, void *v) +{ + int i, j; + unsigned long jif; + u64 user, nice, system, idle, iowait, irq, softirq, steal; + u64 guest, guest_nice; + u64 sum = 0; + u64 sum_softirq = 0; + unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; + struct timespec boottime; + + user = nice = system = idle = iowait = + irq = softirq = steal = 0; + guest = guest_nice = 0; + getboottime(&boottime); + jif = boottime.tv_sec; + + for_each_possible_cpu(i) { + user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; + nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; + system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(i); + iowait += get_iowait_time(i); + irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; + softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; + steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; + guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; + guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + sum += kstat_cpu_irqs_sum(i); + sum += arch_irq_stat_cpu(i); + + for (j = 0; j < NR_SOFTIRQS; j++) { + unsigned int softirq_stat = kstat_softirqs_cpu(j, i); + + per_softirq_sums[j] += softirq_stat; + sum_softirq += softirq_stat; + } + } + sum += arch_irq_stat(); + + seq_puts(p, "cpu "); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ + user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; + nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; + system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(i); + iowait = get_iowait_time(i); + irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; + softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; + steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; + guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; + guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest)); + seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice)); + seq_putc(p, '\n'); + } + seq_printf(p, "intr %llu", (unsigned long long)sum); + + /* sum again ? it could be updated? */ + for_each_irq_nr(j) + seq_put_decimal_ull(p, ' ', kstat_irqs(j)); + + seq_printf(p, + "\nctxt %llu\n" + "btime %lu\n" + "processes %lu\n" + "procs_running %lu\n" + "procs_blocked %lu\n", + nr_context_switches(), + (unsigned long)jif, + total_forks, + nr_running(), + nr_iowait()); + + seq_printf(p, "softirq %llu", (unsigned long long)sum_softirq); + + for (i = 0; i < NR_SOFTIRQS; i++) + seq_put_decimal_ull(p, ' ', per_softirq_sums[i]); + seq_putc(p, '\n'); + + return 0; +} + +static int stat_open(struct inode *inode, struct file *file) +{ + size_t size = 1024 + 128 * num_online_cpus(); + + /* minimum size to display an interrupt count : 2 bytes */ + size += 2 * nr_irqs; + return single_open_size(file, show_stat, NULL, size); +} + +static const struct file_operations proc_stat_operations = { + .open = stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_stat_init(void) +{ + proc_create("stat", 0, NULL, &proc_stat_operations); + return 0; +} +fs_initcall(proc_stat_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 0eaad41f465..cfa63ee92c9 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,19 +1,27 @@ #include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/hugetlb.h> +#include <linux/huge_mm.h> #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/highmem.h> +#include <linux/ptrace.h> +#include <linux/slab.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> +#include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/mmu_notifier.h> #include <asm/elf.h> #include <asm/uaccess.h> #include <asm/tlbflush.h> #include "internal.h" -char *task_mem(struct mm_struct *mm, char *buffer) +void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib; + unsigned long data, text, lib, swap; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; /* @@ -33,26 +41,31 @@ char *task_mem(struct mm_struct *mm, char *buffer) data = mm->total_vm - mm->shared_vm - mm->stack_vm; text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; - buffer += sprintf(buffer, + swap = get_mm_counter(mm, MM_SWAPENTS); + seq_printf(m, "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" "VmLck:\t%8lu kB\n" + "VmPin:\t%8lu kB\n" "VmHWM:\t%8lu kB\n" "VmRSS:\t%8lu kB\n" "VmData:\t%8lu kB\n" "VmStk:\t%8lu kB\n" "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" - "VmPTE:\t%8lu kB\n", + "VmPTE:\t%8lu kB\n" + "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), - (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), + total_vm << (PAGE_SHIFT-10), mm->locked_vm << (PAGE_SHIFT-10), + mm->pinned_vm << (PAGE_SHIFT-10), hiwater_rss << (PAGE_SHIFT-10), total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, - (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10); - return buffer; + (PTRS_PER_PTE * sizeof(pte_t) * + atomic_long_read(&mm->nr_ptes)) >> 10, + swap << (PAGE_SHIFT-10)); } unsigned long task_vsize(struct mm_struct *mm) @@ -60,342 +73,1474 @@ unsigned long task_vsize(struct mm_struct *mm) return PAGE_SIZE * mm->total_vm; } -int task_statm(struct mm_struct *mm, int *shared, int *text, - int *data, int *resident) +unsigned long task_statm(struct mm_struct *mm, + unsigned long *shared, unsigned long *text, + unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, file_rss); + *shared = get_mm_counter(mm, MM_FILEPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; - *resident = *shared + get_mm_counter(mm, anon_rss); + *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); return mm->total_vm; } -int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +#ifdef CONFIG_NUMA +/* + * These functions are for numa_maps but called in generic **maps seq_file + * ->start(), ->stop() ops. + * + * numa_maps scans all vmas under mmap_sem and checks their mempolicy. + * Each mempolicy object is controlled by reference counting. The problem here + * is how to avoid accessing dead mempolicy object. + * + * Because we're holding mmap_sem while reading seq_file, it's safe to access + * each vma's mempolicy, no vma objects will never drop refs to mempolicy. + * + * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy + * is set and replaced under mmap_sem but unrefed and cleared under task_lock(). + * So, without task_lock(), we cannot trust get_vma_policy() because we cannot + * gurantee the task never exits under us. But taking task_lock() around + * get_vma_plicy() causes lock order problem. + * + * To access task->mempolicy without lock, we hold a reference count of an + * object pointed by task->mempolicy and remember it. This will guarantee + * that task->mempolicy points to an alive object or NULL in numa_maps accesses. + */ +static void hold_task_mempolicy(struct proc_maps_private *priv) { - struct vm_area_struct * vma; - int result = -ENOENT; - struct task_struct *task = proc_task(inode); - struct mm_struct * mm = get_task_mm(task); + struct task_struct *task = priv->task; - if (!mm) - goto out; + task_lock(task); + priv->task_mempolicy = task->mempolicy; + mpol_get(priv->task_mempolicy); + task_unlock(task); +} +static void release_task_mempolicy(struct proc_maps_private *priv) +{ + mpol_put(priv->task_mempolicy); +} +#else +static void hold_task_mempolicy(struct proc_maps_private *priv) +{ +} +static void release_task_mempolicy(struct proc_maps_private *priv) +{ +} +#endif + +static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) +{ + if (vma && vma != priv->tail_vma) { + struct mm_struct *mm = vma->vm_mm; + release_task_mempolicy(priv); + up_read(&mm->mmap_sem); + mmput(mm); + } +} + +static void *m_start(struct seq_file *m, loff_t *pos) +{ + struct proc_maps_private *priv = m->private; + unsigned long last_addr = m->version; + struct mm_struct *mm; + struct vm_area_struct *vma, *tail_vma = NULL; + loff_t l = *pos; + + /* Clear the per syscall fields in priv */ + priv->task = NULL; + priv->tail_vma = NULL; + + /* + * We remember last_addr rather than next_addr to hit with + * vmacache most of the time. We have zero last_addr at + * the beginning and also after lseek. We will have -1 last_addr + * after the end of the vmas. + */ + + if (last_addr == -1UL) + return NULL; + + priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + if (!priv->task) + return ERR_PTR(-ESRCH); + + mm = mm_access(priv->task, PTRACE_MODE_READ); + if (!mm || IS_ERR(mm)) + return mm; down_read(&mm->mmap_sem); - vma = mm->mmap; - while (vma) { - if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file) - break; + tail_vma = get_gate_vma(priv->task->mm); + priv->tail_vma = tail_vma; + hold_task_mempolicy(priv); + /* Start with last addr hint */ + vma = find_vma(mm, last_addr); + if (last_addr && vma) { vma = vma->vm_next; + goto out; } - if (vma) { - *mnt = mntget(vma->vm_file->f_vfsmnt); - *dentry = dget(vma->vm_file->f_dentry); - result = 0; + /* + * Check the vma index is within the range and do + * sequential scan until m_index. + */ + vma = NULL; + if ((unsigned long)l < mm->map_count) { + vma = mm->mmap; + while (l-- && vma) + vma = vma->vm_next; + goto out; } + if (l != mm->map_count) + tail_vma = NULL; /* After gate vma */ + +out: + if (vma) + return vma; + + release_task_mempolicy(priv); + /* End of vmas has been reached */ + m->version = (tail_vma != NULL)? 0: -1UL; up_read(&mm->mmap_sem); mmput(mm); -out: - return result; + return tail_vma; } -static void pad_len_spaces(struct seq_file *m, int len) +static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - len = 25 + sizeof(void*) * 6 - len; - if (len < 1) - len = 1; - seq_printf(m, "%*c", len, ' '); + struct proc_maps_private *priv = m->private; + struct vm_area_struct *vma = v; + struct vm_area_struct *tail_vma = priv->tail_vma; + + (*pos)++; + if (vma && (vma != tail_vma) && vma->vm_next) + return vma->vm_next; + vma_stop(priv, vma); + return (vma != tail_vma)? tail_vma: NULL; } -struct mem_size_stats +static void m_stop(struct seq_file *m, void *v) { - unsigned long resident; - unsigned long shared_clean; - unsigned long shared_dirty; - unsigned long private_clean; - unsigned long private_dirty; -}; + struct proc_maps_private *priv = m->private; + struct vm_area_struct *vma = v; + + if (!IS_ERR(vma)) + vma_stop(priv, vma); + if (priv->task) + put_task_struct(priv->task); +} -static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss) +static int do_maps_open(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + struct proc_maps_private *priv; + int ret = -ENOMEM; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + priv->pid = proc_pid(inode); + ret = seq_open(file, ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = priv; + } else { + kfree(priv); + } + } + return ret; +} + +static void +show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) { - struct task_struct *task = m->private; - struct vm_area_struct *vma = v; struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; - int flags = vma->vm_flags; + struct proc_maps_private *priv = m->private; + struct task_struct *task = priv->task; + vm_flags_t flags = vma->vm_flags; unsigned long ino = 0; + unsigned long long pgoff = 0; + unsigned long start, end; dev_t dev = 0; - int len; + const char *name = NULL; if (file) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); dev = inode->i_sb->s_dev; ino = inode->i_ino; + pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; } - seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", - vma->vm_start, - vma->vm_end, + /* We don't show the stack guard page in /proc/maps */ + start = vma->vm_start; + if (stack_guard_page_start(vma, start)) + start += PAGE_SIZE; + end = vma->vm_end; + if (stack_guard_page_end(vma, end)) + end -= PAGE_SIZE; + + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); + seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", + start, + end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? 's' : 'p', - vma->vm_pgoff << PAGE_SHIFT, - MAJOR(dev), MINOR(dev), ino, &len); + pgoff, + MAJOR(dev), MINOR(dev), ino); /* * Print the dentry name for named mappings, and a * special [heap] marker for the heap: */ if (file) { - pad_len_spaces(m, len); - seq_path(m, file->f_vfsmnt, file->f_dentry, "\n"); - } else { - if (mm) { - if (vma->vm_start <= mm->start_brk && - vma->vm_end >= mm->brk) { - pad_len_spaces(m, len); - seq_puts(m, "[heap]"); - } else { - if (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack) { + seq_pad(m, ' '); + seq_path(m, &file->f_path, "\n"); + goto done; + } + + if (vma->vm_ops && vma->vm_ops->name) { + name = vma->vm_ops->name(vma); + if (name) + goto done; + } + + name = arch_vma_name(vma); + if (!name) { + pid_t tid; - pad_len_spaces(m, len); - seq_puts(m, "[stack]"); - } + if (!mm) { + name = "[vdso]"; + goto done; + } + + if (vma->vm_start <= mm->brk && + vma->vm_end >= mm->start_brk) { + name = "[heap]"; + goto done; + } + + tid = vm_is_stack(task, vma, is_pid); + + if (tid != 0) { + /* + * Thread stack in /proc/PID/task/TID/maps or + * the main process stack. + */ + if (!is_pid || (vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack)) { + name = "[stack]"; + } else { + /* Thread stack in /proc/PID/maps */ + seq_pad(m, ' '); + seq_printf(m, "[stack:%d]", tid); } - } else { - pad_len_spaces(m, len); - seq_puts(m, "[vdso]"); + } + } + +done: + if (name) { + seq_pad(m, ' '); + seq_puts(m, name); + } + seq_putc(m, '\n'); +} + +static int show_map(struct seq_file *m, void *v, int is_pid) +{ + struct vm_area_struct *vma = v; + struct proc_maps_private *priv = m->private; + struct task_struct *task = priv->task; + + show_map_vma(m, vma, is_pid); + + if (m->count < m->size) /* vma is copied successfully */ + m->version = (vma != get_gate_vma(task->mm)) + ? vma->vm_start : 0; + return 0; +} + +static int show_pid_map(struct seq_file *m, void *v) +{ + return show_map(m, v, 1); +} + +static int show_tid_map(struct seq_file *m, void *v) +{ + return show_map(m, v, 0); +} + +static const struct seq_operations proc_pid_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_pid_map +}; + +static const struct seq_operations proc_tid_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_tid_map +}; + +static int pid_maps_open(struct inode *inode, struct file *file) +{ + return do_maps_open(inode, file, &proc_pid_maps_op); +} + +static int tid_maps_open(struct inode *inode, struct file *file) +{ + return do_maps_open(inode, file, &proc_tid_maps_op); +} + +const struct file_operations proc_pid_maps_operations = { + .open = pid_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +const struct file_operations proc_tid_maps_operations = { + .open = tid_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +/* + * Proportional Set Size(PSS): my share of RSS. + * + * PSS of a process is the count of pages it has in memory, where each + * page is divided by the number of processes sharing it. So if a + * process has 1000 pages all to itself, and 1000 shared with one other + * process, its PSS will be 1500. + * + * To keep (accumulated) division errors low, we adopt a 64bit + * fixed-point pss counter to minimize division errors. So (pss >> + * PSS_SHIFT) would be the real byte count. + * + * A shift of 12 before division means (assuming 4K page size): + * - 1M 3-user-pages add up to 8KB errors; + * - supports mapcount up to 2^24, or 16M; + * - supports PSS up to 2^52 bytes, or 4PB. + */ +#define PSS_SHIFT 12 + +#ifdef CONFIG_PROC_PAGE_MONITOR +struct mem_size_stats { + struct vm_area_struct *vma; + unsigned long resident; + unsigned long shared_clean; + unsigned long shared_dirty; + unsigned long private_clean; + unsigned long private_dirty; + unsigned long referenced; + unsigned long anonymous; + unsigned long anonymous_thp; + unsigned long swap; + unsigned long nonlinear; + u64 pss; +}; + + +static void smaps_pte_entry(pte_t ptent, unsigned long addr, + unsigned long ptent_size, struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = mss->vma; + pgoff_t pgoff = linear_page_index(vma, addr); + struct page *page = NULL; + int mapcount; + + if (pte_present(ptent)) { + page = vm_normal_page(vma, addr, ptent); + } else if (is_swap_pte(ptent)) { + swp_entry_t swpent = pte_to_swp_entry(ptent); + + if (!non_swap_entry(swpent)) + mss->swap += ptent_size; + else if (is_migration_entry(swpent)) + page = migration_entry_to_page(swpent); + } else if (pte_file(ptent)) { + if (pte_to_pgoff(ptent) != pgoff) + mss->nonlinear += ptent_size; + } + + if (!page) + return; + + if (PageAnon(page)) + mss->anonymous += ptent_size; + + if (page->index != pgoff) + mss->nonlinear += ptent_size; + + mss->resident += ptent_size; + /* Accumulate the size in pages that have been accessed. */ + if (pte_young(ptent) || PageReferenced(page)) + mss->referenced += ptent_size; + mapcount = page_mapcount(page); + if (mapcount >= 2) { + if (pte_dirty(ptent) || PageDirty(page)) + mss->shared_dirty += ptent_size; + else + mss->shared_clean += ptent_size; + mss->pss += (ptent_size << PSS_SHIFT) / mapcount; + } else { + if (pte_dirty(ptent) || PageDirty(page)) + mss->private_dirty += ptent_size; + else + mss->private_clean += ptent_size; + mss->pss += (ptent_size << PSS_SHIFT); + } +} + +static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = mss->vma; + pte_t *pte; + spinlock_t *ptl; + + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk); + spin_unlock(ptl); + mss->anonymous_thp += HPAGE_PMD_SIZE; + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; + /* + * The mmap_sem held all the way back in m_start() is what + * keeps khugepaged out of here and from collapsing things + * in here. + */ + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) + smaps_pte_entry(*pte, addr, PAGE_SIZE, walk); + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + return 0; +} + +static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) +{ + /* + * Don't forget to update Documentation/ on changes. + */ + static const char mnemonics[BITS_PER_LONG][2] = { + /* + * In case if we meet a flag we don't know about. + */ + [0 ... (BITS_PER_LONG-1)] = "??", + + [ilog2(VM_READ)] = "rd", + [ilog2(VM_WRITE)] = "wr", + [ilog2(VM_EXEC)] = "ex", + [ilog2(VM_SHARED)] = "sh", + [ilog2(VM_MAYREAD)] = "mr", + [ilog2(VM_MAYWRITE)] = "mw", + [ilog2(VM_MAYEXEC)] = "me", + [ilog2(VM_MAYSHARE)] = "ms", + [ilog2(VM_GROWSDOWN)] = "gd", + [ilog2(VM_PFNMAP)] = "pf", + [ilog2(VM_DENYWRITE)] = "dw", + [ilog2(VM_LOCKED)] = "lo", + [ilog2(VM_IO)] = "io", + [ilog2(VM_SEQ_READ)] = "sr", + [ilog2(VM_RAND_READ)] = "rr", + [ilog2(VM_DONTCOPY)] = "dc", + [ilog2(VM_DONTEXPAND)] = "de", + [ilog2(VM_ACCOUNT)] = "ac", + [ilog2(VM_NORESERVE)] = "nr", + [ilog2(VM_HUGETLB)] = "ht", + [ilog2(VM_NONLINEAR)] = "nl", + [ilog2(VM_ARCH_1)] = "ar", + [ilog2(VM_DONTDUMP)] = "dd", +#ifdef CONFIG_MEM_SOFT_DIRTY + [ilog2(VM_SOFTDIRTY)] = "sd", +#endif + [ilog2(VM_MIXEDMAP)] = "mm", + [ilog2(VM_HUGEPAGE)] = "hg", + [ilog2(VM_NOHUGEPAGE)] = "nh", + [ilog2(VM_MERGEABLE)] = "mg", + }; + size_t i; + + seq_puts(m, "VmFlags: "); + for (i = 0; i < BITS_PER_LONG; i++) { + if (vma->vm_flags & (1UL << i)) { + seq_printf(m, "%c%c ", + mnemonics[i][0], mnemonics[i][1]); } } seq_putc(m, '\n'); +} - if (mss) - seq_printf(m, - "Size: %8lu kB\n" - "Rss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - mss->resident >> 10, - mss->shared_clean >> 10, - mss->shared_dirty >> 10, - mss->private_clean >> 10, - mss->private_dirty >> 10); +static int show_smap(struct seq_file *m, void *v, int is_pid) +{ + struct proc_maps_private *priv = m->private; + struct task_struct *task = priv->task; + struct vm_area_struct *vma = v; + struct mem_size_stats mss; + struct mm_walk smaps_walk = { + .pmd_entry = smaps_pte_range, + .mm = vma->vm_mm, + .private = &mss, + }; + + memset(&mss, 0, sizeof mss); + mss.vma = vma; + /* mmap_sem is held in m_start */ + if (vma->vm_mm && !is_vm_hugetlb_page(vma)) + walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); + + show_map_vma(m, vma, is_pid); + + seq_printf(m, + "Size: %8lu kB\n" + "Rss: %8lu kB\n" + "Pss: %8lu kB\n" + "Shared_Clean: %8lu kB\n" + "Shared_Dirty: %8lu kB\n" + "Private_Clean: %8lu kB\n" + "Private_Dirty: %8lu kB\n" + "Referenced: %8lu kB\n" + "Anonymous: %8lu kB\n" + "AnonHugePages: %8lu kB\n" + "Swap: %8lu kB\n" + "KernelPageSize: %8lu kB\n" + "MMUPageSize: %8lu kB\n" + "Locked: %8lu kB\n", + (vma->vm_end - vma->vm_start) >> 10, + mss.resident >> 10, + (unsigned long)(mss.pss >> (10 + PSS_SHIFT)), + mss.shared_clean >> 10, + mss.shared_dirty >> 10, + mss.private_clean >> 10, + mss.private_dirty >> 10, + mss.referenced >> 10, + mss.anonymous >> 10, + mss.anonymous_thp >> 10, + mss.swap >> 10, + vma_kernel_pagesize(vma) >> 10, + vma_mmu_pagesize(vma) >> 10, + (vma->vm_flags & VM_LOCKED) ? + (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); + + if (vma->vm_flags & VM_NONLINEAR) + seq_printf(m, "Nonlinear: %8lu kB\n", + mss.nonlinear >> 10); + + show_smap_vma_flags(m, vma); if (m->count < m->size) /* vma is copied successfully */ - m->version = (vma != get_gate_vma(task))? vma->vm_start: 0; + m->version = (vma != get_gate_vma(task->mm)) + ? vma->vm_start : 0; return 0; } -static int show_map(struct seq_file *m, void *v) +static int show_pid_smap(struct seq_file *m, void *v) +{ + return show_smap(m, v, 1); +} + +static int show_tid_smap(struct seq_file *m, void *v) +{ + return show_smap(m, v, 0); +} + +static const struct seq_operations proc_pid_smaps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_pid_smap +}; + +static const struct seq_operations proc_tid_smaps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_tid_smap +}; + +static int pid_smaps_open(struct inode *inode, struct file *file) +{ + return do_maps_open(inode, file, &proc_pid_smaps_op); +} + +static int tid_smaps_open(struct inode *inode, struct file *file) +{ + return do_maps_open(inode, file, &proc_tid_smaps_op); +} + +const struct file_operations proc_pid_smaps_operations = { + .open = pid_smaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +const struct file_operations proc_tid_smaps_operations = { + .open = tid_smaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + +/* + * We do not want to have constant page-shift bits sitting in + * pagemap entries and are about to reuse them some time soon. + * + * Here's the "migration strategy": + * 1. when the system boots these bits remain what they are, + * but a warning about future change is printed in log; + * 2. once anyone clears soft-dirty bits via clear_refs file, + * these flag is set to denote, that user is aware of the + * new API and those page-shift bits change their meaning. + * The respective warning is printed in dmesg; + * 3. In a couple of releases we will remove all the mentions + * of page-shift in pagemap entries. + */ + +static bool soft_dirty_cleared __read_mostly; + +enum clear_refs_types { + CLEAR_REFS_ALL = 1, + CLEAR_REFS_ANON, + CLEAR_REFS_MAPPED, + CLEAR_REFS_SOFT_DIRTY, + CLEAR_REFS_LAST, +}; + +struct clear_refs_private { + struct vm_area_struct *vma; + enum clear_refs_types type; +}; + +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) { - return show_map_internal(m, v, NULL); +#ifdef CONFIG_MEM_SOFT_DIRTY + /* + * The soft-dirty tracker uses #PF-s to catch writes + * to pages, so write-protect the pte as well. See the + * Documentation/vm/soft-dirty.txt for full description + * of how soft-dirty works. + */ + pte_t ptent = *pte; + + if (pte_present(ptent)) { + ptent = pte_wrprotect(ptent); + ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + } else if (is_swap_pte(ptent)) { + ptent = pte_swp_clear_soft_dirty(ptent); + } else if (pte_file(ptent)) { + ptent = pte_file_clear_soft_dirty(ptent); + } + + set_pte_at(vma->vm_mm, addr, pte, ptent); +#endif } -static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - struct mem_size_stats *mss) +static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) { + struct clear_refs_private *cp = walk->private; + struct vm_area_struct *vma = cp->vma; pte_t *pte, ptent; spinlock_t *ptl; - unsigned long pfn; struct page *page; + split_huge_page_pmd(vma, addr, pmd); + if (pmd_trans_unstable(pmd)) + return 0; + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - do { + for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = *pte; + + if (cp->type == CLEAR_REFS_SOFT_DIRTY) { + clear_soft_dirty(vma, addr, pte); + continue; + } + if (!pte_present(ptent)) continue; - mss->resident += PAGE_SIZE; - pfn = pte_pfn(ptent); - if (!pfn_valid(pfn)) + page = vm_normal_page(vma, addr, ptent); + if (!page) continue; - page = pfn_to_page(pfn); - if (page_count(page) >= 2) { - if (pte_dirty(ptent)) - mss->shared_dirty += PAGE_SIZE; - else - mss->shared_clean += PAGE_SIZE; - } else { - if (pte_dirty(ptent)) - mss->private_dirty += PAGE_SIZE; - else - mss->private_clean += PAGE_SIZE; - } - } while (pte++, addr += PAGE_SIZE, addr != end); + /* Clear accessed and referenced bits. */ + ptep_test_and_clear_young(vma, addr, pte); + ClearPageReferenced(page); + } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + return 0; } -static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud, - unsigned long addr, unsigned long end, - struct mem_size_stats *mss) +static ssize_t clear_refs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { - pmd_t *pmd; - unsigned long next; + struct task_struct *task; + char buffer[PROC_NUMBUF]; + struct mm_struct *mm; + struct vm_area_struct *vma; + enum clear_refs_types type; + int itype; + int rv; - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) - continue; - smaps_pte_range(vma, pmd, addr, next, mss); - } while (pmd++, addr = next, addr != end); + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + rv = kstrtoint(strstrip(buffer), 10, &itype); + if (rv < 0) + return rv; + type = (enum clear_refs_types)itype; + if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST) + return -EINVAL; + + if (type == CLEAR_REFS_SOFT_DIRTY) { + soft_dirty_cleared = true; + pr_warn_once("The pagemap bits 55-60 has changed their meaning!" + " See the linux/Documentation/vm/pagemap.txt for " + "details.\n"); + } + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + mm = get_task_mm(task); + if (mm) { + struct clear_refs_private cp = { + .type = type, + }; + struct mm_walk clear_refs_walk = { + .pmd_entry = clear_refs_pte_range, + .mm = mm, + .private = &cp, + }; + down_read(&mm->mmap_sem); + if (type == CLEAR_REFS_SOFT_DIRTY) + mmu_notifier_invalidate_range_start(mm, 0, -1); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + cp.vma = vma; + if (is_vm_hugetlb_page(vma)) + continue; + /* + * Writing 1 to /proc/pid/clear_refs affects all pages. + * + * Writing 2 to /proc/pid/clear_refs only affects + * Anonymous pages. + * + * Writing 3 to /proc/pid/clear_refs only affects file + * mapped pages. + * + * Writing 4 to /proc/pid/clear_refs affects all pages. + */ + if (type == CLEAR_REFS_ANON && vma->vm_file) + continue; + if (type == CLEAR_REFS_MAPPED && !vma->vm_file) + continue; + if (type == CLEAR_REFS_SOFT_DIRTY) { + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + } + walk_page_range(vma->vm_start, vma->vm_end, + &clear_refs_walk); + } + if (type == CLEAR_REFS_SOFT_DIRTY) + mmu_notifier_invalidate_range_end(mm, 0, -1); + flush_tlb_mm(mm); + up_read(&mm->mmap_sem); + mmput(mm); + } + put_task_struct(task); + + return count; } -static inline void smaps_pud_range(struct vm_area_struct *vma, pgd_t *pgd, - unsigned long addr, unsigned long end, - struct mem_size_stats *mss) +const struct file_operations proc_clear_refs_operations = { + .write = clear_refs_write, + .llseek = noop_llseek, +}; + +typedef struct { + u64 pme; +} pagemap_entry_t; + +struct pagemapread { + int pos, len; /* units: PM_ENTRY_BYTES, not bytes */ + pagemap_entry_t *buffer; + bool v2; +}; + +#define PAGEMAP_WALK_SIZE (PMD_SIZE) +#define PAGEMAP_WALK_MASK (PMD_MASK) + +#define PM_ENTRY_BYTES sizeof(pagemap_entry_t) +#define PM_STATUS_BITS 3 +#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS) +#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET) +#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK) +#define PM_PSHIFT_BITS 6 +#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS) +#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET) +#define __PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) +#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1) +#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK) +/* in "new" pagemap pshift bits are occupied with more status bits */ +#define PM_STATUS2(v2, x) (__PM_PSHIFT(v2 ? x : PAGE_SHIFT)) + +#define __PM_SOFT_DIRTY (1LL) +#define PM_PRESENT PM_STATUS(4LL) +#define PM_SWAP PM_STATUS(2LL) +#define PM_FILE PM_STATUS(1LL) +#define PM_NOT_PRESENT(v2) PM_STATUS2(v2, 0) +#define PM_END_OF_BUFFER 1 + +static inline pagemap_entry_t make_pme(u64 val) { - pud_t *pud; - unsigned long next; + return (pagemap_entry_t) { .pme = val }; +} - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - continue; - smaps_pmd_range(vma, pud, addr, next, mss); - } while (pud++, addr = next, addr != end); +static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, + struct pagemapread *pm) +{ + pm->buffer[pm->pos++] = *pme; + if (pm->pos >= pm->len) + return PM_END_OF_BUFFER; + return 0; } -static inline void smaps_pgd_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - struct mem_size_stats *mss) +static int pagemap_pte_hole(unsigned long start, unsigned long end, + struct mm_walk *walk) { - pgd_t *pgd; - unsigned long next; + struct pagemapread *pm = walk->private; + unsigned long addr; + int err = 0; + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); - pgd = pgd_offset(vma->vm_mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - continue; - smaps_pud_range(vma, pgd, addr, next, mss); - } while (pgd++, addr = next, addr != end); + for (addr = start; addr < end; addr += PAGE_SIZE) { + err = add_to_pagemap(addr, &pme, pm); + if (err) + break; + } + return err; } -static int show_smap(struct seq_file *m, void *v) +static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - struct vm_area_struct *vma = v; - struct mem_size_stats mss; + u64 frame, flags; + struct page *page = NULL; + int flags2 = 0; - memset(&mss, 0, sizeof mss); - if (vma->vm_mm) - smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss); - return show_map_internal(m, v, &mss); + if (pte_present(pte)) { + frame = pte_pfn(pte); + flags = PM_PRESENT; + page = vm_normal_page(vma, addr, pte); + if (pte_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; + } else if (is_swap_pte(pte)) { + swp_entry_t entry; + if (pte_swp_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; + entry = pte_to_swp_entry(pte); + frame = swp_type(entry) | + (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + flags = PM_SWAP; + if (is_migration_entry(entry)) + page = migration_entry_to_page(entry); + } else { + if (vma->vm_flags & VM_SOFTDIRTY) + flags2 |= __PM_SOFT_DIRTY; + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); + return; + } + + if (page && !PageAnon(page)) + flags |= PM_FILE; + if ((vma->vm_flags & VM_SOFTDIRTY)) + flags2 |= __PM_SOFT_DIRTY; + + *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags); } -static void *m_start(struct seq_file *m, loff_t *pos) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + pmd_t pmd, int offset, int pmd_flags2) { - struct task_struct *task = m->private; - unsigned long last_addr = m->version; + /* + * Currently pmd for thp is always present because thp can not be + * swapped-out, migrated, or HWPOISONed (split in such cases instead.) + * This if-check is just to prepare for future implementation. + */ + if (pmd_present(pmd)) + *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) + | PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2)); +} +#else +static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + pmd_t pmd, int offset, int pmd_flags2) +{ +} +#endif + +static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma; + struct pagemapread *pm = walk->private; + spinlock_t *ptl; + pte_t *pte; + int err = 0; + pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); + + /* find the first VMA at or above 'addr' */ + vma = find_vma(walk->mm, addr); + if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + int pmd_flags2; + + if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd)) + pmd_flags2 = __PM_SOFT_DIRTY; + else + pmd_flags2 = 0; + + for (; addr != end; addr += PAGE_SIZE) { + unsigned long offset; + + offset = (addr & ~PAGEMAP_WALK_MASK) >> + PAGE_SHIFT; + thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2); + err = add_to_pagemap(addr, &pme, pm); + if (err) + break; + } + spin_unlock(ptl); + return err; + } + + if (pmd_trans_unstable(pmd)) + return 0; + for (; addr != end; addr += PAGE_SIZE) { + int flags2; + + /* check to see if we've left 'vma' behind + * and need a new, higher one */ + if (vma && (addr >= vma->vm_end)) { + vma = find_vma(walk->mm, addr); + if (vma && (vma->vm_flags & VM_SOFTDIRTY)) + flags2 = __PM_SOFT_DIRTY; + else + flags2 = 0; + pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2)); + } + + /* check that 'vma' actually covers this address, + * and that it isn't a huge page vma */ + if (vma && (vma->vm_start <= addr) && + !is_vm_hugetlb_page(vma)) { + pte = pte_offset_map(pmd, addr); + pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); + /* unmap before userspace copy */ + pte_unmap(pte); + } + err = add_to_pagemap(addr, &pme, pm); + if (err) + return err; + } + + cond_resched(); + + return err; +} + +#ifdef CONFIG_HUGETLB_PAGE +static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, + pte_t pte, int offset, int flags2) +{ + if (pte_present(pte)) + *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) | + PM_STATUS2(pm->v2, flags2) | + PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT(pm->v2) | + PM_STATUS2(pm->v2, flags2)); +} + +/* This function walks within one hugetlb entry in the single call */ +static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct pagemapread *pm = walk->private; + struct vm_area_struct *vma; + int err = 0; + int flags2; + pagemap_entry_t pme; + + vma = find_vma(walk->mm, addr); + WARN_ON_ONCE(!vma); + + if (vma && (vma->vm_flags & VM_SOFTDIRTY)) + flags2 = __PM_SOFT_DIRTY; + else + flags2 = 0; + + for (; addr != end; addr += PAGE_SIZE) { + int offset = (addr & ~hmask) >> PAGE_SHIFT; + huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2); + err = add_to_pagemap(addr, &pme, pm); + if (err) + return err; + } + + cond_resched(); + + return err; +} +#endif /* HUGETLB_PAGE */ + +/* + * /proc/pid/pagemap - an array mapping virtual pages to pfns + * + * For each page in the address space, this file contains one 64-bit entry + * consisting of the following: + * + * Bits 0-54 page frame number (PFN) if present + * Bits 0-4 swap type if swapped + * Bits 5-54 swap offset if swapped + * Bits 55-60 page shift (page size = 1<<page shift) + * Bit 61 page is file-page or shared-anon + * Bit 62 page swapped + * Bit 63 page present + * + * If the page is not present but in swap, then the PFN contains an + * encoding of the swap file number and the page's offset into the + * swap. Unmapped pages return a null PFN. This allows determining + * precisely which pages are mapped (or in swap) and comparing mapped + * pages between processes. + * + * Efficient users of this interface will use /proc/pid/maps to + * determine which areas of memory are actually mapped and llseek to + * skip over unmapped regions. + */ +static ssize_t pagemap_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; - struct vm_area_struct *vma, *tail_vma; - loff_t l = *pos; + struct pagemapread pm; + int ret = -ESRCH; + struct mm_walk pagemap_walk = {}; + unsigned long src; + unsigned long svpfn; + unsigned long start_vaddr; + unsigned long end_vaddr; + int copied = 0; + + if (!task) + goto out; + + ret = -EINVAL; + /* file position must be aligned */ + if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES)) + goto out_task; + + ret = 0; + if (!count) + goto out_task; + + pm.v2 = soft_dirty_cleared; + pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); + pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY); + ret = -ENOMEM; + if (!pm.buffer) + goto out_task; + + mm = mm_access(task, PTRACE_MODE_READ); + ret = PTR_ERR(mm); + if (!mm || IS_ERR(mm)) + goto out_free; + + pagemap_walk.pmd_entry = pagemap_pte_range; + pagemap_walk.pte_hole = pagemap_pte_hole; +#ifdef CONFIG_HUGETLB_PAGE + pagemap_walk.hugetlb_entry = pagemap_hugetlb_range; +#endif + pagemap_walk.mm = mm; + pagemap_walk.private = ± + + src = *ppos; + svpfn = src / PM_ENTRY_BYTES; + start_vaddr = svpfn << PAGE_SHIFT; + end_vaddr = TASK_SIZE_OF(task); + + /* watch out for wraparound */ + if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + start_vaddr = end_vaddr; /* - * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at - * the beginning and also after lseek. We will have -1 last_addr - * after the end of the vmas. + * The odds are that this will stop walking way + * before end_vaddr, because the length of the + * user buffer is tracked in "pm", and the walk + * will stop when we hit the end of the buffer. */ + ret = 0; + while (count && (start_vaddr < end_vaddr)) { + int len; + unsigned long end; - if (last_addr == -1UL) + pm.pos = 0; + end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK; + /* overflow ? */ + if (end < start_vaddr || end > end_vaddr) + end = end_vaddr; + down_read(&mm->mmap_sem); + ret = walk_page_range(start_vaddr, end, &pagemap_walk); + up_read(&mm->mmap_sem); + start_vaddr = end; + + len = min(count, PM_ENTRY_BYTES * pm.pos); + if (copy_to_user(buf, pm.buffer, len)) { + ret = -EFAULT; + goto out_mm; + } + copied += len; + buf += len; + count -= len; + } + *ppos += copied; + if (!ret || ret == PM_END_OF_BUFFER) + ret = copied; + +out_mm: + mmput(mm); +out_free: + kfree(pm.buffer); +out_task: + put_task_struct(task); +out: + return ret; +} + +static int pagemap_open(struct inode *inode, struct file *file) +{ + pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " + "to stop being page-shift some time soon. See the " + "linux/Documentation/vm/pagemap.txt for details.\n"); + return 0; +} + +const struct file_operations proc_pagemap_operations = { + .llseek = mem_lseek, /* borrow this */ + .read = pagemap_read, + .open = pagemap_open, +}; +#endif /* CONFIG_PROC_PAGE_MONITOR */ + +#ifdef CONFIG_NUMA + +struct numa_maps { + struct vm_area_struct *vma; + unsigned long pages; + unsigned long anon; + unsigned long active; + unsigned long writeback; + unsigned long mapcount_max; + unsigned long dirty; + unsigned long swapcache; + unsigned long node[MAX_NUMNODES]; +}; + +struct numa_maps_private { + struct proc_maps_private proc_maps; + struct numa_maps md; +}; + +static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty, + unsigned long nr_pages) +{ + int count = page_mapcount(page); + + md->pages += nr_pages; + if (pte_dirty || PageDirty(page)) + md->dirty += nr_pages; + + if (PageSwapCache(page)) + md->swapcache += nr_pages; + + if (PageActive(page) || PageUnevictable(page)) + md->active += nr_pages; + + if (PageWriteback(page)) + md->writeback += nr_pages; + + if (PageAnon(page)) + md->anon += nr_pages; + + if (count > md->mapcount_max) + md->mapcount_max = count; + + md->node[page_to_nid(page)] += nr_pages; +} + +static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pte_present(pte)) return NULL; - mm = get_task_mm(task); - if (!mm) + page = vm_normal_page(vma, addr, pte); + if (!page) return NULL; - tail_vma = get_gate_vma(task); - down_read(&mm->mmap_sem); + if (PageReserved(page)) + return NULL; - /* Start with last addr hint */ - if (last_addr && (vma = find_vma(mm, last_addr))) { - vma = vma->vm_next; - goto out; - } + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; - /* - * Check the vma index is within the range and do - * sequential scan until m_index. - */ - vma = NULL; - if ((unsigned long)l < mm->map_count) { - vma = mm->mmap; - while (l-- && vma) - vma = vma->vm_next; - goto out; + return page; +} + +static int gather_pte_stats(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct numa_maps *md; + spinlock_t *ptl; + pte_t *orig_pte; + pte_t *pte; + + md = walk->private; + + if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) { + pte_t huge_pte = *(pte_t *)pmd; + struct page *page; + + page = can_gather_numa_stats(huge_pte, md->vma, addr); + if (page) + gather_stats(page, md, pte_dirty(huge_pte), + HPAGE_PMD_SIZE/PAGE_SIZE); + spin_unlock(ptl); + return 0; } - if (l != mm->map_count) - tail_vma = NULL; /* After gate vma */ + if (pmd_trans_unstable(pmd)) + return 0; + orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + do { + struct page *page = can_gather_numa_stats(*pte, md->vma, addr); + if (!page) + continue; + gather_stats(page, md, pte_dirty(*pte), 1); -out: - if (vma) - return vma; + } while (pte++, addr += PAGE_SIZE, addr != end); + pte_unmap_unlock(orig_pte, ptl); + return 0; +} +#ifdef CONFIG_HUGETLB_PAGE +static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, struct mm_walk *walk) +{ + struct numa_maps *md; + struct page *page; - /* End of vmas has been reached */ - m->version = (tail_vma != NULL)? 0: -1UL; - up_read(&mm->mmap_sem); - mmput(mm); - return tail_vma; + if (!pte_present(*pte)) + return 0; + + page = pte_page(*pte); + if (!page) + return 0; + + md = walk->private; + gather_stats(page, md, pte_dirty(*pte), 1); + return 0; } -static void m_stop(struct seq_file *m, void *v) +#else +static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct task_struct *task = m->private; + return 0; +} +#endif + +/* + * Display pages allocated per node and memory policy via /proc. + */ +static int show_numa_map(struct seq_file *m, void *v, int is_pid) +{ + struct numa_maps_private *numa_priv = m->private; + struct proc_maps_private *proc_priv = &numa_priv->proc_maps; struct vm_area_struct *vma = v; - if (vma && vma != get_gate_vma(task)) { - struct mm_struct *mm = vma->vm_mm; - up_read(&mm->mmap_sem); - mmput(mm); + struct numa_maps *md = &numa_priv->md; + struct file *file = vma->vm_file; + struct task_struct *task = proc_priv->task; + struct mm_struct *mm = vma->vm_mm; + struct mm_walk walk = {}; + struct mempolicy *pol; + char buffer[64]; + int nid; + + if (!mm) + return 0; + + /* Ensure we start with an empty set of numa_maps statistics. */ + memset(md, 0, sizeof(*md)); + + md->vma = vma; + + walk.hugetlb_entry = gather_hugetbl_stats; + walk.pmd_entry = gather_pte_stats; + walk.private = md; + walk.mm = mm; + + pol = get_vma_policy(task, vma, vma->vm_start); + mpol_to_str(buffer, sizeof(buffer), pol); + mpol_cond_put(pol); + + seq_printf(m, "%08lx %s", vma->vm_start, buffer); + + if (file) { + seq_puts(m, " file="); + seq_path(m, &file->f_path, "\n\t= "); + } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { + seq_puts(m, " heap"); + } else { + pid_t tid = vm_is_stack(task, vma, is_pid); + if (tid != 0) { + /* + * Thread stack in /proc/PID/task/TID/maps or + * the main process stack. + */ + if (!is_pid || (vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack)) + seq_puts(m, " stack"); + else + seq_printf(m, " stack:%d", tid); + } } + + if (is_vm_hugetlb_page(vma)) + seq_puts(m, " huge"); + + walk_page_range(vma->vm_start, vma->vm_end, &walk); + + if (!md->pages) + goto out; + + if (md->anon) + seq_printf(m, " anon=%lu", md->anon); + + if (md->dirty) + seq_printf(m, " dirty=%lu", md->dirty); + + if (md->pages != md->anon && md->pages != md->dirty) + seq_printf(m, " mapped=%lu", md->pages); + + if (md->mapcount_max > 1) + seq_printf(m, " mapmax=%lu", md->mapcount_max); + + if (md->swapcache) + seq_printf(m, " swapcache=%lu", md->swapcache); + + if (md->active < md->pages && !is_vm_hugetlb_page(vma)) + seq_printf(m, " active=%lu", md->active); + + if (md->writeback) + seq_printf(m, " writeback=%lu", md->writeback); + + for_each_node_state(nid, N_MEMORY) + if (md->node[nid]) + seq_printf(m, " N%d=%lu", nid, md->node[nid]); +out: + seq_putc(m, '\n'); + + if (m->count < m->size) + m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0; + return 0; } -static void *m_next(struct seq_file *m, void *v, loff_t *pos) +static int show_pid_numa_map(struct seq_file *m, void *v) { - struct task_struct *task = m->private; - struct vm_area_struct *vma = v; - struct vm_area_struct *tail_vma = get_gate_vma(task); + return show_numa_map(m, v, 1); +} - (*pos)++; - if (vma && (vma != tail_vma) && vma->vm_next) - return vma->vm_next; - m_stop(m, v); - return (vma != tail_vma)? tail_vma: NULL; +static int show_tid_numa_map(struct seq_file *m, void *v) +{ + return show_numa_map(m, v, 0); } -struct seq_operations proc_pid_maps_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_map +static const struct seq_operations proc_pid_numa_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_pid_numa_map, }; -struct seq_operations proc_pid_smaps_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_smap +static const struct seq_operations proc_tid_numa_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_tid_numa_map, }; -#ifdef CONFIG_NUMA -extern int show_numa_map(struct seq_file *m, void *v); +static int numa_maps_open(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + struct numa_maps_private *priv; + int ret = -ENOMEM; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + priv->proc_maps.pid = proc_pid(inode); + ret = seq_open(file, ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = priv; + } else { + kfree(priv); + } + } + return ret; +} -struct seq_operations proc_pid_numa_maps_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_numa_map +static int pid_numa_maps_open(struct inode *inode, struct file *file) +{ + return numa_maps_open(inode, file, &proc_pid_numa_maps_op); +} + +static int tid_numa_maps_open(struct inode *inode, struct file *file) +{ + return numa_maps_open(inode, file, &proc_tid_numa_maps_op); +} + +const struct file_operations proc_pid_numa_maps_operations = { + .open = pid_numa_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, }; -#endif + +const struct file_operations proc_tid_numa_maps_operations = { + .open = tid_numa_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; +#endif /* CONFIG_NUMA */ diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 8f68827ed10..678455d2d68 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -1,37 +1,48 @@ #include <linux/mm.h> #include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/mount.h> +#include <linux/ptrace.h> +#include <linux/slab.h> #include <linux/seq_file.h> #include "internal.h" /* * Logic: we've got two memory sums for each process, "shared", and - * "non-shared". Shared memory may get counted more then once, for + * "non-shared". Shared memory may get counted more than once, for * each process that owns it. Non-shared memory is counted * accurately. */ -char *task_mem(struct mm_struct *mm, char *buffer) +void task_mem(struct seq_file *m, struct mm_struct *mm) { - struct vm_list_struct *vml; - unsigned long bytes = 0, sbytes = 0, slack = 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 (vml = mm->context.vmlist; vml; vml = vml->next) { - if (!vml->vma) - continue; + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + + bytes += kobjsize(vma); + + region = vma->vm_region; + if (region) { + size = kobjsize(region); + size += region->vm_end - region->vm_start; + } else { + size = vma->vm_end - vma->vm_start; + } - bytes += kobjsize(vml); if (atomic_read(&mm->mm_count) > 1 || - atomic_read(&vml->vma->vm_usage) > 1 - ) { - sbytes += kobjsize((void *) vml->vma->vm_start); - sbytes += kobjsize(vml->vma); + vma->vm_flags & VM_MAYSHARE) { + sbytes += size; } else { - bytes += kobjsize((void *) vml->vma->vm_start); - bytes += kobjsize(vml->vma); - slack += kobjsize((void *) vml->vma->vm_start) - - (vml->vma->vm_end - vml->vma->vm_start); + bytes += size; + if (region) + slack = region->vm_end - vma->vm_end; } } @@ -40,7 +51,7 @@ char *task_mem(struct mm_struct *mm, char *buffer) else bytes += kobjsize(mm); - if (current->fs && atomic_read(¤t->fs->count) > 1) + if (current->fs && current->fs->users > 1) sbytes += kobjsize(current->fs); else bytes += kobjsize(current->fs); @@ -57,108 +68,244 @@ char *task_mem(struct mm_struct *mm, char *buffer) bytes += kobjsize(current); /* includes kernel stack */ - buffer += sprintf(buffer, + seq_printf(m, "Mem:\t%8lu bytes\n" "Slack:\t%8lu bytes\n" "Shared:\t%8lu bytes\n", bytes, slack, sbytes); up_read(&mm->mmap_sem); - return buffer; } unsigned long task_vsize(struct mm_struct *mm) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long vsize = 0; down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - if (tbp->vma) - vsize += kobjsize((void *) tbp->vma->vm_start); + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + vsize += vma->vm_end - vma->vm_start; } up_read(&mm->mmap_sem); return vsize; } -int task_statm(struct mm_struct *mm, int *shared, int *text, - int *data, int *resident) +unsigned long task_statm(struct mm_struct *mm, + unsigned long *shared, unsigned long *text, + unsigned long *data, unsigned long *resident) { - struct vm_list_struct *tbp; - int size = kobjsize(mm); + struct vm_area_struct *vma; + struct vm_region *region; + struct rb_node *p; + unsigned long size = kobjsize(mm); down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - size += kobjsize(tbp); - if (tbp->vma) { - size += kobjsize(tbp->vma); - size += kobjsize((void *) tbp->vma->vm_start); + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + size += kobjsize(vma); + region = vma->vm_region; + if (region) { + size += kobjsize(region); + size += region->vm_end - region->vm_start; } } - size += (*text = mm->end_code - mm->start_code); - size += (*data = mm->start_stack - mm->start_data); + *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) + >> PAGE_SHIFT; + *data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK)) + >> PAGE_SHIFT; up_read(&mm->mmap_sem); + size >>= PAGE_SHIFT; + size += *text + *data; *resident = size; return size; } -int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +/* + * display a single VMA to a sequenced file + */ +static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, + int is_pid) { - struct vm_list_struct *vml; - struct vm_area_struct *vma; - struct task_struct *task = proc_task(inode); - struct mm_struct *mm = get_task_mm(task); - int result = -ENOENT; + struct mm_struct *mm = vma->vm_mm; + struct proc_maps_private *priv = m->private; + unsigned long ino = 0; + struct file *file; + dev_t dev = 0; + int flags; + unsigned long long pgoff = 0; - if (!mm) - goto out; - down_read(&mm->mmap_sem); + flags = vma->vm_flags; + file = vma->vm_file; - vml = mm->context.vmlist; - vma = NULL; - while (vml) { - if ((vml->vma->vm_flags & VM_EXECUTABLE) && vml->vma->vm_file) { - vma = vml->vma; - break; - } - vml = vml->next; + if (file) { + struct inode *inode = file_inode(vma->vm_file); + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT; } - if (vma) { - *mnt = mntget(vma->vm_file->f_vfsmnt); - *dentry = dget(vma->vm_file->f_dentry); - result = 0; + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); + seq_printf(m, + "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", + vma->vm_start, + vma->vm_end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', + pgoff, + MAJOR(dev), MINOR(dev), ino); + + if (file) { + seq_pad(m, ' '); + seq_path(m, &file->f_path, ""); + } else if (mm) { + pid_t tid = vm_is_stack(priv->task, vma, is_pid); + + if (tid != 0) { + seq_pad(m, ' '); + /* + * Thread stack in /proc/PID/task/TID/maps or + * the main process stack. + */ + if (!is_pid || (vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack)) + seq_printf(m, "[stack]"); + else + seq_printf(m, "[stack:%d]", tid); + } } - up_read(&mm->mmap_sem); - mmput(mm); -out: - return result; + seq_putc(m, '\n'); + return 0; } /* - * Albert D. Cahalan suggested to fake entries for the traditional - * sections here. This might be worth investigating. + * display mapping lines for a particular process's /proc/pid/maps */ -static int show_map(struct seq_file *m, void *v) +static int show_map(struct seq_file *m, void *_p, int is_pid) { - return 0; + struct rb_node *p = _p; + + return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb), + is_pid); +} + +static int show_pid_map(struct seq_file *m, void *_p) +{ + return show_map(m, _p, 1); } + +static int show_tid_map(struct seq_file *m, void *_p) +{ + return show_map(m, _p, 0); +} + 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; + + /* pin the task and mm whilst we play with them */ + priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + if (!priv->task) + return ERR_PTR(-ESRCH); + + mm = mm_access(priv->task, PTRACE_MODE_READ); + if (!mm || IS_ERR(mm)) { + put_task_struct(priv->task); + priv->task = NULL; + return mm; + } + down_read(&mm->mmap_sem); + + /* start from the Nth VMA */ + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) + if (n-- == 0) + return p; return NULL; } -static void m_stop(struct seq_file *m, void *v) + +static void m_stop(struct seq_file *m, void *_vml) { + struct proc_maps_private *priv = m->private; + + if (priv->task) { + struct mm_struct *mm = priv->task->mm; + up_read(&mm->mmap_sem); + mmput(mm); + put_task_struct(priv->task); + } } -static void *m_next(struct seq_file *m, void *v, loff_t *pos) + +static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - return NULL; + struct rb_node *p = _p; + + (*pos)++; + return p ? rb_next(p) : NULL; } -struct seq_operations proc_pid_maps_op = { + +static const struct seq_operations proc_pid_maps_ops = { .start = m_start, .next = m_next, .stop = m_stop, - .show = show_map + .show = show_pid_map +}; + +static const struct seq_operations proc_tid_maps_ops = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_tid_map +}; + +static int maps_open(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + struct proc_maps_private *priv; + int ret = -ENOMEM; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + priv->pid = proc_pid(inode); + ret = seq_open(file, ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = priv; + } else { + kfree(priv); + } + } + return ret; +} + +static int pid_maps_open(struct inode *inode, struct file *file) +{ + return maps_open(inode, file, &proc_pid_maps_ops); +} + +static int tid_maps_open(struct inode *inode, struct file *file) +{ + return maps_open(inode, file, &proc_tid_maps_ops); +} + +const struct file_operations proc_pid_maps_operations = { + .open = pid_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, }; + +const struct file_operations proc_tid_maps_operations = { + .open = tid_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c new file mode 100644 index 00000000000..33de567c25a --- /dev/null +++ b/fs/proc/uptime.c @@ -0,0 +1,52 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/time.h> +#include <linux/kernel_stat.h> +#include <linux/cputime.h> + +static int uptime_proc_show(struct seq_file *m, void *v) +{ + struct timespec uptime; + struct timespec idle; + u64 idletime; + u64 nsec; + u32 rem; + int i; + + idletime = 0; + for_each_possible_cpu(i) + idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; + + get_monotonic_boottime(&uptime); + nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC; + idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + idle.tv_nsec = rem; + seq_printf(m, "%lu.%02lu %lu.%02lu\n", + (unsigned long) uptime.tv_sec, + (uptime.tv_nsec / (NSEC_PER_SEC / 100)), + (unsigned long) idle.tv_sec, + (idle.tv_nsec / (NSEC_PER_SEC / 100))); + return 0; +} + +static int uptime_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, uptime_proc_show, NULL); +} + +static const struct file_operations uptime_proc_fops = { + .open = uptime_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_uptime_init(void) +{ + proc_create("uptime", 0, NULL, &uptime_proc_fops); + return 0; +} +fs_initcall(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c new file mode 100644 index 00000000000..d2154eb6d78 --- /dev/null +++ b/fs/proc/version.c @@ -0,0 +1,34 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/utsname.h> + +static int version_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, linux_proc_banner, + utsname()->sysname, + utsname()->release, + utsname()->version); + return 0; +} + +static int version_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, version_proc_show, NULL); +} + +static const struct file_operations version_proc_fops = { + .open = version_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_version_init(void) +{ + proc_create("version", 0, NULL, &version_proc_fops); + return 0; +} +fs_initcall(proc_version_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 4063fb32f78..382aa890e22 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -7,20 +7,24 @@ * */ -#include <linux/config.h> #include <linux/mm.h> -#include <linux/proc_fs.h> +#include <linux/kcore.h> #include <linux/user.h> -#include <linux/a.out.h> #include <linux/elf.h> #include <linux/elfcore.h> +#include <linux/export.h> +#include <linux/slab.h> #include <linux/highmem.h> +#include <linux/printk.h> #include <linux/bootmem.h> #include <linux/init.h> #include <linux/crash_dump.h> #include <linux/list.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> #include <asm/uaccess.h> #include <asm/io.h> +#include "internal.h" /* List representing chunks of contiguous memory areas and their offsets in * vmcore file. @@ -30,14 +34,55 @@ static LIST_HEAD(vmcore_list); /* Stores the pointer to the buffer containing kernel elf core headers. */ static char *elfcorebuf; static size_t elfcorebuf_sz; +static size_t elfcorebuf_sz_orig; + +static char *elfnotes_buf; +static size_t elfnotes_sz; /* Total size of vmcore file. */ static u64 vmcore_size; -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +static struct proc_dir_entry *proc_vmcore; -struct proc_dir_entry *proc_vmcore = NULL; +/* + * 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); + +int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)) +{ + if (oldmem_pfn_is_ram) + return -EBUSY; + oldmem_pfn_is_ram = fn; + return 0; +} +EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram); + +void unregister_oldmem_pfn_is_ram(void) +{ + oldmem_pfn_is_ram = NULL; + wmb(); +} +EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram); + +static int pfn_is_ram(unsigned long pfn) +{ + int (*fn)(unsigned long pfn); + /* pfn is ram unless fn() checks pagetype */ + int ret = 1; + + /* + * 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); + + return ret; +} /* Reads a page from the oldmem device from given offset. */ static ssize_t read_from_oldmem(char *buf, size_t count, @@ -52,8 +97,6 @@ static ssize_t read_from_oldmem(char *buf, size_t count, offset = (unsigned long)(*ppos % PAGE_SIZE); pfn = (unsigned long)(*ppos / PAGE_SIZE); - if (pfn > saved_max_pfn) - return -EINVAL; do { if (count > (PAGE_SIZE - offset)) @@ -61,9 +104,15 @@ static ssize_t read_from_oldmem(char *buf, size_t count, else nr_bytes = count; - tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - if (tmp < 0) - return tmp; + /* If pfn is not ram, return zeros for sparse dump files */ + if (pfn_is_ram(pfn) == 0) + memset(buf, 0, nr_bytes); + else { + tmp = copy_oldmem_page(pfn, buf, nr_bytes, + offset, userbuf); + if (tmp < 0) + return tmp; + } *ppos += nr_bytes; count -= nr_bytes; buf += nr_bytes; @@ -75,37 +124,70 @@ static ssize_t read_from_oldmem(char *buf, size_t count, return read; } -/* Maps vmcore file offset to respective physical address in memroy. */ -static u64 map_offset_to_paddr(loff_t offset, struct list_head *vc_list, - struct vmcore **m_ptr) +/* + * Architectures may override this function to allocate ELF header in 2nd kernel + */ +int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { - struct vmcore *m; - u64 paddr; + return 0; +} - list_for_each_entry(m, vc_list, list) { - u64 start, end; - start = m->offset; - end = m->offset + m->size - 1; - if (offset >= start && offset <= end) { - paddr = m->paddr + offset - start; - *m_ptr = m; - return paddr; - } +/* + * Architectures may override this function to free header + */ +void __weak elfcorehdr_free(unsigned long long addr) +{} + +/* + * Architectures may override this function to read from ELF header + */ +ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + return read_from_oldmem(buf, count, ppos, 0); +} + +/* + * Architectures may override this function to read from notes sections + */ +ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) +{ + return read_from_oldmem(buf, count, ppos, 0); +} + +/* + * Architectures may override this function to map oldmem + */ +int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + return remap_pfn_range(vma, from, pfn, size, prot); +} + +/* + * 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); } - *m_ptr = NULL; return 0; } /* 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(struct file *file, char __user *buffer, - size_t buflen, loff_t *fpos) +static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, + int userbuf) { ssize_t acc = 0, tmp; - size_t tsz, nr_bytes; + size_t tsz; u64 start; - struct vmcore *curr_m = NULL; + struct vmcore *m = NULL; if (buflen == 0 || *fpos >= vmcore_size) return 0; @@ -116,10 +198,8 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, /* Read ELF core header */ if (*fpos < elfcorebuf_sz) { - tsz = elfcorebuf_sz - *fpos; - if (buflen < tsz) - tsz = buflen; - if (copy_to_user(buffer, elfcorebuf + *fpos, tsz)) + tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen); + if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf)) return -EFAULT; buflen -= tsz; *fpos += tsz; @@ -131,157 +211,395 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, return acc; } - start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m); - if (!curr_m) - return -EINVAL; - if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen) - tsz = buflen; - - /* Calculate left bytes in current memory segment. */ - nr_bytes = (curr_m->size - (start - curr_m->paddr)); - if (tsz > nr_bytes) - tsz = nr_bytes; - - while (buflen) { - tmp = read_from_oldmem(buffer, tsz, &start, 1); - if (tmp < 0) - return tmp; + /* Read Elf note segment */ + if (*fpos < elfcorebuf_sz + elfnotes_sz) { + void *kaddr; + + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); + kaddr = elfnotes_buf + *fpos - elfcorebuf_sz; + if (copy_to(buffer, kaddr, tsz, userbuf)) + return -EFAULT; buflen -= tsz; *fpos += tsz; buffer += tsz; acc += tsz; - if (start >= (curr_m->paddr + curr_m->size)) { - if (curr_m->list.next == &vmcore_list) - return acc; /*EOF*/ - curr_m = list_entry(curr_m->list.next, - struct vmcore, list); - start = curr_m->paddr; + + /* leave now if filled buffer already */ + if (buflen == 0) + return acc; + } + + list_for_each_entry(m, &vmcore_list, list) { + if (*fpos < m->offset + m->size) { + tsz = min_t(size_t, m->offset + m->size - *fpos, buflen); + start = m->paddr + *fpos - m->offset; + tmp = read_from_oldmem(buffer, tsz, &start, userbuf); + if (tmp < 0) + return tmp; + buflen -= tsz; + *fpos += tsz; + buffer += tsz; + acc += tsz; + + /* leave now if filled buffer already */ + if (buflen == 0) + return acc; } - if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen) - tsz = buflen; - /* Calculate left bytes in current memory segment. */ - nr_bytes = (curr_m->size - (start - curr_m->paddr)); - if (tsz > nr_bytes) - tsz = nr_bytes; } + return acc; } -static int open_vmcore(struct inode *inode, struct file *filp) +static ssize_t read_vmcore(struct file *file, char __user *buffer, + size_t buflen, loff_t *fpos) +{ + return __read_vmcore((__force char *) buffer, buflen, fpos, 1); +} + +/* + * The vmcore fault handler uses the page cache and fills data using the + * standard __vmcore_read() function. + * + * On s390 the fault handler is used for memory regions that can't be mapped + * directly with remap_pfn_range(). + */ +static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { +#ifdef CONFIG_S390 + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t index = vmf->pgoff; + struct page *page; + loff_t offset; + char *buf; + int rc; + + page = find_or_create_page(mapping, index, GFP_KERNEL); + if (!page) + return VM_FAULT_OOM; + if (!PageUptodate(page)) { + offset = (loff_t) index << PAGE_CACHE_SHIFT; + buf = __va((page_to_pfn(page) << PAGE_SHIFT)); + rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0); + if (rc < 0) { + unlock_page(page); + page_cache_release(page); + return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS; + } + SetPageUptodate(page); + } + unlock_page(page); + vmf->page = page; return 0; +#else + return VM_FAULT_SIGBUS; +#endif } -struct file_operations proc_vmcore_operations = { - .read = read_vmcore, - .open = open_vmcore, +static const struct vm_operations_struct vmcore_mmap_ops = { + .fault = mmap_vmcore_fault, }; -static struct vmcore* __init get_new_element(void) +/** + * alloc_elfnotes_buf - allocate buffer for ELF note segment in + * vmalloc memory + * + * @notes_sz: 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(). + * + * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is + * disabled and there's no need to allow users to mmap the buffer. + */ +static inline char *alloc_elfnotes_buf(size_t notes_sz) { - struct vmcore *p; - - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (p) - memset(p, 0, sizeof(*p)); - return p; +#ifdef CONFIG_MMU + return vmalloc_user(notes_sz); +#else + return vzalloc(notes_sz); +#endif } -static u64 __init get_vmcore_size_elf64(char *elfptr) +/* + * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is + * essential for mmap_vmcore() in order to map physically + * non-contiguous objects (ELF header, ELF note segment and memory + * regions in the 1st kernel pointed to by PT_LOAD entries) into + * virtually contiguous user-space in ELF layout. + */ +#ifdef CONFIG_MMU +static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) { - int i; - u64 size; - Elf64_Ehdr *ehdr_ptr; - Elf64_Phdr *phdr_ptr; + size_t size = vma->vm_end - vma->vm_start; + u64 start, end, len, tsz; + struct vmcore *m; - ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); - size = sizeof(Elf64_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr)); - for (i = 0; i < ehdr_ptr->e_phnum; i++) { - size += phdr_ptr->p_memsz; - phdr_ptr++; + start = (u64)vma->vm_pgoff << PAGE_SHIFT; + end = start + size; + + if (size > vmcore_size || end > vmcore_size) + return -EINVAL; + + if (vma->vm_flags & (VM_WRITE | VM_EXEC)) + return -EPERM; + + vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); + vma->vm_flags |= VM_MIXEDMAP; + vma->vm_ops = &vmcore_mmap_ops; + + len = 0; + + if (start < elfcorebuf_sz) { + u64 pfn; + + tsz = min(elfcorebuf_sz - (size_t)start, size); + pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT; + if (remap_pfn_range(vma, vma->vm_start, pfn, tsz, + vma->vm_page_prot)) + return -EAGAIN; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; } - return size; + + if (start < elfcorebuf_sz + elfnotes_sz) { + void *kaddr; + + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); + kaddr = elfnotes_buf + start - elfcorebuf_sz; + if (remap_vmalloc_range_partial(vma, vma->vm_start + len, + kaddr, tsz)) + goto fail; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; + } + + list_for_each_entry(m, &vmcore_list, list) { + if (start < m->offset + m->size) { + u64 paddr = 0; + + tsz = min_t(size_t, m->offset + m->size - start, size); + paddr = m->paddr + start - m->offset; + if (remap_oldmem_pfn_range(vma, vma->vm_start + len, + paddr >> PAGE_SHIFT, tsz, + vma->vm_page_prot)) + goto fail; + size -= tsz; + start += tsz; + len += tsz; + + if (size == 0) + return 0; + } + } + + return 0; +fail: + do_munmap(vma->vm_mm, vma->vm_start, len); + return -EAGAIN; } +#else +static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) +{ + return -ENOSYS; +} +#endif + +static const struct file_operations proc_vmcore_operations = { + .read = read_vmcore, + .llseek = default_llseek, + .mmap = mmap_vmcore, +}; -static u64 __init get_vmcore_size_elf32(char *elfptr) +static struct vmcore* __init get_new_element(void) +{ + return kzalloc(sizeof(struct vmcore), GFP_KERNEL); +} + +static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz, + struct list_head *vc_list) { - int i; u64 size; - Elf32_Ehdr *ehdr_ptr; - Elf32_Phdr *phdr_ptr; + struct vmcore *m; - ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); - size = sizeof(Elf32_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr)); - for (i = 0; i < ehdr_ptr->e_phnum; i++) { - size += phdr_ptr->p_memsz; - phdr_ptr++; + size = elfsz + elfnotesegsz; + list_for_each_entry(m, vc_list, list) { + size += m->size; } return size; } -/* Merges all the PT_NOTE headers into one. */ -static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, - struct list_head *vc_list) +/** + * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry + * + * @ehdr_ptr: ELF header + * + * This function updates p_memsz member of each PT_NOTE entry in the + * program header table pointed to by @ehdr_ptr to real size of ELF + * note segment. + */ +static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) { - int i, nr_ptnote=0, rc=0; - char *tmp; - Elf64_Ehdr *ehdr_ptr; - Elf64_Phdr phdr, *phdr_ptr; + int i, rc=0; + Elf64_Phdr *phdr_ptr; Elf64_Nhdr *nhdr_ptr; - u64 phdr_sz = 0, note_off; - ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); + phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { - int j; void *notes_section; - struct vmcore *new; u64 offset, max_sz, sz, real_sz = 0; if (phdr_ptr->p_type != PT_NOTE) continue; - nr_ptnote++; max_sz = phdr_ptr->p_memsz; offset = phdr_ptr->p_offset; notes_section = kmalloc(max_sz, GFP_KERNEL); if (!notes_section) return -ENOMEM; - rc = read_from_oldmem(notes_section, max_sz, &offset, 0); + rc = elfcorehdr_read_notes(notes_section, max_sz, &offset); if (rc < 0) { kfree(notes_section); return rc; } nhdr_ptr = notes_section; - for (j = 0; j < max_sz; j += sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf64_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz); } - - /* Add this contiguous chunk of notes section to vmcore list.*/ - new = get_new_element(); - if (!new) { - kfree(notes_section); - return -ENOMEM; - } - new->paddr = phdr_ptr->p_offset; - new->size = real_sz; - list_add_tail(&new->list, vc_list); - phdr_sz += real_sz; kfree(notes_section); + phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + } + } + + return 0; +} + +/** + * get_note_number_and_size_elf64 - get the number of PT_NOTE program + * headers and sum of real size of their ELF note segment headers and + * data. + * + * @ehdr_ptr: ELF header + * @nr_ptnote: buffer for the number of PT_NOTE program headers + * @sz_ptnote: buffer for size of unique PT_NOTE program header + * + * This function is used to merge multiple PT_NOTE program headers + * into a unique single one. The resulting unique entry will have + * @sz_ptnote in its phdr->p_mem. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf64 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr, + int *nr_ptnote, u64 *sz_ptnote) +{ + int i; + Elf64_Phdr *phdr_ptr; + + *nr_ptnote = *sz_ptnote = 0; + + phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1); + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + if (phdr_ptr->p_type != PT_NOTE) + continue; + *nr_ptnote += 1; + *sz_ptnote += phdr_ptr->p_memsz; + } + + return 0; +} + +/** + * copy_notes_elf64 - copy ELF note segments in a given buffer + * + * @ehdr_ptr: ELF header + * @notes_buf: buffer into which ELF note segments are copied + * + * This function is used to copy ELF note segment in the 1st kernel + * into the buffer @notes_buf in the 2nd kernel. It is assumed that + * size of the buffer @notes_buf is equal to or larger than sum of the + * real ELF note segment headers and data. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf64 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf) +{ + int i, rc=0; + Elf64_Phdr *phdr_ptr; + + phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1); + + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 offset; + if (phdr_ptr->p_type != PT_NOTE) + continue; + offset = phdr_ptr->p_offset; + rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz, + &offset); + if (rc < 0) + return rc; + notes_buf += phdr_ptr->p_memsz; } + return 0; +} + +/* Merges all the PT_NOTE headers into one. */ +static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, + char **notes_buf, size_t *notes_sz) +{ + int i, nr_ptnote=0, rc=0; + char *tmp; + Elf64_Ehdr *ehdr_ptr; + Elf64_Phdr phdr; + u64 phdr_sz = 0, note_off; + + ehdr_ptr = (Elf64_Ehdr *)elfptr; + + rc = update_note_header_size_elf64(ehdr_ptr); + if (rc < 0) + return rc; + + rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz); + if (rc < 0) + return rc; + + *notes_sz = roundup(phdr_sz, PAGE_SIZE); + *notes_buf = alloc_elfnotes_buf(*notes_sz); + if (!*notes_buf) + return -ENOMEM; + + rc = copy_notes_elf64(ehdr_ptr, *notes_buf); + if (rc < 0) + return rc; + /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; note_off = sizeof(Elf64_Ehdr) + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr); - phdr.p_offset = note_off; + phdr.p_offset = roundup(note_off, PAGE_SIZE); phdr.p_vaddr = phdr.p_paddr = 0; phdr.p_filesz = phdr.p_memsz = phdr_sz; phdr.p_align = 0; @@ -295,6 +613,8 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, i = (nr_ptnote - 1) * sizeof(Elf64_Phdr); *elfsz = *elfsz - i; memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr))); + memset(elfptr + *elfsz, 0, i); + *elfsz = roundup(*elfsz, PAGE_SIZE); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -302,67 +622,170 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, return 0; } -/* Merges all the PT_NOTE headers into one. */ -static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, - struct list_head *vc_list) +/** + * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry + * + * @ehdr_ptr: ELF header + * + * This function updates p_memsz member of each PT_NOTE entry in the + * program header table pointed to by @ehdr_ptr to real size of ELF + * note segment. + */ +static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) { - int i, nr_ptnote=0, rc=0; - char *tmp; - Elf32_Ehdr *ehdr_ptr; - Elf32_Phdr phdr, *phdr_ptr; + int i, rc=0; + Elf32_Phdr *phdr_ptr; Elf32_Nhdr *nhdr_ptr; - u64 phdr_sz = 0, note_off; - ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); + phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { - int j; void *notes_section; - struct vmcore *new; u64 offset, max_sz, sz, real_sz = 0; if (phdr_ptr->p_type != PT_NOTE) continue; - nr_ptnote++; max_sz = phdr_ptr->p_memsz; offset = phdr_ptr->p_offset; notes_section = kmalloc(max_sz, GFP_KERNEL); if (!notes_section) return -ENOMEM; - rc = read_from_oldmem(notes_section, max_sz, &offset, 0); + rc = elfcorehdr_read_notes(notes_section, max_sz, &offset); if (rc < 0) { kfree(notes_section); return rc; } nhdr_ptr = notes_section; - for (j = 0; j < max_sz; j += sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf32_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz); } - - /* Add this contiguous chunk of notes section to vmcore list.*/ - new = get_new_element(); - if (!new) { - kfree(notes_section); - return -ENOMEM; - } - new->paddr = phdr_ptr->p_offset; - new->size = real_sz; - list_add_tail(&new->list, vc_list); - phdr_sz += real_sz; kfree(notes_section); + phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + } } + return 0; +} + +/** + * get_note_number_and_size_elf32 - get the number of PT_NOTE program + * headers and sum of real size of their ELF note segment headers and + * data. + * + * @ehdr_ptr: ELF header + * @nr_ptnote: buffer for the number of PT_NOTE program headers + * @sz_ptnote: buffer for size of unique PT_NOTE program header + * + * This function is used to merge multiple PT_NOTE program headers + * into a unique single one. The resulting unique entry will have + * @sz_ptnote in its phdr->p_mem. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf32 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr, + int *nr_ptnote, u64 *sz_ptnote) +{ + int i; + Elf32_Phdr *phdr_ptr; + + *nr_ptnote = *sz_ptnote = 0; + + phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1); + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + if (phdr_ptr->p_type != PT_NOTE) + continue; + *nr_ptnote += 1; + *sz_ptnote += phdr_ptr->p_memsz; + } + + return 0; +} + +/** + * copy_notes_elf32 - copy ELF note segments in a given buffer + * + * @ehdr_ptr: ELF header + * @notes_buf: buffer into which ELF note segments are copied + * + * This function is used to copy ELF note segment in the 1st kernel + * into the buffer @notes_buf in the 2nd kernel. It is assumed that + * size of the buffer @notes_buf is equal to or larger than sum of the + * real ELF note segment headers and data. + * + * It is assumed that program headers with PT_NOTE type pointed to by + * @ehdr_ptr has already been updated by update_note_header_size_elf32 + * and each of PT_NOTE program headers has actual ELF note segment + * size in its p_memsz member. + */ +static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf) +{ + int i, rc=0; + Elf32_Phdr *phdr_ptr; + + phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1); + + for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 offset; + if (phdr_ptr->p_type != PT_NOTE) + continue; + offset = phdr_ptr->p_offset; + rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz, + &offset); + if (rc < 0) + return rc; + notes_buf += phdr_ptr->p_memsz; + } + + return 0; +} + +/* Merges all the PT_NOTE headers into one. */ +static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, + char **notes_buf, size_t *notes_sz) +{ + int i, nr_ptnote=0, rc=0; + char *tmp; + Elf32_Ehdr *ehdr_ptr; + Elf32_Phdr phdr; + u64 phdr_sz = 0, note_off; + + ehdr_ptr = (Elf32_Ehdr *)elfptr; + + rc = update_note_header_size_elf32(ehdr_ptr); + if (rc < 0) + return rc; + + rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz); + if (rc < 0) + return rc; + + *notes_sz = roundup(phdr_sz, PAGE_SIZE); + *notes_buf = alloc_elfnotes_buf(*notes_sz); + if (!*notes_buf) + return -ENOMEM; + + rc = copy_notes_elf32(ehdr_ptr, *notes_buf); + if (rc < 0) + return rc; + /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; note_off = sizeof(Elf32_Ehdr) + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr); - phdr.p_offset = note_off; + phdr.p_offset = roundup(note_off, PAGE_SIZE); phdr.p_vaddr = phdr.p_paddr = 0; phdr.p_filesz = phdr.p_memsz = phdr_sz; phdr.p_align = 0; @@ -376,6 +799,8 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, i = (nr_ptnote - 1) * sizeof(Elf32_Phdr); *elfsz = *elfsz - i; memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr))); + memset(elfptr + *elfsz, 0, i); + *elfsz = roundup(*elfsz, PAGE_SIZE); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -387,6 +812,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, * the new offset fields of exported program headers. */ static int __init process_ptload_program_headers_elf64(char *elfptr, size_t elfsz, + size_t elfnotes_sz, struct list_head *vc_list) { int i; @@ -398,32 +824,38 @@ static int __init process_ptload_program_headers_elf64(char *elfptr, ehdr_ptr = (Elf64_Ehdr *)elfptr; phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */ - /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf64_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr) + - phdr_ptr->p_memsz; /* Note sections */ + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 paddr, start, end, size; + if (phdr_ptr->p_type != PT_LOAD) continue; + paddr = phdr_ptr->p_offset; + start = rounddown(paddr, PAGE_SIZE); + end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); + size = end - start; + /* Add this contiguous chunk of memory to vmcore list.*/ new = get_new_element(); if (!new) return -ENOMEM; - new->paddr = phdr_ptr->p_offset; - new->size = phdr_ptr->p_memsz; + new->paddr = start; + new->size = size; list_add_tail(&new->list, vc_list); /* Update the program header offset. */ - phdr_ptr->p_offset = vmcore_off; - vmcore_off = vmcore_off + phdr_ptr->p_memsz; + phdr_ptr->p_offset = vmcore_off + (paddr - start); + vmcore_off = vmcore_off + size; } return 0; } static int __init process_ptload_program_headers_elf32(char *elfptr, size_t elfsz, + size_t elfnotes_sz, struct list_head *vc_list) { int i; @@ -435,43 +867,44 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, ehdr_ptr = (Elf32_Ehdr *)elfptr; phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */ - /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf32_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr) + - phdr_ptr->p_memsz; /* Note sections */ + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { + u64 paddr, start, end, size; + if (phdr_ptr->p_type != PT_LOAD) continue; + paddr = phdr_ptr->p_offset; + start = rounddown(paddr, PAGE_SIZE); + end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE); + size = end - start; + /* Add this contiguous chunk of memory to vmcore list.*/ new = get_new_element(); if (!new) return -ENOMEM; - new->paddr = phdr_ptr->p_offset; - new->size = phdr_ptr->p_memsz; + new->paddr = start; + new->size = size; list_add_tail(&new->list, vc_list); /* Update the program header offset */ - phdr_ptr->p_offset = vmcore_off; - vmcore_off = vmcore_off + phdr_ptr->p_memsz; + phdr_ptr->p_offset = vmcore_off + (paddr - start); + vmcore_off = vmcore_off + size; } return 0; } /* Sets offset fields of vmcore elements. */ -static void __init set_vmcore_list_offsets_elf64(char *elfptr, - struct list_head *vc_list) +static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, + struct list_head *vc_list) { loff_t vmcore_off; - Elf64_Ehdr *ehdr_ptr; struct vmcore *m; - ehdr_ptr = (Elf64_Ehdr *)elfptr; - - /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf64_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr); + /* Skip Elf header, program headers and Elf note segment. */ + vmcore_off = elfsz + elfnotes_sz; list_for_each_entry(m, vc_list, list) { m->offset = vmcore_off; @@ -479,24 +912,12 @@ static void __init set_vmcore_list_offsets_elf64(char *elfptr, } } -/* Sets offset fields of vmcore elements. */ -static void __init set_vmcore_list_offsets_elf32(char *elfptr, - struct list_head *vc_list) +static void free_elfcorebuf(void) { - loff_t vmcore_off; - Elf32_Ehdr *ehdr_ptr; - struct vmcore *m; - - ehdr_ptr = (Elf32_Ehdr *)elfptr; - - /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf32_Ehdr) + - (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr); - - list_for_each_entry(m, vc_list, list) { - m->offset = vmcore_off; - vmcore_off += m->size; - } + free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig)); + elfcorebuf = NULL; + vfree(elfnotes_buf); + elfnotes_buf = NULL; } static int __init parse_crash_elf64_headers(void) @@ -508,51 +929,51 @@ static int __init parse_crash_elf64_headers(void) addr = elfcorehdr_addr; /* Read Elf header */ - rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0); + rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr); if (rc < 0) return rc; /* Do some basic Verification. */ if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 || (ehdr.e_type != ET_CORE) || - !elf_check_arch(&ehdr) || + !vmcore_elf64_check_arch(&ehdr) || ehdr.e_ident[EI_CLASS] != ELFCLASS64 || ehdr.e_ident[EI_VERSION] != EV_CURRENT || ehdr.e_version != EV_CURRENT || ehdr.e_ehsize != sizeof(Elf64_Ehdr) || ehdr.e_phentsize != sizeof(Elf64_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } /* Read in all elf headers. */ - elfcorebuf_sz = sizeof(Elf64_Ehdr) + ehdr.e_phnum * sizeof(Elf64_Phdr); - elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL); + elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) + + ehdr.e_phnum * sizeof(Elf64_Phdr); + elfcorebuf_sz = elfcorebuf_sz_orig; + elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(elfcorebuf_sz_orig)); if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); - if (rc < 0) { - kfree(elfcorebuf); - return rc; - } + rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr); + if (rc < 0) + goto fail; /* Merge all PT_NOTE headers into one. */ - rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } + rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, + &elfnotes_buf, &elfnotes_sz); + if (rc) + goto fail; rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz, - &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } - set_vmcore_list_offsets_elf64(elfcorebuf, &vmcore_list); + elfnotes_sz, &vmcore_list); + if (rc) + goto fail; + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); return 0; +fail: + free_elfcorebuf(); + return rc; } static int __init parse_crash_elf32_headers(void) @@ -564,7 +985,7 @@ static int __init parse_crash_elf32_headers(void) addr = elfcorehdr_addr; /* Read Elf header */ - rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0); + rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr); if (rc < 0) return rc; @@ -578,37 +999,36 @@ static int __init parse_crash_elf32_headers(void) ehdr.e_ehsize != sizeof(Elf32_Ehdr) || ehdr.e_phentsize != sizeof(Elf32_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } /* Read in all elf headers. */ - elfcorebuf_sz = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr); - elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL); + elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr); + elfcorebuf_sz = elfcorebuf_sz_orig; + elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(elfcorebuf_sz_orig)); if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); - if (rc < 0) { - kfree(elfcorebuf); - return rc; - } + rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr); + if (rc < 0) + goto fail; /* Merge all PT_NOTE headers into one. */ - rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } + rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, + &elfnotes_buf, &elfnotes_sz); + if (rc) + goto fail; rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz, - &vmcore_list); - if (rc) { - kfree(elfcorebuf); - return rc; - } - set_vmcore_list_offsets_elf32(elfcorebuf, &vmcore_list); + elfnotes_sz, &vmcore_list); + if (rc) + goto fail; + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); return 0; +fail: + free_elfcorebuf(); + return rc; } static int __init parse_crash_elf_headers(void) @@ -618,12 +1038,11 @@ static int __init parse_crash_elf_headers(void) int rc=0; addr = elfcorehdr_addr; - rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0); + rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr); if (rc < 0) return rc; if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) { - printk(KERN_WARNING "Warning: Core image elf header" - " not found\n"); + pr_warn("Warning: Core image elf header not found\n"); return -EINVAL; } @@ -631,21 +1050,19 @@ static int __init parse_crash_elf_headers(void) rc = parse_crash_elf64_headers(); if (rc) return rc; - - /* Determine vmcore size. */ - vmcore_size = get_vmcore_size_elf64(elfcorebuf); } else if (e_ident[EI_CLASS] == ELFCLASS32) { rc = parse_crash_elf32_headers(); if (rc) return rc; - - /* Determine vmcore size. */ - vmcore_size = get_vmcore_size_elf32(elfcorebuf); } else { - printk(KERN_WARNING "Warning: Core image elf header is not" - " sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } + + /* Determine vmcore size. */ + vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz, + &vmcore_list); + return 0; } @@ -654,18 +1071,48 @@ static int __init vmcore_init(void) { int rc = 0; - /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/ - if (!(elfcorehdr_addr < ELFCORE_ADDR_MAX)) + /* Allow architectures to allocate ELF header in 2nd kernel */ + rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size); + if (rc) + return rc; + /* + * If elfcorehdr= has been passed in cmdline or created in 2nd kernel, + * then capture the dump. + */ + if (!(is_vmcore_usable())) return rc; rc = parse_crash_elf_headers(); if (rc) { - printk(KERN_WARNING "Kdump: vmcore not initialized\n"); + pr_warn("Kdump: vmcore not initialized\n"); return rc; } + elfcorehdr_free(elfcorehdr_addr); + elfcorehdr_addr = ELFCORE_ADDR_ERR; - /* Initialize /proc/vmcore size if proc is already up. */ + proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); if (proc_vmcore) proc_vmcore->size = vmcore_size; return 0; } -module_init(vmcore_init) +fs_initcall(vmcore_init); + +/* Cleanup function for vmcore module. */ +void vmcore_cleanup(void) +{ + struct list_head *pos, *next; + + if (proc_vmcore) { + proc_remove(proc_vmcore); + proc_vmcore = NULL; + } + + /* clear the vmcore list. */ + list_for_each_safe(pos, next, &vmcore_list) { + struct vmcore *m; + + m = list_entry(pos, struct vmcore, list); + list_del(&m->list); + kfree(m); + } + free_elfcorebuf(); +} |