diff options
Diffstat (limited to '')
-rw-r--r-- | fs/proc/Kconfig | 1 | ||||
-rw-r--r-- | fs/proc/array.c | 17 | ||||
-rw-r--r-- | fs/proc/base.c | 105 | ||||
-rw-r--r-- | fs/proc/bootconfig.c | 2 | ||||
-rw-r--r-- | fs/proc/cpuinfo.c | 6 | ||||
-rw-r--r-- | fs/proc/devices.c | 6 | ||||
-rw-r--r-- | fs/proc/fd.c | 23 | ||||
-rw-r--r-- | fs/proc/generic.c | 9 | ||||
-rw-r--r-- | fs/proc/inode.c | 25 | ||||
-rw-r--r-- | fs/proc/internal.h | 12 | ||||
-rw-r--r-- | fs/proc/kcore.c | 14 | ||||
-rw-r--r-- | fs/proc/kmsg.c | 3 | ||||
-rw-r--r-- | fs/proc/loadavg.c | 6 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 14 | ||||
-rw-r--r-- | fs/proc/nommu.c | 1 | ||||
-rw-r--r-- | fs/proc/page.c | 4 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 39 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 164 | ||||
-rw-r--r-- | fs/proc/proc_tty.c | 2 | ||||
-rw-r--r-- | fs/proc/root.c | 8 | ||||
-rw-r--r-- | fs/proc/softirqs.c | 6 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 167 | ||||
-rw-r--r-- | fs/proc/task_nommu.c | 45 | ||||
-rw-r--r-- | fs/proc/uptime.c | 6 | ||||
-rw-r--r-- | fs/proc/version.c | 6 | ||||
-rw-r--r-- | fs/proc/vmcore.c | 184 | ||||
-rw-r--r-- | fs/proc_namespace.c | 4 |
27 files changed, 570 insertions, 309 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..32b1116ae137 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -92,6 +92,7 @@ config PROC_PAGE_MONITOR config PROC_CHILDREN bool "Include /proc/<pid>/task/<tid>/children file" + depends on PROC_FS default n help Provides a fast way to retrieve first level children pids of a task. See diff --git a/fs/proc/array.c b/fs/proc/array.c index ff869a66b34e..49283b8103c7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -69,7 +69,6 @@ #include <linux/sched/cputime.h> #include <linux/proc_fs.h> #include <linux/ioport.h> -#include <linux/uaccess.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/hugetlb.h> @@ -88,10 +87,10 @@ #include <linux/pid_namespace.h> #include <linux/prctl.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/string_helpers.h> #include <linux/user_namespace.h> #include <linux/fs_struct.h> +#include <linux/kthread.h> #include <asm/processor.h> #include "internal.h" @@ -100,8 +99,14 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char tcomm[64]; + /* + * Test before PF_KTHREAD because all workqueue worker threads are + * kernel threads. + */ if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); + else if (p->flags & PF_KTHREAD) + get_kthread_comm(tcomm, sizeof(tcomm), p); else __get_task_comm(tcomm, sizeof(tcomm), p); @@ -274,7 +279,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) collect_sigign_sigcatch(p, &ignored, &caught); num_threads = get_nr_threads(p); rcu_read_lock(); /* FIXME: is this correct? */ - qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); + qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); @@ -468,6 +473,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cgtime, gtime; unsigned long rsslim = 0; unsigned long flags; + int exit_code = task->exit_code; state = *get_task_state(task); vsize = eip = esp = 0; @@ -531,6 +537,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, maj_flt += sig->maj_flt; thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; + + if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) + exit_code = sig->group_exit_code; } sid = task_session_nr_ns(task, ns); @@ -630,7 +639,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_puts(m, " 0 0 0 0 0 0 0"); if (permitted) - seq_put_decimal_ll(m, " ", task->exit_code); + seq_put_decimal_ll(m, " ", exit_code); else seq_puts(m, " 0"); diff --git a/fs/proc/base.c b/fs/proc/base.c index 13eda8de2998..9e479d7d202b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -74,7 +74,6 @@ #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> @@ -670,10 +669,10 @@ static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, /************************************************************************/ /* permission checks */ -static int proc_fd_access_allowed(struct inode *inode) +static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; - int allowed = 0; + bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. @@ -1762,27 +1761,27 @@ out: return ERR_PTR(error); } -static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) +static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { - char *tmp = (char *)__get_free_page(GFP_KERNEL); + char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; - pathname = d_path(path, tmp, PAGE_SIZE); + pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; - len = tmp + PAGE_SIZE - 1 - pathname; + len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: - free_page((unsigned long)tmp); + kfree(tmp); return len; } @@ -1886,7 +1885,7 @@ void proc_pid_evict_inode(struct proc_inode *ei) put_pid(pid); } -struct inode *proc_pid_make_inode(struct super_block * sb, +struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; @@ -1915,11 +1914,6 @@ struct inode *proc_pid_make_inode(struct super_block * sb, /* Let the pid remember us for quick removal */ ei->pid = pid; - if (S_ISDIR(mode)) { - spin_lock(&pid->lock); - hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); - spin_unlock(&pid->lock); - } task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); @@ -1932,6 +1926,39 @@ out_unlock: return NULL; } +/* + * Generating an inode and adding it into @pid->inodes, so that task will + * invalidate inode's dentry before being released. + * + * This helper is used for creating dir-type entries under '/proc' and + * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' + * can be released by invalidating '/proc/<tgid>' dentry. + * In theory, dentries under '/proc/<tgid>/task' can also be released by + * invalidating '/proc/<tgid>' dentry, we reserve it to handle single + * thread exiting situation: Any one of threads should invalidate its + * '/proc/<tgid>/task/<pid>' dentry before released. + */ +static struct inode *proc_pid_make_base_inode(struct super_block *sb, + struct task_struct *task, umode_t mode) +{ + struct inode *inode; + struct proc_inode *ei; + struct pid *pid; + + inode = proc_pid_make_inode(sb, task, mode); + if (!inode) + return NULL; + + /* Let proc_flush_pid find this directory inode */ + ei = PROC_I(inode); + pid = ei->pid; + spin_lock(&pid->lock); + hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); + spin_unlock(&pid->lock); + + return inode; +} + int pid_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -2323,6 +2350,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; + struct vma_iterator vmi; genradix_init(&fa); @@ -2361,7 +2389,9 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) * routine might require mmap_lock taken in might_fault(). */ - for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { + pos = 2; + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) @@ -2701,7 +2731,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsm, - (char*)file->f_path.dentry->d_name.name, + file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) @@ -3155,6 +3185,35 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_KSM +static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct mm_struct *mm; + + mm = get_task_mm(task); + if (mm) { + seq_printf(m, "%lu\n", mm->ksm_merging_pages); + mmput(mm); + } + + return 0; +} +static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct mm_struct *mm; + + mm = get_task_mm(task); + if (mm) { + seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); + mmput(mm); + } + + return 0; +} +#endif /* CONFIG_KSM */ + #ifdef CONFIG_STACKLEAK_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) @@ -3286,6 +3345,10 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), + ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3351,7 +3414,8 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); @@ -3619,6 +3683,10 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), + ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3650,7 +3718,8 @@ static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c index 6d8d4bf20837..2e244ada1f97 100644 --- a/fs/proc/bootconfig.c +++ b/fs/proc/bootconfig.c @@ -32,6 +32,8 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size) int ret = 0; key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL); + if (!key) + return -ENOMEM; xbc_for_each_key_value(leaf, val) { ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 419760fd77bd..f38bda5b83ec 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -5,14 +5,10 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> -__weak void arch_freq_prepare_all(void) -{ -} - extern const struct seq_operations cpuinfo_op; + static int cpuinfo_open(struct inode *inode, struct file *file) { - arch_freq_prepare_all(); return seq_open(file, &cpuinfo_op); } diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 837971e74109..fe7bfcb7d049 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -4,6 +4,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/blkdev.h> +#include "internal.h" static int devinfo_show(struct seq_file *f, void *v) { @@ -54,7 +55,10 @@ static const struct seq_operations devinfo_ops = { static int __init proc_devices_init(void) { - proc_create_seq("devices", 0, NULL, &devinfo_ops); + struct proc_dir_entry *pde; + + pde = proc_create_seq("devices", 0, NULL, &devinfo_ops); + pde_make_permanent(pde); return 0; } fs_initcall(proc_devices_init); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 172c86270b31..913bef0d2a36 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -72,7 +72,7 @@ out: return 0; } -static int seq_fdinfo_open(struct inode *inode, struct file *file) +static int proc_fdinfo_access_allowed(struct inode *inode) { bool allowed = false; struct task_struct *task = get_proc_task(inode); @@ -86,6 +86,16 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file) if (!allowed) return -EACCES; + return 0; +} + +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + return single_open(file, seq_show, inode); } @@ -348,12 +358,23 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } +static int proc_open_fdinfo(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + + return 0; +} + const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { + .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5b78739e60e4..587b91d9d998 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -448,6 +448,9 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, proc_set_user(ent, (*parent)->uid, (*parent)->gid); ent->proc_dops = &proc_misc_dentry_ops; + /* Revalidate everything under /proc/${pid}/net */ + if ((*parent)->proc_dops == &proc_net_dentry_ops) + pde_force_lookup(ent); out: return ent; @@ -791,12 +794,6 @@ void proc_remove(struct proc_dir_entry *de) } EXPORT_SYMBOL(proc_remove); -void *PDE_DATA(const struct inode *inode) -{ - return __PDE_DATA(inode); -} -EXPORT_SYMBOL(PDE_DATA); - /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 599eb724ff2d..f495fdb39151 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -26,8 +26,6 @@ #include <linux/mount.h> #include <linux/bug.h> -#include <linux/uaccess.h> - #include "internal.h" static void proc_evict_inode(struct inode *inode) @@ -66,7 +64,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; - ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL); + ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL); if (!ei) return NULL; ei->pid = NULL; @@ -214,7 +212,15 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked on entry, unlocked on exit */ +/* + * At most 2 contexts can enter this function: the one doing the last + * close on the descriptor and whoever is deleting PDE itself. + * + * First to enter calls ->proc_release hook and signals its completion + * to the second one which waits and then does nothing. + * + * PDE is locked on entry, unlocked on exit. + */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) __releases(&pde->pde_unload_lock) { @@ -224,9 +230,6 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) * * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: * "struct file" needs to be available at the right moment. - * - * Therefore, first process to enter this function does ->release() and - * signals its completion to the other process which does nothing. */ if (pdeo->closing) { /* somebody else is doing that, just wait */ @@ -240,10 +243,12 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); + file = pdeo->file; pde->proc_ops->proc_release(file_inode(file), file); + spin_lock(&pde->pde_unload_lock); - /* After ->release. */ + /* Strictly after ->proc_release, see above. */ list_del(&pdeo->lh); c = pdeo->c; spin_unlock(&pde->pde_unload_lock); @@ -489,6 +494,9 @@ static int proc_reg_open(struct inode *inode, struct file *file) typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; + if (!pde->proc_ops->proc_lseek) + file->f_mode &= ~FMODE_LSEEK; + if (pde_is_permanent(pde)) { open = pde->proc_ops->proc_open; if (open) @@ -650,6 +658,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) return NULL; } + inode->i_private = de->data; inode->i_ino = de->low_ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); PROC_I(inode)->pde = de; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 03415f3fb3a8..b701d0207edf 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -79,6 +79,11 @@ static inline bool pde_is_permanent(const struct proc_dir_entry *pde) return pde->flags & PROC_ENTRY_PERMANENT; } +static inline void pde_make_permanent(struct proc_dir_entry *pde) +{ + pde->flags |= PROC_ENTRY_PERMANENT; +} + extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); @@ -115,11 +120,6 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) return PROC_I(inode)->pde; } -static inline void *__PDE_DATA(const struct inode *inode) -{ - return PDE(inode)->data; -} - static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; @@ -290,7 +290,7 @@ struct proc_maps_private { struct task_struct *task; struct mm_struct *mm; #ifdef CONFIG_MMU - struct vm_area_struct *tail_vma; + struct vma_iterator iter; #endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 982e694aae77..dff921f7ca33 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -479,10 +479,15 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) * the previous entry, search for a matching entry. */ if (!m || start < m->addr || start >= m->addr + m->size) { - list_for_each_entry(m, &kclist_head, list) { - if (start >= m->addr && - start < m->addr + m->size) + struct kcore_list *iter; + + m = NULL; + list_for_each_entry(iter, &kclist_head, list) { + if (start >= iter->addr && + start < iter->addr + iter->size) { + m = iter; break; + } } } @@ -492,12 +497,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) page_offline_freeze(); } - if (&m->list == &kclist_head) { + if (!m) { if (clear_user(buffer, tsz)) { ret = -EFAULT; goto out; } - m = NULL; /* skip the list anchor */ goto skip; } diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index b38ad552887f..2fc92a13f9f8 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -15,11 +15,8 @@ #include <linux/fs.h> #include <linux/syslog.h> -#include <linux/uaccess.h> #include <asm/io.h> -extern wait_queue_head_t log_wait; - static int kmsg_open(struct inode * inode, struct file * file) { return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC); diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index f32878d9a39f..817981e57223 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -9,6 +9,7 @@ #include <linux/seq_file.h> #include <linux/seqlock.h> #include <linux/time.h> +#include "internal.h" static int loadavg_proc_show(struct seq_file *m, void *v) { @@ -27,7 +28,10 @@ static int loadavg_proc_show(struct seq_file *m, void *v) static int __init proc_loadavg_init(void) { - proc_create_single("loadavg", 0, NULL, loadavg_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("loadavg", 0, NULL, loadavg_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6fa761c9cc78..5101131e6047 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -86,6 +86,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SwapTotal: ", i.totalswap); show_val_kb(m, "SwapFree: ", i.freeswap); +#ifdef CONFIG_ZSWAP + seq_printf(m, "Zswap: %8lu kB\n", + (unsigned long)(zswap_pool_total_size >> 10)); + seq_printf(m, "Zswapped: %8lu kB\n", + (unsigned long)atomic_read(&zswap_stored_pages) << + (PAGE_SHIFT - 10)); +#endif show_val_kb(m, "Dirty: ", global_node_page_state(NR_FILE_DIRTY)); show_val_kb(m, "Writeback: ", @@ -108,6 +115,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); + show_val_kb(m, "SecPageTables: ", + global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", @@ -155,7 +164,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) static int __init proc_meminfo_init(void) { - proc_create_single("meminfo", 0, NULL, meminfo_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("meminfo", 0, NULL, meminfo_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_meminfo_init); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 13452b32e2bd..4d3493579458 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -21,7 +21,6 @@ #include <linux/seq_file.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> -#include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/div64.h> #include "internal.h" diff --git a/fs/proc/page.c b/fs/proc/page.c index 9f1077d94cde..f2273b164535 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -10,6 +10,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/hugetlb.h> +#include <linux/memremap.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> @@ -90,6 +91,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, } static const struct proc_ops kpagecount_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpagecount_read, }; @@ -267,6 +269,7 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, } static const struct proc_ops kpageflags_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpageflags_read, }; @@ -321,6 +324,7 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, } static const struct proc_ops kpagecgroup_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, .proc_lseek = mem_lseek, .proc_read = kpagecgroup_read, }; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 15c2e55d2ed2..856839b8ae8b 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -8,9 +8,6 @@ * * proc net directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -61,15 +58,27 @@ static int seq_open_net(struct inode *inode, struct file *file) } #ifdef CONFIG_NET_NS p->net = net; + netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } +static void seq_file_net_put_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *priv = seq->private; + + put_net_track(priv->net, &priv->ns_tracker); +#else + put_net(&init_net); +#endif +} + static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; - put_net(seq_file_net(seq)); + seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } @@ -87,7 +96,8 @@ int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - p->net = get_net(current->nsproxy->net_ns); + p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, + GFP_KERNEL); #endif return 0; } @@ -97,7 +107,7 @@ void bpf_iter_fini_seq_net(void *priv_data) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - put_net(p->net); + put_net_track(p->net, &p->ns_tracker); #endif } @@ -125,7 +135,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -140,7 +150,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, @@ -217,7 +227,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -232,7 +242,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, @@ -340,6 +350,12 @@ static __net_init int proc_net_ns_init(struct net *net) kgid_t gid; int err; + /* + * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. + * Corresponding inode (PDE(inode) == net->proc_net) is never + * instantiated therefore blanket zeroing is fine. + * net->proc_net_stat inode is instantiated normally. + */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) @@ -363,6 +379,9 @@ static __net_init int proc_net_ns_init(struct net *net) proc_set_user(netd, uid, gid); + /* Seed dentry revalidation for /proc/${pid}/net */ + pde_force_lookup(netd); + err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5d66faecd4ef..48f2d60bd78a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -16,24 +16,38 @@ #include <linux/module.h> #include <linux/bpf-cgroup.h> #include <linux/mount.h> +#include <linux/kmemleak.h> #include "internal.h" +#define list_for_each_table_entry(entry, table) \ + for ((entry) = (table); (entry)->procname; (entry)++) + static const struct dentry_operations proc_sys_dentry_operations; static const struct file_operations proc_sys_file_operations; static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; -/* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, INT_MAX }; -EXPORT_SYMBOL(sysctl_vals); - /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { { } }; +/** + * register_sysctl_mount_point() - registers a sysctl mount point + * @path: path for the mount point + * + * Used to create a permanently empty directory to serve as mount point. + * There are some subtle but important permission checks this allows in the + * case of unprivileged mounts. + */ +struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return register_sysctl(path, sysctl_mount_point); +} +EXPORT_SYMBOL(register_sysctl_mount_point); + static bool is_empty_dir(struct ctl_table_header *head) { return head->ctl_table[0].child == sysctl_mount_point; @@ -163,7 +177,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else { pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - pr_cont("/%s\n", entry->procname); + pr_cont("%s\n", entry->procname); return -EEXIST; } } @@ -197,15 +211,19 @@ static void init_header(struct ctl_table_header *head, INIT_HLIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; - for (entry = table; entry->procname; entry++, node++) + + list_for_each_table_entry(entry, table) { node->header = head; + node++; + } } } static void erase_header(struct ctl_table_header *head) { struct ctl_table *entry; - for (entry = head->ctl_table; entry->procname; entry++) + + list_for_each_table_entry(entry, head->ctl_table) erase_entry(head, entry); } @@ -230,7 +248,7 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) err = insert_links(header); if (err) goto fail_links; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header->ctl_table) { err = insert_entry(header, entry); if (err) goto fail; @@ -960,7 +978,6 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set, table = (struct ctl_table *)(node + 1); new_name = (char *)(table + 2); memcpy(new_name, name, namelen); - new_name[namelen] = '\0'; table[0].procname = new_name; table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO; init_header(&new->header, set->dir.header.root, set, node, table); @@ -1020,8 +1037,8 @@ failed: if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - pr_cont("/%*.*s %ld\n", - namelen, namelen, name, PTR_ERR(subdir)); + pr_cont("%*.*s %ld\n", namelen, namelen, name, + PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); if (new) @@ -1053,7 +1070,6 @@ static int sysctl_follow_link(struct ctl_table_header **phead, struct ctl_dir *dir; int ret; - ret = 0; spin_lock(&sysctl_lock); root = (*pentry)->data; set = lookup_header_set(root); @@ -1113,35 +1129,36 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) static int sysctl_check_table(const char *path, struct ctl_table *table) { + struct ctl_table *entry; int err = 0; - for (; table->procname; table++) { - if (table->child) - err |= sysctl_err(path, table, "Not a file"); - - if ((table->proc_handler == proc_dostring) || - (table->proc_handler == proc_dointvec) || - (table->proc_handler == proc_douintvec) || - (table->proc_handler == proc_douintvec_minmax) || - (table->proc_handler == proc_dointvec_minmax) || - (table->proc_handler == proc_dou8vec_minmax) || - (table->proc_handler == proc_dointvec_jiffies) || - (table->proc_handler == proc_dointvec_userhz_jiffies) || - (table->proc_handler == proc_dointvec_ms_jiffies) || - (table->proc_handler == proc_doulongvec_minmax) || - (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { - if (!table->data) - err |= sysctl_err(path, table, "No data"); - if (!table->maxlen) - err |= sysctl_err(path, table, "No maxlen"); + list_for_each_table_entry(entry, table) { + if (entry->child) + err |= sysctl_err(path, entry, "Not a file"); + + if ((entry->proc_handler == proc_dostring) || + (entry->proc_handler == proc_dointvec) || + (entry->proc_handler == proc_douintvec) || + (entry->proc_handler == proc_douintvec_minmax) || + (entry->proc_handler == proc_dointvec_minmax) || + (entry->proc_handler == proc_dou8vec_minmax) || + (entry->proc_handler == proc_dointvec_jiffies) || + (entry->proc_handler == proc_dointvec_userhz_jiffies) || + (entry->proc_handler == proc_dointvec_ms_jiffies) || + (entry->proc_handler == proc_doulongvec_minmax) || + (entry->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { + if (!entry->data) + err |= sysctl_err(path, entry, "No data"); + if (!entry->maxlen) + err |= sysctl_err(path, entry, "No maxlen"); else - err |= sysctl_check_table_array(path, table); + err |= sysctl_check_table_array(path, entry); } - if (!table->proc_handler) - err |= sysctl_err(path, table, "No proc_handler"); + if (!entry->proc_handler) + err |= sysctl_err(path, entry, "No proc_handler"); - if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err |= sysctl_err(path, table, "bogus .mode 0%o", - table->mode); + if ((entry->mode & (S_IRUGO|S_IWUGO)) != entry->mode) + err |= sysctl_err(path, entry, "bogus .mode 0%o", + entry->mode); } return err; } @@ -1157,7 +1174,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table name_bytes = 0; nr_entries = 0; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { nr_entries++; name_bytes += strlen(entry->procname) + 1; } @@ -1174,14 +1191,16 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table node = (struct ctl_node *)(links + 1); link_table = (struct ctl_table *)(node + nr_entries); link_name = (char *)&link_table[nr_entries + 1]; + link = link_table; - for (link = link_table, entry = table; entry->procname; link++, entry++) { + list_for_each_table_entry(entry, table) { int len = strlen(entry->procname) + 1; memcpy(link_name, entry->procname, len); link->procname = link_name; link->mode = S_IFLNK|S_IRWXUGO; link->data = link_root; link_name += len; + link++; } init_header(links, dir->header.root, dir->header.set, node, link_table); links->nreg = nr_entries; @@ -1196,7 +1215,7 @@ static bool get_links(struct ctl_dir *dir, struct ctl_table *entry, *link; /* Are there links available for every entry in table? */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { const char *procname = entry->procname; link = find_entry(&head, dir, procname, strlen(procname)); if (!link) @@ -1209,7 +1228,7 @@ static bool get_links(struct ctl_dir *dir, } /* The checks passed. Increase the registration count on the links */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { const char *procname = entry->procname; link = find_entry(&head, dir, procname, strlen(procname)); head->nreg++; @@ -1220,7 +1239,7 @@ static bool get_links(struct ctl_dir *dir, static int insert_links(struct ctl_table_header *head) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; - struct ctl_dir *core_parent = NULL; + struct ctl_dir *core_parent; struct ctl_table_header *links; int err; @@ -1312,11 +1331,11 @@ struct ctl_table_header *__register_sysctl_table( struct ctl_node *node; int nr_entries = 0; - for (entry = table; entry->procname; entry++) + list_for_each_table_entry(entry, table) nr_entries++; header = kzalloc(sizeof(struct ctl_table_header) + - sizeof(struct ctl_node)*nr_entries, GFP_KERNEL); + sizeof(struct ctl_node)*nr_entries, GFP_KERNEL_ACCOUNT); if (!header) return NULL; @@ -1384,6 +1403,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init_bases(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; @@ -1407,7 +1458,7 @@ static int count_subheaders(struct ctl_table *table) if (!table || !table->procname) return 1; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { if (entry->child) nr_subheaders += count_subheaders(entry->child); else @@ -1426,7 +1477,7 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, int nr_dirs = 0; int err = -ENOMEM; - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { if (entry->child) nr_dirs++; else @@ -1443,7 +1494,9 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, goto out; ctl_table_arg = files; - for (new = files, entry = table; entry->procname; entry++) { + new = files; + + list_for_each_table_entry(entry, table) { if (entry->child) continue; *new = *entry; @@ -1467,7 +1520,7 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, } /* Recurse into the subdirectories. */ - for (entry = table; entry->procname; entry++) { + list_for_each_table_entry(entry, table) { char *child_pos; if (!entry->child) @@ -1597,6 +1650,15 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table *table) } EXPORT_SYMBOL(register_sysctl_table); +int __register_sysctl_base(struct ctl_table *base_table) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(base_table); + kmemleak_not_leak(hdr); + return 0; +} + static void put_links(struct ctl_table_header *header) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; @@ -1612,7 +1674,7 @@ static void put_links(struct ctl_table_header *header) if (IS_ERR(core_parent)) return; - for (entry = header->ctl_table; entry->procname; entry++) { + list_for_each_table_entry(entry, header->ctl_table) { struct ctl_table_header *link_head; struct ctl_table *link; const char *name = entry->procname; @@ -1626,7 +1688,7 @@ static void put_links(struct ctl_table_header *header) else { pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - pr_cont("/%s\n", name); + pr_cont("%s\n", name); } } } @@ -1710,7 +1772,7 @@ int __init proc_sys_init(void) proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; - return sysctl_init(); + return sysctl_init_bases(); } struct sysctl_alias { diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index c69ff191e5d8..5c6a5ceab2f1 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -4,8 +4,6 @@ * * Copyright 1997, Theodore Ts'o */ - -#include <linux/uaccess.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> diff --git a/fs/proc/root.c b/fs/proc/root.c index c7e3b1350ef8..3c2ee3eb1138 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -6,9 +6,6 @@ * * proc root directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -305,6 +302,11 @@ void __init proc_root_init(void) proc_mkdir("bus", NULL); proc_sys_init(); + /* + * Last things last. It is not like userspace processes eager + * to open /proc files exist at this point but register last + * anyway. + */ register_filesystem(&proc_fs_type); } diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 12901dcf57e2..f4616083faef 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -3,6 +3,7 @@ #include <linux/kernel_stat.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include "internal.h" /* * /proc/softirqs ... display the number of softirqs @@ -27,7 +28,10 @@ static int show_softirqs(struct seq_file *p, void *v) static int __init proc_softirqs_init(void) { - proc_create_single("softirqs", 0, NULL, show_softirqs); + struct proc_dir_entry *pde; + + pde = proc_create_single("softirqs", 0, NULL, show_softirqs); + pde_make_permanent(pde); return 0; } fs_initcall(proc_softirqs_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ad667dbc96f5..8a74cdcc9af0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/pagewalk.h> -#include <linux/vmacache.h> +#include <linux/mm_inline.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/mount.h> @@ -123,12 +123,26 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif +static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, + loff_t *ppos) +{ + struct vm_area_struct *vma = vma_next(&priv->iter); + + if (vma) { + *ppos = vma->vm_start; + } else { + *ppos = -2UL; + vma = get_gate_vma(priv->mm); + } + + return vma; +} + static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; unsigned long last_addr = *ppos; struct mm_struct *mm; - struct vm_area_struct *vma; /* See m_next(). Zero at the start or after lseek. */ if (last_addr == -1UL) @@ -152,31 +166,21 @@ static void *m_start(struct seq_file *m, loff_t *ppos) return ERR_PTR(-EINTR); } + vma_iter_init(&priv->iter, mm, last_addr); hold_task_mempolicy(priv); - priv->tail_vma = get_gate_vma(mm); - - vma = find_vma(mm, last_addr); - if (vma) - return vma; + if (last_addr == -2UL) + return get_gate_vma(mm); - return priv->tail_vma; + return proc_get_vma(priv, ppos); } static void *m_next(struct seq_file *m, void *v, loff_t *ppos) { - struct proc_maps_private *priv = m->private; - struct vm_area_struct *next, *vma = v; - - if (vma == priv->tail_vma) - next = NULL; - else if (vma->vm_next) - next = vma->vm_next; - else - next = priv->tail_vma; - - *ppos = next ? next->vm_start : -1UL; - - return next; + if (*ppos == -2UL) { + *ppos = -1UL; + return NULL; + } + return proc_get_vma(m->private, ppos); } static void m_stop(struct seq_file *m, void *v) @@ -308,6 +312,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { + struct anon_vma_name *anon_name; + if (!mm) { name = "[vdso]"; goto done; @@ -319,8 +325,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + anon_name = anon_vma_name(vma); + if (anon_name) { + seq_pad(m, ' '); + seq_printf(m, "[anon:%s]", anon_name->name); + } } done: @@ -395,6 +409,7 @@ struct mem_size_stats { u64 pss_anon; u64 pss_file; u64 pss_shmem; + u64 pss_dirty; u64 pss_locked; u64 swap_pss; }; @@ -416,6 +431,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, mss->pss_locked += pss; if (dirty || PageDirty(page)) { + mss->pss_dirty += pss; if (private) mss->private_dirty += size; else @@ -429,7 +445,8 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, } static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty, bool locked) + bool compound, bool young, bool dirty, bool locked, + bool migration) { int i, nr = compound ? compound_nr(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -456,8 +473,15 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * page_count(page) == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate * page_count(). + * + * The page_mapcount() is called to get a snapshot of the mapcount. + * Without holding the page lock this snapshot can be slightly wrong as + * we cannot always read the mapcount atomically. It is not safe to + * call page_mapcount() even with PTL held if the page is not mapped, + * especially for migration entries. Treat regular migration entries + * as mapcount == 1. */ - if (page_count(page) == 1) { + if ((page_count(page) == 1) || migration) { smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty, locked, true); return; @@ -506,9 +530,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -525,8 +552,11 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } else { mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; } - } else if (is_pfn_swap_entry(swpent)) + } else if (is_pfn_swap_entry(swpent)) { + if (is_migration_entry(swpent)) + migration = true; page = pfn_swap_entry_to_page(swpent); + } } else { smaps_pte_hole_lookup(addr, walk); return; @@ -535,7 +565,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -546,6 +576,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + bool migration = false; if (pmd_present(*pmd)) { /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -553,8 +584,10 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) { swp_entry_t entry = pmd_to_swp_entry(*pmd); - if (is_migration_entry(entry)) + if (is_migration_entry(entry)) { + migration = true; page = pfn_swap_entry_to_page(entry); + } } if (IS_ERR_OR_NULL(page)) return; @@ -566,7 +599,9 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else mss->file_thp += HPAGE_PMD_SIZE; - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); + + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), + locked, migration); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -779,6 +814,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Dirty: ", mss->pss_dirty >> PSS_SHIFT); if (rollup_mode) { /* * These are meaningful only for smaps_rollup, otherwise two of @@ -831,7 +867,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_active(vma)); + hugepage_vma_check(vma, vma->vm_flags, true, false, true)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -844,16 +880,16 @@ static int show_smaps_rollup(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; struct mem_size_stats mss; - struct mm_struct *mm; + struct mm_struct *mm = priv->mm; struct vm_area_struct *vma; - unsigned long last_vma_end = 0; + unsigned long vma_start = 0, last_vma_end = 0; int ret = 0; + MA_STATE(mas, &mm->mm_mt, 0, 0); priv->task = get_proc_task(priv->inode); if (!priv->task) return -ESRCH; - mm = priv->mm; if (!mm || !mmget_not_zero(mm)) { ret = -ESRCH; goto out_put_task; @@ -866,8 +902,13 @@ static int show_smaps_rollup(struct seq_file *m, void *v) goto out_put_mm; hold_task_mempolicy(priv); + vma = mas_find(&mas, ULONG_MAX); - for (vma = priv->mm->mmap; vma;) { + if (unlikely(!vma)) + goto empty_set; + + vma_start = vma->vm_start; + do { smap_gather_stats(vma, &mss, 0); last_vma_end = vma->vm_end; @@ -876,6 +917,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) * access it for write request. */ if (mmap_lock_is_contended(mm)) { + mas_pause(&mas); mmap_read_unlock(mm); ret = mmap_read_lock_killable(mm); if (ret) { @@ -919,7 +961,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) * contains last_vma_end. * Iterate VMA' from last_vma_end. */ - vma = find_vma(mm, last_vma_end - 1); + vma = mas_find(&mas, ULONG_MAX); /* Case 3 above */ if (!vma) break; @@ -933,11 +975,10 @@ static int show_smaps_rollup(struct seq_file *m, void *v) smap_gather_stats(vma, &mss, last_vma_end); } /* Case 2 above */ - vma = vma->vm_next; - } + } while ((vma = mas_find(&mas, ULONG_MAX)) != NULL); - show_vma_header_prefix(m, priv->mm->mmap->vm_start, - last_vma_end, 0, 0, 0, 0); +empty_set: + show_vma_header_prefix(m, vma_start, last_vma_end, 0, 0, 0, 0); seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); @@ -1230,6 +1271,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { + MA_STATE(mas, &mm->mm_mt, 0, 0); struct mmu_notifier_range range; struct clear_refs_private cp = { .type = type, @@ -1249,7 +1291,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } if (type == CLEAR_REFS_SOFT_DIRTY) { - for (vma = mm->mmap; vma; vma = vma->vm_next) { + mas_for_each(&mas, vma, ULONG_MAX) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; vma->vm_flags &= ~VM_SOFTDIRTY; @@ -1261,8 +1303,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, 0, NULL, mm, 0, -1UL); mmu_notifier_invalidate_range_start(&range); } - walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops, - &cp); + walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp); if (type == CLEAR_REFS_SOFT_DIRTY) { mmu_notifier_invalidate_range_end(&range); flush_tlb_mm(mm); @@ -1367,6 +1408,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, { u64 frame = 0, flags = 0; struct page *page = NULL; + bool migration = false; if (pte_present(pte)) { if (pm->show_pfn) @@ -1384,17 +1426,30 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pte_swp_uffd_wp(pte)) flags |= PM_UFFD_WP; entry = pte_to_swp_entry(pte); - if (pm->show_pfn) + if (pm->show_pfn) { + pgoff_t offset; + /* + * For PFN swap offsets, keeping the offset field + * to be PFN only to be compatible with old smaps. + */ + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + (offset << MAX_SWAPFILES_SHIFT); + } flags |= PM_SWAP; + migration = is_migration_entry(entry); if (is_pfn_swap_entry(entry)) page = pfn_swap_entry_to_page(entry); + if (pte_marker_entry_uffd_wp(entry)) + flags |= PM_UFFD_WP; } if (page && !PageAnon(page)) flags |= PM_FILE; - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; @@ -1410,8 +1465,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, spinlock_t *ptl; pte_t *pte, *orig_pte; int err = 0; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool migration = false; + ptl = pmd_trans_huge_lock(pmdp, vma); if (ptl) { u64 flags = 0, frame = 0; @@ -1439,7 +1495,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned long offset; if (pm->show_pfn) { - offset = swp_offset(entry) + + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); + offset = offset + ((addr & ~PMD_MASK) >> PAGE_SHIFT); frame = swp_type(entry) | (offset << MAX_SWAPFILES_SHIFT); @@ -1450,11 +1510,12 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, if (pmd_swp_uffd_wp(pmd)) flags |= PM_UFFD_WP; VM_BUG_ON(!is_pmd_migration_entry(pmd)); + migration = is_migration_entry(entry); page = pfn_swap_entry_to_page(entry); } #endif - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; for (; addr != end; addr += PAGE_SIZE) { @@ -1523,10 +1584,15 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, if (page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; + if (huge_pte_uffd_wp(pte)) + flags |= PM_UFFD_WP; + flags |= PM_PRESENT; if (pm->show_pfn) frame = pte_pfn(pte) + ((addr & ~hmask) >> PAGE_SHIFT); + } else if (pte_swp_uffd_wp_any(pte)) { + flags |= PM_UFFD_WP; } for (; addr != end; addr += PAGE_SIZE) { @@ -1564,7 +1630,8 @@ static const struct mm_walk_ops pagemap_ops = { * Bits 5-54 swap offset if swapped * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst) * Bit 56 page exclusively mapped - * Bits 57-60 zero + * Bit 57 pte is uffd-wp write-protected + * Bits 58-60 zero * Bit 61 page is file-page or shared-anon * Bit 62 page swapped * Bit 63 page present @@ -1751,7 +1818,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL; page = vm_normal_page(vma, addr, pte); - if (!page) + if (!page || is_zone_device_page(page)) return NULL; if (PageReserved(page)) @@ -1839,8 +1906,6 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, return 0; page = pte_page(huge_pte); - if (!page) - return 0; md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a6d21fc0033c..2fd06f52b6a4 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -20,15 +20,13 @@ */ void task_mem(struct seq_file *m, struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; struct vm_region *region; - struct rb_node *p; unsigned long bytes = 0, sbytes = 0, slack = 0, size; - - mmap_read_lock(mm); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + mmap_read_lock(mm); + for_each_vma(vmi, vma) { bytes += kobjsize(vma); region = vma->vm_region; @@ -82,15 +80,13 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long task_vsize(struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; - struct rb_node *p; unsigned long vsize = 0; mmap_read_lock(mm); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + for_each_vma(vmi, vma) vsize += vma->vm_end - vma->vm_start; - } mmap_read_unlock(mm); return vsize; } @@ -99,14 +95,13 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; struct vm_region *region; - struct rb_node *p; unsigned long size = kobjsize(mm); mmap_read_lock(mm); - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { - vma = rb_entry(p, struct vm_area_struct, vm_rb); + for_each_vma(vmi, vma) { size += kobjsize(vma); region = vma->vm_region; if (region) { @@ -190,17 +185,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) */ static int show_map(struct seq_file *m, void *_p) { - struct rb_node *p = _p; - - return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb)); + return nommu_vma_show(m, _p); } static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_maps_private *priv = m->private; struct mm_struct *mm; - struct rb_node *p; - loff_t n = *pos; + struct vm_area_struct *vma; + unsigned long addr = *pos; + + /* See m_next(). Zero at the start or after lseek. */ + if (addr == -1UL) + return NULL; /* pin the task and mm whilst we play with them */ priv->task = get_proc_task(priv->inode); @@ -216,10 +213,10 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EINTR); } - /* start from the Nth VMA */ - for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) - if (n-- == 0) - return p; + /* start the next element from addr */ + vma = find_vma(mm, addr); + if (vma) + return vma; mmap_read_unlock(mm); mmput(mm); @@ -242,10 +239,10 @@ static void m_stop(struct seq_file *m, void *_vml) static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - struct rb_node *p = _p; + struct vm_area_struct *vma = _p; - (*pos)++; - return p ? rb_next(p) : NULL; + *pos = vma->vm_end; + return find_vma(vma->vm_mm, vma->vm_end); } static const struct seq_operations proc_pid_maps_ops = { diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index deb99bc9b7e6..b5343d209381 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -7,6 +7,7 @@ #include <linux/time.h> #include <linux/time_namespace.h> #include <linux/kernel_stat.h> +#include "internal.h" static int uptime_proc_show(struct seq_file *m, void *v) { @@ -39,7 +40,10 @@ static int uptime_proc_show(struct seq_file *m, void *v) static int __init proc_uptime_init(void) { - proc_create_single("uptime", 0, NULL, uptime_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("uptime", 0, NULL, uptime_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c index b449f186577f..02e3c3cd4a9a 100644 --- a/fs/proc/version.c +++ b/fs/proc/version.c @@ -5,6 +5,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/utsname.h> +#include "internal.h" static int version_proc_show(struct seq_file *m, void *v) { @@ -17,7 +18,10 @@ static int version_proc_show(struct seq_file *m, void *v) static int __init proc_version_init(void) { - proc_create_single("version", 0, NULL, version_proc_show); + struct proc_dir_entry *pde; + + pde = proc_create_single("version", 0, NULL, version_proc_show); + pde_make_permanent(pde); return 0; } fs_initcall(proc_version_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 509f85148fee..f2aa86c421f2 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -25,7 +25,7 @@ #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> -#include <linux/uaccess.h> +#include <linux/uio.h> #include <linux/cc_platform.h> #include <asm/io.h> #include "internal.h" @@ -62,18 +62,17 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0); /* Device Dump Size */ static size_t vmcoredd_orig_sz; -static DECLARE_RWSEM(vmcore_cb_rwsem); +static DEFINE_SPINLOCK(vmcore_cb_lock); +DEFINE_STATIC_SRCU(vmcore_cb_srcu); /* List of registered vmcore callbacks. */ static LIST_HEAD(vmcore_cb_list); -/* Whether we had a surprise unregistration of a callback. */ -static bool vmcore_cb_unstable; /* Whether the vmcore has been opened once. */ static bool vmcore_opened; void register_vmcore_cb(struct vmcore_cb *cb) { - down_write(&vmcore_cb_rwsem); INIT_LIST_HEAD(&cb->next); + spin_lock(&vmcore_cb_lock); list_add_tail(&cb->next, &vmcore_cb_list); /* * Registering a vmcore callback after the vmcore was opened is @@ -81,24 +80,24 @@ void register_vmcore_cb(struct vmcore_cb *cb) */ if (vmcore_opened) pr_warn_once("Unexpected vmcore callback registration\n"); - up_write(&vmcore_cb_rwsem); + spin_unlock(&vmcore_cb_lock); } EXPORT_SYMBOL_GPL(register_vmcore_cb); void unregister_vmcore_cb(struct vmcore_cb *cb) { - down_write(&vmcore_cb_rwsem); - list_del(&cb->next); + spin_lock(&vmcore_cb_lock); + list_del_rcu(&cb->next); /* * Unregistering a vmcore callback after the vmcore was opened is * very unusual (e.g., forced driver removal), but we cannot stop * unregistering. */ - if (vmcore_opened) { + if (vmcore_opened) pr_warn_once("Unexpected vmcore callback unregistration\n"); - vmcore_cb_unstable = true; - } - up_write(&vmcore_cb_rwsem); + spin_unlock(&vmcore_cb_lock); + + synchronize_srcu(&vmcore_cb_srcu); } EXPORT_SYMBOL_GPL(unregister_vmcore_cb); @@ -107,11 +106,8 @@ static bool pfn_is_ram(unsigned long pfn) struct vmcore_cb *cb; bool ret = true; - lockdep_assert_held_read(&vmcore_cb_rwsem); - if (unlikely(vmcore_cb_unstable)) - return false; - - list_for_each_entry(cb, &vmcore_cb_list, next) { + list_for_each_entry_srcu(cb, &vmcore_cb_list, next, + srcu_read_lock_held(&vmcore_cb_srcu)) { if (unlikely(!cb->pfn_is_ram)) continue; ret = cb->pfn_is_ram(cb, pfn); @@ -124,21 +120,21 @@ static bool pfn_is_ram(unsigned long pfn) static int open_vmcore(struct inode *inode, struct file *file) { - down_read(&vmcore_cb_rwsem); + spin_lock(&vmcore_cb_lock); vmcore_opened = true; - up_read(&vmcore_cb_rwsem); + spin_unlock(&vmcore_cb_lock); return 0; } /* Reads a page from the oldmem device from given offset. */ -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { unsigned long pfn, offset; size_t nr_bytes; ssize_t read = 0, tmp; + int idx; if (!count) return 0; @@ -146,7 +142,7 @@ ssize_t read_from_oldmem(char *buf, size_t count, offset = (unsigned long)(*ppos % PAGE_SIZE); pfn = (unsigned long)(*ppos / PAGE_SIZE); - down_read(&vmcore_cb_rwsem); + idx = srcu_read_lock(&vmcore_cb_srcu); do { if (count > (PAGE_SIZE - offset)) nr_bytes = PAGE_SIZE - offset; @@ -155,35 +151,29 @@ ssize_t read_from_oldmem(char *buf, size_t count, /* If pfn is not ram, return zeros for sparse dump files */ if (!pfn_is_ram(pfn)) { - tmp = 0; - if (!userbuf) - memset(buf, 0, nr_bytes); - else if (clear_user(buf, nr_bytes)) - tmp = -EFAULT; + tmp = iov_iter_zero(nr_bytes, iter); } else { if (encrypted) - tmp = copy_oldmem_page_encrypted(pfn, buf, + tmp = copy_oldmem_page_encrypted(iter, pfn, nr_bytes, - offset, - userbuf); + offset); else - tmp = copy_oldmem_page(pfn, buf, nr_bytes, - offset, userbuf); + tmp = copy_oldmem_page(iter, pfn, nr_bytes, + offset); } - if (tmp < 0) { - up_read(&vmcore_cb_rwsem); - return tmp; + if (tmp < nr_bytes) { + srcu_read_unlock(&vmcore_cb_srcu, idx); + return -EFAULT; } *ppos += nr_bytes; count -= nr_bytes; - buf += nr_bytes; read += nr_bytes; ++pfn; offset = 0; } while (count); + srcu_read_unlock(&vmcore_cb_srcu, idx); - up_read(&vmcore_cb_rwsem); return read; } @@ -206,7 +196,12 @@ void __weak elfcorehdr_free(unsigned long long addr) */ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, false); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, false); } /* @@ -214,7 +209,13 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) */ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); + struct kvec kvec = { .iov_base = buf, .iov_len = count }; + struct iov_iter iter; + + iov_iter_kvec(&iter, READ, &kvec, 1, count); + + return read_from_oldmem(&iter, count, ppos, + cc_platform_has(CC_ATTR_MEM_ENCRYPT)); } /* @@ -231,29 +232,14 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, /* * Architectures which support memory encryption override this. */ -ssize_t __weak -copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, - unsigned long offset, int userbuf) -{ - return copy_oldmem_page(pfn, buf, csize, offset, userbuf); -} - -/* - * Copy to either kernel or user space - */ -static int copy_to(void *target, void *src, size_t size, int userbuf) +ssize_t __weak copy_oldmem_page_encrypted(struct iov_iter *iter, + unsigned long pfn, size_t csize, unsigned long offset) { - if (userbuf) { - if (copy_to_user((char __user *) target, src, size)) - return -EFAULT; - } else { - memcpy(target, src, size); - } - return 0; + return copy_oldmem_page(iter, pfn, csize, offset); } #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP -static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf) +static int vmcoredd_copy_dumps(struct iov_iter *iter, u64 start, size_t size) { struct vmcoredd_node *dump; u64 offset = 0; @@ -266,14 +252,13 @@ static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf) if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; - if (copy_to(dst, buf, tsz, userbuf)) { + if (copy_to_iter(buf, tsz, iter) < tsz) { ret = -EFAULT; goto out_unlock; } size -= tsz; start += tsz; - dst += tsz; /* Leave now if buffer filled already */ if (!size) @@ -329,33 +314,28 @@ out_unlock: /* Read from the ELF header and then the crash dump. On error, negative value is * returned otherwise number of bytes read are returned. */ -static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, - int userbuf) +static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) { ssize_t acc = 0, tmp; size_t tsz; u64 start; struct vmcore *m = NULL; - if (buflen == 0 || *fpos >= vmcore_size) + if (!iov_iter_count(iter) || *fpos >= vmcore_size) return 0; - /* trim buflen to not go beyond EOF */ - if (buflen > vmcore_size - *fpos) - buflen = vmcore_size - *fpos; + iov_iter_truncate(iter, vmcore_size - *fpos); /* Read ELF core header */ if (*fpos < elfcorebuf_sz) { - tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen); - if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf)) + tsz = min(elfcorebuf_sz - (size_t)*fpos, iov_iter_count(iter)); + if (copy_to_iter(elfcorebuf + *fpos, tsz, iter) < tsz) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } @@ -376,35 +356,32 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, /* Read device dumps */ if (*fpos < elfcorebuf_sz + vmcoredd_orig_sz) { tsz = min(elfcorebuf_sz + vmcoredd_orig_sz - - (size_t)*fpos, buflen); + (size_t)*fpos, iov_iter_count(iter)); start = *fpos - elfcorebuf_sz; - if (vmcoredd_copy_dumps(buffer, start, tsz, userbuf)) + if (vmcoredd_copy_dumps(iter, start, tsz)) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (!buflen) + if (!iov_iter_count(iter)) return acc; } #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ /* Read remaining elf notes */ - tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); + tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, + iov_iter_count(iter)); kaddr = elfnotes_buf + *fpos - elfcorebuf_sz - vmcoredd_orig_sz; - if (copy_to(buffer, kaddr, tsz, userbuf)) + if (copy_to_iter(kaddr, tsz, iter) < tsz) return -EFAULT; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } @@ -412,19 +389,17 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, if (*fpos < m->offset + m->size) { tsz = (size_t)min_t(unsigned long long, m->offset + m->size - *fpos, - buflen); + iov_iter_count(iter)); start = m->paddr + *fpos - m->offset; - tmp = read_from_oldmem(buffer, tsz, &start, - userbuf, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); + tmp = read_from_oldmem(iter, tsz, &start, + cc_platform_has(CC_ATTR_MEM_ENCRYPT)); if (tmp < 0) return tmp; - buflen -= tsz; *fpos += tsz; - buffer += tsz; acc += tsz; /* leave now if filled buffer already */ - if (buflen == 0) + if (!iov_iter_count(iter)) return acc; } } @@ -432,15 +407,14 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, return acc; } -static ssize_t read_vmcore(struct file *file, char __user *buffer, - size_t buflen, loff_t *fpos) +static ssize_t read_vmcore(struct kiocb *iocb, struct iov_iter *iter) { - return __read_vmcore((__force char *) buffer, buflen, fpos, 1); + return __read_vmcore(iter, &iocb->ki_pos); } /* * The vmcore fault handler uses the page cache and fills data using the - * standard __vmcore_read() function. + * standard __read_vmcore() function. * * On s390 the fault handler is used for memory regions that can't be mapped * directly with remap_pfn_range(). @@ -450,9 +424,10 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) #ifdef CONFIG_S390 struct address_space *mapping = vmf->vma->vm_file->f_mapping; pgoff_t index = vmf->pgoff; + struct iov_iter iter; + struct kvec kvec; struct page *page; loff_t offset; - char *buf; int rc; page = find_or_create_page(mapping, index, GFP_KERNEL); @@ -460,8 +435,11 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) return VM_FAULT_OOM; if (!PageUptodate(page)) { offset = (loff_t) index << PAGE_SHIFT; - buf = __va((page_to_pfn(page) << PAGE_SHIFT)); - rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0); + kvec.iov_base = page_address(page); + kvec.iov_len = PAGE_SIZE; + iov_iter_kvec(&iter, READ, &kvec, 1, PAGE_SIZE); + + rc = __read_vmcore(&iter, &offset); if (rc < 0) { unlock_page(page); put_page(page); @@ -483,7 +461,7 @@ static const struct vm_operations_struct vmcore_mmap_ops = { /** * vmcore_alloc_buf - allocate buffer in vmalloc memory - * @sizez: size of buffer + * @size: size of buffer * * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap * the buffer to user-space by means of remap_vmalloc_range(). @@ -574,18 +552,18 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot) { - int ret; + int ret, idx; /* - * Check if oldmem_pfn_is_ram was registered to avoid - * looping over all pages without a reason. + * Check if a callback was registered to avoid looping over all + * pages without a reason. */ - down_read(&vmcore_cb_rwsem); - if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable) + idx = srcu_read_lock(&vmcore_cb_srcu); + if (!list_empty(&vmcore_cb_list)) ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot); else ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot); - up_read(&vmcore_cb_rwsem); + srcu_read_unlock(&vmcore_cb_srcu, idx); return ret; } @@ -711,7 +689,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) static const struct proc_ops vmcore_proc_ops = { .proc_open = open_vmcore, - .proc_read = read_vmcore, + .proc_read_iter = read_vmcore, .proc_lseek = default_llseek, .proc_mmap = mmap_vmcore, }; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 392ef5162655..846f9455ae22 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -80,13 +80,13 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, fs_infop->str); } - if (mnt_user_ns(mnt) != &init_user_ns) + if (is_idmapped_mnt(mnt)) seq_puts(m, ",idmapped"); } static inline void mangle(struct seq_file *m, const char *s) { - seq_escape(m, s, " \t\n\\"); + seq_escape(m, s, " \t\n\\#"); } static void show_type(struct seq_file *m, struct super_block *sb) |