summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig19
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c103
-rw-r--r--fs/proc/fd.c14
-rw-r--r--fs/proc/generic.c28
-rw-r--r--fs/proc/inode.c10
-rw-r--r--fs/proc/internal.h73
-rw-r--r--fs/proc/kcore.c91
-rw-r--r--fs/proc/meminfo.c8
-rw-r--r--fs/proc/namespaces.c5
-rw-r--r--fs/proc/page.c202
-rw-r--r--fs/proc/proc_sysctl.c28
-rw-r--r--fs/proc/root.c10
-rw-r--r--fs/proc/task_mmu.c277
-rw-r--r--fs/proc/task_nommu.c4
-rw-r--r--fs/proc/vmcore.c293
16 files changed, 772 insertions, 395 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index d80a1431ef7b..6ae966c561e7 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -61,6 +61,25 @@ config PROC_VMCORE_DEVICE_DUMP
as ELF notes to /proc/vmcore. You can still disable device
dump using the kernel command line option 'novmcoredd'.
+config NEED_PROC_VMCORE_DEVICE_RAM
+ bool
+
+config PROC_VMCORE_DEVICE_RAM
+ def_bool y
+ depends on PROC_VMCORE && NEED_PROC_VMCORE_DEVICE_RAM
+ depends on VIRTIO_MEM
+ help
+ If the elfcore hdr is allocated and prepared by the dump kernel
+ ("2nd kernel") instead of the crashed kernel, RAM provided by memory
+ devices such as virtio-mem will not be included in the dump
+ image, because only the device driver can properly detect them.
+
+ With this config enabled, these RAM ranges will be queried from the
+ device drivers once the device gets probed, so they can be included
+ in the crash dump.
+
+ Relevant architectures should select NEED_PROC_VMCORE_DEVICE_RAM.
+
config PROC_SYSCTL
bool "Sysctl support (/proc/sys)" if EXPERT
depends on PROC_FS
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 55ed3510d2bb..d6a0369caa93 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -500,7 +500,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
* a program is not able to use ptrace(2) in that case. It is
* safe because the task has stopped executing permanently.
*/
- if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) {
+ if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) {
if (try_get_task_stack(task)) {
eip = KSTK_EIP(task);
esp = KSTK_ESP(task);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0edf14a9840e..62d35631ba8c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -416,7 +416,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
#ifdef CONFIG_KALLSYMS
/*
* Provides a wchan file via kallsyms in a proper one-value-per-file format.
- * Returns the resolved symbol. If that fails, simply return the address.
+ * Returns the resolved symbol to user space.
*/
static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
@@ -827,7 +827,13 @@ static const struct file_operations proc_single_file_operations = {
.release = single_release,
};
-
+/*
+ * proc_mem_open() can return errno, NULL or mm_struct*.
+ *
+ * - Returns NULL if the task has no mm (PF_KTHREAD or PF_EXITING)
+ * - Returns mm_struct* on success
+ * - Returns error code on failure
+ */
struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
{
struct task_struct *task = get_proc_task(inode);
@@ -854,8 +860,8 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
{
struct mm_struct *mm = proc_mem_open(inode, mode);
- if (IS_ERR(mm))
- return PTR_ERR(mm);
+ if (IS_ERR_OR_NULL(mm))
+ return mm ? PTR_ERR(mm) : -ESRCH;
file->private_data = mm;
return 0;
@@ -1489,7 +1495,6 @@ static const struct file_operations proc_fail_nth_operations = {
#endif
-#ifdef CONFIG_SCHED_DEBUG
/*
* Print out various scheduling related per-task fields:
*/
@@ -1539,8 +1544,6 @@ static const struct file_operations proc_pid_sched_operations = {
.release = single_release,
};
-#endif
-
#ifdef CONFIG_SCHED_AUTOGROUP
/*
* Print out autogroup related information:
@@ -2058,7 +2061,8 @@ void pid_update_inode(struct task_struct *task, struct inode *inode)
* performed a setuid(), etc.
*
*/
-static int pid_revalidate(struct dentry *dentry, unsigned int flags)
+static int pid_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
@@ -2123,7 +2127,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
unsigned type = DT_UNKNOWN;
ino_t ino = 1;
- child = d_hash_and_lookup(dir, &qname);
+ child = try_lookup_noperm(&qname, dir);
if (!child) {
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
child = d_alloc_parallel(dir, &qname, &wq);
@@ -2191,7 +2195,8 @@ static int dname_to_vma_addr(struct dentry *dentry,
return 0;
}
-static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int map_files_d_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
bool exact_vma_exists = false;
@@ -2495,11 +2500,9 @@ static const struct file_operations proc_map_files_operations = {
#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
struct timers_private {
- struct pid *pid;
- struct task_struct *task;
- struct sighand_struct *sighand;
- struct pid_namespace *ns;
- unsigned long flags;
+ struct pid *pid;
+ struct task_struct *task;
+ struct pid_namespace *ns;
};
static void *timers_start(struct seq_file *m, loff_t *pos)
@@ -2510,54 +2513,48 @@ static void *timers_start(struct seq_file *m, loff_t *pos)
if (!tp->task)
return ERR_PTR(-ESRCH);
- tp->sighand = lock_task_sighand(tp->task, &tp->flags);
- if (!tp->sighand)
- return ERR_PTR(-ESRCH);
-
- return seq_hlist_start(&tp->task->signal->posix_timers, *pos);
+ rcu_read_lock();
+ return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos);
}
static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
{
struct timers_private *tp = m->private;
- return seq_hlist_next(v, &tp->task->signal->posix_timers, pos);
+
+ return seq_hlist_next_rcu(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;
+ rcu_read_unlock();
}
}
static int show_timer(struct seq_file *m, void *v)
{
- struct k_itimer *timer;
- struct timers_private *tp = m->private;
- int notify;
static const char * const nstr[] = {
- [SIGEV_SIGNAL] = "signal",
- [SIGEV_NONE] = "none",
- [SIGEV_THREAD] = "thread",
+ [SIGEV_SIGNAL] = "signal",
+ [SIGEV_NONE] = "none",
+ [SIGEV_THREAD] = "thread",
};
- timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
- notify = timer->it_sigev_notify;
+ struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
+ struct timers_private *tp = m->private;
+ int notify = timer->it_sigev_notify;
+
+ guard(spinlock_irq)(&timer->it_lock);
+ if (!posixtimer_valid(timer))
+ return 0;
seq_printf(m, "ID: %d\n", timer->it_id);
- seq_printf(m, "signal: %d/%px\n",
- timer->sigq.info.si_signo,
+ seq_printf(m, "signal: %d/%px\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],
+ 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);
@@ -2707,8 +2704,7 @@ static struct dentry *proc_pident_instantiate(struct dentry *dentry,
inode->i_fop = p->fop;
ei->op = p->op;
pid_update_inode(task, inode);
- d_set_d_op(dentry, &pid_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
}
static struct dentry *proc_pident_lookup(struct inode *dir,
@@ -3269,6 +3265,7 @@ 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;
+ int ret = 0;
mm = get_task_mm(task);
if (mm) {
@@ -3276,6 +3273,16 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm));
seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
+ seq_printf(m, "ksm_merge_any: %s\n",
+ test_bit(MMF_VM_MERGE_ANY, &mm->flags) ? "yes" : "no");
+ ret = mmap_read_lock_killable(mm);
+ if (ret) {
+ mmput(mm);
+ return ret;
+ }
+ seq_printf(m, "ksm_mergeable: %s\n",
+ ksm_process_mergeable(mm) ? "yes" : "no");
+ mmap_read_unlock(mm);
mmput(mm);
}
@@ -3283,7 +3290,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
}
#endif /* CONFIG_KSM */
-#ifdef CONFIG_STACKLEAK_METRICS
+#ifdef CONFIG_KSTACK_ERASE_METRICS
static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -3296,7 +3303,7 @@ static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
prev_depth, depth);
return 0;
}
-#endif /* CONFIG_STACKLEAK_METRICS */
+#endif /* CONFIG_KSTACK_ERASE_METRICS */
/*
* Thread groups
@@ -3318,9 +3325,7 @@ static const struct pid_entry tgid_base_stuff[] = {
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("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
@@ -3405,7 +3410,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_LIVEPATCH
ONE("patch_state", S_IRUSR, proc_pid_patch_state),
#endif
-#ifdef CONFIG_STACKLEAK_METRICS
+#ifdef CONFIG_KSTACK_ERASE_METRICS
ONE("stack_depth", S_IRUGO, proc_stack_depth),
#endif
#ifdef CONFIG_PROC_PID_ARCH_STATUS
@@ -3495,8 +3500,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry,
set_nlink(inode, nlink_tgid);
pid_update_inode(task, inode);
- d_set_d_op(dentry, &pid_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
}
struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
@@ -3669,9 +3673,7 @@ static const struct pid_entry tid_base_stuff[] = {
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("limits", S_IRUGO, proc_pid_limits),
-#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
-#endif
NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
&proc_tid_comm_inode_operations,
&proc_pid_set_comm_operations, {}),
@@ -3800,8 +3802,7 @@ static struct dentry *proc_task_instantiate(struct dentry *dentry,
set_nlink(inode, nlink_tid);
pid_update_inode(task, inode);
- d_set_d_op(dentry, &pid_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
}
static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 24baf23e864f..9eeccff49b2a 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -140,7 +140,8 @@ static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
security_task_to_inode(task, inode);
}
-static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
+static int tid_fd_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
struct task_struct *task;
struct inode *inode;
@@ -351,18 +352,9 @@ static int proc_fd_getattr(struct mnt_idmap *idmap,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
- int rv = 0;
generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
-
- /* If it's a directory, put the number of open fds there */
- if (S_ISDIR(inode->i_mode)) {
- rv = proc_readfd_count(inode, &stat->size);
- if (rv < 0)
- return rv;
- }
-
- return rv;
+ return proc_readfd_count(inode, &stat->size);
}
const struct inode_operations proc_fd_inode_operations = {
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index dbe82cf23ee4..76e800e38c8f 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -216,7 +216,8 @@ void proc_free_inum(unsigned int inum)
ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
}
-static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
if (flags & LOOKUP_RCU)
return -ECHILD;
@@ -253,8 +254,11 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, de->proc_dops);
- return d_splice_alias(inode, dentry);
+ if (de->flags & PROC_ENTRY_FORCE_LOOKUP)
+ return d_splice_alias_ops(inode, dentry,
+ &proc_net_dentry_ops);
+ return d_splice_alias_ops(inode, dentry,
+ &proc_misc_dentry_ops);
}
read_unlock(&proc_subdir_lock);
return ERR_PTR(-ENOENT);
@@ -343,7 +347,8 @@ static const struct file_operations proc_dir_operations = {
.iterate_shared = proc_readdir,
};
-static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
return 0;
}
@@ -446,9 +451,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
INIT_LIST_HEAD(&ent->pde_openers);
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)
+ if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP)
pde_force_lookup(ent);
out:
@@ -557,10 +561,18 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
return p;
}
-static inline void pde_set_flags(struct proc_dir_entry *pde)
+static void pde_set_flags(struct proc_dir_entry *pde)
{
if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
pde->flags |= PROC_ENTRY_PERMANENT;
+ if (pde->proc_ops->proc_read_iter)
+ pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+ if (pde->proc_ops->proc_compat_ioctl)
+ pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
+ if (pde->proc_ops->proc_lseek)
+ pde->flags |= PROC_ENTRY_proc_lseek;
}
struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
@@ -624,6 +636,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
p->proc_ops = &proc_seq_ops;
p->seq_ops = ops;
p->state_size = state_size;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_seq_private);
@@ -654,6 +667,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
return NULL;
p->proc_ops = &proc_single_ops;
p->single_show = show;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_single_data);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 626ad7bd94f2..129490151be1 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -42,7 +42,7 @@ static void proc_evict_inode(struct inode *inode)
head = ei->sysctl;
if (head) {
- RCU_INIT_POINTER(ei->sysctl, NULL);
+ WRITE_ONCE(ei->sysctl, NULL);
proc_sys_evict_inode(inode, head);
}
}
@@ -473,7 +473,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
typeof_member(struct proc_ops, proc_open) open;
struct pde_opener *pdeo;
- if (!pde->proc_ops->proc_lseek)
+ if (!pde_has_proc_lseek(pde))
file->f_mode &= ~FMODE_LSEEK;
if (pde_is_permanent(pde)) {
@@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
if (S_ISREG(inode->i_mode)) {
inode->i_op = de->proc_iops;
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops;
else
inode->i_fop = &proc_reg_file_ops;
#ifdef CONFIG_COMPAT
- if (de->proc_ops->proc_compat_ioctl) {
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_compat_ioctl(de)) {
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops_compat;
else
inode->i_fop = &proc_reg_file_ops_compat;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 1695509370b8..e737401d7383 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,7 +44,6 @@ struct proc_dir_entry {
const struct proc_ops *proc_ops;
const struct file_operations *proc_dir_ops;
};
- const struct dentry_operations *proc_dops;
union {
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
@@ -85,6 +84,25 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde)
pde->flags |= PROC_ENTRY_PERMANENT;
}
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+ return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+ return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+ return false;
+#endif
+}
+
+static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde)
+{
+ return pde->flags & PROC_ENTRY_proc_lseek;
+}
+
extern struct kmem_cache *proc_dir_entry_cache;
void pde_free(struct proc_dir_entry *pde);
@@ -143,6 +161,7 @@ unsigned name_to_int(const struct qstr *qstr);
/* Worst case buffer size needed for holding an integer. */
#define PROC_NUMBUF 13
+#ifdef CONFIG_PAGE_MAPCOUNT
/**
* folio_precise_page_mapcount() - Number of mappings of this folio page.
* @folio: The folio.
@@ -173,7 +192,49 @@ static inline int folio_precise_page_mapcount(struct folio *folio,
return mapcount;
}
+#else /* !CONFIG_PAGE_MAPCOUNT */
+static inline int folio_precise_page_mapcount(struct folio *folio,
+ struct page *page)
+{
+ BUILD_BUG();
+}
+#endif /* CONFIG_PAGE_MAPCOUNT */
+/**
+ * folio_average_page_mapcount() - Average number of mappings per page in this
+ * folio
+ * @folio: The folio.
+ *
+ * The average number of user page table entries that reference each page in
+ * this folio as tracked via the RMAP: either referenced directly (PTE) or
+ * as part of a larger area that covers this page (e.g., PMD).
+ *
+ * The average is calculated by rounding to the nearest integer; however,
+ * to avoid duplicated code in current callers, the average is at least
+ * 1 if any page of the folio is mapped.
+ *
+ * Returns: The average number of mappings per page in this folio.
+ */
+static inline int folio_average_page_mapcount(struct folio *folio)
+{
+ int mapcount, entire_mapcount, avg;
+
+ if (!folio_test_large(folio))
+ return atomic_read(&folio->_mapcount) + 1;
+
+ mapcount = folio_large_mapcount(folio);
+ if (unlikely(mapcount <= 0))
+ return 0;
+ entire_mapcount = folio_entire_mapcount(folio);
+ if (mapcount <= entire_mapcount)
+ return entire_mapcount;
+ mapcount -= entire_mapcount;
+
+ /* Round to closest integer ... */
+ avg = ((unsigned int)mapcount + folio_large_nr_pages(folio) / 2) >> folio_large_order(folio);
+ /* ... but return at least 1. */
+ return max_t(int, avg + entire_mapcount, 1);
+}
/*
* array.c
*/
@@ -322,6 +383,11 @@ struct proc_maps_private {
struct task_struct *task;
struct mm_struct *mm;
struct vma_iterator iter;
+ loff_t last_pos;
+#ifdef CONFIG_PER_VMA_LOCK
+ bool mmap_locked;
+ struct vm_area_struct *locked_vma;
+#endif
#ifdef CONFIG_NUMA
struct mempolicy *task_mempolicy;
#endif
@@ -346,7 +412,7 @@ extern const struct dentry_operations proc_net_dentry_ops;
static inline void pde_force_lookup(struct proc_dir_entry *pde)
{
/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
- pde->proc_dops = &proc_net_dentry_ops;
+ pde->flags |= PROC_ENTRY_FORCE_LOOKUP;
}
/*
@@ -357,7 +423,6 @@ static inline void pde_force_lookup(struct proc_dir_entry *pde)
static inline struct dentry *proc_splice_unmountable(struct inode *inode,
struct dentry *dentry, const struct dentry_operations *d_ops)
{
- d_set_d_op(dentry, d_ops);
dont_mount(dentry);
- return d_splice_alias(inode, dentry);
+ return d_splice_alias_ops(inode, dentry, d_ops);
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e376f48c4b8b..728630b10fdf 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -34,8 +34,6 @@
#include <asm/sections.h>
#include "internal.h"
-#define CORE_STR "CORE"
-
#ifndef ELF_CORE_EFLAGS
#define ELF_CORE_EFLAGS 0
#endif
@@ -65,7 +63,11 @@ static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt)
#endif
static LIST_HEAD(kclist_head);
-static DECLARE_RWSEM(kclist_lock);
+static int kcore_nphdr;
+static size_t kcore_phdrs_len;
+static size_t kcore_notes_len;
+static size_t kcore_data_offset;
+DEFINE_STATIC_PERCPU_RWSEM(kclist_lock);
static int kcore_need_update = 1;
/*
@@ -101,33 +103,34 @@ void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
list_add_tail(&new->list, &kclist_head);
}
-static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len,
- size_t *data_offset)
+static void update_kcore_size(void)
{
size_t try, size;
struct kcore_list *m;
- *nphdr = 1; /* PT_NOTE */
+ kcore_nphdr = 1; /* PT_NOTE */
size = 0;
list_for_each_entry(m, &kclist_head, list) {
try = kc_vaddr_to_offset((size_t)m->addr + m->size);
if (try > size)
size = try;
- *nphdr = *nphdr + 1;
+ kcore_nphdr++;
}
- *phdrs_len = *nphdr * sizeof(struct elf_phdr);
- *notes_len = (4 * sizeof(struct elf_note) +
- 3 * ALIGN(sizeof(CORE_STR), 4) +
- VMCOREINFO_NOTE_NAME_BYTES +
- ALIGN(sizeof(struct elf_prstatus), 4) +
- ALIGN(sizeof(struct elf_prpsinfo), 4) +
- ALIGN(arch_task_struct_size, 4) +
- ALIGN(vmcoreinfo_size, 4));
- *data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len +
- *notes_len);
- return *data_offset + size;
+ kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr);
+ kcore_notes_len = (4 * sizeof(struct elf_note) +
+ ALIGN(sizeof(NN_PRSTATUS), 4) +
+ ALIGN(sizeof(NN_PRPSINFO), 4) +
+ ALIGN(sizeof(NN_TASKSTRUCT), 4) +
+ VMCOREINFO_NOTE_NAME_BYTES +
+ ALIGN(sizeof(struct elf_prstatus), 4) +
+ ALIGN(sizeof(struct elf_prpsinfo), 4) +
+ ALIGN(arch_task_struct_size, 4) +
+ ALIGN(vmcoreinfo_size, 4));
+ kcore_data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + kcore_phdrs_len +
+ kcore_notes_len);
+ proc_root_kcore->size = kcore_data_offset + size;
}
#ifdef CONFIG_HIGHMEM
@@ -270,12 +273,10 @@ static int kcore_update_ram(void)
{
LIST_HEAD(list);
LIST_HEAD(garbage);
- int nphdr;
- size_t phdrs_len, notes_len, data_offset;
struct kcore_list *tmp, *pos;
int ret = 0;
- down_write(&kclist_lock);
+ percpu_down_write(&kclist_lock);
if (!xchg(&kcore_need_update, 0))
goto out;
@@ -293,11 +294,10 @@ static int kcore_update_ram(void)
}
list_splice_tail(&list, &kclist_head);
- proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, &notes_len,
- &data_offset);
+ update_kcore_size();
out:
- up_write(&kclist_lock);
+ percpu_up_write(&kclist_lock);
list_for_each_entry_safe(pos, tmp, &garbage, list) {
list_del(&pos->list);
kfree(pos);
@@ -326,27 +326,24 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
struct file *file = iocb->ki_filp;
char *buf = file->private_data;
loff_t *fpos = &iocb->ki_pos;
- size_t phdrs_offset, notes_offset, data_offset;
+ size_t phdrs_offset, notes_offset;
size_t page_offline_frozen = 1;
- size_t phdrs_len, notes_len;
struct kcore_list *m;
size_t tsz;
- int nphdr;
unsigned long start;
size_t buflen = iov_iter_count(iter);
size_t orig_buflen = buflen;
int ret = 0;
- down_read(&kclist_lock);
+ percpu_down_read(&kclist_lock);
/*
* Don't race against drivers that set PageOffline() and expect no
* further page access.
*/
page_offline_freeze();
- get_kcore_size(&nphdr, &phdrs_len, &notes_len, &data_offset);
phdrs_offset = sizeof(struct elfhdr);
- notes_offset = phdrs_offset + phdrs_len;
+ notes_offset = phdrs_offset + kcore_phdrs_len;
/* ELF file header. */
if (buflen && *fpos < sizeof(struct elfhdr)) {
@@ -368,7 +365,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
.e_flags = ELF_CORE_EFLAGS,
.e_ehsize = sizeof(struct elfhdr),
.e_phentsize = sizeof(struct elf_phdr),
- .e_phnum = nphdr,
+ .e_phnum = kcore_nphdr,
};
tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
@@ -382,10 +379,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
}
/* ELF program headers. */
- if (buflen && *fpos < phdrs_offset + phdrs_len) {
+ if (buflen && *fpos < phdrs_offset + kcore_phdrs_len) {
struct elf_phdr *phdrs, *phdr;
- phdrs = kzalloc(phdrs_len, GFP_KERNEL);
+ phdrs = kzalloc(kcore_phdrs_len, GFP_KERNEL);
if (!phdrs) {
ret = -ENOMEM;
goto out;
@@ -393,13 +390,14 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
phdrs[0].p_type = PT_NOTE;
phdrs[0].p_offset = notes_offset;
- phdrs[0].p_filesz = notes_len;
+ phdrs[0].p_filesz = kcore_notes_len;
phdr = &phdrs[1];
list_for_each_entry(m, &kclist_head, list) {
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R | PF_W | PF_X;
- phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
+ phdr->p_offset = kc_vaddr_to_offset(m->addr)
+ + kcore_data_offset;
phdr->p_vaddr = (size_t)m->addr;
if (m->type == KCORE_RAM)
phdr->p_paddr = __pa(m->addr);
@@ -412,7 +410,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
phdr++;
}
- tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
+ tsz = min_t(size_t, buflen,
+ phdrs_offset + kcore_phdrs_len - *fpos);
if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz,
iter) != tsz) {
kfree(phdrs);
@@ -426,7 +425,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
}
/* ELF note segment. */
- if (buflen && *fpos < notes_offset + notes_len) {
+ if (buflen && *fpos < notes_offset + kcore_notes_len) {
struct elf_prstatus prstatus = {};
struct elf_prpsinfo prpsinfo = {
.pr_sname = 'R',
@@ -438,17 +437,17 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
strscpy(prpsinfo.pr_psargs, saved_command_line,
sizeof(prpsinfo.pr_psargs));
- notes = kzalloc(notes_len, GFP_KERNEL);
+ notes = kzalloc(kcore_notes_len, GFP_KERNEL);
if (!notes) {
ret = -ENOMEM;
goto out;
}
- append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
+ append_kcore_note(notes, &i, NN_PRSTATUS, NT_PRSTATUS, &prstatus,
sizeof(prstatus));
- append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
+ append_kcore_note(notes, &i, NN_PRPSINFO, NT_PRPSINFO, &prpsinfo,
sizeof(prpsinfo));
- append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
+ append_kcore_note(notes, &i, NN_TASKSTRUCT, NT_TASKSTRUCT, current,
arch_task_struct_size);
/*
* vmcoreinfo_size is mostly constant after init time, but it
@@ -459,9 +458,10 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
*/
append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
vmcoreinfo_data,
- min(vmcoreinfo_size, notes_len - i));
+ min(vmcoreinfo_size, kcore_notes_len - i));
- tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
+ tsz = min_t(size_t, buflen,
+ notes_offset + kcore_notes_len - *fpos);
if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) {
kfree(notes);
ret = -EFAULT;
@@ -477,7 +477,7 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
* Check to see if our file offset matches with any of
* the addresses in the elf_phdr on our list.
*/
- start = kc_offset_to_vaddr(*fpos - data_offset);
+ start = kc_offset_to_vaddr(*fpos - kcore_data_offset);
if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
tsz = buflen;
@@ -626,7 +626,7 @@ skip:
out:
page_offline_thaw();
- up_read(&kclist_lock);
+ percpu_up_read(&kclist_lock);
if (ret)
return ret;
return orig_buflen - buflen;
@@ -663,6 +663,7 @@ static int release_kcore(struct inode *inode, struct file *file)
}
static const struct proc_ops kcore_proc_ops = {
+ .proc_flags = PROC_ENTRY_PERMANENT,
.proc_read_iter = read_kcore_iter,
.proc_open = open_kcore,
.proc_release = release_kcore,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8ba9b1472390..a458f1e112fd 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -120,10 +120,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
global_node_page_state(NR_SECONDARY_PAGETABLE));
show_val_kb(m, "NFS_Unstable: ", 0);
- show_val_kb(m, "Bounce: ",
- global_zone_page_state(NR_BOUNCE));
- show_val_kb(m, "WritebackTmp: ",
- global_node_page_state(NR_WRITEBACK_TEMP));
+ show_val_kb(m, "Bounce: ", 0);
+ show_val_kb(m, "WritebackTmp: ", 0);
show_val_kb(m, "CommitLimit: ", vm_commit_limit());
show_val_kb(m, "Committed_AS: ", committed);
seq_printf(m, "VmallocTotal: %8lu kB\n",
@@ -162,6 +160,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
show_val_kb(m, "Unaccepted: ",
global_zone_page_state(NR_UNACCEPTED));
#endif
+ show_val_kb(m, "Balloon: ",
+ global_node_page_state(NR_BALLOON_PAGES));
hugetlb_report_meminfo(m);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 8e159fc78c0a..4403a2e20c16 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -83,7 +83,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
- res = readlink_copy(buffer, buflen, name);
+ res = readlink_copy(buffer, buflen, name, strlen(name));
}
put_task_struct(task);
return res;
@@ -111,8 +111,7 @@ static struct dentry *proc_ns_instantiate(struct dentry *dentry,
ei->ns_ops = ns_ops;
pid_update_inode(task, inode);
- d_set_d_op(dentry, &pid_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
}
static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/page.c b/fs/proc/page.c
index a55f5acefa97..ba3568e97fd1 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -22,6 +22,12 @@
#define KPMMASK (KPMSIZE - 1)
#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
+enum kpage_operation {
+ KPAGE_FLAGS,
+ KPAGE_COUNT,
+ KPAGE_CGROUP,
+};
+
static inline unsigned long get_max_dump_pfn(void)
{
#ifdef CONFIG_SPARSEMEM
@@ -37,19 +43,33 @@ static inline unsigned long get_max_dump_pfn(void)
#endif
}
-/* /proc/kpagecount - an array exposing page mapcounts
- *
- * Each entry is a u64 representing the corresponding
- * physical page mapcount.
- */
-static ssize_t kpagecount_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
+static u64 get_kpage_count(const struct page *page)
+{
+ struct page_snapshot ps;
+ u64 ret;
+
+ snapshot_page(&ps, page);
+
+ if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+ ret = folio_precise_page_mapcount(&ps.folio_snapshot,
+ &ps.page_snapshot);
+ else
+ ret = folio_average_page_mapcount(&ps.folio_snapshot);
+
+ return ret;
+}
+
+static ssize_t kpage_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos,
+ enum kpage_operation op)
{
const unsigned long max_dump_pfn = get_max_dump_pfn();
u64 __user *out = (u64 __user *)buf;
+ struct page *page;
unsigned long src = *ppos;
unsigned long pfn;
ssize_t ret = 0;
+ u64 info;
pfn = src / KPMSIZE;
if (src & KPMMASK || count & KPMMASK)
@@ -59,19 +79,31 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
while (count > 0) {
- struct page *page;
- u64 mapcount = 0;
-
/*
* TODO: ZONE_DEVICE support requires to identify
* memmaps that were actually initialized.
*/
page = pfn_to_online_page(pfn);
- if (page)
- mapcount = folio_precise_page_mapcount(page_folio(page),
- page);
- if (put_user(mapcount, out)) {
+ if (page) {
+ switch (op) {
+ case KPAGE_FLAGS:
+ info = stable_page_flags(page);
+ break;
+ case KPAGE_COUNT:
+ info = get_kpage_count(page);
+ break;
+ case KPAGE_CGROUP:
+ info = page_cgroup_ino(page);
+ break;
+ default:
+ info = 0;
+ break;
+ }
+ } else
+ info = 0;
+
+ if (put_user(info, out)) {
ret = -EFAULT;
break;
}
@@ -89,17 +121,23 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
return ret;
}
+/* /proc/kpagecount - an array exposing page mapcounts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page mapcount.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return kpage_read(file, buf, count, ppos, KPAGE_COUNT);
+}
+
static const struct proc_ops kpagecount_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_lseek = mem_lseek,
.proc_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)
{
@@ -109,6 +147,7 @@ static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
u64 stable_page_flags(const struct page *page)
{
const struct folio *folio;
+ struct page_snapshot ps;
unsigned long k;
unsigned long mapping;
bool is_anon;
@@ -120,20 +159,22 @@ u64 stable_page_flags(const struct page *page)
*/
if (!page)
return 1 << KPF_NOPAGE;
- folio = page_folio(page);
+
+ snapshot_page(&ps, page);
+ folio = &ps.folio_snapshot;
k = folio->flags;
mapping = (unsigned long)folio->mapping;
- is_anon = mapping & PAGE_MAPPING_ANON;
+ is_anon = mapping & FOLIO_MAPPING_ANON;
/*
* pseudo flags for the well known (anonymous) memory mapped pages
*/
- if (page_mapped(page))
+ if (folio_mapped(folio))
u |= 1 << KPF_MMAP;
if (is_anon) {
u |= 1 << KPF_ANON;
- if (mapping & PAGE_MAPPING_KSM)
+ if (mapping & FOLIO_MAPPING_KSM)
u |= 1 << KPF_KSM;
}
@@ -141,7 +182,7 @@ u64 stable_page_flags(const struct page *page)
* compound pages: export both head/tail info
* they together define a compound page's start/end pos and order
*/
- if (page == &folio->page)
+ if (ps.idx == 0)
u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
else
u |= 1 << KPF_COMPOUND_TAIL;
@@ -151,25 +192,19 @@ u64 stable_page_flags(const struct page *page)
folio_test_large_rmappable(folio)) {
/* Note: we indicate any THPs here, not just PMD-sized ones */
u |= 1 << KPF_THP;
- } else if (is_huge_zero_folio(folio)) {
+ } else if (is_huge_zero_pfn(ps.pfn)) {
u |= 1 << KPF_ZERO_PAGE;
u |= 1 << KPF_THP;
- } else if (is_zero_folio(folio)) {
+ } else if (is_zero_pfn(ps.pfn)) {
u |= 1 << KPF_ZERO_PAGE;
}
- /*
- * Caveats on high order pages: PG_buddy and PG_slab will only be set
- * on the head page.
- */
- if (PageBuddy(page))
- u |= 1 << KPF_BUDDY;
- else if (page_count(page) == 0 && is_free_buddy_page(page))
+ if (ps.flags & PAGE_SNAPSHOT_PG_BUDDY)
u |= 1 << KPF_BUDDY;
- if (PageOffline(page))
+ if (folio_test_offline(folio))
u |= 1 << KPF_OFFLINE;
- if (PageTable(page))
+ if (folio_test_pgtable(folio))
u |= 1 << KPF_PGTABLE;
if (folio_test_slab(folio))
u |= 1 << KPF_SLAB;
@@ -177,7 +212,7 @@ u64 stable_page_flags(const struct page *page)
#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
u |= kpf_copy_bit(k, KPF_IDLE, PG_idle);
#else
- if (folio_test_idle(folio))
+ if (ps.flags & PAGE_SNAPSHOT_PG_IDLE)
u |= 1 << KPF_IDLE;
#endif
@@ -203,7 +238,7 @@ u64 stable_page_flags(const struct page *page)
if (u & (1 << KPF_HUGE))
u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
else
- u |= kpf_copy_bit(page->flags, KPF_HWPOISON, PG_hwpoison);
+ u |= kpf_copy_bit(ps.page_snapshot.flags, KPF_HWPOISON, PG_hwpoison);
#endif
u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
@@ -220,47 +255,17 @@ u64 stable_page_flags(const struct page *page)
#endif
return u;
-};
+}
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
static ssize_t kpageflags_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
+ size_t count, loff_t *ppos)
{
- const unsigned long max_dump_pfn = get_max_dump_pfn();
- u64 __user *out = (u64 __user *)buf;
- unsigned long src = *ppos;
- unsigned long pfn;
- ssize_t ret = 0;
-
- pfn = src / KPMSIZE;
- if (src & KPMMASK || count & KPMMASK)
- return -EINVAL;
- if (src >= max_dump_pfn * KPMSIZE)
- return 0;
- count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
-
- while (count > 0) {
- /*
- * TODO: ZONE_DEVICE support requires to identify
- * memmaps that were actually initialized.
- */
- struct page *page = pfn_to_online_page(pfn);
-
- if (put_user(stable_page_flags(page), out)) {
- ret = -EFAULT;
- break;
- }
-
- pfn++;
- out++;
- count -= KPMSIZE;
-
- cond_resched();
- }
-
- *ppos += (char __user *)out - buf;
- if (!ret)
- ret = (char __user *)out - buf;
- return ret;
+ return kpage_read(file, buf, count, ppos, KPAGE_FLAGS);
}
static const struct proc_ops kpageflags_proc_ops = {
@@ -271,53 +276,10 @@ static const struct proc_ops kpageflags_proc_ops = {
#ifdef CONFIG_MEMCG
static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
+ size_t count, loff_t *ppos)
{
- const unsigned long max_dump_pfn = get_max_dump_pfn();
- u64 __user *out = (u64 __user *)buf;
- struct page *ppage;
- unsigned long src = *ppos;
- unsigned long pfn;
- ssize_t ret = 0;
- u64 ino;
-
- pfn = src / KPMSIZE;
- if (src & KPMMASK || count & KPMMASK)
- return -EINVAL;
- if (src >= max_dump_pfn * KPMSIZE)
- return 0;
- count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
-
- while (count > 0) {
- /*
- * TODO: ZONE_DEVICE support requires to identify
- * memmaps that were actually initialized.
- */
- ppage = pfn_to_online_page(pfn);
-
- if (ppage)
- ino = page_cgroup_ino(ppage);
- else
- ino = 0;
-
- if (put_user(ino, out)) {
- ret = -EFAULT;
- break;
- }
-
- pfn++;
- out++;
- count -= KPMSIZE;
-
- cond_resched();
- }
-
- *ppos += (char __user *)out - buf;
- if (!ret)
- ret = (char __user *)out - buf;
- return ret;
+ return kpage_read(file, buf, count, ppos, KPAGE_CGROUP);
}
-
static const struct proc_ops kpagecgroup_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_lseek = mem_lseek,
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 27a283d85a6e..49ab74e0bfde 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -540,9 +540,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- d_set_d_op(dentry, &proc_sys_dentry_operations);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- err = d_splice_alias(inode, dentry);
+ err = d_splice_alias_ops(inode, dentry, &proc_sys_dentry_operations);
out:
if (h)
@@ -699,9 +698,9 @@ static bool proc_sys_fill_cache(struct file *file,
return false;
if (d_in_lookup(child)) {
struct dentry *res;
- d_set_d_op(child, &proc_sys_dentry_operations);
inode = proc_sys_make_inode(dir->d_sb, head, table);
- res = d_splice_alias(inode, child);
+ res = d_splice_alias_ops(inode, child,
+ &proc_sys_dentry_operations);
d_lookup_done(child);
if (unlikely(res)) {
dput(child);
@@ -884,7 +883,8 @@ static const struct inode_operations proc_sys_dir_operations = {
.getattr = proc_sys_getattr,
};
-static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_sys_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
if (flags & LOOKUP_RCU)
return -ECHILD;
@@ -917,17 +917,21 @@ static int proc_sys_compare(const struct dentry *dentry,
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 = d_inode_rcu(dentry);
- 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);
+
+ // false positive is fine here - we'll recheck anyway
+ if (d_in_lookup(dentry))
+ return 0;
+
+ inode = d_inode_rcu(dentry);
+ // we just might have run into dentry in the middle of __dentry_kill()
+ if (!inode)
+ return 1;
+
+ head = READ_ONCE(PROC_I(inode)->sysctl);
return !head || !sysctl_is_seen(head);
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 06a297a27ba3..ed86ac710384 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -363,12 +363,12 @@ static const struct inode_operations proc_root_inode_operations = {
* This is the root "inode" in the /proc tree..
*/
struct proc_dir_entry proc_root = {
- .low_ino = PROC_ROOT_INO,
- .namelen = 5,
- .mode = S_IFDIR | S_IRUGO | S_IXUGO,
- .nlink = 2,
+ .low_ino = PROCFS_ROOT_INO,
+ .namelen = 5,
+ .mode = S_IFDIR | S_IRUGO | S_IXUGO,
+ .nlink = 2,
.refcnt = REFCOUNT_INIT(1),
- .proc_iops = &proc_root_inode_operations,
+ .proc_iops = &proc_root_inode_operations,
.proc_dir_ops = &proc_root_operations,
.parent = &proc_root,
.subdir = RB_ROOT,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 38a5a3e9cba2..29cca0e6d0ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -29,6 +29,9 @@
#include <asm/tlbflush.h>
#include "internal.h"
+#define SENTINEL_VMA_END -1
+#define SENTINEL_VMA_GATE -2
+
#define SEQ_PUT_DEC(str, val) \
seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8)
void task_mem(struct seq_file *m, struct mm_struct *mm)
@@ -36,9 +39,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
unsigned long text, lib, swap, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
- anon = get_mm_counter(mm, MM_ANONPAGES);
- file = get_mm_counter(mm, MM_FILEPAGES);
- shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+ anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+ file = get_mm_counter_sum(mm, MM_FILEPAGES);
+ shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +62,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
text = min(text, mm->exec_vm << PAGE_SHIFT);
lib = (mm->exec_vm << PAGE_SHIFT) - text;
- swap = get_mm_counter(mm, MM_SWAPENTS);
+ swap = get_mm_counter_sum(mm, MM_SWAPENTS);
SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +95,12 @@ 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, MM_FILEPAGES) +
- get_mm_counter(mm, MM_SHMEMPAGES);
+ *shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+ get_mm_counter_sum(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->data_vm + mm->stack_vm;
- *resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+ *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
return mm->total_vm;
}
@@ -127,15 +130,134 @@ 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)
+#ifdef CONFIG_PER_VMA_LOCK
+
+static void unlock_vma(struct proc_maps_private *priv)
+{
+ if (priv->locked_vma) {
+ vma_end_read(priv->locked_vma);
+ priv->locked_vma = NULL;
+ }
+}
+
+static const struct seq_operations proc_pid_maps_op;
+
+static inline bool lock_vma_range(struct seq_file *m,
+ struct proc_maps_private *priv)
+{
+ /*
+ * smaps and numa_maps perform page table walk, therefore require
+ * mmap_lock but maps can be read with locking just the vma and
+ * walking the vma tree under rcu read protection.
+ */
+ if (m->op != &proc_pid_maps_op) {
+ if (mmap_read_lock_killable(priv->mm))
+ return false;
+
+ priv->mmap_locked = true;
+ } else {
+ rcu_read_lock();
+ priv->locked_vma = NULL;
+ priv->mmap_locked = false;
+ }
+
+ return true;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+ if (priv->mmap_locked) {
+ mmap_read_unlock(priv->mm);
+ } else {
+ unlock_vma(priv);
+ rcu_read_unlock();
+ }
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+ loff_t last_pos)
+{
+ struct vm_area_struct *vma;
+
+ if (priv->mmap_locked)
+ return vma_next(&priv->iter);
+
+ unlock_vma(priv);
+ vma = lock_next_vma(priv->mm, &priv->iter, last_pos);
+ if (!IS_ERR_OR_NULL(vma))
+ priv->locked_vma = vma;
+
+ return vma;
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+ loff_t pos)
+{
+ if (priv->mmap_locked)
+ return false;
+
+ rcu_read_unlock();
+ mmap_read_lock(priv->mm);
+ /* Reinitialize the iterator after taking mmap_lock */
+ vma_iter_set(&priv->iter, pos);
+ priv->mmap_locked = true;
+
+ return true;
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline bool lock_vma_range(struct seq_file *m,
+ struct proc_maps_private *priv)
+{
+ return mmap_read_lock_killable(priv->mm) == 0;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+ mmap_read_unlock(priv->mm);
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+ loff_t last_pos)
+{
+ return vma_next(&priv->iter);
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+ loff_t pos)
+{
+ return false;
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
+static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos)
{
- struct vm_area_struct *vma = vma_next(&priv->iter);
+ struct proc_maps_private *priv = m->private;
+ struct vm_area_struct *vma;
+retry:
+ vma = get_next_vma(priv, *ppos);
+ /* EINTR of EAGAIN is possible */
+ if (IS_ERR(vma)) {
+ if (PTR_ERR(vma) == -EAGAIN && fallback_to_mmap_lock(priv, *ppos))
+ goto retry;
+
+ return vma;
+ }
+
+ /* Store previous position to be able to restart if needed */
+ priv->last_pos = *ppos;
if (vma) {
- *ppos = vma->vm_start;
+ /*
+ * Track the end of the reported vma to ensure position changes
+ * even if previous vma was merged with the next vma and we
+ * found the extended vma with the same vm_start.
+ */
+ *ppos = vma->vm_end;
} else {
- *ppos = -2UL;
+ *ppos = SENTINEL_VMA_GATE;
vma = get_gate_vma(priv->mm);
}
@@ -145,11 +267,11 @@ static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
static void *m_start(struct seq_file *m, loff_t *ppos)
{
struct proc_maps_private *priv = m->private;
- unsigned long last_addr = *ppos;
+ loff_t last_addr = *ppos;
struct mm_struct *mm;
/* See m_next(). Zero at the start or after lseek. */
- if (last_addr == -1UL)
+ if (last_addr == SENTINEL_VMA_END)
return NULL;
priv->task = get_proc_task(priv->inode);
@@ -163,28 +285,34 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
return NULL;
}
- if (mmap_read_lock_killable(mm)) {
+ if (!lock_vma_range(m, priv)) {
mmput(mm);
put_task_struct(priv->task);
priv->task = NULL;
return ERR_PTR(-EINTR);
}
- vma_iter_init(&priv->iter, mm, last_addr);
+ /*
+ * Reset current position if last_addr was set before
+ * and it's not a sentinel.
+ */
+ if (last_addr > 0)
+ *ppos = last_addr = priv->last_pos;
+ vma_iter_init(&priv->iter, mm, (unsigned long)last_addr);
hold_task_mempolicy(priv);
- if (last_addr == -2UL)
+ if (last_addr == SENTINEL_VMA_GATE)
return get_gate_vma(mm);
- return proc_get_vma(priv, ppos);
+ return proc_get_vma(m, ppos);
}
static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
{
- if (*ppos == -2UL) {
- *ppos = -1UL;
+ if (*ppos == SENTINEL_VMA_GATE) {
+ *ppos = SENTINEL_VMA_END;
return NULL;
}
- return proc_get_vma(m->private, ppos);
+ return proc_get_vma(m, ppos);
}
static void m_stop(struct seq_file *m, void *v)
@@ -196,7 +324,7 @@ static void m_stop(struct seq_file *m, void *v)
return;
release_task_mempolicy(priv);
- mmap_read_unlock(mm);
+ unlock_vma_range(priv);
mmput(mm);
put_task_struct(priv->task);
priv->task = NULL;
@@ -707,6 +835,8 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
struct folio *folio = page_folio(page);
int i, nr = compound ? compound_nr(page) : 1;
unsigned long size = nr * PAGE_SIZE;
+ bool exclusive;
+ int mapcount;
/*
* First accumulate quantities that depend only on |size| and the type
@@ -747,18 +877,29 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
dirty, locked, present);
return;
}
+
+ if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
+ mapcount = folio_average_page_mapcount(folio);
+ exclusive = !folio_maybe_mapped_shared(folio);
+ }
+
/*
* We obtain a snapshot of the mapcount. Without holding the folio lock
* this snapshot can be slightly wrong as we cannot always read the
* mapcount atomically.
*/
for (i = 0; i < nr; i++, page++) {
- int mapcount = folio_precise_page_mapcount(folio, page);
unsigned long pss = PAGE_SIZE << PSS_SHIFT;
+
+ if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) {
+ mapcount = folio_precise_page_mapcount(folio, page);
+ exclusive = mapcount < 2;
+ }
+
if (mapcount >= 2)
pss /= mapcount;
smaps_page_accumulate(mss, folio, PAGE_SIZE, pss,
- dirty, locked, mapcount < 2);
+ dirty, locked, exclusive);
}
}
@@ -1007,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
- pte_t ptent = huge_ptep_get(walk->mm, addr, pte);
struct folio *folio = NULL;
bool present = false;
+ spinlock_t *ptl;
+ pte_t ptent;
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
+ ptent = huge_ptep_get(walk->mm, addr, pte);
if (pte_present(ptent)) {
folio = page_folio(pte_page(ptent));
present = true;
@@ -1023,12 +1167,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
if (folio) {
/* We treat non-present entries as "maybe shared". */
- if (!present || folio_likely_mapped_shared(folio) ||
+ if (!present || folio_maybe_mapped_shared(folio) ||
hugetlb_pmd_shared(pte))
mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
else
mss->private_hugetlb += huge_page_size(hstate_vma(vma));
}
+ spin_unlock(ptl);
return 0;
}
#else
@@ -1312,8 +1457,8 @@ static int smaps_rollup_open(struct inode *inode, struct file *file)
priv->inode = inode;
priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
- if (IS_ERR(priv->mm)) {
- ret = PTR_ERR(priv->mm);
+ if (IS_ERR_OR_NULL(priv->mm)) {
+ ret = priv->mm ? PTR_ERR(priv->mm) : -ESRCH;
single_release(inode, file);
goto out_free;
@@ -1632,6 +1777,7 @@ struct pagemapread {
#define PM_SOFT_DIRTY BIT_ULL(55)
#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
#define PM_UFFD_WP BIT_ULL(57)
+#define PM_GUARD_REGION BIT_ULL(58)
#define PM_FILE BIT_ULL(61)
#define PM_SWAP BIT_ULL(62)
#define PM_PRESENT BIT_ULL(63)
@@ -1651,6 +1797,13 @@ static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm)
return 0;
}
+static bool __folio_page_mapped_exclusively(struct folio *folio, struct page *page)
+{
+ if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+ return folio_precise_page_mapcount(folio, page) == 1;
+ return !folio_maybe_mapped_shared(folio);
+}
+
static int pagemap_pte_hole(unsigned long start, unsigned long end,
__always_unused int depth, struct mm_walk *walk)
{
@@ -1732,6 +1885,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
page = pfn_swap_entry_to_page(entry);
if (pte_marker_entry_uffd_wp(entry))
flags |= PM_UFFD_WP;
+ if (is_guard_swp_entry(entry))
+ flags |= PM_GUARD_REGION;
}
if (page) {
@@ -1739,7 +1894,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
if (!folio_test_anon(folio))
flags |= PM_FILE;
if ((flags & PM_PRESENT) &&
- folio_precise_page_mapcount(folio, page) == 1)
+ __folio_page_mapped_exclusively(folio, page))
flags |= PM_MMAP_EXCLUSIVE;
}
if (vma->vm_flags & VM_SOFTDIRTY)
@@ -1810,11 +1965,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
}
for (; addr != end; addr += PAGE_SIZE, idx++) {
- unsigned long cur_flags = flags;
+ u64 cur_flags = flags;
pagemap_entry_t pme;
if (folio && (flags & PM_PRESENT) &&
- folio_precise_page_mapcount(folio, page + idx) == 1)
+ __folio_page_mapped_exclusively(folio, page))
cur_flags |= PM_MMAP_EXCLUSIVE;
pme = make_pme(frame, cur_flags);
@@ -1866,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
struct pagemapread *pm = walk->private;
struct vm_area_struct *vma = walk->vma;
u64 flags = 0, frame = 0;
+ spinlock_t *ptl;
int err = 0;
pte_t pte;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep);
pte = huge_ptep_get(walk->mm, addr, ptep);
if (pte_present(pte)) {
struct folio *folio = page_folio(pte_page(pte));
@@ -1879,7 +2036,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
if (!folio_test_anon(folio))
flags |= PM_FILE;
- if (!folio_likely_mapped_shared(folio) &&
+ if (!folio_maybe_mapped_shared(folio) &&
!hugetlb_pmd_shared(ptep))
flags |= PM_MMAP_EXCLUSIVE;
@@ -1899,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
err = add_to_pagemap(&pme, pm);
if (err)
- return err;
+ break;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
}
+ spin_unlock(ptl);
cond_resched();
return err;
@@ -1931,7 +2089,8 @@ static const struct mm_walk_ops pagemap_ops = {
* Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
* Bit 56 page exclusively mapped
* Bit 57 pte is uffd-wp write-protected
- * Bits 58-60 zero
+ * Bit 58 pte is a guard region
+ * Bits 59-60 zero
* Bit 61 page is file-page or shared-anon
* Bit 62 page swapped
* Bit 63 page present
@@ -2045,8 +2204,8 @@ static int pagemap_open(struct inode *inode, struct file *file)
struct mm_struct *mm;
mm = proc_mem_open(inode, PTRACE_MODE_READ);
- if (IS_ERR(mm))
- return PTR_ERR(mm);
+ if (IS_ERR_OR_NULL(mm))
+ return mm ? PTR_ERR(mm) : -ESRCH;
file->private_data = mm;
return 0;
}
@@ -2063,7 +2222,8 @@ static int pagemap_release(struct inode *inode, struct file *file)
#define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \
PAGE_IS_FILE | PAGE_IS_PRESENT | \
PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \
- PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY)
+ PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY | \
+ PAGE_IS_GUARD)
#define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
struct pagemap_scan_private {
@@ -2104,12 +2264,14 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
if (!pte_swp_uffd_wp_any(pte))
categories |= PAGE_IS_WRITTEN;
- if (p->masks_of_interest & PAGE_IS_FILE) {
- swp = pte_to_swp_entry(pte);
- if (is_pfn_swap_entry(swp) &&
- !folio_test_anon(pfn_swap_entry_folio(swp)))
- categories |= PAGE_IS_FILE;
- }
+ swp = pte_to_swp_entry(pte);
+ if (is_guard_swp_entry(swp))
+ categories |= PAGE_IS_GUARD;
+ else if ((p->masks_of_interest & PAGE_IS_FILE) &&
+ is_pfn_swap_entry(swp) &&
+ !folio_test_anon(pfn_swap_entry_folio(swp)))
+ categories |= PAGE_IS_FILE;
+
if (pte_swp_soft_dirty(pte))
categories |= PAGE_IS_SOFT_DIRTY;
}
@@ -2155,7 +2317,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
categories |= PAGE_IS_FILE;
}
- if (is_zero_pfn(pmd_pfn(pmd)))
+ if (is_huge_zero_pmd(pmd))
categories |= PAGE_IS_PFNZERO;
if (pmd_soft_dirty(pmd))
categories |= PAGE_IS_SOFT_DIRTY;
@@ -2455,22 +2617,19 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
spinlock_t *ptl;
int ret;
- arch_enter_lazy_mmu_mode();
-
ret = pagemap_scan_thp_entry(pmd, start, end, walk);
- if (ret != -ENOENT) {
- arch_leave_lazy_mmu_mode();
+ if (ret != -ENOENT)
return ret;
- }
ret = 0;
start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
if (!pte) {
- arch_leave_lazy_mmu_mode();
walk->action = ACTION_AGAIN;
return 0;
}
+ arch_enter_lazy_mmu_mode();
+
if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
/* Fast path for performing exclusive WP */
for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
@@ -2539,8 +2698,8 @@ flush_and_return:
if (flush_end)
flush_tlb_range(vma, start, addr);
- pte_unmap_unlock(start_pte, ptl);
arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(start_pte, ptl);
cond_resched();
return ret;
@@ -2855,7 +3014,12 @@ static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
unsigned long nr_pages)
{
struct folio *folio = page_folio(page);
- int count = folio_precise_page_mapcount(folio, page);
+ int count;
+
+ if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+ count = folio_precise_page_mapcount(folio, page);
+ else
+ count = folio_average_page_mapcount(folio);
md->pages += nr_pages;
if (pte_dirty || folio_test_dirty(folio))
@@ -2971,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
- pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte);
+ pte_t huge_pte;
struct numa_maps *md;
struct page *page;
+ spinlock_t *ptl;
+ ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
+ huge_pte = huge_ptep_get(walk->mm, addr, pte);
if (!pte_present(huge_pte))
- return 0;
+ goto out;
page = pte_page(huge_pte);
md = walk->private;
gather_stats(page, md, pte_dirty(huge_pte), 1);
+out:
+ spin_unlock(ptl);
return 0;
}
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index bce674533000..59bfd61d653a 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -260,8 +260,8 @@ static int maps_open(struct inode *inode, struct file *file,
priv->inode = inode;
priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
- if (IS_ERR(priv->mm)) {
- int err = PTR_ERR(priv->mm);
+ if (IS_ERR_OR_NULL(priv->mm)) {
+ int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH;
seq_release_private(inode, file);
return err;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 3d8a82cee63e..f188bd900eb2 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -8,6 +8,8 @@
*
*/
+#define pr_fmt(fmt) "vmcore: " fmt
+
#include <linux/mm.h>
#include <linux/kcore.h>
#include <linux/user.h>
@@ -51,9 +53,14 @@ static u64 vmcore_size;
static struct proc_dir_entry *proc_vmcore;
#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+struct vmcoredd_node {
+ struct list_head list; /* List of dumps */
+ void *buf; /* Buffer containing device's dump */
+ unsigned int size; /* Size of the buffer */
+};
+
/* Device Dump list and mutex to synchronize access to list */
static LIST_HEAD(vmcoredd_list);
-static DEFINE_MUTEX(vmcoredd_mutex);
static bool vmcoredd_disabled;
core_param(novmcoredd, vmcoredd_disabled, bool, 0);
@@ -62,17 +69,22 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
/* Device Dump Size */
static size_t vmcoredd_orig_sz;
-static DEFINE_SPINLOCK(vmcore_cb_lock);
+static DEFINE_MUTEX(vmcore_mutex);
+
DEFINE_STATIC_SRCU(vmcore_cb_srcu);
/* List of registered vmcore callbacks. */
static LIST_HEAD(vmcore_cb_list);
/* Whether the vmcore has been opened once. */
static bool vmcore_opened;
+/* Whether the vmcore is currently open. */
+static unsigned int vmcore_open;
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb);
void register_vmcore_cb(struct vmcore_cb *cb)
{
INIT_LIST_HEAD(&cb->next);
- spin_lock(&vmcore_cb_lock);
+ mutex_lock(&vmcore_mutex);
list_add_tail(&cb->next, &vmcore_cb_list);
/*
* Registering a vmcore callback after the vmcore was opened is
@@ -80,13 +92,15 @@ void register_vmcore_cb(struct vmcore_cb *cb)
*/
if (vmcore_opened)
pr_warn_once("Unexpected vmcore callback registration\n");
- spin_unlock(&vmcore_cb_lock);
+ if (!vmcore_open && cb->get_device_ram)
+ vmcore_process_device_ram(cb);
+ mutex_unlock(&vmcore_mutex);
}
EXPORT_SYMBOL_GPL(register_vmcore_cb);
void unregister_vmcore_cb(struct vmcore_cb *cb)
{
- spin_lock(&vmcore_cb_lock);
+ mutex_lock(&vmcore_mutex);
list_del_rcu(&cb->next);
/*
* Unregistering a vmcore callback after the vmcore was opened is
@@ -95,7 +109,7 @@ void unregister_vmcore_cb(struct vmcore_cb *cb)
*/
if (vmcore_opened)
pr_warn_once("Unexpected vmcore callback unregistration\n");
- spin_unlock(&vmcore_cb_lock);
+ mutex_unlock(&vmcore_mutex);
synchronize_srcu(&vmcore_cb_srcu);
}
@@ -120,9 +134,23 @@ static bool pfn_is_ram(unsigned long pfn)
static int open_vmcore(struct inode *inode, struct file *file)
{
- spin_lock(&vmcore_cb_lock);
+ mutex_lock(&vmcore_mutex);
vmcore_opened = true;
- spin_unlock(&vmcore_cb_lock);
+ if (vmcore_open + 1 == 0) {
+ mutex_unlock(&vmcore_mutex);
+ return -EBUSY;
+ }
+ vmcore_open++;
+ mutex_unlock(&vmcore_mutex);
+
+ return 0;
+}
+
+static int release_vmcore(struct inode *inode, struct file *file)
+{
+ mutex_lock(&vmcore_mutex);
+ vmcore_open--;
+ mutex_unlock(&vmcore_mutex);
return 0;
}
@@ -243,33 +271,27 @@ static int vmcoredd_copy_dumps(struct iov_iter *iter, u64 start, size_t size)
{
struct vmcoredd_node *dump;
u64 offset = 0;
- int ret = 0;
size_t tsz;
char *buf;
- mutex_lock(&vmcoredd_mutex);
list_for_each_entry(dump, &vmcoredd_list, list) {
if (start < offset + dump->size) {
tsz = min(offset + (u64)dump->size - start, (u64)size);
buf = dump->buf + start - offset;
- if (copy_to_iter(buf, tsz, iter) < tsz) {
- ret = -EFAULT;
- goto out_unlock;
- }
+ if (copy_to_iter(buf, tsz, iter) < tsz)
+ return -EFAULT;
size -= tsz;
start += tsz;
/* Leave now if buffer filled already */
if (!size)
- goto out_unlock;
+ return 0;
}
offset += dump->size;
}
-out_unlock:
- mutex_unlock(&vmcoredd_mutex);
- return ret;
+ return 0;
}
#ifdef CONFIG_MMU
@@ -278,20 +300,16 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
{
struct vmcoredd_node *dump;
u64 offset = 0;
- int ret = 0;
size_t tsz;
char *buf;
- mutex_lock(&vmcoredd_mutex);
list_for_each_entry(dump, &vmcoredd_list, list) {
if (start < offset + dump->size) {
tsz = min(offset + (u64)dump->size - start, (u64)size);
buf = dump->buf + start - offset;
if (remap_vmalloc_range_partial(vma, dst, buf, 0,
- tsz)) {
- ret = -EFAULT;
- goto out_unlock;
- }
+ tsz))
+ return -EFAULT;
size -= tsz;
start += tsz;
@@ -299,14 +317,12 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
/* Leave now if buffer filled already */
if (!size)
- goto out_unlock;
+ return 0;
}
offset += dump->size;
}
-out_unlock:
- mutex_unlock(&vmcoredd_mutex);
- return ret;
+ return 0;
}
#endif /* CONFIG_MMU */
#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
@@ -316,10 +332,10 @@ out_unlock:
*/
static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
{
+ struct vmcore_range *m = NULL;
ssize_t acc = 0, tmp;
size_t tsz;
u64 start;
- struct vmcore *m = NULL;
if (!iov_iter_count(iter) || *fpos >= vmcore_size)
return 0;
@@ -404,6 +420,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
if (!iov_iter_count(iter))
return acc;
}
+
+ cond_resched();
}
return acc;
@@ -574,7 +592,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
u64 start, end, len, tsz;
- struct vmcore *m;
+ struct vmcore_range *m;
start = (u64)vma->vm_pgoff << PAGE_SHIFT;
end = start + size;
@@ -691,21 +709,17 @@ 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_release = release_vmcore,
.proc_read_iter = read_vmcore,
.proc_lseek = default_llseek,
.proc_mmap = mmap_vmcore,
};
-static struct vmcore* __init get_new_element(void)
-{
- return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
-}
-
static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
struct list_head *vc_list)
{
+ struct vmcore_range *m;
u64 size;
- struct vmcore *m;
size = elfsz + elfnotesegsz;
list_for_each_entry(m, vc_list, list) {
@@ -1107,7 +1121,6 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
Elf64_Ehdr *ehdr_ptr;
Elf64_Phdr *phdr_ptr;
loff_t vmcore_off;
- struct vmcore *new;
ehdr_ptr = (Elf64_Ehdr *)elfptr;
phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
@@ -1126,13 +1139,8 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
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)
+ if (vmcore_alloc_add_range(vc_list, start, size))
return -ENOMEM;
- new->paddr = start;
- new->size = size;
- list_add_tail(&new->list, vc_list);
/* Update the program header offset. */
phdr_ptr->p_offset = vmcore_off + (paddr - start);
@@ -1150,7 +1158,6 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
Elf32_Ehdr *ehdr_ptr;
Elf32_Phdr *phdr_ptr;
loff_t vmcore_off;
- struct vmcore *new;
ehdr_ptr = (Elf32_Ehdr *)elfptr;
phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */
@@ -1169,13 +1176,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
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)
+ if (vmcore_alloc_add_range(vc_list, start, size))
return -ENOMEM;
- new->paddr = start;
- new->size = size;
- list_add_tail(&new->list, vc_list);
/* Update the program header offset */
phdr_ptr->p_offset = vmcore_off + (paddr - start);
@@ -1188,8 +1190,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
struct list_head *vc_list)
{
+ struct vmcore_range *m;
loff_t vmcore_off;
- struct vmcore *m;
/* Skip ELF header, program headers and ELF note segment. */
vmcore_off = elfsz + elfnotes_sz;
@@ -1488,10 +1490,8 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
return -EINVAL;
dump = vzalloc(sizeof(*dump));
- if (!dump) {
- ret = -ENOMEM;
- goto out_err;
- }
+ if (!dump)
+ return -ENOMEM;
/* Keep size of the buffer page aligned so that it can be mmaped */
data_size = roundup(sizeof(struct vmcoredd_header) + data->size,
@@ -1516,12 +1516,18 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
dump->buf = buf;
dump->size = data_size;
- /* Add the dump to driver sysfs list */
- mutex_lock(&vmcoredd_mutex);
- list_add_tail(&dump->list, &vmcoredd_list);
- mutex_unlock(&vmcoredd_mutex);
+ /* Add the dump to driver sysfs list and update the elfcore hdr */
+ scoped_guard(mutex, &vmcore_mutex) {
+ if (vmcore_opened)
+ pr_warn_once("Unexpected adding of device dump\n");
+ if (vmcore_open) {
+ ret = -EBUSY;
+ goto out_err;
+ }
- vmcoredd_update_size(data_size);
+ list_add_tail(&dump->list, &vmcoredd_list);
+ vmcoredd_update_size(data_size);
+ }
return 0;
out_err:
@@ -1533,11 +1539,163 @@ out_err:
EXPORT_SYMBOL(vmcore_add_device_dump);
#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+static int vmcore_realloc_elfcore_buffer_elf64(size_t new_size)
+{
+ char *elfcorebuf_new;
+
+ if (WARN_ON_ONCE(new_size < elfcorebuf_sz))
+ return -EINVAL;
+ if (get_order(elfcorebuf_sz_orig) == get_order(new_size)) {
+ elfcorebuf_sz_orig = new_size;
+ return 0;
+ }
+
+ elfcorebuf_new = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ get_order(new_size));
+ if (!elfcorebuf_new)
+ return -ENOMEM;
+ memcpy(elfcorebuf_new, elfcorebuf, elfcorebuf_sz);
+ free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
+ elfcorebuf = elfcorebuf_new;
+ elfcorebuf_sz_orig = new_size;
+ return 0;
+}
+
+static void vmcore_reset_offsets_elf64(void)
+{
+ Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+ loff_t vmcore_off = elfcorebuf_sz + elfnotes_sz;
+ Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+ Elf64_Phdr *phdr;
+ int i;
+
+ for (i = 0, phdr = phdr_start; i < ehdr->e_phnum; i++, phdr++) {
+ u64 start, end;
+
+ /*
+ * After merge_note_headers_elf64() we should only have a single
+ * PT_NOTE entry that starts immediately after elfcorebuf_sz.
+ */
+ if (phdr->p_type == PT_NOTE) {
+ phdr->p_offset = elfcorebuf_sz;
+ continue;
+ }
+
+ start = rounddown(phdr->p_offset, PAGE_SIZE);
+ end = roundup(phdr->p_offset + phdr->p_memsz, PAGE_SIZE);
+ phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+ vmcore_off = vmcore_off + end - start;
+ }
+ set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+}
+
+static int vmcore_add_device_ram_elf64(struct list_head *list, size_t count)
+{
+ Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+ Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+ struct vmcore_range *cur;
+ Elf64_Phdr *phdr;
+ size_t new_size;
+ int rc;
+
+ if ((Elf32_Half)(ehdr->e_phnum + count) != ehdr->e_phnum + count) {
+ pr_err("too many device ram ranges\n");
+ return -ENOSPC;
+ }
+
+ /* elfcorebuf_sz must always cover full pages. */
+ new_size = sizeof(Elf64_Ehdr) +
+ (ehdr->e_phnum + count) * sizeof(Elf64_Phdr);
+ new_size = roundup(new_size, PAGE_SIZE);
+
+ /*
+ * Make sure we have sufficient space to include the new PT_LOAD
+ * entries.
+ */
+ rc = vmcore_realloc_elfcore_buffer_elf64(new_size);
+ if (rc) {
+ pr_err("resizing elfcore failed\n");
+ return rc;
+ }
+
+ /* Modify our used elfcore buffer size to cover the new entries. */
+ elfcorebuf_sz = new_size;
+
+ /* Fill the added PT_LOAD entries. */
+ phdr = phdr_start + ehdr->e_phnum;
+ list_for_each_entry(cur, list, list) {
+ WARN_ON_ONCE(!IS_ALIGNED(cur->paddr | cur->size, PAGE_SIZE));
+ elfcorehdr_fill_device_ram_ptload_elf64(phdr, cur->paddr, cur->size);
+
+ /* p_offset will be adjusted later. */
+ phdr++;
+ ehdr->e_phnum++;
+ }
+ list_splice_tail(list, &vmcore_list);
+
+ /* We changed elfcorebuf_sz and added new entries; reset all offsets. */
+ vmcore_reset_offsets_elf64();
+
+ /* Finally, recalculate the total vmcore size. */
+ vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+ &vmcore_list);
+ proc_vmcore->size = vmcore_size;
+ return 0;
+}
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+ unsigned char *e_ident = (unsigned char *)elfcorebuf;
+ struct vmcore_range *first, *m;
+ LIST_HEAD(list);
+ int count;
+
+ /* We only support Elf64 dumps for now. */
+ if (WARN_ON_ONCE(e_ident[EI_CLASS] != ELFCLASS64)) {
+ pr_err("device ram ranges only support Elf64\n");
+ return;
+ }
+
+ if (cb->get_device_ram(cb, &list)) {
+ pr_err("obtaining device ram ranges failed\n");
+ return;
+ }
+ count = list_count_nodes(&list);
+ if (!count)
+ return;
+
+ /*
+ * For some reason these ranges are already know? Might happen
+ * with unusual register->unregister->register sequences; we'll simply
+ * sanity check using the first range.
+ */
+ first = list_first_entry(&list, struct vmcore_range, list);
+ list_for_each_entry(m, &vmcore_list, list) {
+ unsigned long long m_end = m->paddr + m->size;
+ unsigned long long first_end = first->paddr + first->size;
+
+ if (first->paddr < m_end && m->paddr < first_end)
+ goto out_free;
+ }
+
+ /* If adding the mem nodes succeeds, they must not be freed. */
+ if (!vmcore_add_device_ram_elf64(&list, count))
+ return;
+out_free:
+ vmcore_free_ranges(&list);
+}
+#else /* !CONFIG_PROC_VMCORE_DEVICE_RAM */
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
+
/* Free all dumps in vmcore device dump list */
static void vmcore_free_device_dumps(void)
{
#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
- mutex_lock(&vmcoredd_mutex);
+ mutex_lock(&vmcore_mutex);
while (!list_empty(&vmcoredd_list)) {
struct vmcoredd_node *dump;
@@ -1547,7 +1705,7 @@ static void vmcore_free_device_dumps(void)
vfree(dump->buf);
vfree(dump);
}
- mutex_unlock(&vmcoredd_mutex);
+ mutex_unlock(&vmcore_mutex);
#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
}
@@ -1569,7 +1727,7 @@ static int __init vmcore_init(void)
rc = parse_crash_elf_headers();
if (rc) {
elfcorehdr_free(elfcorehdr_addr);
- pr_warn("Kdump: vmcore not initialized\n");
+ pr_warn("not initialized\n");
return rc;
}
elfcorehdr_free(elfcorehdr_addr);
@@ -1590,14 +1748,7 @@ void vmcore_cleanup(void)
proc_vmcore = NULL;
}
- /* clear the vmcore list. */
- while (!list_empty(&vmcore_list)) {
- struct vmcore *m;
-
- m = list_first_entry(&vmcore_list, struct vmcore, list);
- list_del(&m->list);
- kfree(m);
- }
+ vmcore_free_ranges(&vmcore_list);
free_elfcorebuf();
/* clear vmcore device dump list */
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-26 02:34:39 +0300