summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-03-22 09:04:48 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-22 09:04:48 -0700
commit95211279c5ad00a317c98221d7e4365e02f20836 (patch)
tree2ddc8625378d2915b8c96392f3cf6663b705ed55 /fs
parent5375871d432ae9fc581014ac117b96aaee3cd0c7 (diff)
parent12724850e8064f64b6223d26d78c0597c742c65a (diff)
downloadlinux-3.10-95211279c5ad00a317c98221d7e4365e02f20836.tar.gz
linux-3.10-95211279c5ad00a317c98221d7e4365e02f20836.tar.bz2
linux-3.10-95211279c5ad00a317c98221d7e4365e02f20836.zip
Merge branch 'akpm' (Andrew's patch-bomb)
Merge first batch of patches from Andrew Morton: "A few misc things and all the MM queue" * emailed from Andrew Morton <akpm@linux-foundation.org>: (92 commits) memcg: avoid THP split in task migration thp: add HPAGE_PMD_* definitions for !CONFIG_TRANSPARENT_HUGEPAGE memcg: clean up existing move charge code mm/memcontrol.c: remove unnecessary 'break' in mem_cgroup_read() mm/memcontrol.c: remove redundant BUG_ON() in mem_cgroup_usage_unregister_event() mm/memcontrol.c: s/stealed/stolen/ memcg: fix performance of mem_cgroup_begin_update_page_stat() memcg: remove PCG_FILE_MAPPED memcg: use new logic for page stat accounting memcg: remove PCG_MOVE_LOCK flag from page_cgroup memcg: simplify move_account() check memcg: remove EXPORT_SYMBOL(mem_cgroup_update_page_stat) memcg: kill dead prev_priority stubs memcg: remove PCG_CACHE page_cgroup flag memcg: let css_get_next() rely upon rcu_read_lock() cgroup: revert ss_id_lock to spinlock idr: make idr_get_next() good for rcu_read_lock() memcg: remove unnecessary thp check in page stat accounting memcg: remove redundant returns memcg: enum lru_list lru ...
Diffstat (limited to 'fs')
-rw-r--r--fs/exec.c2
-rw-r--r--fs/hugetlbfs/inode.c138
-rw-r--r--fs/namei.c6
-rw-r--r--fs/proc/base.c12
-rw-r--r--fs/proc/internal.h9
-rw-r--r--fs/proc/page.c2
-rw-r--r--fs/proc/task_mmu.c357
-rw-r--r--fs/proc/task_nommu.c69
-rw-r--r--fs/seq_file.c28
9 files changed, 432 insertions, 191 deletions
diff --git a/fs/exec.c b/fs/exec.c
index 0b931471d4f..23559c227d9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -822,7 +822,7 @@ static int exec_mmap(struct mm_struct *mm)
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
- sync_mm_rss(tsk, old_mm);
+ sync_mm_rss(old_mm);
mm_release(tsk, old_mm);
if (old_mm) {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 81932fa1861..ea251749d9d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -41,6 +41,25 @@ const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
+struct hugetlbfs_config {
+ uid_t uid;
+ gid_t gid;
+ umode_t mode;
+ long nr_blocks;
+ long nr_inodes;
+ struct hstate *hstate;
+};
+
+struct hugetlbfs_inode_info {
+ struct shared_policy policy;
+ struct inode vfs_inode;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+ return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
@@ -154,10 +173,12 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
return addr;
}
- start_addr = mm->free_area_cache;
-
- if (len <= mm->cached_hole_size)
+ if (len > mm->cached_hole_size)
+ start_addr = mm->free_area_cache;
+ else {
start_addr = TASK_UNMAPPED_BASE;
+ mm->cached_hole_size = 0;
+ }
full_search:
addr = ALIGN(start_addr, huge_page_size(h));
@@ -171,13 +192,18 @@ full_search:
*/
if (start_addr != TASK_UNMAPPED_BASE) {
start_addr = TASK_UNMAPPED_BASE;
+ mm->cached_hole_size = 0;
goto full_search;
}
return -ENOMEM;
}
- if (!vma || addr + len <= vma->vm_start)
+ if (!vma || addr + len <= vma->vm_start) {
+ mm->free_area_cache = addr + len;
return addr;
+ }
+ if (addr + mm->cached_hole_size < vma->vm_start)
+ mm->cached_hole_size = vma->vm_start - addr;
addr = ALIGN(vma->vm_end, huge_page_size(h));
}
}
@@ -238,17 +264,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
loff_t isize;
ssize_t retval = 0;
- mutex_lock(&inode->i_mutex);
-
/* validate length */
if (len == 0)
goto out;
- isize = i_size_read(inode);
- if (!isize)
- goto out;
-
- end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
unsigned long nr, ret;
@@ -256,18 +275,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
+ isize = i_size_read(inode);
+ if (!isize)
+ goto out;
+ end_index = (isize - 1) >> huge_page_shift(h);
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
- if (nr <= offset) {
+ if (nr <= offset)
goto out;
- }
}
nr = nr - offset;
/* Find the page */
- page = find_get_page(mapping, index);
+ page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
/*
* We have a HOLE, zero out the user-buffer for the
@@ -279,17 +301,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
else
ra = 0;
} else {
+ unlock_page(page);
+
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
+ page_cache_release(page);
}
if (ra < 0) {
if (retval == 0)
retval = ra;
- if (page)
- page_cache_release(page);
goto out;
}
@@ -299,16 +322,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
- if (page)
- page_cache_release(page);
-
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
- mutex_unlock(&inode->i_mutex);
return retval;
}
@@ -607,9 +626,15 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
* blocks, like simple_statfs() */
- if (sbinfo->max_blocks >= 0) {
- buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+ if (sbinfo->spool) {
+ long free_pages;
+
+ spin_lock(&sbinfo->spool->lock);
+ buf->f_blocks = sbinfo->spool->max_hpages;
+ free_pages = sbinfo->spool->max_hpages
+ - sbinfo->spool->used_hpages;
+ buf->f_bavail = buf->f_bfree = free_pages;
+ spin_unlock(&sbinfo->spool->lock);
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
@@ -625,6 +650,10 @@ static void hugetlbfs_put_super(struct super_block *sb)
if (sbi) {
sb->s_fs_info = NULL;
+
+ if (sbi->spool)
+ hugepage_put_subpool(sbi->spool);
+
kfree(sbi);
}
}
@@ -853,10 +882,14 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_fs_info = sbinfo;
sbinfo->hstate = config.hstate;
spin_lock_init(&sbinfo->stat_lock);
- sbinfo->max_blocks = config.nr_blocks;
- sbinfo->free_blocks = config.nr_blocks;
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
+ sbinfo->spool = NULL;
+ if (config.nr_blocks != -1) {
+ sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+ if (!sbinfo->spool)
+ goto out_free;
+ }
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = huge_page_size(config.hstate);
sb->s_blocksize_bits = huge_page_shift(config.hstate);
@@ -868,38 +901,12 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
goto out_free;
return 0;
out_free:
+ if (sbinfo->spool)
+ kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
-int hugetlb_get_quota(struct address_space *mapping, long delta)
-{
- int ret = 0;
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks - delta >= 0)
- sbinfo->free_blocks -= delta;
- else
- ret = -ENOMEM;
- spin_unlock(&sbinfo->stat_lock);
- }
-
- return ret;
-}
-
-void hugetlb_put_quota(struct address_space *mapping, long delta)
-{
- struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
-
- if (sbinfo->free_blocks > -1) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += delta;
- spin_unlock(&sbinfo->stat_lock);
- }
-}
-
static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
@@ -919,8 +926,8 @@ static int can_do_hugetlb_shm(void)
return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
}
-struct file *hugetlb_file_setup(const char *name, size_t size,
- vm_flags_t acctflag,
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+ size_t size, vm_flags_t acctflag,
struct user_struct **user, int creat_flags)
{
int error = -ENOMEM;
@@ -929,6 +936,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
struct path path;
struct dentry *root;
struct qstr quick_string;
+ struct hstate *hstate;
+ unsigned long num_pages;
*user = NULL;
if (!hugetlbfs_vfsmount)
@@ -937,7 +946,11 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
*user = current_user();
if (user_shm_lock(size, *user)) {
- printk_once(KERN_WARNING "Using mlock ulimits for SHM_HUGETLB is deprecated\n");
+ task_lock(current);
+ printk_once(KERN_WARNING
+ "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
+ current->comm, current->pid);
+ task_unlock(current);
} else {
*user = NULL;
return ERR_PTR(-EPERM);
@@ -958,10 +971,12 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
if (!inode)
goto out_dentry;
+ hstate = hstate_inode(inode);
+ size += addr & ~huge_page_mask(hstate);
+ num_pages = ALIGN(size, huge_page_size(hstate)) >>
+ huge_page_shift(hstate);
error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0,
- size >> huge_page_shift(hstate_inode(inode)), NULL,
- acctflag))
+ if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
goto out_inode;
d_instantiate(path.dentry, inode);
@@ -997,6 +1012,7 @@ static int __init init_hugetlbfs_fs(void)
if (error)
return error;
+ error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
0, 0, init_once);
@@ -1015,10 +1031,10 @@ static int __init init_hugetlbfs_fs(void)
}
error = PTR_ERR(vfsmount);
+ unregister_filesystem(&hugetlbfs_fs_type);
out:
- if (error)
- kmem_cache_destroy(hugetlbfs_inode_cachep);
+ kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
diff --git a/fs/namei.c b/fs/namei.c
index 13e6a1f191a..a94a7f9a03e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1455,9 +1455,15 @@ done:
}
EXPORT_SYMBOL(full_name_hash);
+#ifdef CONFIG_64BIT
#define ONEBYTES 0x0101010101010101ul
#define SLASHBYTES 0x2f2f2f2f2f2f2f2ful
#define HIGHBITS 0x8080808080808080ul
+#else
+#define ONEBYTES 0x01010101ul
+#define SLASHBYTES 0x2f2f2f2ful
+#define HIGHBITS 0x80808080ul
+#endif
/* Return the high bit set in the first byte that is a zero */
static inline unsigned long has_zero(unsigned long a)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 965d4bde3a3..3b42c1418f3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2989,9 +2989,9 @@ static const struct pid_entry tgid_base_stuff[] = {
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_pid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
@@ -3002,7 +3002,7 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("mountstats", S_IRUSR, proc_mountstats_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_pid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
@@ -3348,9 +3348,9 @@ static const struct pid_entry tid_base_stuff[] = {
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_tid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
@@ -3360,7 +3360,7 @@ static const struct pid_entry tid_base_stuff[] = {
REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_tid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 292577531ad..c44efe19798 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -53,9 +53,12 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task);
extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
-extern const struct file_operations proc_maps_operations;
-extern const struct file_operations proc_numa_maps_operations;
-extern const struct file_operations proc_smaps_operations;
+extern const struct file_operations proc_pid_maps_operations;
+extern const struct file_operations proc_tid_maps_operations;
+extern const struct file_operations proc_pid_numa_maps_operations;
+extern const struct file_operations proc_tid_numa_maps_operations;
+extern const struct file_operations proc_pid_smaps_operations;
+extern const struct file_operations proc_tid_smaps_operations;
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
extern const struct file_operations proc_net_operations;
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 6d8e6a9e93a..7fcd0d60a96 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -115,6 +115,8 @@ u64 stable_page_flags(struct page *page)
u |= 1 << KPF_COMPOUND_TAIL;
if (PageHuge(page))
u |= 1 << KPF_HUGE;
+ else if (PageTransCompound(page))
+ u |= 1 << KPF_THP;
/*
* Caveats on high order pages: page->_count will only be set
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7dcd2a25049..9694cc28351 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -209,16 +209,20 @@ static int do_maps_open(struct inode *inode, struct file *file,
return ret;
}
-static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+static void
+show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
unsigned long start, end;
dev_t dev = 0;
int len;
+ const char *name = NULL;
if (file) {
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
@@ -252,36 +256,57 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
if (file) {
pad_len_spaces(m, len);
seq_path(m, &file->f_path, "\n");
- } else {
- const char *name = arch_vma_name(vma);
- if (!name) {
- if (mm) {
- if (vma->vm_start <= mm->brk &&
- vma->vm_end >= mm->start_brk) {
- name = "[heap]";
- } else if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
- name = "[stack]";
- }
+ goto done;
+ }
+
+ name = arch_vma_name(vma);
+ if (!name) {
+ pid_t tid;
+
+ if (!mm) {
+ name = "[vdso]";
+ goto done;
+ }
+
+ if (vma->vm_start <= mm->brk &&
+ vma->vm_end >= mm->start_brk) {
+ name = "[heap]";
+ goto done;
+ }
+
+ tid = vm_is_stack(task, vma, is_pid);
+
+ if (tid != 0) {
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack)) {
+ name = "[stack]";
} else {
- name = "[vdso]";
+ /* Thread stack in /proc/PID/maps */
+ pad_len_spaces(m, len);
+ seq_printf(m, "[stack:%d]", tid);
}
}
- if (name) {
- pad_len_spaces(m, len);
- seq_puts(m, name);
- }
+ }
+
+done:
+ if (name) {
+ pad_len_spaces(m, len);
+ seq_puts(m, name);
}
seq_putc(m, '\n');
}
-static int show_map(struct seq_file *m, void *v)
+static int show_map(struct seq_file *m, void *v, int is_pid)
{
struct vm_area_struct *vma = v;
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
- show_map_vma(m, vma);
+ show_map_vma(m, vma, is_pid);
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task->mm))
@@ -289,20 +314,49 @@ static int show_map(struct seq_file *m, void *v)
return 0;
}
+static int show_pid_map(struct seq_file *m, void *v)
+{
+ return show_map(m, v, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *v)
+{
+ return show_map(m, v, 0);
+}
+
static const struct seq_operations proc_pid_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_map
+ .show = show_pid_map
};
-static int maps_open(struct inode *inode, struct file *file)
+static const struct seq_operations proc_tid_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_map
+};
+
+static int pid_maps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_maps_op);
}
-const struct file_operations proc_maps_operations = {
- .open = maps_open,
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_tid_maps_op);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+ .open = pid_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+ .open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
@@ -394,21 +448,15 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte;
spinlock_t *ptl;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(vma->anon_vma, pmd);
- } else {
- smaps_pte_entry(*(pte_t *)pmd, addr,
- HPAGE_PMD_SIZE, walk);
- spin_unlock(&walk->mm->page_table_lock);
- mss->anonymous_thp += HPAGE_PMD_SIZE;
- return 0;
- }
- } else {
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
spin_unlock(&walk->mm->page_table_lock);
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ return 0;
}
+
+ if (pmd_trans_unstable(pmd))
+ return 0;
/*
* The mmap_sem held all the way back in m_start() is what
* keeps khugepaged out of here and from collapsing things
@@ -422,7 +470,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
return 0;
}
-static int show_smap(struct seq_file *m, void *v)
+static int show_smap(struct seq_file *m, void *v, int is_pid)
{
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
@@ -440,7 +488,7 @@ static int show_smap(struct seq_file *m, void *v)
if (vma->vm_mm && !is_vm_hugetlb_page(vma))
walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
- show_map_vma(m, vma);
+ show_map_vma(m, vma, is_pid);
seq_printf(m,
"Size: %8lu kB\n"
@@ -479,20 +527,49 @@ static int show_smap(struct seq_file *m, void *v)
return 0;
}
+static int show_pid_smap(struct seq_file *m, void *v)
+{
+ return show_smap(m, v, 1);
+}
+
+static int show_tid_smap(struct seq_file *m, void *v)
+{
+ return show_smap(m, v, 0);
+}
+
static const struct seq_operations proc_pid_smaps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_smap
+ .show = show_pid_smap
+};
+
+static const struct seq_operations proc_tid_smaps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_smap
};
-static int smaps_open(struct inode *inode, struct file *file)
+static int pid_smaps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_smaps_op);
}
-const struct file_operations proc_smaps_operations = {
- .open = smaps_open,
+static int tid_smaps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_tid_smaps_op);
+}
+
+const struct file_operations proc_pid_smaps_operations = {
+ .open = pid_smaps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_smaps_operations = {
+ .open = tid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
@@ -507,6 +584,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
struct page *page;
split_huge_page_pmd(walk->mm, pmd);
+ if (pmd_trans_unstable(pmd))
+ return 0;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -598,11 +677,18 @@ const struct file_operations proc_clear_refs_operations = {
.llseek = noop_llseek,
};
+typedef struct {
+ u64 pme;
+} pagemap_entry_t;
+
struct pagemapread {
int pos, len;
- u64 *buffer;
+ pagemap_entry_t *buffer;
};
+#define PAGEMAP_WALK_SIZE (PMD_SIZE)
+#define PAGEMAP_WALK_MASK (PMD_MASK)
+
#define PM_ENTRY_BYTES sizeof(u64)
#define PM_STATUS_BITS 3
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
@@ -620,10 +706,15 @@ struct pagemapread {
#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT)
#define PM_END_OF_BUFFER 1
-static int add_to_pagemap(unsigned long addr, u64 pfn,
+static inline pagemap_entry_t make_pme(u64 val)
+{
+ return (pagemap_entry_t) { .pme = val };
+}
+
+static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
struct pagemapread *pm)
{
- pm->buffer[pm->pos++] = pfn;
+ pm->buffer[pm->pos++] = *pme;
if (pm->pos >= pm->len)
return PM_END_OF_BUFFER;
return 0;
@@ -635,8 +726,10 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
struct pagemapread *pm = walk->private;
unsigned long addr;
int err = 0;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+
for (addr = start; addr < end; addr += PAGE_SIZE) {
- err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
break;
}
@@ -649,17 +742,35 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
}
-static u64 pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
{
- u64 pme = 0;
if (is_swap_pte(pte))
- pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+ *pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
else if (pte_present(pte))
- pme = PM_PFRAME(pte_pfn(pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
- return pme;
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+ pmd_t pmd, int offset)
+{
+ /*
+ * Currently pmd for thp is always present because thp can not be
+ * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
+ * This if-check is just to prepare for future implementation.
+ */
+ if (pmd_present(pmd))
+ *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
}
+#else
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+ pmd_t pmd, int offset)
+{
+}
+#endif
static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
@@ -668,13 +779,30 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct pagemapread *pm = walk->private;
pte_t *pte;
int err = 0;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
- split_huge_page_pmd(walk->mm, pmd);
+ if (pmd_trans_unstable(pmd))
+ return 0;
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
+ spin_lock(&walk->mm->page_table_lock);
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ for (; addr != end; addr += PAGE_SIZE) {
+ unsigned long offset;
+
+ offset = (addr & ~PAGEMAP_WALK_MASK) >>
+ PAGE_SHIFT;
+ thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ break;
+ }
+ spin_unlock(&walk->mm->page_table_lock);
+ return err;
+ }
+
for (; addr != end; addr += PAGE_SIZE) {
- u64 pfn = PM_NOT_PRESENT;
/* check to see if we've left 'vma' behind
* and need a new, higher one */
@@ -686,11 +814,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (vma && (vma->vm_start <= addr) &&
!is_vm_hugetlb_page(vma)) {
pte = pte_offset_map(pmd, addr);
- pfn = pte_to_pagemap_entry(*pte);
+ pte_to_pagemap_entry(&pme, *pte);
/* unmap before userspace copy */
pte_unmap(pte);
}
- err = add_to_pagemap(addr, pfn, pm);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
}
@@ -701,13 +829,12 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
}
#ifdef CONFIG_HUGETLB_PAGE
-static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+ pte_t pte, int offset)
{
- u64 pme = 0;
if (pte_present(pte))
- pme = PM_PFRAME(pte_pfn(pte) + offset)
- | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
- return pme;
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
}
/* This function walks within one hugetlb entry in the single call */
@@ -717,12 +844,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
{
struct pagemapread *pm = walk->private;
int err = 0;
- u64 pfn;
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
for (; addr != end; addr += PAGE_SIZE) {
int offset = (addr & ~hmask) >> PAGE_SHIFT;
- pfn = huge_pte_to_pagemap_entry(*pte, offset);
- err = add_to_pagemap(addr, pfn, pm);
+ huge_pte_to_pagemap_entry(&pme, *pte, offset);
+ err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
}
@@ -757,8 +884,6 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
* determine which areas of memory are actually mapped and llseek to
* skip over unmapped regions.
*/
-#define PAGEMAP_WALK_SIZE (PMD_SIZE)
-#define PAGEMAP_WALK_MASK (PMD_MASK)
static ssize_t pagemap_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
@@ -941,26 +1066,21 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
pte_t *pte;
md = walk->private;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(md->vma->anon_vma, pmd);
- } else {
- pte_t huge_pte = *(pte_t *)pmd;
- struct page *page;
-
- page = can_gather_numa_stats(huge_pte, md->vma, addr);
- if (page)
- gather_stats(page, md, pte_dirty(huge_pte),
- HPAGE_PMD_SIZE/PAGE_SIZE);
- spin_unlock(&walk->mm->page_table_lock);
- return 0;
- }
- } else {
+
+ if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+ pte_t huge_pte = *(pte_t *)pmd;
+ struct page *page;
+
+ page = can_gather_numa_stats(huge_pte, md->vma, addr);
+ if (page)
+ gather_stats(page, md, pte_dirty(huge_pte),
+ HPAGE_PMD_SIZE/PAGE_SIZE);
spin_unlock(&walk->mm->page_table_lock);
+ return 0;
}
+ if (pmd_trans_unstable(pmd))
+ return 0;
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
do {
struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1002,7 +1122,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
/*
* Display pages allocated per node and memory policy via /proc.
*/
-static int show_numa_map(struct seq_file *m, void *v)
+static int show_numa_map(struct seq_file *m, void *v, int is_pid)
{
struct numa_maps_private *numa_priv = m->private;
struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
@@ -1039,9 +1159,19 @@ static int show_numa_map(struct seq_file *m, void *v)
seq_path(m, &file->f_path, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_printf(m, " heap");
- } else if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
- seq_printf(m, " stack");
+ } else {
+ pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+ if (tid != 0) {
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack))
+ seq_printf(m, " stack");
+ else
+ seq_printf(m, " stack:%d", tid);
+ }
}
if (is_vm_hugetlb_page(vma))
@@ -1084,21 +1214,39 @@ out:
return 0;
}
+static int show_pid_numa_map(struct seq_file *m, void *v)
+{
+ return show_numa_map(m, v, 1);
+}
+
+static int show_tid_numa_map(struct seq_file *m, void *v)
+{
+ return show_numa_map(m, v, 0);
+}
+
static const struct seq_operations proc_pid_numa_maps_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_numa_map,
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_pid_numa_map,
+};
+
+static const struct seq_operations proc_tid_numa_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_numa_map,
};
-static int numa_maps_open(struct inode *inode, struct file *file)
+static int numa_maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
{
struct numa_maps_private *priv;
int ret = -ENOMEM;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (priv) {
priv->proc_maps.pid = proc_pid(inode);
- ret = seq_open(file, &proc_pid_numa_maps_op);
+ ret = seq_open(file, ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = priv;
@@ -1109,8 +1257,25 @@ static int numa_maps_open(struct inode *inode, struct file *file)
return ret;
}
-const struct file_operations proc_numa_maps_operations = {
- .open = numa_maps_open,
+static int pid_numa_maps_open(struct inode *inode, struct file *file)
+{
+ return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+static int tid_numa_maps_open(struct inode *inode, struct file *file)
+{
+ return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
+}
+
+const struct file_operations proc_pid_numa_maps_operations = {
+ .open = pid_numa_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_numa_maps_operations = {
+ .open = tid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 980de547c07..74fe164d1b2 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -134,9 +134,11 @@ static void pad_len_spaces(struct seq_file *m, int len)
/*
* display a single VMA to a sequenced file
*/
-static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
+ int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
+ struct proc_maps_private *priv = m->private;
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
@@ -168,10 +170,19 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
pad_len_spaces(m, len);
seq_path(m, &file->f_path, "");
} else if (mm) {
- if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
+ pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+
+ if (tid != 0) {
pad_len_spaces(m, len);
- seq_puts(m, "[stack]");
+ /*
+ * Thread stack in /proc/PID/task/TID/maps or
+ * the main process stack.
+ */
+ if (!is_pid || (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack))
+ seq_printf(m, "[stack]");
+ else
+ seq_printf(m, "[stack:%d]", tid);
}
}
@@ -182,11 +193,22 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
/*
* display mapping lines for a particular process's /proc/pid/maps
*/
-static int show_map(struct seq_file *m, void *_p)
+static int show_map(struct seq_file *m, void *_p, int is_pid)
{
struct rb_node *p = _p;
- return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
+ return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb),
+ is_pid);
+}
+
+static int show_pid_map(struct seq_file *m, void *_p)
+{
+ return show_map(m, _p, 1);
+}
+
+static int show_tid_map(struct seq_file *m, void *_p)
+{
+ return show_map(m, _p, 0);
}
static void *m_start(struct seq_file *m, loff_t *pos)
@@ -240,10 +262,18 @@ static const struct seq_operations proc_pid_maps_ops = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_map
+ .show = show_pid_map
+};
+
+static const struct seq_operations proc_tid_maps_ops = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_tid_map
};
-static int maps_open(struct inode *inode, struct file *file)
+static int maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
{
struct proc_maps_private *priv;
int ret = -ENOMEM;
@@ -251,7 +281,7 @@ static int maps_open(struct inode *inode, struct file *file)
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (priv) {
priv->pid = proc_pid(inode);
- ret = seq_open(file, &proc_pid_maps_ops);
+ ret = seq_open(file, ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = priv;
@@ -262,8 +292,25 @@ static int maps_open(struct inode *inode, struct file *file)
return ret;
}
-const struct file_operations proc_maps_operations = {
- .open = maps_open,
+static int pid_maps_open(struct inode *inode, struct file *file)
+{
+ return maps_open(inode, file, &proc_pid_maps_ops);
+}
+
+static int tid_maps_open(struct inode *inode, struct file *file)
+{
+ return maps_open(inode, file, &proc_tid_maps_ops);
+}
+
+const struct file_operations proc_pid_maps_operations = {
+ .open = pid_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+const struct file_operations proc_tid_maps_operations = {
+ .open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4023d6be939..aa242dc9937 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -140,9 +140,21 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
mutex_lock(&m->lock);
+ /*
+ * seq_file->op->..m_start/m_stop/m_next may do special actions
+ * or optimisations based on the file->f_version, so we want to
+ * pass the file->f_version to those methods.
+ *
+ * seq_file->version is just copy of f_version, and seq_file
+ * methods can treat it simply as file version.
+ * It is copied in first and copied out after all operations.
+ * It is convenient to have it as part of structure to avoid the
+ * need of passing another argument to all the seq_file methods.
+ */
+ m->version = file->f_version;
+
/* Don't assume *ppos is where we left it */
if (unlikely(*ppos != m->read_pos)) {
- m->read_pos = *ppos;
while ((err = traverse(m, *ppos)) == -EAGAIN)
;
if (err) {
@@ -152,21 +164,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
m->index = 0;
m->count = 0;
goto Done;
+ } else {
+ m->read_pos = *ppos;
}
}
- /*
- * seq_file->op->..m_start/m_stop/m_next may do special actions
- * or optimisations based on the file->f_version, so we want to
- * pass the file->f_version to those methods.
- *
- * seq_file->version is just copy of f_version, and seq_file
- * methods can treat it simply as file version.
- * It is copied in first and copied out after all operations.
- * It is convenient to have it as part of structure to avoid the
- * need of passing another argument to all the seq_file methods.
- */
- m->version = file->f_version;
/* grab buffer if we didn't have one */
if (!m->buf) {
m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);