2015-02-26 13:51:37

by Vlastimil Babka

Subject: [PATCH 0/4] enhance shmem process and swap accounting

This series is based on Jerome Marchand's [1] so let me quote the first
paragraph from there:

There are several shortcomings with the accounting of shared memory
(sysV shm, shared anonymous mapping, mapping to a tmpfs file). The
values in /proc/<pid>/status and statm don't allow to distinguish
between shmem memory and a shared mapping to a regular file, even
though theirs implication on memory usage are quite different: at
reclaim, file mapping can be dropped or write back on disk while shmem
needs a place in swap. As for shmem pages that are swapped-out or in
swap cache, they aren't accounted at all.

The original motivation for myself is that a customer found (IMHO rightfully)
confusing that e.g. top output for process swap usage is unreliable with
respect to swapped out shmem pages, which are not accounted for.

The fundamental difference between private anonymous and shmem pages is that
the latter has PTE's converted to pte_none, and not swapents. As such, they are
not accounted to the number of swapents visible e.g. in /proc/pid/status VmSwap
row. It might be theoretically possible to use swapents when swapping out shmem
(without extra cost, as one has to change all mappers anyway), and on swap in
only convert the swapent for the faulting process, leaving swapents in other
processes until they also fault (so again no extra cost). But I don't know how
many assumptions this would break, and it would be too disruptive change for a
relatively small benefit.

Instead, my approach is to document the limitation of VmSwap, and provide means
to determine the swap usage for shmem areas for those who are interested and
willing to pay the price, using /proc/pid/smaps. Because outside of ipcs, I
don't think it's possible to currently to determine the usage at all. The
previous patchset [1] did introduce new shmem-specific fields into smaps
output, and functions to determine the values. I take a simpler approach,
noting that smaps output already has a "Swap: X kB" line, where currently X ==
0 always for shmem areas. I think we can just consider this a bug and provide
the proper value by consulting the radix tree, as e.g. mincore_page() does. In the
patch changelog I explain why this is also not perfect (and cannot be without
swapents), but still arguably much better than showing a 0.

The last two patches are adapted from Jerome's patchset and provide a VmRSS
breakdown to VmAnon, VmFile and VmShm in /proc/pid/status. Hugh noted that
this is a welcome addition, and I agree that it might help e.g. debugging
process memory usage at albeit non-zero, but still rather low cost of extra
per-mm counter and some page flag checks. I updated these patches to 4.0-rc1,
made them respect !CONFIG_SHMEM so that tiny systems don't pay the cost, and
optimized the page flag checking somewhat.

[1] http://lwn.net/Articles/611966/

Jerome Marchand (2):
mm, shmem: Add shmem resident memory accounting
mm, procfs: Display VmAnon, VmFile and VmShm in /proc/pid/status

Vlastimil Babka (2):
mm, documentation: clarify /proc/pid/status VmSwap limitations
mm, proc: account for shmem swap in /proc/pid/smaps

Documentation/filesystems/proc.txt | 15 +++++++++++++--
arch/s390/mm/pgtable.c | 5 +----
fs/proc/task_mmu.c | 35 +++++++++++++++++++++++++++++++++--
include/linux/mm.h | 28 ++++++++++++++++++++++++++++
include/linux/mm_types.h | 9 ++++++---
kernel/events/uprobes.c | 2 +-
mm/memory.c | 30 ++++++++++--------------------
mm/oom_kill.c | 5 +++--
mm/rmap.c | 15 ++++-----------
9 files changed, 99 insertions(+), 45 deletions(-)

--
2.1.4

2015-02-26 13:51:38

by Vlastimil Babka

Subject: [PATCH 1/4] mm, documentation: clarify /proc/pid/status VmSwap limitations

The documentation for /proc/pid/status does not mention that the value of
VmSwap counts only swapped out anonymous private pages and not shmem. This is
not obvious, so document this limitation.

Signed-off-by: Vlastimil Babka <[email protected]>
---
I've noticed that proc(5) manpage is currently missing the VmSwap field
altogether.

Documentation/filesystems/proc.txt | 2 ++
1 file changed, 2 insertions(+)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a07ba61..d4f56ec 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -231,6 +231,8 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7)
VmLib size of shared library code
VmPTE size of page table entries
VmSwap size of swap usage (the number of referred swapents)
+ by anonymous private data (shmem swap usage is not
+ included)
Threads number of threads
SigQ number of signals queued/max. number for queue
SigPnd bitmap of pending signals for the thread
--
2.1.4

2015-02-26 13:51:39

by Vlastimil Babka

Subject: [PATCH 2/4] mm, procfs: account for shmem swap in /proc/pid/smaps

Currently, /proc/pid/smaps will always show "Swap: 0 kB" for shmem-backed
mappings, even if the mapped portion does contain pages that were swapped out.
This is because unlike private anonymous mappings, shmem does not change pte
to swap entry, but pte_none when swapping the page out. In the smaps page
walk, such page thus looks like it was never faulted in.

This patch changes smaps_pte_entry() to determine the swap status for such
pte_none entries for shmem mappings, similarly to how mincore_page() does it.
Swapped out pages are thus accounted for.

The accounting is arguably still not as precise as for private anonymous
mappings, since now we will count also pages that the process in question never
accessed, but only another process populated them and then let them become
swapped out. I believe it is still less confusing and subtle than not showing
any swap usage by shmem mappings at all. Also, swapped out pages only becomee a
performance issue for future accesses, and we cannot predict those for neither
kind of mapping.

Signed-off-by: Vlastimil Babka <[email protected]>
---
Documentation/filesystems/proc.txt | 3 ++-
fs/proc/task_mmu.c | 20 ++++++++++++++++++++
2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index d4f56ec..8b30543 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -437,7 +437,8 @@ indicates the amount of memory currently marked as referenced or accessed.
a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
and a page is modified, the file page is replaced by a private anonymous copy.
"Swap" shows how much would-be-anonymous memory is also used, but out on
-swap.
+swap. For shmem mappings, "Swap" shows how much of the mapped portion of the
+underlying shmem object is on swap.

"VmFlags" field deserves a separate description. This member represents the kernel
flags associated with the particular virtual memory area in two letter encoded
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 956b75d..0410309 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -13,6 +13,7 @@
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
+#include <linux/shmem_fs.h>

#include <asm/elf.h>
#include <asm/uaccess.h>
@@ -496,6 +497,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
mss->swap += PAGE_SIZE;
else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
+ } else if (IS_ENABLED(CONFIG_SHMEM) && IS_ENABLED(CONFIG_SWAP) &&
+ pte_none(*pte) && vma->vm_file) {
+ struct address_space *mapping =
+ file_inode(vma->vm_file)->i_mapping;
+
+ /*
+ * shmem does not use swap pte's so we have to consult
+ * the radix tree to account for swap
+ */
+ if (shmem_mapping(mapping)) {
+ page = find_get_entry(mapping, pgoff);
+ if (page) {
+ if (radix_tree_exceptional_entry(page))
+ mss->swap += PAGE_SIZE;
+ else
+ page_cache_release(page);
+ }
+ page = NULL;
+ }
}

if (!page)
--
2.1.4

2015-02-26 13:51:35

by Vlastimil Babka

Subject: [PATCH 3/4] mm, shmem: Add shmem resident memory accounting

From: Jerome Marchand <[email protected]>

Currently looking at /proc/<pid>/status or statm, there is no way to
distinguish shmem pages from pages mapped to a regular file (shmem
pages are mapped to /dev/zero), even though their implication in
actual memory use is quite different.
This patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
shmem pages instead of MM_FILEPAGES.

[[email protected]: port to 4.0, add #ifdefs, mm_counter_file() variant]
Signed-off-by: Jerome Marchand <[email protected]>
Signed-off-by: Vlastimil Babka <[email protected]>
---
arch/s390/mm/pgtable.c | 5 +----
fs/proc/task_mmu.c | 4 +++-
include/linux/mm.h | 28 ++++++++++++++++++++++++++++
include/linux/mm_types.h | 9 ++++++---
kernel/events/uprobes.c | 2 +-
mm/memory.c | 30 ++++++++++--------------------
mm/oom_kill.c | 5 +++--
mm/rmap.c | 15 ++++-----------
8 files changed, 56 insertions(+), 42 deletions(-)

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b2c1542..5bffd5d 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -617,10 +617,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
else if (is_migration_entry(entry)) {
struct page *page = migration_entry_to_page(entry);

- if (PageAnon(page))
- dec_mm_counter(mm, MM_ANONPAGES);
- else
- dec_mm_counter(mm, MM_FILEPAGES);
+ dec_mm_counter(mm, mm_counter(page));
}
free_swap_and_cache(entry);
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 0410309..d70334c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -81,7 +81,8 @@ 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);
+ *shared = get_mm_counter(mm, MM_FILEPAGES) +
+ get_mm_counter(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->total_vm - mm->shared_vm;
@@ -501,6 +502,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
pte_none(*pte) && vma->vm_file) {
struct address_space *mapping =
file_inode(vma->vm_file)->i_mapping;
+ pgoff_t pgoff = linear_page_index(vma, addr);

/*
* shmem does not use swap pte's so we have to consult
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 47a9392..adfbb5b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1364,6 +1364,16 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
return (unsigned long)val;
}

+/* A wrapper for the CONFIG_SHMEM dependent counter */
+static inline unsigned long get_mm_counter_shmem(struct mm_struct *mm)
+{
+#ifdef CONFIG_SHMEM
+ return get_mm_counter(mm, MM_SHMEMPAGES);
+#else
+ return 0;
+#endif
+}
+
static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
{
atomic_long_add(value, &mm->rss_stat.count[member]);
@@ -1379,9 +1389,27 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member)
atomic_long_dec(&mm->rss_stat.count[member]);
}

+/* Optimized variant when page is already known not to be PageAnon */
+static inline int mm_counter_file(struct page *page)
+{
+#ifdef CONFIG_SHMEM
+ if (PageSwapBacked(page))
+ return MM_SHMEMPAGES;
+#endif
+ return MM_FILEPAGES;
+}
+
+static inline int mm_counter(struct page *page)
+{
+ if (PageAnon(page))
+ return MM_ANONPAGES;
+ return mm_counter_file(page);
+}
+
static inline unsigned long get_mm_rss(struct mm_struct *mm)
{
return get_mm_counter(mm, MM_FILEPAGES) +
+ get_mm_counter_shmem(mm) +
get_mm_counter(mm, MM_ANONPAGES);
}

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 199a03a..d3c2372 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -327,9 +327,12 @@ struct core_state {
};

enum {
- MM_FILEPAGES,
- MM_ANONPAGES,
- MM_SWAPENTS,
+ MM_FILEPAGES, /* Resident file mapping pages */
+ MM_ANONPAGES, /* Resident anonymous pages */
+ MM_SWAPENTS, /* Anonymous swap entries */
+#ifdef CONFIG_SHMEM
+ MM_SHMEMPAGES, /* Resident shared memory pages */
+#endif
NR_MM_COUNTERS
};

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index cb346f2..0a08fdd 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
lru_cache_add_active_or_unevictable(kpage, vma);

if (!PageAnon(page)) {
- dec_mm_counter(mm, MM_FILEPAGES);
+ dec_mm_counter(mm, mm_counter_file(page));
inc_mm_counter(mm, MM_ANONPAGES);
}

diff --git a/mm/memory.c b/mm/memory.c
index 8068893..f145d9e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
} else if (is_migration_entry(entry)) {
page = migration_entry_to_page(entry);

- if (PageAnon(page))
- rss[MM_ANONPAGES]++;
- else
- rss[MM_FILEPAGES]++;
+ rss[mm_counter(page)]++;

if (is_write_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
@@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
if (page) {
get_page(page);
page_dup_rmap(page);
- if (PageAnon(page))
- rss[MM_ANONPAGES]++;
- else
- rss[MM_FILEPAGES]++;
+ rss[mm_counter(page)]++;
}

out_set_pte:
@@ -1113,9 +1107,8 @@ again:
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
- if (PageAnon(page))
- rss[MM_ANONPAGES]--;
- else {
+
+ if (!PageAnon(page)) {
if (pte_dirty(ptent)) {
force_flush = 1;
set_page_dirty(page);
@@ -1123,8 +1116,8 @@ again:
if (pte_young(ptent) &&
likely(!(vma->vm_flags & VM_SEQ_READ)))
mark_page_accessed(page);
- rss[MM_FILEPAGES]--;
}
+ rss[mm_counter(page)]--;
page_remove_rmap(page);
if (unlikely(page_mapcount(page) < 0))
print_bad_pte(vma, addr, ptent, page);
@@ -1146,11 +1139,7 @@ again:
struct page *page;

page = migration_entry_to_page(entry);
-
- if (PageAnon(page))
- rss[MM_ANONPAGES]--;
- else
- rss[MM_FILEPAGES]--;
+ rss[mm_counter(page)]--;
}
if (unlikely(!free_swap_and_cache(entry)))
print_bad_pte(vma, addr, ptent, NULL);
@@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,

/* Ok, finally just insert the thing.. */
get_page(page);
- inc_mm_counter_fast(mm, MM_FILEPAGES);
+ inc_mm_counter_fast(mm, mm_counter_file(page));
page_add_file_rmap(page);
set_pte_at(mm, addr, pte, mk_pte(page, prot));

@@ -2174,7 +2163,8 @@ gotten:
if (likely(pte_same(*page_table, orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
- dec_mm_counter_fast(mm, MM_FILEPAGES);
+ dec_mm_counter_fast(mm,
+ mm_counter_file(old_page));
inc_mm_counter_fast(mm, MM_ANONPAGES);
}
} else
@@ -2703,7 +2693,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
} else {
- inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
+ inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
page_add_file_rmap(page);
}
set_pte_at(vma->vm_mm, address, pte, entry);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 642f38c..a5ee3a2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -573,10 +573,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
/* mm cannot safely be dereferenced after task_unlock(victim) */
mm = victim->mm;
mark_tsk_oom_victim(victim);
- pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
+ pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
K(get_mm_counter(victim->mm, MM_ANONPAGES)),
- K(get_mm_counter(victim->mm, MM_FILEPAGES)));
+ K(get_mm_counter(victim->mm, MM_FILEPAGES)),
+ K(get_mm_counter_shmem(victim->mm)));
task_unlock(victim);

/*
diff --git a/mm/rmap.c b/mm/rmap.c
index 5e3e090..e3c4392 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1216,12 +1216,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
update_hiwater_rss(mm);

if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
- if (!PageHuge(page)) {
- if (PageAnon(page))
- dec_mm_counter(mm, MM_ANONPAGES);
- else
- dec_mm_counter(mm, MM_FILEPAGES);
- }
+ if (!PageHuge(page))
+ dec_mm_counter(mm, mm_counter(page));
set_pte_at(mm, address, pte,
swp_entry_to_pte(make_hwpoison_entry(page)));
} else if (pte_unused(pteval)) {
@@ -1230,10 +1226,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* interest anymore. Simply discard the pte, vmscan
* will take care of the rest.
*/
- if (PageAnon(page))
- dec_mm_counter(mm, MM_ANONPAGES);
- else
- dec_mm_counter(mm, MM_FILEPAGES);
+ dec_mm_counter(mm, mm_counter(page));
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
pte_t swp_pte;
@@ -1276,7 +1269,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
entry = make_migration_entry(page, pte_write(pteval));
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
} else
- dec_mm_counter(mm, MM_FILEPAGES);
+ dec_mm_counter(mm, mm_counter_file(page));

page_remove_rmap(page);
page_cache_release(page);
--
2.1.4

2015-02-26 13:51:33

by Vlastimil Babka

Subject: [PATCH 4/4] mm, procfs: Display VmAnon, VmFile and VmShm in /proc/pid/status

From: Jerome Marchand <[email protected]>

It's currently inconvenient to retrieve MM_ANONPAGES value from status
and statm files and there is no way to separate MM_FILEPAGES and
MM_SHMEMPAGES. Add VmAnon, VmFile and VmShm lines in /proc/<pid>/status
to solve these issues.

Signed-off-by: Jerome Marchand <[email protected]>
Signed-off-by: Vlastimil Babka <[email protected]>
---
Documentation/filesystems/proc.txt | 10 +++++++++-
fs/proc/task_mmu.c | 13 +++++++++++--
2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 8b30543..c777adb 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -168,6 +168,9 @@ read the file /proc/PID/status:
VmLck: 0 kB
VmHWM: 476 kB
VmRSS: 476 kB
+ VmAnon: 352 kB
+ VmFile: 120 kB
+ VmShm: 4 kB
VmData: 156 kB
VmStk: 88 kB
VmExe: 68 kB
@@ -224,7 +227,12 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7)
VmSize total program size
VmLck locked memory size
VmHWM peak resident set size ("high water mark")
- VmRSS size of memory portions
+ VmRSS size of memory portions. It contains the three
+ following parts (VmRSS = VmAnon + VmFile + VmShm)
+ VmAnon size of resident anonymous memory
+ VmFile size of resident file mappings
+ VmShm size of resident shmem memory (includes SysV shm,
+ mapping of tmpfs and shared anonymous mappings)
VmData size of data, stack, and text segments
VmStk size of data, stack, and text segments
VmExe size of text segment
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index d70334c..a77a3ac 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -22,7 +22,7 @@

void task_mem(struct seq_file *m, struct mm_struct *mm)
{
- unsigned long data, text, lib, swap, ptes, pmds;
+ unsigned long data, text, lib, swap, ptes, pmds, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;

/*
@@ -39,6 +39,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
if (hiwater_rss < mm->hiwater_rss)
hiwater_rss = mm->hiwater_rss;

+ anon = get_mm_counter(mm, MM_ANONPAGES);
+ file = get_mm_counter(mm, MM_FILEPAGES);
+ shmem = get_mm_counter_shmem(mm);
data = mm->total_vm - mm->shared_vm - mm->stack_vm;
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
@@ -52,6 +55,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
"VmPin:\t%8lu kB\n"
"VmHWM:\t%8lu kB\n"
"VmRSS:\t%8lu kB\n"
+ "VmAnon:\t%8lu kB\n"
+ "VmFile:\t%8lu kB\n"
+ "VmShm:\t%8lu kB\n"
"VmData:\t%8lu kB\n"
"VmStk:\t%8lu kB\n"
"VmExe:\t%8lu kB\n"
@@ -65,6 +71,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
mm->pinned_vm << (PAGE_SHIFT-10),
hiwater_rss << (PAGE_SHIFT-10),
total_rss << (PAGE_SHIFT-10),
+ anon << (PAGE_SHIFT-10),
+ file << (PAGE_SHIFT-10),
+ shmem << (PAGE_SHIFT-10),
data << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
ptes >> 10,
@@ -82,7 +91,7 @@ unsigned long task_statm(struct mm_struct *mm,
unsigned long *data, unsigned long *resident)
{
*shared = get_mm_counter(mm, MM_FILEPAGES) +
- get_mm_counter(mm, MM_SHMEMPAGES);
+ get_mm_counter_shmem(mm);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->total_vm - mm->shared_vm;
--
2.1.4

2015-02-26 14:40:39

by Jerome Marchand

Subject: Re: [PATCH 2/4] mm, procfs: account for shmem swap in /proc/pid/smaps

On 02/26/2015 02:51 PM, Vlastimil Babka wrote:
> Currently, /proc/pid/smaps will always show "Swap: 0 kB" for shmem-backed
> mappings, even if the mapped portion does contain pages that were swapped out.
> This is because unlike private anonymous mappings, shmem does not change pte
> to swap entry, but pte_none when swapping the page out. In the smaps page
> walk, such page thus looks like it was never faulted in.
>
> This patch changes smaps_pte_entry() to determine the swap status for such
> pte_none entries for shmem mappings, similarly to how mincore_page() does it.
> Swapped out pages are thus accounted for.
>
> The accounting is arguably still not as precise as for private anonymous
> mappings, since now we will count also pages that the process in question never
> accessed, but only another process populated them and then let them become
> swapped out. I believe it is still less confusing and subtle than not showing
> any swap usage by shmem mappings at all. Also, swapped out pages only becomee a
> performance issue for future accesses, and we cannot predict those for neither
> kind of mapping.
>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> Documentation/filesystems/proc.txt | 3 ++-
> fs/proc/task_mmu.c | 20 ++++++++++++++++++++
> 2 files changed, 22 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index d4f56ec..8b30543 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -437,7 +437,8 @@ indicates the amount of memory currently marked as referenced or accessed.
> a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
> and a page is modified, the file page is replaced by a private anonymous copy.
> "Swap" shows how much would-be-anonymous memory is also used, but out on
> -swap.
> +swap. For shmem mappings, "Swap" shows how much of the mapped portion of the
> +underlying shmem object is on swap.
>
> "VmFlags" field deserves a separate description. This member represents the kernel
> flags associated with the particular virtual memory area in two letter encoded
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 956b75d..0410309 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -13,6 +13,7 @@
> #include <linux/swap.h>
> #include <linux/swapops.h>
> #include <linux/mmu_notifier.h>
> +#include <linux/shmem_fs.h>
>
> #include <asm/elf.h>
> #include <asm/uaccess.h>
> @@ -496,6 +497,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
> mss->swap += PAGE_SIZE;
> else if (is_migration_entry(swpent))
> page = migration_entry_to_page(swpent);
> + } else if (IS_ENABLED(CONFIG_SHMEM) && IS_ENABLED(CONFIG_SWAP) &&
> + pte_none(*pte) && vma->vm_file) {
> + struct address_space *mapping =
> + file_inode(vma->vm_file)->i_mapping;
> +
> + /*
> + * shmem does not use swap pte's so we have to consult
> + * the radix tree to account for swap
> + */
> + if (shmem_mapping(mapping)) {
> + page = find_get_entry(mapping, pgoff);
> + if (page) {
> + if (radix_tree_exceptional_entry(page))
> + mss->swap += PAGE_SIZE;
> + else
> + page_cache_release(page);
> + }
> + page = NULL;
> + }

Hi Vlastimil,

I'm afraid that isn't enough. Without walking the pte holes too, big
chunks of swapped out shmem pages may be missed.

Jerome

> }
>
> if (!page)
>

Attachments:

2015-02-26 15:00:10

by Jerome Marchand

Subject: Re: [PATCH 3/4] mm, shmem: Add shmem resident memory accounting

On 02/26/2015 02:51 PM, Vlastimil Babka wrote:
> From: Jerome Marchand <[email protected]>
>
> Currently looking at /proc/<pid>/status or statm, there is no way to
> distinguish shmem pages from pages mapped to a regular file (shmem
> pages are mapped to /dev/zero), even though their implication in
> actual memory use is quite different.
> This patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
> shmem pages instead of MM_FILEPAGES.
>
> [[email protected]: port to 4.0, add #ifdefs, mm_counter_file() variant]
> Signed-off-by: Jerome Marchand <[email protected]>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> arch/s390/mm/pgtable.c | 5 +----
> fs/proc/task_mmu.c | 4 +++-
> include/linux/mm.h | 28 ++++++++++++++++++++++++++++
> include/linux/mm_types.h | 9 ++++++---
> kernel/events/uprobes.c | 2 +-
> mm/memory.c | 30 ++++++++++--------------------
> mm/oom_kill.c | 5 +++--
> mm/rmap.c | 15 ++++-----------
> 8 files changed, 56 insertions(+), 42 deletions(-)
>
> diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
> index b2c1542..5bffd5d 100644
> --- a/arch/s390/mm/pgtable.c
> +++ b/arch/s390/mm/pgtable.c
> @@ -617,10 +617,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
> else if (is_migration_entry(entry)) {
> struct page *page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> }
> free_swap_and_cache(entry);
> }
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 0410309..d70334c 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -81,7 +81,8 @@ 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);
> + *shared = get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter(mm, MM_SHMEMPAGES);
> *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
> >> PAGE_SHIFT;
> *data = mm->total_vm - mm->shared_vm;
> @@ -501,6 +502,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
> pte_none(*pte) && vma->vm_file) {
> struct address_space *mapping =
> file_inode(vma->vm_file)->i_mapping;
> + pgoff_t pgoff = linear_page_index(vma, addr);
>
> /*
> * shmem does not use swap pte's so we have to consult
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 47a9392..adfbb5b 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1364,6 +1364,16 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
> return (unsigned long)val;
> }
>
> +/* A wrapper for the CONFIG_SHMEM dependent counter */
> +static inline unsigned long get_mm_counter_shmem(struct mm_struct *mm)
> +{
> +#ifdef CONFIG_SHMEM
> + return get_mm_counter(mm, MM_SHMEMPAGES);
> +#else
> + return 0;
> +#endif
> +}
> +
> static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
> {
> atomic_long_add(value, &mm->rss_stat.count[member]);
> @@ -1379,9 +1389,27 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member)
> atomic_long_dec(&mm->rss_stat.count[member]);
> }
>
> +/* Optimized variant when page is already known not to be PageAnon */
> +static inline int mm_counter_file(struct page *page)

Just a nitpick, but I don't like that name as it keeps the confusion we
currently have between shmem and file backed pages. I'm not sure what
other name to use though. mm_counter_shared() maybe? I'm not sure it is
less confusing...

Jerome

> +{
> +#ifdef CONFIG_SHMEM
> + if (PageSwapBacked(page))
> + return MM_SHMEMPAGES;
> +#endif
> + return MM_FILEPAGES;
> +}
> +
> +static inline int mm_counter(struct page *page)
> +{
> + if (PageAnon(page))
> + return MM_ANONPAGES;
> + return mm_counter_file(page);
> +}
> +
> static inline unsigned long get_mm_rss(struct mm_struct *mm)
> {
> return get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter_shmem(mm) +
> get_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 199a03a..d3c2372 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -327,9 +327,12 @@ struct core_state {
> };
>
> enum {
> - MM_FILEPAGES,
> - MM_ANONPAGES,
> - MM_SWAPENTS,
> + MM_FILEPAGES, /* Resident file mapping pages */
> + MM_ANONPAGES, /* Resident anonymous pages */
> + MM_SWAPENTS, /* Anonymous swap entries */
> +#ifdef CONFIG_SHMEM
> + MM_SHMEMPAGES, /* Resident shared memory pages */
> +#endif
> NR_MM_COUNTERS
> };
>
> diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
> index cb346f2..0a08fdd 100644
> --- a/kernel/events/uprobes.c
> +++ b/kernel/events/uprobes.c
> @@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
> lru_cache_add_active_or_unevictable(kpage, vma);
>
> if (!PageAnon(page)) {
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
> inc_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/mm/memory.c b/mm/memory.c
> index 8068893..f145d9e 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> } else if (is_migration_entry(entry)) {
> page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
>
> if (is_write_migration_entry(entry) &&
> is_cow_mapping(vm_flags)) {
> @@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> if (page) {
> get_page(page);
> page_dup_rmap(page);
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
> }
>
> out_set_pte:
> @@ -1113,9 +1107,8 @@ again:
> tlb_remove_tlb_entry(tlb, pte, addr);
> if (unlikely(!page))
> continue;
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else {
> +
> + if (!PageAnon(page)) {
> if (pte_dirty(ptent)) {
> force_flush = 1;
> set_page_dirty(page);
> @@ -1123,8 +1116,8 @@ again:
> if (pte_young(ptent) &&
> likely(!(vma->vm_flags & VM_SEQ_READ)))
> mark_page_accessed(page);
> - rss[MM_FILEPAGES]--;
> }
> + rss[mm_counter(page)]--;
> page_remove_rmap(page);
> if (unlikely(page_mapcount(page) < 0))
> print_bad_pte(vma, addr, ptent, page);
> @@ -1146,11 +1139,7 @@ again:
> struct page *page;
>
> page = migration_entry_to_page(entry);
> -
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else
> - rss[MM_FILEPAGES]--;
> + rss[mm_counter(page)]--;
> }
> if (unlikely(!free_swap_and_cache(entry)))
> print_bad_pte(vma, addr, ptent, NULL);
> @@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
>
> /* Ok, finally just insert the thing.. */
> get_page(page);
> - inc_mm_counter_fast(mm, MM_FILEPAGES);
> + inc_mm_counter_fast(mm, mm_counter_file(page));
> page_add_file_rmap(page);
> set_pte_at(mm, addr, pte, mk_pte(page, prot));
>
> @@ -2174,7 +2163,8 @@ gotten:
> if (likely(pte_same(*page_table, orig_pte))) {
> if (old_page) {
> if (!PageAnon(old_page)) {
> - dec_mm_counter_fast(mm, MM_FILEPAGES);
> + dec_mm_counter_fast(mm,
> + mm_counter_file(old_page));
> inc_mm_counter_fast(mm, MM_ANONPAGES);
> }
> } else
> @@ -2703,7 +2693,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
> inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
> page_add_new_anon_rmap(page, vma, address);
> } else {
> - inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
> + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
> page_add_file_rmap(page);
> }
> set_pte_at(vma->vm_mm, address, pte, entry);
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 642f38c..a5ee3a2 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -573,10 +573,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
> /* mm cannot safely be dereferenced after task_unlock(victim) */
> mm = victim->mm;
> mark_tsk_oom_victim(victim);
> - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
> + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
> task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
> K(get_mm_counter(victim->mm, MM_ANONPAGES)),
> - K(get_mm_counter(victim->mm, MM_FILEPAGES)));
> + K(get_mm_counter(victim->mm, MM_FILEPAGES)),
> + K(get_mm_counter_shmem(victim->mm)));
> task_unlock(victim);
>
> /*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 5e3e090..e3c4392 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1216,12 +1216,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> update_hiwater_rss(mm);
>
> if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
> - if (!PageHuge(page)) {
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> - }
> + if (!PageHuge(page))
> + dec_mm_counter(mm, mm_counter(page));
> set_pte_at(mm, address, pte,
> swp_entry_to_pte(make_hwpoison_entry(page)));
> } else if (pte_unused(pteval)) {
> @@ -1230,10 +1226,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> * interest anymore. Simply discard the pte, vmscan
> * will take care of the rest.
> */
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> } else if (PageAnon(page)) {
> swp_entry_t entry = { .val = page_private(page) };
> pte_t swp_pte;
> @@ -1276,7 +1269,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> entry = make_migration_entry(page, pte_write(pteval));
> set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
> } else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
>
> page_remove_rmap(page);
> page_cache_release(page);
>

Attachments:

2015-02-27 04:03:02

by Hillf Danton

Subject: Re: [PATCH 3/4] mm, shmem: Add shmem resident memory accounting

> @@ -501,6 +502,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
> pte_none(*pte) && vma->vm_file) {
> struct address_space *mapping =
> file_inode(vma->vm_file)->i_mapping;
> + pgoff_t pgoff = linear_page_index(vma, addr);
>
> /*
> * shmem does not use swap pte's so we have to consult

This hunk should go to patch 2/4
Hillf

2015-02-27 10:37:08

by Michael Kerrisk (man-pages)

Subject: Re: [PATCH 0/4] enhance shmem process and swap accounting

[CC += linux-api@]

Hello Vlastimil,

Since this is a kernel-user-space API change, please CC linux-api@.
The kernel source file Documentation/SubmitChecklist notes that all
Linux kernel patches that change userspace interfaces should be CCed
to [email protected], so that the various parties who are
interested in API changes are informed. For further information, see
https://www.kernel.org/doc/man-pages/linux-api-ml.html

Cheers,

Michael


On Thu, Feb 26, 2015 at 2:51 PM, Vlastimil Babka <[email protected]> wrote:
> This series is based on Jerome Marchand's [1] so let me quote the first
> paragraph from there:
>
> There are several shortcomings with the accounting of shared memory
> (sysV shm, shared anonymous mapping, mapping to a tmpfs file). The
> values in /proc/<pid>/status and statm don't allow to distinguish
> between shmem memory and a shared mapping to a regular file, even
> though theirs implication on memory usage are quite different: at
> reclaim, file mapping can be dropped or write back on disk while shmem
> needs a place in swap. As for shmem pages that are swapped-out or in
> swap cache, they aren't accounted at all.
>
> The original motivation for myself is that a customer found (IMHO rightfully)
> confusing that e.g. top output for process swap usage is unreliable with
> respect to swapped out shmem pages, which are not accounted for.
>
> The fundamental difference between private anonymous and shmem pages is that
> the latter has PTE's converted to pte_none, and not swapents. As such, they are
> not accounted to the number of swapents visible e.g. in /proc/pid/status VmSwap
> row. It might be theoretically possible to use swapents when swapping out shmem
> (without extra cost, as one has to change all mappers anyway), and on swap in
> only convert the swapent for the faulting process, leaving swapents in other
> processes until they also fault (so again no extra cost). But I don't know how
> many assumptions this would break, and it would be too disruptive change for a
> relatively small benefit.
>
> Instead, my approach is to document the limitation of VmSwap, and provide means
> to determine the swap usage for shmem areas for those who are interested and
> willing to pay the price, using /proc/pid/smaps. Because outside of ipcs, I
> don't think it's possible to currently to determine the usage at all. The
> previous patchset [1] did introduce new shmem-specific fields into smaps
> output, and functions to determine the values. I take a simpler approach,
> noting that smaps output already has a "Swap: X kB" line, where currently X ==
> 0 always for shmem areas. I think we can just consider this a bug and provide
> the proper value by consulting the radix tree, as e.g. mincore_page() does. In the
> patch changelog I explain why this is also not perfect (and cannot be without
> swapents), but still arguably much better than showing a 0.
>
> The last two patches are adapted from Jerome's patchset and provide a VmRSS
> breakdown to VmAnon, VmFile and VmShm in /proc/pid/status. Hugh noted that
> this is a welcome addition, and I agree that it might help e.g. debugging
> process memory usage at albeit non-zero, but still rather low cost of extra
> per-mm counter and some page flag checks. I updated these patches to 4.0-rc1,
> made them respect !CONFIG_SHMEM so that tiny systems don't pay the cost, and
> optimized the page flag checking somewhat.
>
> [1] http://lwn.net/Articles/611966/
>
> Jerome Marchand (2):
> mm, shmem: Add shmem resident memory accounting
> mm, procfs: Display VmAnon, VmFile and VmShm in /proc/pid/status
>
> Vlastimil Babka (2):
> mm, documentation: clarify /proc/pid/status VmSwap limitations
> mm, proc: account for shmem swap in /proc/pid/smaps
>
> Documentation/filesystems/proc.txt | 15 +++++++++++++--
> arch/s390/mm/pgtable.c | 5 +----
> fs/proc/task_mmu.c | 35 +++++++++++++++++++++++++++++++++--
> include/linux/mm.h | 28 ++++++++++++++++++++++++++++
> include/linux/mm_types.h | 9 ++++++---
> kernel/events/uprobes.c | 2 +-
> mm/memory.c | 30 ++++++++++--------------------
> mm/oom_kill.c | 5 +++--
> mm/rmap.c | 15 ++++-----------
> 9 files changed, 99 insertions(+), 45 deletions(-)
>
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to [email protected]. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"[email protected]"> [email protected] </a>



--
Michael Kerrisk Linux man-pages maintainer;
http://www.kernel.org/doc/man-pages/
Author of "The Linux Programming Interface", http://blog.man7.org/

2015-02-27 10:37:59

by Michael Kerrisk (man-pages)

Subject: Re: [PATCH 1/4] mm, documentation: clarify /proc/pid/status VmSwap limitations

[CC += linux-api@]

On Thu, Feb 26, 2015 at 2:51 PM, Vlastimil Babka <[email protected]> wrote:
> The documentation for /proc/pid/status does not mention that the value of
> VmSwap counts only swapped out anonymous private pages and not shmem. This is
> not obvious, so document this limitation.
>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> I've noticed that proc(5) manpage is currently missing the VmSwap field
> altogether.
>
> Documentation/filesystems/proc.txt | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index a07ba61..d4f56ec 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -231,6 +231,8 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7)
> VmLib size of shared library code
> VmPTE size of page table entries
> VmSwap size of swap usage (the number of referred swapents)
> + by anonymous private data (shmem swap usage is not
> + included)
> Threads number of threads
> SigQ number of signals queued/max. number for queue
> SigPnd bitmap of pending signals for the thread
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to [email protected]. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"[email protected]"> [email protected] </a>



--
Michael Kerrisk Linux man-pages maintainer;
http://www.kernel.org/doc/man-pages/
Author of "The Linux Programming Interface", http://blog.man7.org/

2015-02-27 10:38:28

by Michael Kerrisk (man-pages)

Subject: Re: [PATCH 2/4] mm, procfs: account for shmem swap in /proc/pid/smaps

[CC += linux-api@]

On Thu, Feb 26, 2015 at 2:51 PM, Vlastimil Babka <[email protected]> wrote:
> Currently, /proc/pid/smaps will always show "Swap: 0 kB" for shmem-backed
> mappings, even if the mapped portion does contain pages that were swapped out.
> This is because unlike private anonymous mappings, shmem does not change pte
> to swap entry, but pte_none when swapping the page out. In the smaps page
> walk, such page thus looks like it was never faulted in.
>
> This patch changes smaps_pte_entry() to determine the swap status for such
> pte_none entries for shmem mappings, similarly to how mincore_page() does it.
> Swapped out pages are thus accounted for.
>
> The accounting is arguably still not as precise as for private anonymous
> mappings, since now we will count also pages that the process in question never
> accessed, but only another process populated them and then let them become
> swapped out. I believe it is still less confusing and subtle than not showing
> any swap usage by shmem mappings at all. Also, swapped out pages only becomee a
> performance issue for future accesses, and we cannot predict those for neither
> kind of mapping.
>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> Documentation/filesystems/proc.txt | 3 ++-
> fs/proc/task_mmu.c | 20 ++++++++++++++++++++
> 2 files changed, 22 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index d4f56ec..8b30543 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -437,7 +437,8 @@ indicates the amount of memory currently marked as referenced or accessed.
> a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
> and a page is modified, the file page is replaced by a private anonymous copy.
> "Swap" shows how much would-be-anonymous memory is also used, but out on
> -swap.
> +swap. For shmem mappings, "Swap" shows how much of the mapped portion of the
> +underlying shmem object is on swap.
>
> "VmFlags" field deserves a separate description. This member represents the kernel
> flags associated with the particular virtual memory area in two letter encoded
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 956b75d..0410309 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -13,6 +13,7 @@
> #include <linux/swap.h>
> #include <linux/swapops.h>
> #include <linux/mmu_notifier.h>
> +#include <linux/shmem_fs.h>
>
> #include <asm/elf.h>
> #include <asm/uaccess.h>
> @@ -496,6 +497,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
> mss->swap += PAGE_SIZE;
> else if (is_migration_entry(swpent))
> page = migration_entry_to_page(swpent);
> + } else if (IS_ENABLED(CONFIG_SHMEM) && IS_ENABLED(CONFIG_SWAP) &&
> + pte_none(*pte) && vma->vm_file) {
> + struct address_space *mapping =
> + file_inode(vma->vm_file)->i_mapping;
> +
> + /*
> + * shmem does not use swap pte's so we have to consult
> + * the radix tree to account for swap
> + */
> + if (shmem_mapping(mapping)) {
> + page = find_get_entry(mapping, pgoff);
> + if (page) {
> + if (radix_tree_exceptional_entry(page))
> + mss->swap += PAGE_SIZE;
> + else
> + page_cache_release(page);
> + }
> + page = NULL;
> + }
> }
>
> if (!page)
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to [email protected]. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"[email protected]"> [email protected] </a>



--
Michael Kerrisk Linux man-pages maintainer;
http://www.kernel.org/doc/man-pages/
Author of "The Linux Programming Interface", http://blog.man7.org/

2015-02-27 10:38:52

by Michael Kerrisk (man-pages)

Subject: Re: [PATCH 3/4] mm, shmem: Add shmem resident memory accounting

[CC += linux-api@]

On Thu, Feb 26, 2015 at 2:51 PM, Vlastimil Babka <[email protected]> wrote:
> From: Jerome Marchand <[email protected]>
>
> Currently looking at /proc/<pid>/status or statm, there is no way to
> distinguish shmem pages from pages mapped to a regular file (shmem
> pages are mapped to /dev/zero), even though their implication in
> actual memory use is quite different.
> This patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for
> shmem pages instead of MM_FILEPAGES.
>
> [[email protected]: port to 4.0, add #ifdefs, mm_counter_file() variant]
> Signed-off-by: Jerome Marchand <[email protected]>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> arch/s390/mm/pgtable.c | 5 +----
> fs/proc/task_mmu.c | 4 +++-
> include/linux/mm.h | 28 ++++++++++++++++++++++++++++
> include/linux/mm_types.h | 9 ++++++---
> kernel/events/uprobes.c | 2 +-
> mm/memory.c | 30 ++++++++++--------------------
> mm/oom_kill.c | 5 +++--
> mm/rmap.c | 15 ++++-----------
> 8 files changed, 56 insertions(+), 42 deletions(-)
>
> diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
> index b2c1542..5bffd5d 100644
> --- a/arch/s390/mm/pgtable.c
> +++ b/arch/s390/mm/pgtable.c
> @@ -617,10 +617,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
> else if (is_migration_entry(entry)) {
> struct page *page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> }
> free_swap_and_cache(entry);
> }
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 0410309..d70334c 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -81,7 +81,8 @@ 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);
> + *shared = get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter(mm, MM_SHMEMPAGES);
> *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
> >> PAGE_SHIFT;
> *data = mm->total_vm - mm->shared_vm;
> @@ -501,6 +502,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
> pte_none(*pte) && vma->vm_file) {
> struct address_space *mapping =
> file_inode(vma->vm_file)->i_mapping;
> + pgoff_t pgoff = linear_page_index(vma, addr);
>
> /*
> * shmem does not use swap pte's so we have to consult
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 47a9392..adfbb5b 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1364,6 +1364,16 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
> return (unsigned long)val;
> }
>
> +/* A wrapper for the CONFIG_SHMEM dependent counter */
> +static inline unsigned long get_mm_counter_shmem(struct mm_struct *mm)
> +{
> +#ifdef CONFIG_SHMEM
> + return get_mm_counter(mm, MM_SHMEMPAGES);
> +#else
> + return 0;
> +#endif
> +}
> +
> static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
> {
> atomic_long_add(value, &mm->rss_stat.count[member]);
> @@ -1379,9 +1389,27 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member)
> atomic_long_dec(&mm->rss_stat.count[member]);
> }
>
> +/* Optimized variant when page is already known not to be PageAnon */
> +static inline int mm_counter_file(struct page *page)
> +{
> +#ifdef CONFIG_SHMEM
> + if (PageSwapBacked(page))
> + return MM_SHMEMPAGES;
> +#endif
> + return MM_FILEPAGES;
> +}
> +
> +static inline int mm_counter(struct page *page)
> +{
> + if (PageAnon(page))
> + return MM_ANONPAGES;
> + return mm_counter_file(page);
> +}
> +
> static inline unsigned long get_mm_rss(struct mm_struct *mm)
> {
> return get_mm_counter(mm, MM_FILEPAGES) +
> + get_mm_counter_shmem(mm) +
> get_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 199a03a..d3c2372 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -327,9 +327,12 @@ struct core_state {
> };
>
> enum {
> - MM_FILEPAGES,
> - MM_ANONPAGES,
> - MM_SWAPENTS,
> + MM_FILEPAGES, /* Resident file mapping pages */
> + MM_ANONPAGES, /* Resident anonymous pages */
> + MM_SWAPENTS, /* Anonymous swap entries */
> +#ifdef CONFIG_SHMEM
> + MM_SHMEMPAGES, /* Resident shared memory pages */
> +#endif
> NR_MM_COUNTERS
> };
>
> diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
> index cb346f2..0a08fdd 100644
> --- a/kernel/events/uprobes.c
> +++ b/kernel/events/uprobes.c
> @@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
> lru_cache_add_active_or_unevictable(kpage, vma);
>
> if (!PageAnon(page)) {
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
> inc_mm_counter(mm, MM_ANONPAGES);
> }
>
> diff --git a/mm/memory.c b/mm/memory.c
> index 8068893..f145d9e 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> } else if (is_migration_entry(entry)) {
> page = migration_entry_to_page(entry);
>
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
>
> if (is_write_migration_entry(entry) &&
> is_cow_mapping(vm_flags)) {
> @@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> if (page) {
> get_page(page);
> page_dup_rmap(page);
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]++;
> - else
> - rss[MM_FILEPAGES]++;
> + rss[mm_counter(page)]++;
> }
>
> out_set_pte:
> @@ -1113,9 +1107,8 @@ again:
> tlb_remove_tlb_entry(tlb, pte, addr);
> if (unlikely(!page))
> continue;
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else {
> +
> + if (!PageAnon(page)) {
> if (pte_dirty(ptent)) {
> force_flush = 1;
> set_page_dirty(page);
> @@ -1123,8 +1116,8 @@ again:
> if (pte_young(ptent) &&
> likely(!(vma->vm_flags & VM_SEQ_READ)))
> mark_page_accessed(page);
> - rss[MM_FILEPAGES]--;
> }
> + rss[mm_counter(page)]--;
> page_remove_rmap(page);
> if (unlikely(page_mapcount(page) < 0))
> print_bad_pte(vma, addr, ptent, page);
> @@ -1146,11 +1139,7 @@ again:
> struct page *page;
>
> page = migration_entry_to_page(entry);
> -
> - if (PageAnon(page))
> - rss[MM_ANONPAGES]--;
> - else
> - rss[MM_FILEPAGES]--;
> + rss[mm_counter(page)]--;
> }
> if (unlikely(!free_swap_and_cache(entry)))
> print_bad_pte(vma, addr, ptent, NULL);
> @@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
>
> /* Ok, finally just insert the thing.. */
> get_page(page);
> - inc_mm_counter_fast(mm, MM_FILEPAGES);
> + inc_mm_counter_fast(mm, mm_counter_file(page));
> page_add_file_rmap(page);
> set_pte_at(mm, addr, pte, mk_pte(page, prot));
>
> @@ -2174,7 +2163,8 @@ gotten:
> if (likely(pte_same(*page_table, orig_pte))) {
> if (old_page) {
> if (!PageAnon(old_page)) {
> - dec_mm_counter_fast(mm, MM_FILEPAGES);
> + dec_mm_counter_fast(mm,
> + mm_counter_file(old_page));
> inc_mm_counter_fast(mm, MM_ANONPAGES);
> }
> } else
> @@ -2703,7 +2693,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
> inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
> page_add_new_anon_rmap(page, vma, address);
> } else {
> - inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
> + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
> page_add_file_rmap(page);
> }
> set_pte_at(vma->vm_mm, address, pte, entry);
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> index 642f38c..a5ee3a2 100644
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -573,10 +573,11 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
> /* mm cannot safely be dereferenced after task_unlock(victim) */
> mm = victim->mm;
> mark_tsk_oom_victim(victim);
> - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
> + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
> task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
> K(get_mm_counter(victim->mm, MM_ANONPAGES)),
> - K(get_mm_counter(victim->mm, MM_FILEPAGES)));
> + K(get_mm_counter(victim->mm, MM_FILEPAGES)),
> + K(get_mm_counter_shmem(victim->mm)));
> task_unlock(victim);
>
> /*
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 5e3e090..e3c4392 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1216,12 +1216,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> update_hiwater_rss(mm);
>
> if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
> - if (!PageHuge(page)) {
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> - }
> + if (!PageHuge(page))
> + dec_mm_counter(mm, mm_counter(page));
> set_pte_at(mm, address, pte,
> swp_entry_to_pte(make_hwpoison_entry(page)));
> } else if (pte_unused(pteval)) {
> @@ -1230,10 +1226,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> * interest anymore. Simply discard the pte, vmscan
> * will take care of the rest.
> */
> - if (PageAnon(page))
> - dec_mm_counter(mm, MM_ANONPAGES);
> - else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter(page));
> } else if (PageAnon(page)) {
> swp_entry_t entry = { .val = page_private(page) };
> pte_t swp_pte;
> @@ -1276,7 +1269,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> entry = make_migration_entry(page, pte_write(pteval));
> set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
> } else
> - dec_mm_counter(mm, MM_FILEPAGES);
> + dec_mm_counter(mm, mm_counter_file(page));
>
> page_remove_rmap(page);
> page_cache_release(page);
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to [email protected]. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"[email protected]"> [email protected] </a>



--
Michael Kerrisk Linux man-pages maintainer;
http://www.kernel.org/doc/man-pages/
Author of "The Linux Programming Interface", http://blog.man7.org/

2015-02-27 10:39:12

by Michael Kerrisk (man-pages)

Subject: Re: [PATCH 4/4] mm, procfs: Display VmAnon, VmFile and VmShm in /proc/pid/status

[CC += linux-api@]

On Thu, Feb 26, 2015 at 2:51 PM, Vlastimil Babka <[email protected]> wrote:
> From: Jerome Marchand <[email protected]>
>
> It's currently inconvenient to retrieve MM_ANONPAGES value from status
> and statm files and there is no way to separate MM_FILEPAGES and
> MM_SHMEMPAGES. Add VmAnon, VmFile and VmShm lines in /proc/<pid>/status
> to solve these issues.
>
> Signed-off-by: Jerome Marchand <[email protected]>
> Signed-off-by: Vlastimil Babka <[email protected]>
> ---
> Documentation/filesystems/proc.txt | 10 +++++++++-
> fs/proc/task_mmu.c | 13 +++++++++++--
> 2 files changed, 20 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index 8b30543..c777adb 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -168,6 +168,9 @@ read the file /proc/PID/status:
> VmLck: 0 kB
> VmHWM: 476 kB
> VmRSS: 476 kB
> + VmAnon: 352 kB
> + VmFile: 120 kB
> + VmShm: 4 kB
> VmData: 156 kB
> VmStk: 88 kB
> VmExe: 68 kB
> @@ -224,7 +227,12 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7)
> VmSize total program size
> VmLck locked memory size
> VmHWM peak resident set size ("high water mark")
> - VmRSS size of memory portions
> + VmRSS size of memory portions. It contains the three
> + following parts (VmRSS = VmAnon + VmFile + VmShm)
> + VmAnon size of resident anonymous memory
> + VmFile size of resident file mappings
> + VmShm size of resident shmem memory (includes SysV shm,
> + mapping of tmpfs and shared anonymous mappings)
> VmData size of data, stack, and text segments
> VmStk size of data, stack, and text segments
> VmExe size of text segment
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index d70334c..a77a3ac 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -22,7 +22,7 @@
>
> void task_mem(struct seq_file *m, struct mm_struct *mm)
> {
> - unsigned long data, text, lib, swap, ptes, pmds;
> + unsigned long data, text, lib, swap, ptes, pmds, anon, file, shmem;
> unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
>
> /*
> @@ -39,6 +39,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
> if (hiwater_rss < mm->hiwater_rss)
> hiwater_rss = mm->hiwater_rss;
>
> + anon = get_mm_counter(mm, MM_ANONPAGES);
> + file = get_mm_counter(mm, MM_FILEPAGES);
> + shmem = get_mm_counter_shmem(mm);
> data = mm->total_vm - mm->shared_vm - mm->stack_vm;
> text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
> lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
> @@ -52,6 +55,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
> "VmPin:\t%8lu kB\n"
> "VmHWM:\t%8lu kB\n"
> "VmRSS:\t%8lu kB\n"
> + "VmAnon:\t%8lu kB\n"
> + "VmFile:\t%8lu kB\n"
> + "VmShm:\t%8lu kB\n"
> "VmData:\t%8lu kB\n"
> "VmStk:\t%8lu kB\n"
> "VmExe:\t%8lu kB\n"
> @@ -65,6 +71,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
> mm->pinned_vm << (PAGE_SHIFT-10),
> hiwater_rss << (PAGE_SHIFT-10),
> total_rss << (PAGE_SHIFT-10),
> + anon << (PAGE_SHIFT-10),
> + file << (PAGE_SHIFT-10),
> + shmem << (PAGE_SHIFT-10),
> data << (PAGE_SHIFT-10),
> mm->stack_vm << (PAGE_SHIFT-10), text, lib,
> ptes >> 10,
> @@ -82,7 +91,7 @@ unsigned long task_statm(struct mm_struct *mm,
> unsigned long *data, unsigned long *resident)
> {
> *shared = get_mm_counter(mm, MM_FILEPAGES) +
> - get_mm_counter(mm, MM_SHMEMPAGES);
> + get_mm_counter_shmem(mm);
> *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
> >> PAGE_SHIFT;
> *data = mm->total_vm - mm->shared_vm;
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to [email protected]. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"[email protected]"> [email protected] </a>



--
Michael Kerrisk Linux man-pages maintainer;
http://www.kernel.org/doc/man-pages/
Author of "The Linux Programming Interface", http://blog.man7.org/

2015-02-27 10:52:28

by Vlastimil Babka

Subject: Re: [PATCH 0/4] enhance shmem process and swap accounting

On 02/27/2015 11:36 AM, Michael Kerrisk wrote:
> [CC += linux-api@]
>
> Hello Vlastimil,
>
> Since this is a kernel-user-space API change, please CC linux-api@.
> The kernel source file Documentation/SubmitChecklist notes that all
> Linux kernel patches that change userspace interfaces should be CCed
> to [email protected], so that the various parties who are
> interested in API changes are informed. For further information, see
> https://www.kernel.org/doc/man-pages/linux-api-ml.html

Yes I meant to do that but forgot in the end, what a shame. Sorry for the trouble.