The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100436-ergonomic-enviably-bf14@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001
From: Zheng Yejian <zhengyejian1(a)huawei.com>
Date: Thu, 21 Sep 2023 20:54:25 +0800
Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats
The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of
bytes in cpu buffer that have not been consumed. However, currently
after consuming data by reading file 'trace_pipe', the 'bytes' info
was not changed as expected.
# cat per_cpu/cpu0/stats
entries: 0
overrun: 0
commit overrun: 0
bytes: 568 <--- 'bytes' is problematical !!!
oldest event ts: 8651.371479
now ts: 8653.912224
dropped events: 0
read events: 8
The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it:
1. When stat 'read_bytes', account consumed event in rb_advance_reader();
2. When stat 'entries_bytes', exclude the discarded padding event which
is smaller than minimum size because it is invisible to reader. Then
use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for
page-based read/remove/overrun.
Also correct the comments of ring_buffer_bytes_cpu() in this patch.
Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye…
Cc: stable(a)vger.kernel.org
Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events")
Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1651edc48d5..28daf0ce95c5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage)
local_set(&bpage->commit, 0);
}
+static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
static void free_buffer_page(struct buffer_page *bpage)
{
free_page((unsigned long)bpage->page);
@@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
* Increment overrun to account for the lost events.
*/
local_add(page_entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
}
@@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->read);
}
-static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
-{
- return local_read(&bpage->page->commit);
-}
-
static struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
@@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
* the counters.
*/
local_add(entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
/*
@@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
- /* account for padding bytes */
- local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
-
/*
* Save the original length to the meta data.
* This will be used by the reader to add lost event
@@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* write counter enough to allow another writer to slip
* in on this page.
* We put in a discarded commit instead, to make sure
- * that this space is not used again.
+ * that this space is not used again, and this space will
+ * not be accounted into 'entries_bytes'.
*
* If we are less than the minimum size, we don't need to
* worry about it.
@@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* time delta must be non zero */
event->time_delta = 1;
+ /* account for padding bytes */
+ local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
/* Make sure the padding is visible before the tail_page->write update */
smp_wmb();
@@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
/**
- * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer
* @buffer: The ring buffer
* @cpu: The per CPU buffer to read from.
*/
@@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
length = rb_event_length(event);
cpu_buffer->reader_page->read += length;
+ cpu_buffer->read_bytes += length;
}
static void rb_advance_iter(struct ring_buffer_iter *iter)
@@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
} else {
/* update the entry counter */
cpu_buffer->read += rb_page_entries(reader);
- cpu_buffer->read_bytes += BUF_PAGE_SIZE;
+ cpu_buffer->read_bytes += rb_page_commit(reader);
/* swap the pages */
rb_init_page(bpage);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100434-majestic-daisy-4a02@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001
From: Zheng Yejian <zhengyejian1(a)huawei.com>
Date: Thu, 21 Sep 2023 20:54:25 +0800
Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats
The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of
bytes in cpu buffer that have not been consumed. However, currently
after consuming data by reading file 'trace_pipe', the 'bytes' info
was not changed as expected.
# cat per_cpu/cpu0/stats
entries: 0
overrun: 0
commit overrun: 0
bytes: 568 <--- 'bytes' is problematical !!!
oldest event ts: 8651.371479
now ts: 8653.912224
dropped events: 0
read events: 8
The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it:
1. When stat 'read_bytes', account consumed event in rb_advance_reader();
2. When stat 'entries_bytes', exclude the discarded padding event which
is smaller than minimum size because it is invisible to reader. Then
use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for
page-based read/remove/overrun.
Also correct the comments of ring_buffer_bytes_cpu() in this patch.
Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye…
Cc: stable(a)vger.kernel.org
Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events")
Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1651edc48d5..28daf0ce95c5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage)
local_set(&bpage->commit, 0);
}
+static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
static void free_buffer_page(struct buffer_page *bpage)
{
free_page((unsigned long)bpage->page);
@@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
* Increment overrun to account for the lost events.
*/
local_add(page_entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
}
@@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->read);
}
-static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
-{
- return local_read(&bpage->page->commit);
-}
-
static struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
@@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
* the counters.
*/
local_add(entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
/*
@@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
- /* account for padding bytes */
- local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
-
/*
* Save the original length to the meta data.
* This will be used by the reader to add lost event
@@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* write counter enough to allow another writer to slip
* in on this page.
* We put in a discarded commit instead, to make sure
- * that this space is not used again.
+ * that this space is not used again, and this space will
+ * not be accounted into 'entries_bytes'.
*
* If we are less than the minimum size, we don't need to
* worry about it.
@@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* time delta must be non zero */
event->time_delta = 1;
+ /* account for padding bytes */
+ local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
/* Make sure the padding is visible before the tail_page->write update */
smp_wmb();
@@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
/**
- * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer
* @buffer: The ring buffer
* @cpu: The per CPU buffer to read from.
*/
@@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
length = rb_event_length(event);
cpu_buffer->reader_page->read += length;
+ cpu_buffer->read_bytes += length;
}
static void rb_advance_iter(struct ring_buffer_iter *iter)
@@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
} else {
/* update the entry counter */
cpu_buffer->read += rb_page_entries(reader);
- cpu_buffer->read_bytes += BUF_PAGE_SIZE;
+ cpu_buffer->read_bytes += rb_page_commit(reader);
/* swap the pages */
rb_init_page(bpage);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 45d99ea451d0c30bfd4864f0fe485d7dac014902
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100433-pumice-despise-a596@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 45d99ea451d0c30bfd4864f0fe485d7dac014902 Mon Sep 17 00:00:00 2001
From: Zheng Yejian <zhengyejian1(a)huawei.com>
Date: Thu, 21 Sep 2023 20:54:25 +0800
Subject: [PATCH] ring-buffer: Fix bytes info in per_cpu buffer stats
The 'bytes' info in file 'per_cpu/cpu<X>/stats' means the number of
bytes in cpu buffer that have not been consumed. However, currently
after consuming data by reading file 'trace_pipe', the 'bytes' info
was not changed as expected.
# cat per_cpu/cpu0/stats
entries: 0
overrun: 0
commit overrun: 0
bytes: 568 <--- 'bytes' is problematical !!!
oldest event ts: 8651.371479
now ts: 8653.912224
dropped events: 0
read events: 8
The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it:
1. When stat 'read_bytes', account consumed event in rb_advance_reader();
2. When stat 'entries_bytes', exclude the discarded padding event which
is smaller than minimum size because it is invisible to reader. Then
use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for
page-based read/remove/overrun.
Also correct the comments of ring_buffer_bytes_cpu() in this patch.
Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengye…
Cc: stable(a)vger.kernel.org
Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events")
Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1651edc48d5..28daf0ce95c5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage)
local_set(&bpage->commit, 0);
}
+static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
static void free_buffer_page(struct buffer_page *bpage)
{
free_page((unsigned long)bpage->page);
@@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
* Increment overrun to account for the lost events.
*/
local_add(page_entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
}
@@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->read);
}
-static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
-{
- return local_read(&bpage->page->commit);
-}
-
static struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
@@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
* the counters.
*/
local_add(entries, &cpu_buffer->overrun);
- local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+ local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes);
local_inc(&cpu_buffer->pages_lost);
/*
@@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
- /* account for padding bytes */
- local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
-
/*
* Save the original length to the meta data.
* This will be used by the reader to add lost event
@@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* write counter enough to allow another writer to slip
* in on this page.
* We put in a discarded commit instead, to make sure
- * that this space is not used again.
+ * that this space is not used again, and this space will
+ * not be accounted into 'entries_bytes'.
*
* If we are less than the minimum size, we don't need to
* worry about it.
@@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* time delta must be non zero */
event->time_delta = 1;
+ /* account for padding bytes */
+ local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
/* Make sure the padding is visible before the tail_page->write update */
smp_wmb();
@@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu)
EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
/**
- * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer
* @buffer: The ring buffer
* @cpu: The per CPU buffer to read from.
*/
@@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
length = rb_event_length(event);
cpu_buffer->reader_page->read += length;
+ cpu_buffer->read_bytes += length;
}
static void rb_advance_iter(struct ring_buffer_iter *iter)
@@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
} else {
/* update the entry counter */
cpu_buffer->read += rb_page_entries(reader);
- cpu_buffer->read_bytes += BUF_PAGE_SIZE;
+ cpu_buffer->read_bytes += rb_page_commit(reader);
/* swap the pages */
rb_init_page(bpage);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100431-ascertain-evade-5e53@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100429-unwatched-blaspheme-2d9d@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100427-urban-cognition-691b@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100424-koala-ivory-c2e4@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100422-twistable-umbrella-a71d@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100420-grafting-raft-1e1b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang(a)os.amperecomputing.com>
Date: Wed, 20 Sep 2023 15:32:42 -0700
Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and
MPOL_MF_MOVE are specified
When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel
should attempt to migrate all existing pages, and return -EIO if there is
misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply
page table walker on queue_pages_range()") messed up the return value and
didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The
return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy:
make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke
the VMA walk early if unmovable page is met, it may cause some pages are
not migrated as expected.
The code should conceptually do:
if (MPOL_MF_MOVE|MOVEALL)
scan all vmas
try to migrate the existing pages
return success
else if (MPOL_MF_MOVE* | MPOL_MF_STRICT)
scan all vmas
try to migrate the existing pages
return -EIO if unmovable or migration failed
else /* MPOL_MF_STRICT alone */
break early if meets unmovable and don't call mbind_range() at all
else /* none of those flags */
check the ranges in test_walk, EFAULT without mbind_range() if discontig.
Fixed the behavior.
Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.…
Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified")
Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Rafael Aquini <aquini(a)redhat.com>
Cc: Kirill A. Shutemov <kirill(a)shutemov.name>
Cc: David Rientjes <rientjes(a)google.com>
Cc: <stable(a)vger.kernel.org> [4.9+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 578d7699e5c2add8c2e9549d9d75dfb56c460cb3
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100409-shorten-demanding-15d2@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 Mon Sep 17 00:00:00 2001
From: Ben Wolsieffer <Ben.Wolsieffer(a)hefring.com>
Date: Thu, 14 Sep 2023 12:30:20 -0400
Subject: [PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock
The no-MMU implementation of /proc/<pid>/map doesn't normally release
the mmap read lock, because it uses !IS_ERR_OR_NULL(_vml) to determine
whether to release the lock. Since _vml is NULL when the end of the
mappings is reached, the lock is not released.
Reading /proc/1/maps twice doesn't cause a hang because it only
takes the read lock, which can be taken multiple times and therefore
doesn't show any problem if the lock isn't released. Instead, you need
to perform some operation that attempts to take the write lock after
reading /proc/<pid>/maps. To actually reproduce the bug, compile the
following code as 'proc_maps_bug':
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>
int main(int argc, char *argv[]) {
void *buf;
sleep(1);
buf = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
puts("mmap returned");
return 0;
}
Then, run:
./proc_maps_bug &; cat /proc/$!/maps; fg
Without this patch, mmap() will hang and the command will never
complete.
This code was incorrectly adapted from the MMU implementation, which at
the time released the lock in m_next() before returning the last entry.
The MMU implementation has diverged further from the no-MMU version since
then, so this patch brings their locking and error handling into sync,
fixing the bug and hopefully avoiding similar issues in the future.
Link: https://lkml.kernel.org/r/20230914163019.4050530-2-ben.wolsieffer@hefring.c…
Fixes: 47fecca15c09 ("fs/proc/task_nommu.c: don't use priv->task->mm")
Signed-off-by: Ben Wolsieffer <ben.wolsieffer(a)hefring.com>
Acked-by: Oleg Nesterov <oleg(a)redhat.com>
Cc: Giulio Benetti <giulio.benetti(a)benettiengineering.com>
Cc: Greg Ungerer <gerg(a)uclinux.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index a8ac0dd8041e..bc2e843f4810 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -192,11 +192,16 @@ static void *m_start(struct seq_file *m, loff_t *pos)
return ERR_PTR(-ESRCH);
mm = priv->mm;
- if (!mm || !mmget_not_zero(mm))
+ if (!mm || !mmget_not_zero(mm)) {
+ put_task_struct(priv->task);
+ priv->task = NULL;
return NULL;
+ }
if (mmap_read_lock_killable(mm)) {
mmput(mm);
+ put_task_struct(priv->task);
+ priv->task = NULL;
return ERR_PTR(-EINTR);
}
@@ -205,23 +210,21 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (vma)
return vma;
- mmap_read_unlock(mm);
- mmput(mm);
return NULL;
}
-static void m_stop(struct seq_file *m, void *_vml)
+static void m_stop(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
+ struct mm_struct *mm = priv->mm;
- if (!IS_ERR_OR_NULL(_vml)) {
- mmap_read_unlock(priv->mm);
- mmput(priv->mm);
- }
- if (priv->task) {
- put_task_struct(priv->task);
- priv->task = NULL;
- }
+ if (!priv->task)
+ return;
+
+ mmap_read_unlock(mm);
+ mmput(mm);
+ put_task_struct(priv->task);
+ priv->task = NULL;
}
static void *m_next(struct seq_file *m, void *_p, loff_t *pos)