From: Tejun Heo <tj@kernel.org>
To: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
mingo@redhat.com, benh@kernel.crashing.org, davem@davemloft.net,
dhowells@redhat.com, npiggin@suse.de, JBeulich@novell.comc
Cc: Tejun Heo <tj@kernel.org>
Subject: [PATCH 01/20] percpu: fix pcpu_reclaim() locking
Date: Tue, 21 Jul 2009 19:26:00 +0900 [thread overview]
Message-ID: <1248171979-29166-2-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1248171979-29166-1-git-send-email-tj@kernel.org>
pcpu_reclaim() calls pcpu_depopulate_chunk() which makes use of pages
array and bitmap returned by pcpu_get_pages_and_bitmap() and thus
should be called under pcpu_alloc_mutex. pcpu_reclaim() released the
mutex before calling depopulate leading to double free and other
strange problems caused by the unexpected concurrent usages of pages
array and bitmap. Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
mm/percpu.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/mm/percpu.c b/mm/percpu.c
index f993dc8..c44a5b2 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1181,12 +1181,13 @@ static void pcpu_reclaim(struct work_struct *work)
}
spin_unlock_irq(&pcpu_lock);
- mutex_unlock(&pcpu_alloc_mutex);
list_for_each_entry_safe(chunk, next, &todo, list) {
pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
free_pcpu_chunk(chunk);
}
+
+ mutex_unlock(&pcpu_alloc_mutex);
}
/**
--
1.6.0.2
WARNING: multiple messages have this Message-ID (diff)
From: Tejun Heo <tj@kernel.org>
To: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
mingo@redhat.com, benh@kernel.crashing.org, davem@davemloft.net,
dhowells@redhat.com, npiggin@suse.de, JBeulich@novell.com,
cl@linux-foundation.org, rusty@rustcorp.com.au, hpa@zytor.com,
tglx@linutronix.de, akpm@linux-foundation.org, x86@kernel.org,
andi@firstfloor.org
Cc: Tejun Heo <tj@kernel.org>
Subject: [PATCH 01/20] percpu: fix pcpu_reclaim() locking
Date: Tue, 21 Jul 2009 19:26:00 +0900 [thread overview]
Message-ID: <1248171979-29166-2-git-send-email-tj@kernel.org> (raw)
Message-ID: <20090721102600.EUzttxsBF4-X1HcroYRkUF4iUNAGJTxdw5oIgCf7j1w@z> (raw)
In-Reply-To: <1248171979-29166-1-git-send-email-tj@kernel.org>
pcpu_reclaim() calls pcpu_depopulate_chunk() which makes use of pages
array and bitmap returned by pcpu_get_pages_and_bitmap() and thus
should be called under pcpu_alloc_mutex. pcpu_reclaim() released the
mutex before calling depopulate leading to double free and other
strange problems caused by the unexpected concurrent usages of pages
array and bitmap. Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
mm/percpu.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/mm/percpu.c b/mm/percpu.c
index f993dc8..c44a5b2 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1181,12 +1181,13 @@ static void pcpu_reclaim(struct work_struct *work)
}
spin_unlock_irq(&pcpu_lock);
- mutex_unlock(&pcpu_alloc_mutex);
list_for_each_entry_safe(chunk, next, &todo, list) {
pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
free_pcpu_chunk(chunk);
}
+
+ mutex_unlock(&pcpu_alloc_mutex);
}
/**
--
1.6.0.2
next prev parent reply other threads:[~2009-07-21 10:28 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-21 10:25 [PATCHSET percpu#for-next] implement and use sparse embedding first chunk allocator Tejun Heo
2009-07-21 10:25 ` Tejun Heo
2009-07-21 10:26 ` Tejun Heo [this message]
2009-07-21 10:26 ` [PATCH 01/20] percpu: fix pcpu_reclaim() locking Tejun Heo
2009-07-21 21:41 ` Christoph Lameter
2009-07-21 10:26 ` [PATCH 02/20] percpu: improve boot messages Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 21:43 ` Christoph Lameter
2009-07-21 10:26 ` [PATCH 03/20] percpu: rename 4k first chunk allocator to page Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 21:47 ` Christoph Lameter
2009-07-22 4:38 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 04/20] percpu: build first chunk allocators selectively Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 05/20] percpu: generalize first chunk allocator selection Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 06/20] percpu: drop @static_size from first chunk allocators Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 07/20] percpu: make @dyn_size mandatory for pcpu_setup_first_chunk() Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 08/20] percpu: add @align to pcpu_fc_alloc_fn_t Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 09/20] percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 10/20] percpu: introduce pcpu_alloc_info and pcpu_group_info Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 11/20] percpu: add pcpu_unit_offsets[] Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 12/20] percpu: add chunk->base_addr Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 13/20] vmalloc: separate out insert_vmalloc_vm() Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 14/20] vmalloc: implement pcpu_get_vm_areas() Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-08-14 6:07 ` Tejun Heo
2009-08-14 6:07 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 15/20] percpu: use group information to allocate vmap areas sparsely Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 16/20] percpu: update embedding first chunk allocator to handle sparse units Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 17/20] x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 18/20] percpu: kill lpage first chunk allocator Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 10:26 ` [PATCH 19/20] sparc64: use embedding percpu " Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-22 3:54 ` David Miller
2009-07-21 10:26 ` [PATCH 20/20] powerpc64: convert to dynamic percpu allocator Tejun Heo
2009-07-21 10:26 ` Tejun Heo
2009-07-21 12:22 ` [RFC PATCH] percpu: kill legacy " Tejun Heo
2009-07-21 12:22 ` Tejun Heo
2009-07-22 4:30 ` Rusty Russell
2009-08-14 6:09 ` [PATCHSET percpu#for-next] implement and use sparse embedding first chunk allocator Tejun Heo
2009-08-14 6:09 ` Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1248171979-29166-2-git-send-email-tj@kernel.org \
--to=tj@kernel.org \
--cc=JBeulich@novell.comc \
--cc=benh@kernel.crashing.org \
--cc=davem@davemloft.net \
--cc=dhowells@redhat.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=npiggin@suse.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox