--- /dev/null
+From 6abe4a87f7bc7978705c386dbba0ca0c7790b3ec Mon Sep 17 00:00:00 2001
+From: Boaz Harrosh <bharrosh@panasas.com>
+Date: Wed, 16 May 2012 14:22:21 +0300
+Subject: exofs: Fix CRASH on very early IO errors.
+
+From: Boaz Harrosh <bharrosh@panasas.com>
+
+commit 6abe4a87f7bc7978705c386dbba0ca0c7790b3ec upstream.
+
+If at exofs_fill_super() we had an early termination
+do to any error, like an IO error while reading the
+super-block. We would crash inside exofs_free_sbi().
+
+This is because sbi->oc.numdevs was set to 1, before
+we actually have a device table at all.
+
+Fix it by moving the sbi->oc.numdevs = 1 to after the
+allocation of the device table.
+
+Reported-by: Johannes Schild <JSchild@gmx.de>
+
+Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/exofs/super.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/fs/exofs/super.c
++++ b/fs/exofs/super.c
+@@ -745,7 +745,6 @@ static int exofs_fill_super(struct super
+ sbi->one_comp.obj.partition = opts->pid;
+ sbi->one_comp.obj.id = 0;
+ exofs_make_credential(sbi->one_comp.cred, &sbi->one_comp.obj);
+- sbi->oc.numdevs = 1;
+ sbi->oc.single_comp = EC_SINGLE_COMP;
+ sbi->oc.comps = &sbi->one_comp;
+
+@@ -804,6 +803,7 @@ static int exofs_fill_super(struct super
+ goto free_sbi;
+
+ ore_comp_set_dev(&sbi->oc, 0, od);
++ sbi->oc.numdevs = 1;
+ }
+
+ __sbi_read_stats(sbi);
--- /dev/null
+From 59516b07b4ffa7e607a5787674ea3c405f1b390c Mon Sep 17 00:00:00 2001
+From: Lars-Peter Clausen <lars@metafoo.de>
+Date: Mon, 9 Apr 2012 15:05:44 +0200
+Subject: microblaze: Do not select GENERIC_GPIO by default
+
+From: Lars-Peter Clausen <lars@metafoo.de>
+
+commit 59516b07b4ffa7e607a5787674ea3c405f1b390c upstream.
+
+The microblaze architecture does not provide a native GPIO API implementation
+nor requires GPIOLIB, but still selects GENERIC_GPIO by default. As a result the
+following build error occurs, if GPIOLIB is not selected:
+
+ include/asm-generic/gpio.h: In function 'gpio_get_value_cansleep':
+ include/asm-generic/gpio.h:218: error: implicit declaration of function '__gpio_get_value'
+ include/asm-generic/gpio.h: In function 'gpio_set_value_cansleep':
+ include/asm-generic/gpio.h:224: error: implicit declaration of function '__gpio_set_value'
+
+This patch addresses the issue by not selecting GENERIC_GPIO by default. This
+causes the GPIO API to be stubbed out if no implementation is provided.
+
+Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
+Tested-by: Michal Simek <monstr@monstr.eu>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/microblaze/Kconfig | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/arch/microblaze/Kconfig
++++ b/arch/microblaze/Kconfig
+@@ -57,7 +57,7 @@ config GENERIC_CLOCKEVENTS
+ def_bool y
+
+ config GENERIC_GPIO
+- def_bool y
++ bool
+
+ config GENERIC_CSUM
+ def_bool y
--- /dev/null
+From e48982734ea0500d1eba4f9d96195acc5406cad6 Mon Sep 17 00:00:00 2001
+From: Michal Hocko <mhocko@suse.cz>
+Date: Tue, 29 May 2012 15:06:45 -0700
+Subject: mm: consider all swapped back pages in used-once logic
+
+From: Michal Hocko <mhocko@suse.cz>
+
+commit e48982734ea0500d1eba4f9d96195acc5406cad6 upstream.
+
+Commit 645747462435 ("vmscan: detect mapped file pages used only once")
+made mapped pages have another round in inactive list because they might
+be just short lived and so we could consider them again next time. This
+heuristic helps to reduce pressure on the active list with a streaming
+IO worklods.
+
+This patch fixes a regression introduced by this commit for heavy shmem
+based workloads because unlike Anon pages, which are excluded from this
+heuristic because they are usually long lived, shmem pages are handled
+as a regular page cache.
+
+This doesn't work quite well, unfortunately, if the workload is mostly
+backed by shmem (in memory database sitting on 80% of memory) with a
+streaming IO in the background (backup - up to 20% of memory). Anon
+inactive list is full of (dirty) shmem pages when watermarks are hit.
+Shmem pages are kept in the inactive list (they are referenced) in the
+first round and it is hard to reclaim anything else so we reach lower
+scanning priorities very quickly which leads to an excessive swap out.
+
+Let's fix this by excluding all swap backed pages (they tend to be long
+lived wrt. the regular page cache anyway) from used-once heuristic and
+rather activate them if they are referenced.
+
+The customer's workload is shmem backed database (80% of RAM) and they
+are measuring transactions/s with an IO in the background (20%).
+Transactions touch more or less random rows in the table. The
+transaction rate fell by a factor of 3 (in the worst case) because of
+commit 64574746. This patch restores the previous numbers.
+
+Signed-off-by: Michal Hocko <mhocko@suse.cz>
+Acked-by: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Mel Gorman <mel@csn.ul.ie>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+Reviewed-by: Rik van Riel <riel@redhat.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/vmscan.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -722,7 +722,7 @@ static enum page_references page_check_r
+ return PAGEREF_RECLAIM;
+
+ if (referenced_ptes) {
+- if (PageAnon(page))
++ if (PageSwapBacked(page))
+ return PAGEREF_ACTIVATE;
+ /*
+ * All mapped pages start out with page table
--- /dev/null
+From 08fa29d916c6e271ad13978cd993e7238c68db97 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <levinsasha928@gmail.com>
+Date: Tue, 29 May 2012 15:06:15 -0700
+Subject: mm: fix NULL ptr deref when walking hugepages
+
+From: Sasha Levin <levinsasha928@gmail.com>
+
+commit 08fa29d916c6e271ad13978cd993e7238c68db97 upstream.
+
+A missing validation of the value returned by find_vma() could cause a
+NULL ptr dereference when walking the pagetable.
+
+This is triggerable from usermode by a simple user by trying to read a
+page info out of /proc/pid/pagemap which doesn't exist.
+
+Introduced by commit 025c5b2451e4 ("thp: optimize away unnecessary page
+table locking").
+
+Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
+Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Cc: David Rientjes <rientjes@google.com>
+Cc: Andi Kleen <andi@firstfloor.org>
+Cc: Andrea Arcangeli <aarcange@redhat.com>
+Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/proc/task_mmu.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -784,7 +784,7 @@ static int pagemap_pte_range(pmd_t *pmd,
+
+ /* find the first VMA at or above 'addr' */
+ vma = find_vma(walk->mm, addr);
+- if (pmd_trans_huge_lock(pmd, vma) == 1) {
++ if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+ for (; addr != end; addr += PAGE_SIZE) {
+ unsigned long offset;
+
--- /dev/null
+From 7edc8b0ac16cbaed7cb4ea4c6b95ce98d2997e84 Mon Sep 17 00:00:00 2001
+From: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com>
+Date: Tue, 29 May 2012 15:06:22 -0700
+Subject: mm/fork: fix overflow in vma length when copying mmap on clone
+
+From: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com>
+
+commit 7edc8b0ac16cbaed7cb4ea4c6b95ce98d2997e84 upstream.
+
+The vma length in dup_mmap is calculated and stored in a unsigned int,
+which is insufficient and hence overflows for very large maps (beyond
+16TB). The following program demonstrates this:
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+#define GIG 1024 * 1024 * 1024L
+#define EXTENT 16393
+
+int main(void)
+{
+ int i, r;
+ void *m;
+ char buf[1024];
+
+ for (i = 0; i < EXTENT; i++) {
+ m = mmap(NULL, (size_t) 1 * 1024 * 1024 * 1024L,
+ PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+
+ if (m == (void *)-1)
+ printf("MMAP Failed: %d\n", m);
+ else
+ printf("%d : MMAP returned %p\n", i, m);
+
+ r = fork();
+
+ if (r == 0) {
+ printf("%d: successed\n", i);
+ return 0;
+ } else if (r < 0)
+ printf("FORK Failed: %d\n", r);
+ else if (r > 0)
+ wait(NULL);
+ }
+ return 0;
+}
+
+Increase the storage size of the result to unsigned long, which is
+sufficient for storing the difference between addresses.
+
+Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Oleg Nesterov <oleg@redhat.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
+Acked-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/fork.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -356,7 +356,8 @@ static int dup_mmap(struct mm_struct *mm
+ }
+ charge = 0;
+ if (mpnt->vm_flags & VM_ACCOUNT) {
+- unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
++ unsigned long len;
++ len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+ if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
+ goto fail_nomem;
+ charge = len;
--- /dev/null
+From b7e94a1686c5daef4f649f7f4f839cc294f07710 Mon Sep 17 00:00:00 2001
+From: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
+Date: Tue, 22 May 2012 18:57:17 +0900
+Subject: SCSI: Fix dm-multipath starvation when scsi host is busy
+
+From: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
+
+commit b7e94a1686c5daef4f649f7f4f839cc294f07710 upstream.
+
+block congestion control doesn't have any concept of fairness across
+multiple queues. This means that if SCSI reports the host as busy in
+the queue congestion control it can result in an unfair starvation
+situation in dm-mp if there are multiple multipath devices on the same
+host. For example:
+http://www.redhat.com/archives/dm-devel/2012-May/msg00123.html
+
+The fix for this is to report only the sdev busy state (and ignore the
+host busy state) in the block congestion control call back.
+The host is still congested, but the SCSI subsystem will sort out the
+congestion in a fair way because it knows the relation between the
+queues and the host.
+
+[jejb: fixed up trailing whitespace]
+Reported-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
+Tested-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de>
+Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
+Signed-off-by: James Bottomley <JBottomley@Parallels.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/scsi/scsi_lib.c | 11 +++++++----
+ 1 file changed, 7 insertions(+), 4 deletions(-)
+
+--- a/drivers/scsi/scsi_lib.c
++++ b/drivers/scsi/scsi_lib.c
+@@ -1378,16 +1378,19 @@ static int scsi_lld_busy(struct request_
+ {
+ struct scsi_device *sdev = q->queuedata;
+ struct Scsi_Host *shost;
+- struct scsi_target *starget;
+
+ if (!sdev)
+ return 0;
+
+ shost = sdev->host;
+- starget = scsi_target(sdev);
+
+- if (scsi_host_in_recovery(shost) || scsi_host_is_busy(shost) ||
+- scsi_target_is_busy(starget) || scsi_device_is_busy(sdev))
++ /*
++ * Ignore host/starget busy state.
++ * Since block layer does not have a concept of fairness across
++ * multiple queues, congestion of host/starget needs to be handled
++ * in SCSI layer.
++ */
++ if (scsi_host_in_recovery(shost) || scsi_device_is_busy(sdev))
+ return 1;
+
+ return 0;
--- /dev/null
+From 1ff2f40305772b159a91c19590ee159d3a504afc Mon Sep 17 00:00:00 2001
+From: James Bottomley <jbottomley@parallels.com>
+Date: Wed, 30 May 2012 09:45:39 +0000
+Subject: SCSI: fix scsi_wait_scan
+
+From: James Bottomley <jbottomley@parallels.com>
+
+commit 1ff2f40305772b159a91c19590ee159d3a504afc upstream.
+
+Commit c751085943362143f84346d274e0011419c84202
+Author: Rafael J. Wysocki <rjw@sisk.pl>
+Date: Sun Apr 12 20:06:56 2009 +0200
+
+ PM/Hibernate: Wait for SCSI devices scan to complete during resume
+
+Broke the scsi_wait_scan module in 2.6.30. Apparently debian still uses it so
+fix it and backport to stable before removing it in 3.6.
+
+The breakage is caused because the function template in
+include/scsi/scsi_scan.h is defined to be a nop unless SCSI is built in.
+That means that in the modular case (which is every distro), the
+scsi_wait_scan module does a simple async_synchronize_full() instead of
+waiting for scans.
+
+Signed-off-by: James Bottomley <JBottomley@Parallels.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/scsi/scsi_wait_scan.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/scsi/scsi_wait_scan.c
++++ b/drivers/scsi/scsi_wait_scan.c
+@@ -12,7 +12,7 @@
+
+ #include <linux/module.h>
+ #include <linux/device.h>
+-#include <scsi/scsi_scan.h>
++#include "scsi_priv.h"
+
+ static int __init wait_scan_init(void)
+ {
--- /dev/null
+exofs-fix-crash-on-very-early-io-errors.patch
+microblaze-do-not-select-generic_gpio-by-default.patch
+scsi-fix-scsi_wait_scan.patch
+scsi-fix-dm-multipath-starvation-when-scsi-host-is-busy.patch
+mm-fork-fix-overflow-in-vma-length-when-copying-mmap-on-clone.patch
+mm-fix-null-ptr-deref-when-walking-hugepages.patch
+mm-consider-all-swapped-back-pages-in-used-once-logic.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
