--- /dev/null
+From da1aab3dca9aa88ae34ca392470b8943159e25fe Mon Sep 17 00:00:00 2001
+From: NeilBrown <neilb@suse.de>
+Date: Wed, 9 Apr 2014 12:25:43 +1000
+Subject: md/raid1: r1buf_pool_alloc: free allocate pages when subsequent allocation fails.
+
+From: NeilBrown <neilb@suse.de>
+
+commit da1aab3dca9aa88ae34ca392470b8943159e25fe upstream.
+
+When performing a user-request check/repair (MD_RECOVERY_REQUEST is set)
+on a raid1, we allocate multiple bios each with their own set of pages.
+
+If the page allocations for one bio fails, we currently do *not* free
+the pages allocated for the previous bios, nor do we free the bio itself.
+
+This patch frees all the already-allocate pages, and makes sure that
+all the bios are freed as well.
+
+This bug can cause a memory leak which can ultimately OOM a machine.
+It was introduced in 3.10-rc1.
+
+Fixes: a07876064a0b73ab5ef1ebcf14b1cf0231c07858
+Cc: Kent Overstreet <koverstreet@google.com>
+Reported-by: Russell King - ARM Linux <linux@arm.linux.org.uk>
+Signed-off-by: NeilBrown <neilb@suse.de>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/md/raid1.c | 17 +++++++++++++----
+ 1 file changed, 13 insertions(+), 4 deletions(-)
+
+--- a/drivers/md/raid1.c
++++ b/drivers/md/raid1.c
+@@ -94,6 +94,7 @@ static void * r1buf_pool_alloc(gfp_t gfp
+ struct pool_info *pi = data;
+ struct r1bio *r1_bio;
+ struct bio *bio;
++ int need_pages;
+ int i, j;
+
+ r1_bio = r1bio_pool_alloc(gfp_flags, pi);
+@@ -116,15 +117,15 @@ static void * r1buf_pool_alloc(gfp_t gfp
+ * RESYNC_PAGES for each bio.
+ */
+ if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
+- j = pi->raid_disks;
++ need_pages = pi->raid_disks;
+ else
+- j = 1;
+- while(j--) {
++ need_pages = 1;
++ for (j = 0; j < need_pages; j++) {
+ bio = r1_bio->bios[j];
+ bio->bi_vcnt = RESYNC_PAGES;
+
+ if (bio_alloc_pages(bio, gfp_flags))
+- goto out_free_bio;
++ goto out_free_pages;
+ }
+ /* If not user-requests, copy the page pointers to all bios */
+ if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
+@@ -138,6 +139,14 @@ static void * r1buf_pool_alloc(gfp_t gfp
+
+ return r1_bio;
+
++out_free_pages:
++ while (--j >= 0) {
++ struct bio_vec *bv;
++
++ bio_for_each_segment_all(bv, r1_bio->bios[j], i)
++ __free_page(bv->bv_page);
++ }
++
+ out_free_bio:
+ while (++j < pi->raid_disks)
+ bio_put(r1_bio->bios[j]);
--- /dev/null
+From 7848a4bf51b34f41fcc9bd77e837126d99ae84e3 Mon Sep 17 00:00:00 2001
+From: "Mizuma, Masayoshi" <m.mizuma@jp.fujitsu.com>
+Date: Fri, 18 Apr 2014 15:07:18 -0700
+Subject: mm/hugetlb.c: add cond_resched_lock() in return_unused_surplus_pages()
+
+From: "Mizuma, Masayoshi" <m.mizuma@jp.fujitsu.com>
+
+commit 7848a4bf51b34f41fcc9bd77e837126d99ae84e3 upstream.
+
+soft lockup in freeing gigantic hugepage fixed in commit 55f67141a892 "mm:
+hugetlb: fix softlockup when a large number of hugepages are freed." can
+happen in return_unused_surplus_pages(), so let's fix it.
+
+Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
+Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
+Cc: Michal Hocko <mhocko@suse.cz>
+Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
+Cc: KOSAKI Motohiro <kosaki.motohiro@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>
+
+---
+ mm/hugetlb.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/mm/hugetlb.c
++++ b/mm/hugetlb.c
+@@ -1100,6 +1100,7 @@ static void return_unused_surplus_pages(
+ while (nr_pages--) {
+ if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
+ break;
++ cond_resched_lock(&hugetlb_lock);
+ }
+ }
+
--- /dev/null
+From 29c7787075c92ca8af353acd5301481e6f37082f Mon Sep 17 00:00:00 2001
+From: Mel Gorman <mgorman@suse.de>
+Date: Fri, 18 Apr 2014 15:07:21 -0700
+Subject: mm: use paravirt friendly ops for NUMA hinting ptes
+
+From: Mel Gorman <mgorman@suse.de>
+
+commit 29c7787075c92ca8af353acd5301481e6f37082f upstream.
+
+David Vrabel identified a regression when using automatic NUMA balancing
+under Xen whereby page table entries were getting corrupted due to the
+use of native PTE operations. Quoting him
+
+ Xen PV guest page tables require that their entries use machine
+ addresses if the preset bit (_PAGE_PRESENT) is set, and (for
+ successful migration) non-present PTEs must use pseudo-physical
+ addresses. This is because on migration MFNs in present PTEs are
+ translated to PFNs (canonicalised) so they may be translated back
+ to the new MFN in the destination domain (uncanonicalised).
+
+ pte_mknonnuma(), pmd_mknonnuma(), pte_mknuma() and pmd_mknuma()
+ set and clear the _PAGE_PRESENT bit using pte_set_flags(),
+ pte_clear_flags(), etc.
+
+ In a Xen PV guest, these functions must translate MFNs to PFNs
+ when clearing _PAGE_PRESENT and translate PFNs to MFNs when setting
+ _PAGE_PRESENT.
+
+His suggested fix converted p[te|md]_[set|clear]_flags to using
+paravirt-friendly ops but this is overkill. He suggested an alternative
+of using p[te|md]_modify in the NUMA page table operations but this is
+does more work than necessary and would require looking up a VMA for
+protections.
+
+This patch modifies the NUMA page table operations to use paravirt
+friendly operations to set/clear the flags of interest. Unfortunately
+this will take a performance hit when updating the PTEs on
+CONFIG_PARAVIRT but I do not see a way around it that does not break
+Xen.
+
+Signed-off-by: Mel Gorman <mgorman@suse.de>
+Acked-by: David Vrabel <david.vrabel@citrix.com>
+Tested-by: David Vrabel <david.vrabel@citrix.com>
+Cc: Ingo Molnar <mingo@kernel.org>
+Cc: Peter Anvin <hpa@zytor.com>
+Cc: Fengguang Wu <fengguang.wu@intel.com>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Steven Noonan <steven@uplinklabs.net>
+Cc: Rik van Riel <riel@redhat.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Andrea Arcangeli <aarcange@redhat.com>
+Cc: Dave Hansen <dave.hansen@intel.com>
+Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
+Cc: Cyrill Gorcunov <gorcunov@gmail.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>
+
+---
+ include/asm-generic/pgtable.h | 31 +++++++++++++++++++++++--------
+ 1 file changed, 23 insertions(+), 8 deletions(-)
+
+--- a/include/asm-generic/pgtable.h
++++ b/include/asm-generic/pgtable.h
+@@ -620,32 +620,47 @@ static inline int pmd_numa(pmd_t pmd)
+ #ifndef pte_mknonnuma
+ static inline pte_t pte_mknonnuma(pte_t pte)
+ {
+- pte = pte_clear_flags(pte, _PAGE_NUMA);
+- return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
++ pteval_t val = pte_val(pte);
++
++ val &= ~_PAGE_NUMA;
++ val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
++ return __pte(val);
+ }
+ #endif
+
+ #ifndef pmd_mknonnuma
+ static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+ {
+- pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
+- return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
++ pmdval_t val = pmd_val(pmd);
++
++ val &= ~_PAGE_NUMA;
++ val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
++
++ return __pmd(val);
+ }
+ #endif
+
+ #ifndef pte_mknuma
+ static inline pte_t pte_mknuma(pte_t pte)
+ {
+- pte = pte_set_flags(pte, _PAGE_NUMA);
+- return pte_clear_flags(pte, _PAGE_PRESENT);
++ pteval_t val = pte_val(pte);
++
++ val &= ~_PAGE_PRESENT;
++ val |= _PAGE_NUMA;
++
++ return __pte(val);
+ }
+ #endif
+
+ #ifndef pmd_mknuma
+ static inline pmd_t pmd_mknuma(pmd_t pmd)
+ {
+- pmd = pmd_set_flags(pmd, _PAGE_NUMA);
+- return pmd_clear_flags(pmd, _PAGE_PRESENT);
++ pmdval_t val = pmd_val(pmd);
++
++ val &= ~_PAGE_PRESENT;
++ val |= _PAGE_NUMA;
++
++ return __pmd(val);
+ }
+ #endif
+ #else
projects / thirdparty / kernel / stable-queue.git / commitdiff
