incoming
Subsystems (12)
Andrew Morton
maintainer12 patches, based on f8c7e4ede46fe63ff10000669652648aab09d112.
Subsystems affected by this patch series:
sysctl
binfmt
ia64
mm/memory-failure
mm/folios
selftests
mm/kasan
mm/psi
ocfs2
Subsystem: sysctl
Andrew Morton <[email protected]>:
include/linux/sysctl.h: fix register_sysctl_mount_point() return type
Subsystem: binfmt
Tong Zhang <[email protected]>:
binfmt_misc: fix crash when load/unload module
Subsystem: ia64
Randy Dunlap <[email protected]>:
ia64: make IA64_MCA_RECOVERY bool instead of tristate
Subsystem: mm/memory-failure
Joao Martins <[email protected]>:
memory-failure: fetch compound_head after pgmap_pfn_valid()
Subsystem: mm/folios
Wei Yang <[email protected]>:
mm: page->mapping folio->mapping should have the same offset
Subsystem: selftests
Maor Gottlieb <[email protected]>:
tools/testing/scatterlist: add missing defines
Subsystem: mm/kasan
Marco Elver <[email protected]>:
kasan: test: fix compatibility with FORTIFY_SOURCE
Peter Collingbourne <[email protected]>:
mm, kasan: use compare-exchange operation to set KASAN page tag
Subsystem: mm/psi
Suren Baghdasaryan <[email protected]>:
psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n
psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n
Subsystem: ocfs2
Joseph Qi <[email protected]>:
Patch series "ocfs2: fix a deadlock case":
jbd2: export jbd2_journal_[grab|put]_journal_head
ocfs2: fix a deadlock when commit trans
arch/ia64/Kconfig | 2 fs/binfmt_misc.c | 8 +-- fs/jbd2/journal.c | 2 fs/ocfs2/suballoc.c | 25 ++++------- include/linux/mm.h | 17 +++++-- include/linux/mm_types.h | 1 include/linux/psi.h | 11 ++-- include/linux/sysctl.h | 2 kernel/sched/psi.c | 79 ++++++++++++++++++----------------- lib/test_kasan.c | 5 ++ mm/memory-failure.c | 6 ++ tools/testing/scatterlist/linux/mm.h | 3 - 12 files changed, 91 insertions(+), 70 deletions(-)
Andrew Morton
maintainerPATCH 1/12 include/linux/sysctl.h: fix register_sysctl_mount_point() return type
From: Andrew Morton <[email protected]>
Subject: include/linux/sysctl.h: fix register_sysctl_mount_point() return type
The CONFIG_SYSCTL=n stub returns the wrong type.
---
include/linux/sysctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/linux/sysctl.h renamed from include/linux/sysctl.h~include-linux-sysctlh-fix-register_sysctl_mount_point-return-type +1 -1
@@ -265,7 +265,7 @@ static inline struct ctl_table_header *rreturn NULL ; } -static inline struct sysctl_header *register_sysctl_mount_point (const char *path) +static inline struct ctl_table_header *register_sysctl_mount_point (const char *path) {return NULL ; }
_
Andrew Morton
maintainerPATCH 2/12 binfmt_misc: fix crash when load/unload module
In reply to Andrew MortonFrom: Tong Zhang <[email protected]>
Subject: binfmt_misc: fix crash when load/unload module
We should unregister the table upon module unload otherwise something horrible will happen when we load binfmt_misc module again. Also note that we should keep value returned by register_sysctl_mount_point() and release it later, otherwise it will leak.
Also, per Christian's comment, to fully restore the old behavior that won't break userspace the check(binfmt_misc_header) should be eliminated.
reproduce:
modprobe binfmt_misc
modprobe -r binfmt_misc
modprobe binfmt_misc
modprobe -r binfmt_misc
modprobe binfmt_misc
[ 18.032038] Call Trace: [ 18.032108] <TASK> [ 18.032169] dump_stack_lvl+0x34/0x44 [ 18.032273] __register_sysctl_table+0x6f4/0x720 [ 18.032397] ? preempt_count_sub+0xf/0xb0 [ 18.032508] ? 0xffffffffc0040000 [ 18.032600] init_misc_binfmt+0x2d/0x1000 [binfmt_misc] [ 18.042520] binfmt_misc: Failed to create fs/binfmt_misc sysctl mount point modprobe: can't load module binfmt_misc (kernel/fs/binfmt_misc.ko): Cannot allocate memory [ 18.063549] binfmt_misc: Failed to create fs/binfmt_misc sysctl mount point [ 18.204779] BUG: unable to handle page fault for address: fffffbfff8004802
---
fs/binfmt_misc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
fs/binfmt_misc.c renamed from fs/binfmt_misc.c~binfmt_misc-fix-crash-when-load-unload-module +4 -4
@@ -817,20 +817,20 @@ static struct file_system_type bm_fs_typ };MODULE_ALIAS_FS ("binfmt_misc" ); +static struct ctl_table_header *binfmt_misc_header; +static int __init init_misc_binfmt (void ) {int err =register_filesystem (&bm_fs_type);if (!err)insert_binfmt (&misc_format); -if (!register_sysctl_mount_point ("fs/binfmt_misc" )) { -pr_warn ("Failed to create fs/binfmt_misc sysctl mount point" ); -return -ENOMEM ; - } + binfmt_misc_header =register_sysctl_mount_point ("fs/binfmt_misc" );return 0 ; } static void __exit exit_misc_binfmt(void) { +unregister_sysctl_table (binfmt_misc_header);unregister_binfmt (&misc_format);unregister_filesystem (&bm_fs_type); }
_
Andrew Morton
maintainerPATCH 3/12 ia64: make IA64_MCA_RECOVERY bool instead of tristate
In reply to Andrew MortonFrom: Randy Dunlap <[email protected]>
Subject: ia64: make IA64_MCA_RECOVERY bool instead of tristate
In linux-next, IA64_MCA_RECOVERY uses the (new) function make_task_dead(), which is not exported for use by modules. Instead of exporting it for one user, convert IA64_MCA_RECOVERY to be a bool Kconfig symbol.
In a config file from "kernel test robot <[email protected]>" for a different problem, this linker error was exposed when CONFIG_IA64_MCA_RECOVERY=m.
Fixes this build error:
ERROR: modpost: "make_task_dead" [arch/ia64/kernel/mca_recovery.ko] undefined!
---
arch/ia64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/ia64/Kconfig renamed from arch/ia64/Kconfig~ia64-make-ia64_mca_recovery-bool-instead-of-tristate +1 -1
@@ -318,7 +318,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB." config IA64_PALINFO tristate "/proc/pal support"
_
Andrew Morton
maintainerPATCH 4/12 memory-failure: fetch compound_head after pgmap_pfn_valid()
In reply to Andrew MortonFrom: Joao Martins <[email protected]>
Subject: memory-failure: fetch compound_head after pgmap_pfn_valid()
memory_failure_dev_pagemap() at the moment assumes base pages (e.g. dax_lock_page()). For devmap with compound pages fetch the compound_head in case a tail page memory failure is being handled.
Currently this is a nop, but in the advent of compound pages in dev_pagemap it allows memory_failure_dev_pagemap() to keep working.
Without this fix memory-failure handling (i.e. MCEs on pmem) with device-dax configured namespaces will regress (and crash).
---
mm/memory-failure.c | 6 ++++++ 1 file changed, 6 insertions(+)
mm/memory-failure.c renamed from mm/memory-failure.c~memory-failure-fetch-compound_head-after-pgmap_pfn_valid +6 -0
@@ -1596,6 +1596,12 @@ static int memory_failure_dev_pagemap(un }/* +* Pages instantiated by device-dax (not filesystem-dax) +* may be compound pages. +*/ + page =compound_head (page); + +/* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by * lock_page(), but dax pages do not use the page lock. This
_
Andrew Morton
maintainerPATCH 5/12 mm: page->mapping folio->mapping should have the same offset
In reply to Andrew MortonFrom: Wei Yang <[email protected]>
Subject: mm: page->mapping folio->mapping should have the same offset
As with the other members of folio, the offset of page->mapping and folio->mapping must be the same. The compile-time check was inadvertently removed during development. Add it back.
---
include/linux/mm_types.h | 1 + 1 file changed, 1 insertion(+)
include/linux/mm_types.h renamed from include/linux/mm_types.h~mm-page-mapping-folio-mapping-should-have-the-same-offset +1 -0
@@ -261,6 +261,7 @@ static_assert(sizeof(struct page) == siz static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))FOLIO_MATCH (flags, flags);FOLIO_MATCH (lru, lru); +FOLIO_MATCH (mapping, mapping);FOLIO_MATCH (compound_head, lru);FOLIO_MATCH (index, index);FOLIO_MATCH (private, private);
_
Andrew Morton
maintainerPATCH 6/12 tools/testing/scatterlist: add missing defines
In reply to Andrew MortonFrom: Maor Gottlieb <[email protected]>
Subject: tools/testing/scatterlist: add missing defines
The cited commits replaced preemptible with pagefault_disabled and flush_kernel_dcache_page with flush_dcache_page respectively, hence need to update the corresponding defines in the test.
scatterlist.c: In function ‘sg_miter_stop’:
scatterlist.c:919:4: warning: implicit declaration of function ‘flush_dcache_page’ [-Wimplicit-function-declaration]
flush_dcache_page(miter->page);
^~~~~~~~~~~~~~~~~
In file included from ./linux/scatterlist.h:8:0,
from scatterlist.c:9:
scatterlist.c:922:18: warning: implicit declaration of function ‘pagefault_disabled’ [-Wimplicit-function-declaration]
WARN_ON_ONCE(!pagefault_disabled());
^
./linux/mm.h:23:25: note: in definition of macro ‘WARN_ON_ONCE’
int __ret_warn_on = !!(condition); \
^~~~~~~~~---
tools/testing/scatterlist/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/testing/scatterlist/linux/mm.h renamed from tools/testing/scatterlist/linux/mm.h~tools-testing-scatterlist-add-missing-defines +2 -1
@@ -74,7 +74,7 @@ static inline unsigned long page_to_phys __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) -#define preemptible () (1) +#define pagefault_disabled () (0)static inline void *kmap (struct page *page) {
@@ -127,6 +127,7 @@ kmalloc_array(unsigned int n, unsigned i#define kmemleak_free (a)#define PageSlab (p) (0) +#define flush_dcache_page (p)#define MAX_ERRNO 4095
_
Andrew Morton
maintainerPATCH 7/12 kasan: test: fix compatibility with FORTIFY_SOURCE
In reply to Andrew MortonFrom: Marco Elver <[email protected]>
Subject: kasan: test: fix compatibility with FORTIFY_SOURCE
With CONFIG_FORTIFY_SOURCE enabled, string functions will also perform dynamic checks using __builtin_object_size(ptr), which when failed will panic the kernel.
Because the KASAN test deliberately performs out-of-bounds operations, the kernel panics with FORTIFY_SOURCE, for example:
| kernel BUG at lib/string_helpers.c:910! | invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI | CPU: 1 PID: 137 Comm: kunit_try_catch Tainted: G B 5.16.0-rc3+ #3 | Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 | RIP: 0010:fortify_panic+0x19/0x1b | ... | Call Trace: | <TASK> | kmalloc_oob_in_memset.cold+0x16/0x16 | ...
Fix it by also hiding ptr from the optimizer, which will ensure that __builtin_object_size() does not return a valid size, preventing fortified string functions from panicking.
---
lib/test_kasan.c | 5 +++++ 1 file changed, 5 insertions(+)
lib/test_kasan.c renamed from lib/test_kasan.c~kasan-test-fix-compatibility-with-fortify_source +5 -0
@@ -492,6 +492,7 @@ static void kmalloc_oob_in_memset(struct ptr =kmalloc (size,GFP_KERNEL );KUNIT_ASSERT_NOT_ERR_OR_NULL (test, ptr); +OPTIMIZER_HIDE_VAR (ptr);OPTIMIZER_HIDE_VAR (size);KUNIT_EXPECT_KASAN_FAIL (test,memset (ptr,0 , size +KASAN_GRANULE_SIZE ));
@@ -515,6 +516,7 @@ static void kmalloc_memmove_negative_sizKUNIT_ASSERT_NOT_ERR_OR_NULL (test, ptr);memset ((char *)ptr,0 ,64 ); +OPTIMIZER_HIDE_VAR (ptr);OPTIMIZER_HIDE_VAR (invalid_size);KUNIT_EXPECT_KASAN_FAIL (test,memmove ((char *)ptr, (char *)ptr +4 , invalid_size));
@@ -531,6 +533,7 @@ static void kmalloc_memmove_invalid_sizeKUNIT_ASSERT_NOT_ERR_OR_NULL (test, ptr);memset ((char *)ptr,0 ,64 ); +OPTIMIZER_HIDE_VAR (ptr);KUNIT_EXPECT_KASAN_FAIL (test,memmove ((char *)ptr, (char *)ptr +4 , invalid_size));kfree (ptr);
@@ -893,6 +896,7 @@ static void kasan_memchr(struct kunit *t ptr =kmalloc (size,GFP_KERNEL | __GFP_ZERO);KUNIT_ASSERT_NOT_ERR_OR_NULL (test, ptr); +OPTIMIZER_HIDE_VAR (ptr);OPTIMIZER_HIDE_VAR (size);KUNIT_EXPECT_KASAN_FAIL (test, kasan_ptr_result =memchr (ptr,'1' , size +1 ));
@@ -919,6 +923,7 @@ static void kasan_memcmp(struct kunit *tKUNIT_ASSERT_NOT_ERR_OR_NULL (test, ptr);memset (arr,0 ,sizeof (arr)); +OPTIMIZER_HIDE_VAR (ptr);OPTIMIZER_HIDE_VAR (size);KUNIT_EXPECT_KASAN_FAIL (test, kasan_int_result =memcmp (ptr, arr, size+1 ));
_
Andrew Morton
maintainerPATCH 8/12 mm, kasan: use compare-exchange operation to set KASAN page tag
In reply to Andrew MortonFrom: Peter Collingbourne <[email protected]>
Subject: mm, kasan: use compare-exchange operation to set KASAN page tag
It has been reported that the tag setting operation on newly-allocated pages can cause the page flags to be corrupted when performed concurrently with other flag updates as a result of the use of non-atomic operations. Fix the problem by using a compare-exchange loop to update the tag.
---
include/linux/mm.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
include/linux/mm.h renamed from include/linux/mm.h~mm-use-compare-exchange-operation-to-set-kasan-page-tag +12 -5
@@ -1506,11 +1506,18 @@ static inline u8 page_kasan_tag(const ststatic inline void page_kasan_tag_set (struct page *page,u8 tag) { -if (kasan_enabled ()) { - tag ^=0xff ; - page->flags &= ~(KASAN_TAG_MASK <<KASAN_TAG_PGSHIFT ); - page->flags |= (tag &KASAN_TAG_MASK ) <<KASAN_TAG_PGSHIFT ; - } +unsigned long old_flags, flags; + +if (!kasan_enabled ()) +return ; + + tag ^=0xff ; + old_flags =READ_ONCE (page->flags); +do { + flags = old_flags; + flags &= ~(KASAN_TAG_MASK <<KASAN_TAG_PGSHIFT ); + flags |= (tag &KASAN_TAG_MASK ) <<KASAN_TAG_PGSHIFT ; + }while (unlikely (!try_cmpxchg (&page->flags, &old_flags, flags))); }static inline void page_kasan_tag_reset (struct page *page)
_
Andrew Morton
maintainerPATCH 9/12 psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n
In reply to Andrew MortonFrom: Suren Baghdasaryan <[email protected]>
Subject: psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n
When CONFIG_CGROUPS is disabled psi code generates the following warnings:
kernel/sched/psi.c:1112:21: warning: no previous prototype for 'psi_trigger_create' [-Wmissing-prototypes]
1112 | struct psi_trigger *psi_trigger_create(struct psi_group *group,
| ^~~~~~~~~~~~~~~~~~kernel/sched/psi.c:1182:6: warning: no previous prototype for 'psi_trigger_destroy' [-Wmissing-prototypes]
1182 | void psi_trigger_destroy(struct psi_trigger *t)
| ^~~~~~~~~~~~~~~~~~~kernel/sched/psi.c:1249:10: warning: no previous prototype for 'psi_trigger_poll' [-Wmissing-prototypes]
1249 | __poll_t psi_trigger_poll(void **trigger_ptr,
| ^~~~~~~~~~~~~~~~Change declarations of these functions in the header to provide the prototypes even when they are unused.
---
include/linux/psi.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
include/linux/psi.h renamed from include/linux/psi.h~psi-fix-no-previous-prototype-warnings-when-config_cgroups=n +5 -6
@@ -25,18 +25,17 @@ void psi_memstall_enter(unsigned long *fvoid psi_memstall_leave (unsigned long *flags);int psi_show (struct seq_file *s,struct psi_group *group,enum psi_res res); - -#ifdef CONFIG_CGROUPS -int psi_cgroup_alloc (struct cgroup *cgrp); -void psi_cgroup_free (struct cgroup *cgrp); -void cgroup_move_task (struct task_struct *p,struct css_set *to); -struct psi_trigger *psi_trigger_create (struct psi_group *group,char *buf,size_t nbytes,enum psi_res res);void psi_trigger_destroy (struct psi_trigger *t);__poll_t psi_trigger_poll (void **trigger_ptr,struct file *file,poll_table *wait); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc (struct cgroup *cgrp); +void psi_cgroup_free (struct cgroup *cgrp); +void cgroup_move_task (struct task_struct *p,struct css_set *to);#endif #else /* CONFIG_PSI */
_
Andrew Morton
maintainerPATCH 10/12 psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n
In reply to Andrew MortonFrom: Suren Baghdasaryan <[email protected]>
Subject: psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n
When CONFIG_PROC_FS is disabled psi code generates the following warnings:
kernel/sched/psi.c:1364:30: warning: 'psi_cpu_proc_ops' defined but not used [-Wunused-const-variable=]
1364 | static const struct proc_ops psi_cpu_proc_ops = {
| ^~~~~~~~~~~~~~~~
kernel/sched/psi.c:1355:30: warning: 'psi_memory_proc_ops' defined but not used [-Wunused-const-variable=]
1355 | static const struct proc_ops psi_memory_proc_ops = {
| ^~~~~~~~~~~~~~~~~~~
kernel/sched/psi.c:1346:30: warning: 'psi_io_proc_ops' defined but not used [-Wunused-const-variable=]
1346 | static const struct proc_ops psi_io_proc_ops = {
| ^~~~~~~~~~~~~~~Make definitions of these structures and related functions conditional on CONFIG_PROC_FS config.
---
kernel/sched/psi.c | 79 ++++++++++++++++++++++--------------------- 1 file changed, 41 insertions(+), 38 deletions(-)
kernel/sched/psi.c renamed from kernel/sched/psi.c~psi-fix-defined-but-not-used-warnings-when-config_proc_fs=n +41 -38
@@ -1082,44 +1082,6 @@ int psi_show(struct seq_file *m, structreturn 0 ; } -static int psi_io_show (struct seq_file *m,void *v) -{ -return psi_show (m, &psi_system,PSI_IO ); -} - -static int psi_memory_show (struct seq_file *m,void *v) -{ -return psi_show (m, &psi_system,PSI_MEM ); -} - -static int psi_cpu_show (struct seq_file *m,void *v) -{ -return psi_show (m, &psi_system,PSI_CPU ); -} - -static int psi_open (struct file *file,int (*psi_show)(struct seq_file *,void *)) -{ -if (file->f_mode &FMODE_WRITE && !capable (CAP_SYS_RESOURCE )) -return -EPERM ; - -return single_open (file, psi_show,NULL ); -} - -static int psi_io_open (struct inode *inode,struct file *file) -{ -return psi_open (file, psi_io_show); -} - -static int psi_memory_open (struct inode *inode,struct file *file) -{ -return psi_open (file, psi_memory_show); -} - -static int psi_cpu_open (struct inode *inode,struct file *file) -{ -return psi_open (file, psi_cpu_show); -} -struct psi_trigger *psi_trigger_create (struct psi_group *group,char *buf,size_t nbytes,enum psi_res res) {
@@ -1278,6 +1240,45 @@ __poll_t psi_trigger_poll(void **triggerreturn ret; } +#ifdef CONFIG_PROC_FS +static int psi_io_show (struct seq_file *m,void *v) +{ +return psi_show (m, &psi_system,PSI_IO ); +} + +static int psi_memory_show (struct seq_file *m,void *v) +{ +return psi_show (m, &psi_system,PSI_MEM ); +} + +static int psi_cpu_show (struct seq_file *m,void *v) +{ +return psi_show (m, &psi_system,PSI_CPU ); +} + +static int psi_open (struct file *file,int (*psi_show)(struct seq_file *,void *)) +{ +if (file->f_mode &FMODE_WRITE && !capable (CAP_SYS_RESOURCE )) +return -EPERM ; + +return single_open (file, psi_show,NULL ); +} + +static int psi_io_open (struct inode *inode,struct file *file) +{ +return psi_open (file, psi_io_show); +} + +static int psi_memory_open (struct inode *inode,struct file *file) +{ +return psi_open (file, psi_memory_show); +} + +static int psi_cpu_open (struct inode *inode,struct file *file) +{ +return psi_open (file, psi_cpu_show); +} +static ssize_t psi_write (struct file *file,const char __user *user_buf,size_t nbytes,enum psi_res res) {
@@ -1392,3 +1393,5 @@ static int __init psi_proc_init(void) return 0; }module_init (psi_proc_init); + +#endif /* CONFIG_PROC_FS */
_
Andrew Morton
maintainerPATCH 11/12 jbd2: export jbd2_journal_[grab|put]_journal_head
In reply to Andrew MortonFrom: Joseph Qi <[email protected]>
Subject: jbd2: export jbd2_journal_[grab|put]_journal_head
Patch series "ocfs2: fix a deadlock case".
This fixes a deadlock case in ocfs2. We firstly export jbd2 symbols jbd2_journal_[grab|put]_journal_head as preparation and later use them in ocfs2 insread of jbd_[lock|unlock]_bh_journal_head to fix the deadlock.
This patch (of 2):
This exports symbols jbd2_journal_[grab|put]_journal_head, which will be used outside modules, e.g. ocfs2.
---
fs/jbd2/journal.c | 2 ++ 1 file changed, 2 insertions(+)
fs/jbd2/journal.c renamed from fs/jbd2/journal.c~jbd2-export-jbd2_journal__journal_head +2 -0
@@ -2972,6 +2972,7 @@ struct journal_head *jbd2_journal_grab_jjbd_unlock_bh_journal_head (bh);return jh; } +EXPORT_SYMBOL (jbd2_journal_grab_journal_head);static void __journal_remove_journal_head (struct buffer_head *bh) {
@@ -3024,6 +3025,7 @@ void jbd2_journal_put_journal_head(strucjbd_unlock_bh_journal_head (bh); } } +EXPORT_SYMBOL (jbd2_journal_put_journal_head);/* * Initialize jbd inode head
_
Andrew Morton
maintainerPATCH 12/12 ocfs2: fix a deadlock when commit trans
In reply to Andrew MortonFrom: Joseph Qi <[email protected]>
Subject: ocfs2: fix a deadlock when commit trans
commit 6f1b228529ae introduces a regression which can deadlock as follows:
Task1: Task2: jbd2_journal_commit_transaction ocfs2_test_bg_bit_allocatable spin_lock(&jh->b_state_lock) jbd_lock_bh_journal_head __jbd2_journal_remove_checkpoint spin_lock(&jh->b_state_lock)
jbd2_journal_put_journal_headjbd_lock_bh_journal_head
Task1 and Task2 lock bh->b_state and jh->b_state_lock in different order, which finally result in a deadlock.
So use jbd2_journal_[grab|put]_journal_head instead in ocfs2_test_bg_bit_allocatable() to fix it.
---
fs/ocfs2/suballoc.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-)
fs/ocfs2/suballoc.c renamed from fs/ocfs2/suballoc.c~ocfs2-fix-a-deadlock-when-commit-trans +11 -14
@@ -1251,26 +1251,23 @@ static int ocfs2_test_bg_bit_allocatable {struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;struct journal_head *jh; -int ret =1 ; +int ret;if (ocfs2_test_bit (nr, (unsigned long *)bg->bg_bitmap))return 0 ; -if (!buffer_jbd (bg_bh)) + jh =jbd2_journal_grab_journal_head (bg_bh); +if (!jh)return 1 ; -jbd_lock_bh_journal_head (bg_bh); -if (buffer_jbd (bg_bh)) { - jh =bh2jh (bg_bh); -spin_lock (&jh->b_state_lock); - bg = (struct ocfs2_group_desc *) jh->b_committed_data; -if (bg) - ret = !ocfs2_test_bit (nr, (unsigned long *)bg->bg_bitmap); -else - ret =1 ; -spin_unlock (&jh->b_state_lock); - } -jbd_unlock_bh_journal_head (bg_bh); +spin_lock (&jh->b_state_lock); + bg = (struct ocfs2_group_desc *) jh->b_committed_data; +if (bg) + ret = !ocfs2_test_bit (nr, (unsigned long *)bg->bg_bitmap); +else + ret =1 ; +spin_unlock (&jh->b_state_lock); +jbd2_journal_put_journal_head (jh);return ret; }
_