[PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
From: "Gautham R. Shenoy" During a memory hotplug operations involving resizing of the HPT, we invoke a stop_machine() to perform the resizing. In this code path, we end up recursively taking the cpu_hotplug_lock, first in memory_hotplug_begin() and then subsequently in stop_machine(). This causes the system to hang. With lockdep enabled we get the following error message before the hang. swapper/0/1 is trying to acquire lock: (ptrval) (cpu_hotplug_lock.rw_sem){}, at: stop_machine+0x2c/0x60 but task is already holding lock: (ptrval) (cpu_hotplug_lock.rw_sem){}, at: mem_hotplug_begin+0x20/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 lock(cpu_hotplug_lock.rw_sem); lock(cpu_hotplug_lock.rw_sem); *** DEADLOCK *** Fix this issue by 1) Requiring all the calls to pseries_lpar_resize_hpt() be made with cpu_hotplug_lock held. 2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked() as a consequence of 1) 3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt() with cpu_hotplug_lock held. Reported-by: Aneesh Kumar K.V Signed-off-by: Gautham R. Shenoy --- arch/powerpc/mm/hash_utils_64.c | 9 - arch/powerpc/platforms/pseries/lpar.c | 8 ++-- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0a4f939..b05c79c 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -1890,10 +1891,16 @@ static int hpt_order_get(void *data, u64 *val) static int hpt_order_set(void *data, u64 val) { + int ret; + if (!mmu_hash_ops.resize_hpt) return -ENODEV; - return mmu_hash_ops.resize_hpt(val); + cpus_read_lock(); + ret = mmu_hash_ops.resize_hpt(val); + cpus_read_unlock(); + + return ret; } DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f2a9f0a..65df95b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -859,7 +859,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) return 0; } -/* Must be called in user context */ +/* + * Must be called in user context. The caller should hold the + * cpus_lock. + */ static int pseries_lpar_resize_hpt(unsigned long shift) { struct hpt_resize_state state = { @@ -911,7 +914,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) t1 = ktime_get(); - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, +&state, NULL); t2 = ktime_get(); -- 1.9.4
[RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
From: "Gautham R. Shenoy" During a memory hotplug operations involving resizing of the HPT, we invoke a stop_machine() to perform the resizing. In this code path, we end up recursively taking the cpu_hotplug_lock, first in memory_hotplug_begin() and then subsequently in stop_machine(). This causes the system to hang. With lockdep enabled we get the following error message before the hang. swapper/0/1 is trying to acquire lock: (ptrval) (cpu_hotplug_lock.rw_sem){}, at: stop_machine+0x2c/0x60 but task is already holding lock: (ptrval) (cpu_hotplug_lock.rw_sem){}, at: mem_hotplug_begin+0x20/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 lock(cpu_hotplug_lock.rw_sem); lock(cpu_hotplug_lock.rw_sem); *** DEADLOCK *** Fix this issue by 1) Requiring all the calls to pseries_lpar_resize_hpt() be made with cpu_hotplug_lock held. 2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked() as a consequence of 1) 3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt() with cpu_hotplug_lock held. Reported-by: Aneesh Kumar K.V Signed-off-by: Gautham R. Shenoy --- Rebased this one against powerpc/next instead of linux/master. arch/powerpc/mm/book3s64/hash_utils.c | 9 - arch/powerpc/platforms/pseries/lpar.c | 8 ++-- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 919a861..d07fcafd 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1928,10 +1929,16 @@ static int hpt_order_get(void *data, u64 *val) static int hpt_order_set(void *data, u64 val) { + int ret; + if (!mmu_hash_ops.resize_hpt) return -ENODEV; - return mmu_hash_ops.resize_hpt(val); + cpus_read_lock(); + ret = mmu_hash_ops.resize_hpt(val); + cpus_read_unlock(); + + return ret; } DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 1034ef1..2fc9756 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -859,7 +859,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) return 0; } -/* Must be called in user context */ +/* + * Must be called in user context. The caller should hold the + * cpus_lock. + */ static int pseries_lpar_resize_hpt(unsigned long shift) { struct hpt_resize_state state = { @@ -913,7 +916,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) t1 = ktime_get(); - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, +&state, NULL); t2 = ktime_get(); -- 1.9.4
Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
"Gautham R. Shenoy" writes: > From: "Gautham R. Shenoy" > > During a memory hotplug operations involving resizing of the HPT, we > invoke a stop_machine() to perform the resizing. In this code path, we > end up recursively taking the cpu_hotplug_lock, first in > memory_hotplug_begin() and then subsequently in stop_machine(). This > causes the system to hang. This implies we have never tested a memory hotplug that resized the HPT. Is that really true? Or did something change? > With lockdep enabled we get the following > error message before the hang. > > swapper/0/1 is trying to acquire lock: > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: stop_machine+0x2c/0x60 > > but task is already holding lock: > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > mem_hotplug_begin+0x20/0x50 Do we have the full stack trace? > other info that might help us debug this: >Possible unsafe locking scenario: > > CPU0 > > lock(cpu_hotplug_lock.rw_sem); > lock(cpu_hotplug_lock.rw_sem); > >*** DEADLOCK *** > > Fix this issue by > 1) Requiring all the calls to pseries_lpar_resize_hpt() be made > with cpu_hotplug_lock held. > > 2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked() > as a consequence of 1) > > 3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt() > with cpu_hotplug_lock held. > > Reported-by: Aneesh Kumar K.V > Signed-off-by: Gautham R. Shenoy > --- > > Rebased this one against powerpc/next instead of linux/master. > > arch/powerpc/mm/book3s64/hash_utils.c | 9 - > arch/powerpc/platforms/pseries/lpar.c | 8 ++-- > 2 files changed, 14 insertions(+), 3 deletions(-) > > diff --git a/arch/powerpc/mm/book3s64/hash_utils.c > b/arch/powerpc/mm/book3s64/hash_utils.c > index 919a861..d07fcafd 100644 > --- a/arch/powerpc/mm/book3s64/hash_utils.c > +++ b/arch/powerpc/mm/book3s64/hash_utils.c > @@ -38,6 +38,7 @@ > #include > #include > #include > +#include > > #include > #include > @@ -1928,10 +1929,16 @@ static int hpt_order_get(void *data, u64 *val) > > static int hpt_order_set(void *data, u64 val) > { > + int ret; > + > if (!mmu_hash_ops.resize_hpt) > return -ENODEV; > > - return mmu_hash_ops.resize_hpt(val); > + cpus_read_lock(); > + ret = mmu_hash_ops.resize_hpt(val); > + cpus_read_unlock(); > + > + return ret; > } > > DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, > "%llu\n"); > diff --git a/arch/powerpc/platforms/pseries/lpar.c > b/arch/powerpc/platforms/pseries/lpar.c > index 1034ef1..2fc9756 100644 > --- a/arch/powerpc/platforms/pseries/lpar.c > +++ b/arch/powerpc/platforms/pseries/lpar.c > @@ -859,7 +859,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) > return 0; > } > > -/* Must be called in user context */ > +/* > + * Must be called in user context. The caller should hold the I realise you're just copying that comment, but it seems wrong. "user context" means userspace. I think it means "process context" doesn't it? Also "should" should be "must" :) > + * cpus_lock. > + */ > static int pseries_lpar_resize_hpt(unsigned long shift) > { > struct hpt_resize_state state = { > @@ -913,7 +916,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) > > t1 = ktime_get(); > > - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); > + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, > + &state, NULL); > > t2 = ktime_get(); cheers
Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
"Gautham R. Shenoy" writes: > From: "Gautham R. Shenoy" > > Subject: Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition > in resize_hpt ps. A "RESEND" implies the patch is unchanged and you're just resending it because it was ignored. In this case it should have just been "PATCH v2", with a note below the "---" saying "v2: Rebased onto powerpc/next ..." cheers > During a memory hotplug operations involving resizing of the HPT, we > invoke a stop_machine() to perform the resizing. In this code path, we > end up recursively taking the cpu_hotplug_lock, first in > memory_hotplug_begin() and then subsequently in stop_machine(). This > causes the system to hang. With lockdep enabled we get the following > error message before the hang. > > swapper/0/1 is trying to acquire lock: > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: stop_machine+0x2c/0x60 > > but task is already holding lock: > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > mem_hotplug_begin+0x20/0x50 > > other info that might help us debug this: >Possible unsafe locking scenario: > > CPU0 > > lock(cpu_hotplug_lock.rw_sem); > lock(cpu_hotplug_lock.rw_sem); > >*** DEADLOCK *** > > Fix this issue by > 1) Requiring all the calls to pseries_lpar_resize_hpt() be made > with cpu_hotplug_lock held. > > 2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked() > as a consequence of 1) > > 3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt() > with cpu_hotplug_lock held. > > Reported-by: Aneesh Kumar K.V > Signed-off-by: Gautham R. Shenoy > --- > > Rebased this one against powerpc/next instead of linux/master. > > arch/powerpc/mm/book3s64/hash_utils.c | 9 - > arch/powerpc/platforms/pseries/lpar.c | 8 ++-- > 2 files changed, 14 insertions(+), 3 deletions(-) > > diff --git a/arch/powerpc/mm/book3s64/hash_utils.c > b/arch/powerpc/mm/book3s64/hash_utils.c > index 919a861..d07fcafd 100644 > --- a/arch/powerpc/mm/book3s64/hash_utils.c > +++ b/arch/powerpc/mm/book3s64/hash_utils.c > @@ -38,6 +38,7 @@ > #include > #include > #include > +#include > > #include > #include > @@ -1928,10 +1929,16 @@ static int hpt_order_get(void *data, u64 *val) > > static int hpt_order_set(void *data, u64 val) > { > + int ret; > + > if (!mmu_hash_ops.resize_hpt) > return -ENODEV; > > - return mmu_hash_ops.resize_hpt(val); > + cpus_read_lock(); > + ret = mmu_hash_ops.resize_hpt(val); > + cpus_read_unlock(); > + > + return ret; > } > > DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, > "%llu\n"); > diff --git a/arch/powerpc/platforms/pseries/lpar.c > b/arch/powerpc/platforms/pseries/lpar.c > index 1034ef1..2fc9756 100644 > --- a/arch/powerpc/platforms/pseries/lpar.c > +++ b/arch/powerpc/platforms/pseries/lpar.c > @@ -859,7 +859,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) > return 0; > } > > -/* Must be called in user context */ > +/* > + * Must be called in user context. The caller should hold the > + * cpus_lock. > + */ > static int pseries_lpar_resize_hpt(unsigned long shift) > { > struct hpt_resize_state state = { > @@ -913,7 +916,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) > > t1 = ktime_get(); > > - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); > + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, > + &state, NULL); > > t2 = ktime_get(); > > -- > 1.9.4
Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
Hi Michael, On Tue, May 14, 2019 at 05:00:19PM +1000, Michael Ellerman wrote: > "Gautham R. Shenoy" writes: > > From: "Gautham R. Shenoy" > > > > During a memory hotplug operations involving resizing of the HPT, we > > invoke a stop_machine() to perform the resizing. In this code path, we > > end up recursively taking the cpu_hotplug_lock, first in > > memory_hotplug_begin() and then subsequently in stop_machine(). This > > causes the system to hang. > > This implies we have never tested a memory hotplug that resized the HPT. > Is that really true? Or did something change? > This was reported by Aneesh during a testcase involving reconfiguring the namespace for nvdimm where we do a memory remove followed by add. The memory add invokes resize_hpt(). It seems we can hit this issue when we perform a memory hotplug/unplug in the guest. > > With lockdep enabled we get the following > > error message before the hang. > > > > swapper/0/1 is trying to acquire lock: > > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > > stop_machine+0x2c/0x60 > > > > but task is already holding lock: > > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > > mem_hotplug_begin+0x20/0x50 > > Do we have the full stack trace? Yes, here is the complete log: [0.537123] swapper/0/1 is trying to acquire lock: [0.537197] (ptrval) (cpu_hotplug_lock.rw_sem){}, at: stop_machine+0x2c/0x60 [0.537336] [0.537336] but task is already holding lock: [0.537429] (ptrval) (cpu_hotplug_lock.rw_sem){}, at: mem_hotplug_begin+0x20/0x50 [0.537570] [0.537570] other info that might help us debug this: [0.537663] Possible unsafe locking scenario: [0.537663] [0.537756]CPU0 [0.537794] [0.537832] lock(cpu_hotplug_lock.rw_sem); [0.537906] lock(cpu_hotplug_lock.rw_sem); [0.537980] [0.537980] *** DEADLOCK *** [0.537980] [0.538074] May be due to missing lock nesting notation [0.538074] [0.538168] 3 locks held by swapper/0/1: [0.538224] #0: (ptrval) (&dev->mutex){}, at: __driver_attach+0x12c/0x1b0 [0.538348] #1: (ptrval) (cpu_hotplug_lock.rw_sem){}, at: mem_hotplug_begin+0x20/0x50 [0.538477] #2: (ptrval) (mem_hotplug_lock.rw_sem){}, at: percpu_down_write+0x54/0x1a0 [0.538608] [0.538608] stack backtrace: [0.538685] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.0.0-rc5-58373-gbc99402235f3-dirty #166 [0.538812] Call Trace: [0.538863] [c000feb03150] [c0e32bd4] dump_stack+0xe8/0x164 (unreliable) [0.538975] [c000feb031a0] [c020d6c0] __lock_acquire+0x1110/0x1c70 [0.539086] [c000feb03320] [c020f080] lock_acquire+0x240/0x290 [0.539180] [c000feb033e0] [c017f554] cpus_read_lock+0x64/0xf0 [0.539273] [c000feb03420] [c029ebac] stop_machine+0x2c/0x60 [0.539367] [c000feb03460] [c00d7f7c] pseries_lpar_resize_hpt+0x19c/0x2c0 [0.539479] [c000feb03500] [c00788d0] resize_hpt_for_hotplug+0x70/0xd0 [0.539590] [c000feb03570] [c0e5d278] arch_add_memory+0x58/0xfc [0.539683] [c000feb03610] [c03553a8] devm_memremap_pages+0x5e8/0x8f0 [0.539804] [c000feb036c0] [c09c2394] pmem_attach_disk+0x764/0x830 [0.539916] [c000feb037d0] [c09a7c38] nvdimm_bus_probe+0x118/0x240 [0.540026] [c000feb03860] [c0968500] really_probe+0x230/0x4b0 [0.540119] [c000feb038f0] [c0968aec] driver_probe_device+0x16c/0x1e0 [0.540230] [c000feb03970] [c0968ca8] __driver_attach+0x148/0x1b0 [0.540340] [c000feb039f0] [c09650b0] bus_for_each_dev+0x90/0x130 [0.540451] [c000feb03a50] [c0967dd4] driver_attach+0x34/0x50 [0.540544] [c000feb03a70] [c0967068] bus_add_driver+0x1a8/0x360 [0.540654] [c000feb03b00] [c096a498] driver_register+0x108/0x170 [0.540766] [c000feb03b70] [c09a7400] __nd_driver_register+0xd0/0xf0 [0.540898] [c000feb03bd0] [c128aa90] nd_pmem_driver_init+0x34/0x48 [0.541010] [c000feb03bf0] [c0010a10] do_one_initcall+0x1e0/0x45c [0.541122] [c000feb03cd0] [c122462c] kernel_init_freeable+0x540/0x64c [0.541232] [c000feb03db0] [c001110c] kernel_init+0x2c/0x16
Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock acquisition in resize_hpt
On Tue, May 14, 2019 at 05:02:16PM +1000, Michael Ellerman wrote: > "Gautham R. Shenoy" writes: > > From: "Gautham R. Shenoy" > > > > Subject: Re: [RESEND PATCH] powerpc/pseries: Fix cpu_hotplug_lock > > acquisition in resize_hpt > > ps. A "RESEND" implies the patch is unchanged and you're just resending > it because it was ignored. > > In this case it should have just been "PATCH v2", with a note below the "---" > saying "v2: Rebased onto powerpc/next ..." Ok. I will send a v3 :-) > > cheers > > > During a memory hotplug operations involving resizing of the HPT, we > > invoke a stop_machine() to perform the resizing. In this code path, we > > end up recursively taking the cpu_hotplug_lock, first in > > memory_hotplug_begin() and then subsequently in stop_machine(). This > > causes the system to hang. With lockdep enabled we get the following > > error message before the hang. > > > > swapper/0/1 is trying to acquire lock: > > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > > stop_machine+0x2c/0x60 > > > > but task is already holding lock: > > (ptrval) (cpu_hotplug_lock.rw_sem){}, at: > > mem_hotplug_begin+0x20/0x50 > > > > other info that might help us debug this: > >Possible unsafe locking scenario: > > > > CPU0 > > > > lock(cpu_hotplug_lock.rw_sem); > > lock(cpu_hotplug_lock.rw_sem); > > > >*** DEADLOCK *** > > > > Fix this issue by > > 1) Requiring all the calls to pseries_lpar_resize_hpt() be made > > with cpu_hotplug_lock held. > > > > 2) In pseries_lpar_resize_hpt() invoke stop_machine_cpuslocked() > > as a consequence of 1) > > > > 3) To satisfy 1), in hpt_order_set(), call mmu_hash_ops.resize_hpt() > > with cpu_hotplug_lock held. > > > > Reported-by: Aneesh Kumar K.V > > Signed-off-by: Gautham R. Shenoy > > --- > > > > Rebased this one against powerpc/next instead of linux/master. > > > > arch/powerpc/mm/book3s64/hash_utils.c | 9 - > > arch/powerpc/platforms/pseries/lpar.c | 8 ++-- > > 2 files changed, 14 insertions(+), 3 deletions(-) > > > > diff --git a/arch/powerpc/mm/book3s64/hash_utils.c > > b/arch/powerpc/mm/book3s64/hash_utils.c > > index 919a861..d07fcafd 100644 > > --- a/arch/powerpc/mm/book3s64/hash_utils.c > > +++ b/arch/powerpc/mm/book3s64/hash_utils.c > > @@ -38,6 +38,7 @@ > > #include > > #include > > #include > > +#include > > > > #include > > #include > > @@ -1928,10 +1929,16 @@ static int hpt_order_get(void *data, u64 *val) > > > > static int hpt_order_set(void *data, u64 val) > > { > > + int ret; > > + > > if (!mmu_hash_ops.resize_hpt) > > return -ENODEV; > > > > - return mmu_hash_ops.resize_hpt(val); > > + cpus_read_lock(); > > + ret = mmu_hash_ops.resize_hpt(val); > > + cpus_read_unlock(); > > + > > + return ret; > > } > > > > DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, > > "%llu\n"); > > diff --git a/arch/powerpc/platforms/pseries/lpar.c > > b/arch/powerpc/platforms/pseries/lpar.c > > index 1034ef1..2fc9756 100644 > > --- a/arch/powerpc/platforms/pseries/lpar.c > > +++ b/arch/powerpc/platforms/pseries/lpar.c > > @@ -859,7 +859,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) > > return 0; > > } > > > > -/* Must be called in user context */ > > +/* > > + * Must be called in user context. The caller should hold the > > + * cpus_lock. > > + */ > > static int pseries_lpar_resize_hpt(unsigned long shift) > > { > > struct hpt_resize_state state = { > > @@ -913,7 +916,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) > > > > t1 = ktime_get(); > > > > - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); > > + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, > > +&state, NULL); > > > > t2 = ktime_get(); > > > > -- > > 1.9.4 >