[PATCH 1/2] x86: mm: Fix vmalloc_fault oops during lazy MMU updates.

[PATCH 1/2] x86: mm: Fix vmalloc_fault oops during lazy MMU updates.

[Konrad Rzeszutek Wilk]

From: Samu Kallio <samu.kallio@aberdeencloud.com>

In paravirtualized x86_64 kernels, vmalloc_fault may cause an oops
when lazy MMU updates are enabled, because set_pgd effects are being
deferred.

One instance of this problem is during process mm cleanup with memory
cgroups enabled. The chain of events is as follows:

- zap_pte_range enables lazy MMU updates
- zap_pte_range eventually calls mem_cgroup_charge_statistics,
  which accesses the vmalloc'd mem_cgroup per-cpu stat area
- vmalloc_fault is triggered which tries to sync the corresponding
  PGD entry with set_pgd, but the update is deferred
- vmalloc_fault oopses due to a mismatch in the PUD entries

The OOPs usually looks as so:

------------[ cut here ]------------
kernel BUG at arch/x86/mm/fault.c:396!
invalid opcode: 0000 [#1] SMP
.. snip ..
CPU 1
Pid: 10866, comm: httpd Not tainted 3.6.10-4.fc18.x86_64 #1
RIP: e030:[<ffffffff816271bf>]  [<ffffffff816271bf>] vmalloc_fault+0x11f/0x208
.. snip ..
Call Trace:
 [<ffffffff81627759>] do_page_fault+0x399/0x4b0
 [<ffffffff81004f4c>] ? xen_mc_extend_args+0xec/0x110
 [<ffffffff81624065>] page_fault+0x25/0x30
 [<ffffffff81184d03>] ? mem_cgroup_charge_statistics.isra.13+0x13/0x50
 [<ffffffff81186f78>] __mem_cgroup_uncharge_common+0xd8/0x350
 [<ffffffff8118aac7>] mem_cgroup_uncharge_page+0x57/0x60
 [<ffffffff8115fbc0>] page_remove_rmap+0xe0/0x150
 [<ffffffff8115311a>] ? vm_normal_page+0x1a/0x80
 [<ffffffff81153e61>] unmap_single_vma+0x531/0x870
 [<ffffffff81154962>] unmap_vmas+0x52/0xa0
 [<ffffffff81007442>] ? pte_mfn_to_pfn+0x72/0x100
 [<ffffffff8115c8f8>] exit_mmap+0x98/0x170
 [<ffffffff810050d9>] ? __raw_callee_save_xen_pmd_val+0x11/0x1e
 [<ffffffff81059ce3>] mmput+0x83/0xf0
 [<ffffffff810624c4>] exit_mm+0x104/0x130
 [<ffffffff8106264a>] do_exit+0x15a/0x8c0
 [<ffffffff810630ff>] do_group_exit+0x3f/0xa0
 [<ffffffff81063177>] sys_exit_group+0x17/0x20
 [<ffffffff8162bae9>] system_call_fastpath+0x16/0x1b

Calling arch_flush_lazy_mmu_mode immediately after set_pgd makes the
changes visible to the consistency checks.

CC: stable@vger.kernel.org
RedHat-Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=914737
Tested-by: Josh Boyer <jwboyer@redhat.com>
Reported-and-Tested-by: Krishna Raman <kraman@redhat.com>
Signed-off-by: Samu Kallio <samu.kallio@aberdeencloud.com>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/mm/fault.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2b97525..0e88336 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd))
+	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
-	else
+		arch_flush_lazy_mmu_mode();
+	} else {
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	}
 
 	/*
 	 * Below here mismatches are bugs because these lower tables
-- 
1.8.0.2

[PATCH 2/2] mm/x86: Patch out arch_flush_lazy_mmu_mode() when running on bare metal

[Konrad Rzeszutek Wilk]

From: Boris Ostrovsky <boris.ostrovsky@oracle.com>

Invoking arch_flush_lazy_mmu_mode() results in calls to
preempt_enable()/disable() which may have performance impact.

Since lazy MMU is not used on bare metal we can patch away
arch_flush_lazy_mmu_mode() so that it is never called in such
environment.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Tested-by: Josh Boyer <jwboyer@redhat.com>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/paravirt.h       |  5 ++++-
 arch/x86/include/asm/paravirt_types.h |  2 ++
 arch/x86/kernel/paravirt.c            | 25 +++++++++++++------------
 arch/x86/lguest/boot.c                |  1 +
 arch/x86/xen/mmu.c                    |  1 +
 5 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5edd174..7361e47 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				phys_addr_t phys, pgprot_t flags)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 142236e..b3b0ec1 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,6 +91,7 @@ struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
 	void (*enter)(void);
 	void (*leave)(void);
+	void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 17fff18..8bfb335 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return this_cpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 1cbd89c..7114c63 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1334,6 +1334,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
 	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
+	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e8e3493..f4f4105 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2197,6 +2197,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
 		.leave = xen_leave_lazy_mmu,
+		.flush = paravirt_flush_lazy_mmu,
 	},
 
 	.set_fixmap = xen_set_fixmap,
-- 
1.8.0.2

Re: [PATCH 2/2] mm/x86: Patch out arch_flush_lazy_mmu_mode() when running on bare metal

[Boris Ostrovsky]

On 03/23/2013 09:36 AM, Konrad Rzeszutek Wilk wrote:
> From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>
> Invoking arch_flush_lazy_mmu_mode() results in calls to
> preempt_enable()/disable() which may have performance impact.
>
> Since lazy MMU is not used on bare metal we can patch away
> arch_flush_lazy_mmu_mode() so that it is never called in such
> environment.
>
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Tested-by: Josh Boyer <jwboyer@redhat.com>
> Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Acked-by: Borislav Petkov <bp@suse.de>
> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Peter, what's the status of these two patches? They are not going into
3.9, right?

Thanks.
-boris


> ---
>   arch/x86/include/asm/paravirt.h       |  5 ++++-
>   arch/x86/include/asm/paravirt_types.h |  2 ++
>   arch/x86/kernel/paravirt.c            | 25 +++++++++++++------------
>   arch/x86/lguest/boot.c                |  1 +
>   arch/x86/xen/mmu.c                    |  1 +
>   5 files changed, 21 insertions(+), 13 deletions(-)
>
> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
> index 5edd174..7361e47 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
>   	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
>   }
>   
> -void arch_flush_lazy_mmu_mode(void);
> +static inline void arch_flush_lazy_mmu_mode(void)
> +{
> +	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
> +}
>   
>   static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
>   				phys_addr_t phys, pgprot_t flags)
> diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
> index 142236e..b3b0ec1 100644
> --- a/arch/x86/include/asm/paravirt_types.h
> +++ b/arch/x86/include/asm/paravirt_types.h
> @@ -91,6 +91,7 @@ struct pv_lazy_ops {
>   	/* Set deferred update mode, used for batching operations. */
>   	void (*enter)(void);
>   	void (*leave)(void);
> +	void (*flush)(void);
>   };
>   
>   struct pv_time_ops {
> @@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next);
>   
>   void paravirt_enter_lazy_mmu(void);
>   void paravirt_leave_lazy_mmu(void);
> +void paravirt_flush_lazy_mmu(void);
>   
>   void _paravirt_nop(void);
>   u32 _paravirt_ident_32(u32);
> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
> index 17fff18..8bfb335 100644
> --- a/arch/x86/kernel/paravirt.c
> +++ b/arch/x86/kernel/paravirt.c
> @@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
>   	leave_lazy(PARAVIRT_LAZY_MMU);
>   }
>   
> +void paravirt_flush_lazy_mmu(void)
> +{
> +	preempt_disable();
> +
> +	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
> +		arch_leave_lazy_mmu_mode();
> +		arch_enter_lazy_mmu_mode();
> +	}
> +
> +	preempt_enable();
> +}
> +
>   void paravirt_start_context_switch(struct task_struct *prev)
>   {
>   	BUG_ON(preemptible());
> @@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
>   	return this_cpu_read(paravirt_lazy_mode);
>   }
>   
> -void arch_flush_lazy_mmu_mode(void)
> -{
> -	preempt_disable();
> -
> -	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
> -		arch_leave_lazy_mmu_mode();
> -		arch_enter_lazy_mmu_mode();
> -	}
> -
> -	preempt_enable();
> -}
> -
>   struct pv_info pv_info = {
>   	.name = "bare hardware",
>   	.paravirt_enabled = 0,
> @@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
>   	.lazy_mode = {
>   		.enter = paravirt_nop,
>   		.leave = paravirt_nop,
> +		.flush = paravirt_nop,
>   	},
>   
>   	.set_fixmap = native_set_fixmap,
> diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
> index 1cbd89c..7114c63 100644
> --- a/arch/x86/lguest/boot.c
> +++ b/arch/x86/lguest/boot.c
> @@ -1334,6 +1334,7 @@ __init void lguest_init(void)
>   	pv_mmu_ops.read_cr3 = lguest_read_cr3;
>   	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
>   	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
> +	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
>   	pv_mmu_ops.pte_update = lguest_pte_update;
>   	pv_mmu_ops.pte_update_defer = lguest_pte_update;
>   
> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
> index e8e3493..f4f4105 100644
> --- a/arch/x86/xen/mmu.c
> +++ b/arch/x86/xen/mmu.c
> @@ -2197,6 +2197,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
>   	.lazy_mode = {
>   		.enter = paravirt_enter_lazy_mmu,
>   		.leave = xen_leave_lazy_mmu,
> +		.flush = paravirt_flush_lazy_mmu,
>   	},
>   
>   	.set_fixmap = xen_set_fixmap,