x86: Add guard pages to exception and interrupt stacks
Subsystems (7)
v3 cover x86: Add guard pages to exception and interrupt stacks
Hi!
This is an updated version of the guard page series:
V1: https://lkml.kernel.org/r/[email protected]
V2: https://lkml.kernel.org/r/[email protected]
Changes vs. V2:
- Fixed the broken stack trace storage in slub
- Adjust the guard page ordering and fix the top macro (Sean)
- Fix an off by one in the debug stack check (Sean)
- Rename ISTACK_ prefix to ESTACK_ (Josh)
- Collected Acked/Reviewed-by tags
The lot is also available from tip:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git WIP.x86/stackguards
310a7f5b0b42 ("x86/irq/64: Remove stack overflow debug code")Thanks,
tglx
8<-------------
Documentation/x86/kernel-stacks | 13 +++- arch/x86/Kconfig | 2 arch/x86/entry/entry_64.S | 16 ++--- arch/x86/include/asm/cpu_entry_area.h | 69 +++++++++++++++++++++-- arch/x86/include/asm/debugreg.h | 2 arch/x86/include/asm/irq.h | 6 -- arch/x86/include/asm/page_32_types.h | 8 +- arch/x86/include/asm/page_64_types.h | 16 ++--- arch/x86/include/asm/processor.h | 43 +++++--------- arch/x86/include/asm/smp.h | 2 arch/x86/include/asm/stackprotector.h | 6 +- arch/x86/include/asm/stacktrace.h | 2 arch/x86/kernel/asm-offsets_64.c | 4 + arch/x86/kernel/cpu/common.c | 60 +++----------------- arch/x86/kernel/dumpstack_32.c | 8 +- arch/x86/kernel/dumpstack_64.c | 99 +++++++++++++++++++++++----------- arch/x86/kernel/head_64.S | 2 arch/x86/kernel/idt.c | 19 +++--- arch/x86/kernel/irq_32.c | 41 +++++++------- arch/x86/kernel/irq_64.c | 89 +++++++++++++++--------------- arch/x86/kernel/irqinit.c | 4 - arch/x86/kernel/nmi.c | 20 ++++++ arch/x86/kernel/setup_percpu.c | 5 - arch/x86/kernel/smpboot.c | 15 ++++- arch/x86/kernel/vmlinux.lds.S | 7 +- arch/x86/mm/cpu_entry_area.c | 64 +++++++++++++++------ arch/x86/mm/fault.c | 3 - arch/x86/tools/relocs.c | 2 arch/x86/xen/smp_pv.c | 4 + arch/x86/xen/xen-head.S | 10 +-- drivers/xen/events/events_base.c | 1 mm/slab.c | 30 ++++------ 32 files changed, 382 insertions(+), 290 deletions(-)
PATCH v3 1/32 mm/slab: Fix broken stack trace storage
kstack_end() is broken on interrupt stacks as they are not guaranteed to be sized THREAD_SIZE and THREAD_SIZE aligned.
Use the stack tracer instead. Remove the pointless pointer increment at the end of the function while at it.
--- mm/slab.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-)
mm/slab.c +12 -16
@@ -1470,33 +1470,29 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { + .max_entries = size - 4; + .entries = addr; + .skip = 3; + }; +save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ; } static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
Andy Lutomirski
maintainerRe: [patch V3 01/32] mm/slab: Fix broken stack trace storage
Quoted 44 lines · Thomas Gleixner
kstack_end()is broken on interrupt stacks as they are not guaranteed to be sizedTHREAD_SIZEandTHREAD_SIZEaligned.Use the stack tracer instead. Remove the pointless pointer increment at the end of the function while at it.
Fixes 98eb235b7feb ("[PATCH] page unmapping debug") - History treeSigned-off-by Thomas Gleixner <[email protected]>Cc Andrew Morton <[email protected]>Cc Pekka Enberg <[email protected]>--- mm/slab.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-)mm/slab.c +3
-10@@ -1470,33 +1470,29 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue;
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1489
Quoted 10 lines
mm/slab.c +5
-5- size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { + .max_entries = size - 4; + .entries = addr; + .skip = 3; + };
This looks correct, but I think that it would have been clearer if you left the size -= 3 above. You're still incrementing addr, but you're not decrementing size, so they're out of sync and the resulting code is hard to follow.
--Andy
Re: [patch V3 01/32] mm/slab: Fix broken stack trace storage
Quoted 10 lines · Andy Lutomirski
Review
Quoted 5 lines
(quoted diff) +5
-0+ struct stack_trace trace = { + .max_entries = size - 4; + .entries = addr; + .skip = 3; + };This looks correct, but I think that it would have been clearer if you left the size -= 3 above. You're still incrementing addr, but you're not decrementing size, so they're out of sync and the resulting code is hard to follow.
What about the below?
mm/slab.c +3 -1
@@ -1480,10 +1480,12 @@ static void store_stackinfo(struct kmem_ *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); + size -=3 ;#ifdef CONFIG_STACKTRACE {struct stack_trace trace = { - .max_entries = size - 4; +/* Leave one for the end marker below */ + .max_entries = size - 1; .entries = addr; .skip = 3; };
PATCH v4 1/32 mm/slab: Fix broken stack trace storage
kstack_end() is broken on interrupt stacks as they are not guaranteed to be sized THREAD_SIZE and THREAD_SIZE aligned.
Use the stack tracer instead. Remove the pointless pointer increment at the end of the function while at it.
---
V4: Made the code simpler to understand (Andy) and make it actually compile
--- mm/slab.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-)
mm/slab.c +14 -16
@@ -1470,33 +1470,31 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); + size -=3 ; +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size -1 , + .entries = addr, + .skip =3 , + }; +save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ; } static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 54 lines · Thomas Gleixner
kstack_end()is broken on interrupt stacks as they are not guaranteed to be sizedTHREAD_SIZEandTHREAD_SIZEaligned.Use the stack tracer instead. Remove the pointless pointer increment at the end of the function while at it.
Fixes 98eb235b7feb ("[PATCH] page unmapping debug") - History treeSigned-off-by Thomas Gleixner <[email protected]>Cc Andrew Morton <[email protected]>Cc Pekka Enberg <[email protected]>---
V4: Made the code simpler to understand (Andy) and make it actually compile--- mm/slab.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-)mm/slab.c +7
-15@@ -1470,33 +1470,31 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); + size -=3 ; +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size - 1,
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1497
Quoted 10 lines
mm/slab.c +7
-1+ .entries = addr, + .skip =3 , + }; +save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ;
Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
Who actually reads this stack trace? I couldn't find a consumer.
Signature · 1 line
Josh
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 33 lines · Josh Poimboeuf
Quoted 32 lines · Thomas Gleixner
mm/slab.c +9
-14addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); + size -=3 ; +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size -1 , + .entries = addr, + .skip =3 , + };
Quoted 9 lines
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1497
Quoted 6 lines
mm/slab.c +4
-1+save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ;Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Thanks,
tglx
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 44 lines · Thomas Gleixner
Quoted 33 lines · Josh Poimboeuf
Quoted 32 lines · Thomas Gleixner
mm/slab.c +9
-14addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <5 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); + size -=3 ; +#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size -1 , + .entries = addr, + .skip =3 , + };Quoted 9 lines
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1497
Quoted 6 lines
mm/slab.c +4
-1+save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ;Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
Quoted 2 lines
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Hm, it seems you are correct. And I thought I knew C.
Quoted 5 lines
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Right... but who reads it?
Signature · 1 line
Josh
Andy Lutomirski
maintainerRe: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 51 lines · Josh Poimboeuf
Quoted 44 lines · Thomas Gleixner
Quoted 33 lines · Josh Poimboeuf
Quoted 32 lines · Thomas Gleixner
addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];- if (size < 5 * sizeof(unsigned long))
+ if (size < 5)return;*addr++ =
0x12345678;
*addr++ = caller;
*addr++ =smp_processor_id();
- size -= 3 * sizeof(unsigned long);
+ size -= 3;mm/slab.c +7
-12+#ifdef CONFIG_STACKTRACE { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } +struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size -1 , + .entries = addr, + .skip =3 , + };Quoted 9 lines
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1497
Quoted 6 lines
mm/slab.c +4
-1+save_stack_trace (&trace); + addr += trace.nr_entries; } - *addr++ =0x87654321 ; +#endif + *addr =0x87654321 ;Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
Quoted 2 lines
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Hm, it seems you are correct. And I thought I knew C.
Quoted 7 lines
Quoted 5 lines
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Right... but who reads it?
That seems like a reasonable question. After some grepping and some git searching, it looks like there might not be any users. I found SLAB_STORE_USER, but that seems to be independent.
So maybe the whole mess should just be deleted. If anyone ever notices, they can re-add it better.
--Andy
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 12 lines · Andy Lutomirski
Quoted 11 lines · Josh Poimboeuf
Quoted 5 lines · Thomas Gleixner
Quoted 2 lines
Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Hm, it seems you are correct. And I thought I knew C.
Quoted 2 lines
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Right... but who reads it?
That seems like a reasonable question. After some grepping and some git searching, it looks like there might not be any users. I found
Anymore. There was something 10y+ ago...
Quoted 4 lines
SLAB_STORE_USER, but that seems to be independent.So maybe the whole mess should just be deleted. If anyone ever notices, they can re-add it better.
No objections from my side, but the mm people might have opinions.
Thanks,
tglx
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
Quoted 17 lines · Thomas Gleixner
Quoted 16 lines · Andy Lutomirski
Quoted 15 lines · Josh Poimboeuf
Quoted 5 lines · Thomas Gleixner
Quoted 2 lines
Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Hm, it seems you are correct. And I thought I knew C.
Quoted 5 lines
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Right... but who reads it?
That seems like a reasonable question. After some grepping and some git searching, it looks like there might not be any users. I found
Anymore. There was something 10y+ ago.
In theory it can be useful in a crash dump. But I don't see any related debugging
check that would trigger a panic, in order to get one.
Quoted 6 lines
Quoted 4 lines
SLAB_STORE_USER, but that seems to be independent.So maybe the whole mess should just be deleted. If anyone ever notices, they can re-add it better.
No objections from my side, but the mm people might have opinions.
Anyone who wants to debug wrong slab usage probably uses SLUB anyway, so I don't think it's a problem to remove broken SLAB debugging. Perhaps even SLAB itself will be removed soon if there's performance data supporting it [1].
[1]
https://lore.kernel.org/linux-mm/[email protected]/T/#u
Quoted 4 lines
Thanks,
tglx
PATCH v5 1/32 mm/slab: Remove broken stack trace storage
kstack_end() is broken on interrupt stacks as they are not guaranteed to be sized THREAD_SIZE and THREAD_SIZE aligned.
As SLAB seems not to be used much with debugging enabled and might just go away completely according to:
https://lkml.kernel.org/r/[email protected]
just remove the bogus code instead of trying to fix it.
---
V5: Remove the cruft.
V4: Make it actually work
V2: Made the code simpler to understand (Andy)
--- mm/slab.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-)
mm/slab.c +3 -19
@@ -1470,33 +1470,17 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <4 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); - { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } - - } - *addr++ =0x87654321 ; + *addr =0x87654321 ; } static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
Re: [patch V5 01/32] mm/slab: Remove broken stack trace storage
Quoted 8 lines · Thomas Gleixner
kstack_end()is broken on interrupt stacks as they are not guaranteed to be sizedTHREAD_SIZEandTHREAD_SIZEaligned.As SLAB seems not to be used much with debugging enabled and might just go away completely according to:
Quoted 7 lines
just remove the bogus code instead of trying to fix it.
Fixes 98eb235b7feb ("[PATCH] page unmapping debug") - History treeSigned-off-by Thomas Gleixner <[email protected]>Cc Andrew Morton <[email protected]>Cc Pekka Enberg <[email protected]>
Thanks.
Quoted 48 lines
---
V5: Remove the cruft.
V4: Make it actually work
V2: Made the code simpler to understand (Andy)--- mm/slab.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-)mm/slab.c +3
-19@@ -1470,33 +1470,17 @@ static bool is_debug_pagealloc_cache(strstatic void store_stackinfo (struct kmem_cache *cachep,unsigned long *addr,unsigned long caller) { -int size = cachep->object_size; +int size = cachep->object_size /sizeof (unsigned long ); addr = (unsigned long *)&((char *)addr)[obj_offset (cachep)]; -if (size <5 *sizeof (unsigned long )) +if (size <4 )return ; *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id (); - size -=3 *sizeof (unsigned long ); - { -unsigned long *sptr = &caller; -unsigned long svalue; - -while (!kstack_end (sptr)) { - svalue = *sptr++; -if (kernel_text_address (svalue)) { - *addr++ = svalue; - size -=sizeof (unsigned long ); -if (size <=sizeof (unsigned long )) -break ; - } - } - - } - *addr++ =0x87654321 ; + *addr =0x87654321 ; } static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
Re: [patch V4 01/32] mm/slab: Fix broken stack trace storage
In reply to Josh PoimboeufQuoted 9 lines · Josh Poimboeuf
Quoted 6 lines · Thomas Gleixner
Quoted 3 lines
Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Hm, it seems you are correct. And I thought I knew C.
:)
Quoted 7 lines
Quoted 5 lines
Quoted 1 line
Who actually reads this stack trace? I couldn't find a consumer.
It's stored directly in the memory pointed to by @addr and that's the freed cache memory. If that is used later (UAF) then the stack trace can be printed to see where it was freed.
Right... but who reads it?
Indeed. I didn't check but I know that I saw that info printed at least a decade ago. Looks like that debug magic in slab.c has seen major changes since then.
Thanks,
tglx
Peter Zijlstra
maintainerRe: [patch V4 01/32] mm/slab: Fix broken stack trace storage
In reply to Thomas GleixnerQuoted 11 lines · Thomas Gleixner
Quoted 9 lines · Josh Poimboeuf
mm/slab.c static bool is_debug_pagealloc_cache(str · line 1491
Quoted 6 lines
mm/slab.c +6
-0+struct stack_trace trace = { +/* Leave one for the end marker below */ + .max_entries = size -1 , + .entries = addr, + .skip =3 , + };Looks like stack_trace.nr_entries isn't initialized? (though this code gets eventually replaced by a later patch)
Quoted 2 lines
struct initializer initialized the non mentioned fields to 0, if I'm not totally mistaken.
Correct.
Andy Lutomirski
maintainerRe: [patch V3 01/32] mm/slab: Fix broken stack trace storage
In reply to Thomas GleixnerQuoted 21 lines · Thomas Gleixner
Quoted 10 lines · Andy Lutomirski
Review
Quoted 5 lines
(quoted diff) +5
-0+ struct stack_trace trace = { + .max_entries = size - 4; + .entries = addr; + .skip = 3; + };This looks correct, but I think that it would have been clearer if you left the size -= 3 above. You're still incrementing addr, but you're not decrementing size, so they're out of sync and the resulting code is hard to follow.
What about the below?
mm/slab.c +0
-0@@ -1480,10 +1480,12 @@ static void store_stackinfo(struct kmem_ *addr++ =0x12345678 ; *addr++ = caller; *addr++ =smp_processor_id ();
mm/slab.c static void store_stackinfo(struct kmem_ · line 1491
Quoted 10 lines
mm/slab.c +3
-1+ size -=3 ;#ifdef CONFIG_STACKTRACE {struct stack_trace trace = { - .max_entries = size - 4; +/* Leave one for the end marker below */ + .max_entries = size - 1; .entries = addr; .skip = 3; };
Looks good to me.
PATCH v3 2/32 x86/irq/64: Limit IST stack overflow check to #DB stack
In reply to Thomas Gleixnercommit 37fe6a42b343 ("x86: Check stack overflow in detail") added a broad check for the full exception stack area, i.e. it considers the full exception stack area as valid.
That's wrong in two aspects:
1) It does not check the individual areas one by one
2) #DF, NMI and #MCE are not enabling interrupts which means that a regular device interrupt cannot happen in their context. In fact if a device interrupt hits one of those IST stacks that's a bug because some code path enabled interrupts while handling the exception.
Limit the check to the #DB stack and consider all other IST stacks as 'overflow' or invalid.
--- arch/x86/kernel/irq_64.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
arch/x86/kernel/irq_64.c +14 -5
@@ -26,9 +26,18 @@ int sysctl_panic_on_stackoverflow;/* * Probabilistic stack overflow check: * -* Only check the stack in process context, because everything else -* runs on the big interrupt stacks. Checking reliably is too expensive, -* so we just check from interrupts. +* Regular device interrupts can enter on the following stacks: +* +* - User stack +* +* - Kernel task stack +* +* - Interrupt stack if a device driver reenables interrupts +* which should only happen in really old drivers. +* +* - Debug IST stack +* +* All other contexts are invalid. */ static inline void stack_overflow_check (struct pt_regs *regs) {
@@ -53,8 +62,8 @@ static inline void stack_overflow_check(return ; oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[0 ] -EXCEPTION_STKSZ +STACK_TOP_MARGIN ; - estack_bottom = (u64 )oist->ist[N_EXCEPTION_STACKS -1 ]; + estack_bottom = (u64 )oist->ist[DEBUG_STACK ]; + estack_top = estack_bottom -DEBUG_STKSZ +STACK_TOP_MARGIN ;if (regs->sp >= estack_top && regs->sp <= estack_bottom)return ;
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Limit IST stack overflow check to #DB stack
x86/irq/64: Limit IST stack overflow check to #DB stack
Commit-ID: 7dbcf2b0b770eeb803a416ee8dcbef78e6389d40 Gitweb: https://git.kernel.org/tip/7dbcf2b0b770eeb803a416ee8dcbef78e6389d40 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:38 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:06:56 +0200
x86/irq/64: Limit IST stack overflow check to #DB stack
Commit
37fe6a42b343 ("x86: Check stack overflow in detail")
added a broad check for the full exception stack area, i.e. it considers the full exception stack area as valid.
That's wrong in two aspects:
1) It does not check the individual areas one by one
2) #DF, NMI and #MCE are not enabling interrupts which means that a regular device interrupt cannot happen in their context. In fact if a device interrupt hits one of those IST stacks that's a bug because some code path enabled interrupts while handling the exception.
Limit the check to the #DB stack and consider all other IST stacks as 'overflow' or invalid.
--- arch/x86/kernel/irq_64.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
arch/x86/kernel/irq_64.c +14 -5
@@ -26,9 +26,18 @@ int sysctl_panic_on_stackoverflow;/* * Probabilistic stack overflow check: * -* Only check the stack in process context, because everything else -* runs on the big interrupt stacks. Checking reliably is too expensive, -* so we just check from interrupts. +* Regular device interrupts can enter on the following stacks: +* +* - User stack +* +* - Kernel task stack +* +* - Interrupt stack if a device driver reenables interrupts +* which should only happen in really old drivers. +* +* - Debug IST stack +* +* All other contexts are invalid. */ static inline void stack_overflow_check (struct pt_regs *regs) {
@@ -53,8 +62,8 @@ static inline void stack_overflow_check(struct pt_regs *regs)return ; oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[0 ] -EXCEPTION_STKSZ +STACK_TOP_MARGIN ; - estack_bottom = (u64 )oist->ist[N_EXCEPTION_STACKS -1 ]; + estack_bottom = (u64 )oist->ist[DEBUG_STACK ]; + estack_top = estack_bottom -DEBUG_STKSZ +STACK_TOP_MARGIN ;if (regs->sp >= estack_top && regs->sp <= estack_bottom)return ;
PATCH v3 3/32 x86/dumpstack: Fix off-by-one errors in stack identification
In reply to Thomas GleixnerFrom: Andy Lutomirski <[email protected]>
The get_stack_info() function is off-by-one when checking whether an address is on a IRQ stack or a IST stack. This prevents a overflowed IRQ or IST stack from being dumped properly.
[ tglx: Do the same for 32-bit ]
--- arch/x86/kernel/dumpstack_32.c | 4 ++-- arch/x86/kernel/dumpstack_64.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-)
arch/x86/kernel/dumpstack_32.c +2 -2
@@ -41,7 +41,7 @@ static bool in_hardirq_stack(unsigned lo* This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack > end)return false; info->type =STACK_TYPE_IRQ ;
@@ -66,7 +66,7 @@ static bool in_softirq_stack(unsigned lo* This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack > end)return false; info->type =STACK_TYPE_SOFTIRQ ;
arch/x86/kernel/dumpstack_64.c +2 -2
@@ -65,7 +65,7 @@ static bool in_exception_stack(unsigned begin = end - (exception_stack_sizes[k] /sizeof (long )); regs = (struct pt_regs *)end -1 ; -if (stack <= begin || stack >= end) +if (stack < begin || stack >= end)continue ; info->type =STACK_TYPE_EXCEPTION + k;
@@ -88,7 +88,7 @@ static bool in_irq_stack(unsigned long ** This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack >= end)return false; info->type =STACK_TYPE_IRQ ;
tip-bot for Andy Lutomirski
merge bot[tip:x86/irq] x86/dumpstack: Fix off-by-one errors in stack identification
x86/dumpstack: Fix off-by-one errors in stack identification
Commit-ID: fa33215422fd415a07ec2a00e9f1acdaf0fa8e94 Gitweb: https://git.kernel.org/tip/fa33215422fd415a07ec2a00e9f1acdaf0fa8e94 Author: Andy Lutomirski <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:39 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:26:50 +0200
x86/dumpstack: Fix off-by-one errors in stack identification
The get_stack_info() function is off-by-one when checking whether an address is on a IRQ stack or a IST stack. This prevents an overflowed IRQ or IST stack from being dumped properly.
[ tglx: Do the same for 32-bit ]
--- arch/x86/kernel/dumpstack_32.c | 4 ++-- arch/x86/kernel/dumpstack_64.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-)
arch/x86/kernel/dumpstack_32.c +2 -2
@@ -41,7 +41,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)* This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack > end)return false; info->type =STACK_TYPE_IRQ ;
@@ -66,7 +66,7 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)* This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack > end)return false; info->type =STACK_TYPE_SOFTIRQ ;
arch/x86/kernel/dumpstack_64.c +2 -2
@@ -65,7 +65,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) begin = end - (exception_stack_sizes[k] /sizeof (long )); regs = (struct pt_regs *)end -1 ; -if (stack <= begin || stack >= end) +if (stack < begin || stack >= end)continue ; info->type =STACK_TYPE_EXCEPTION + k;
@@ -88,7 +88,7 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info)* This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ -if (stack <= begin || stack > end) +if (stack < begin || stack >= end)return false; info->type =STACK_TYPE_IRQ ;
PATCH v3 4/32 x86/irq/64: Remove a hardcoded irq_stack_union access
In reply to Thomas GleixnerFrom: Andy Lutomirski <[email protected]>
stack_overflow_check() is using both irq_stack_ptr and irq_stack_union to find the IRQ stack. That's going to break when vmapped irq stacks are introduced.
Change it to just use irq_stack_ptr.
--- arch/x86/kernel/irq_64.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
arch/x86/kernel/irq_64.c +1 -2
@@ -55,9 +55,8 @@ static inline void stack_overflow_check( regs->sp <= curbase + THREAD_SIZE)return ; - irq_stack_top = (u64 )this_cpu_ptr (irq_stack_union.irq_stack) + -STACK_TOP_MARGIN ; irq_stack_bottom = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_top = irq_stack_bottom -IRQ_STACK_SIZE +STACK_TOP_MARGIN ;if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)return ;
tip-bot for Andy Lutomirski
merge bot[tip:x86/irq] x86/irq/64: Remove a hardcoded irq_stack_union access
x86/irq/64: Remove a hardcoded irq_stack_union access
Commit-ID: 4f44b8f0b33b7111216f0fad353315f796b81617 Gitweb: https://git.kernel.org/tip/4f44b8f0b33b7111216f0fad353315f796b81617 Author: Andy Lutomirski <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:40 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:31:38 +0200
x86/irq/64: Remove a hardcoded irq_stack_union access
stack_overflow_check() is using both irq_stack_ptr and irq_stack_union to find the IRQ stack. That's going to break when vmapped irq stacks are introduced.
Change it to just use irq_stack_ptr.
--- arch/x86/kernel/irq_64.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
arch/x86/kernel/irq_64.c +1 -2
@@ -55,9 +55,8 @@ static inline void stack_overflow_check(struct pt_regs *regs) regs->sp <= curbase + THREAD_SIZE)return ; - irq_stack_top = (u64 )this_cpu_ptr (irq_stack_union.irq_stack) + -STACK_TOP_MARGIN ; irq_stack_bottom = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_top = irq_stack_bottom -IRQ_STACK_SIZE +STACK_TOP_MARGIN ;if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)return ;
PATCH v3 5/32 x86/irq/64: Sanitize the top/bottom confusion
In reply to Thomas GleixnerOn x86 stacks go top to bottom, but the stack overflow check uses it the other way round, which is just confusing. Clean it up and sanitize the warning string a bit.
--- arch/x86/kernel/irq_64.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-)
arch/x86/kernel/irq_64.c +11 -11
@@ -42,7 +42,7 @@ int sysctl_panic_on_stackoverflow;static inline void stack_overflow_check (struct pt_regs *regs) {#ifdef CONFIG_DEBUG_STACKOVERFLOW -#define STACK_TOP_MARGIN 128 +#define STACK_MARGIN 128struct orig_ist *oist;u64 irq_stack_top, irq_stack_bottom;u64 estack_top, estack_bottom;
@@ -51,25 +51,25 @@ static inline void stack_overflow_check(if (user_mode (regs))return ; -if (regs->sp >= curbase +sizeof (struct pt_regs ) +STACK_TOP_MARGIN && +if (regs->sp >= curbase +sizeof (struct pt_regs ) +STACK_MARGIN && regs->sp <= curbase +THREAD_SIZE )return ; - irq_stack_bottom = (u64 )__this_cpu_read (irq_stack_ptr); - irq_stack_top = irq_stack_bottom -IRQ_STACK_SIZE +STACK_TOP_MARGIN ; -if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom) + irq_stack_top = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_bottom = irq_stack_top -IRQ_STACK_SIZE +STACK_MARGIN ; +if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ; oist =this_cpu_ptr (&orig_ist); - estack_bottom = (u64 )oist->ist[DEBUG_STACK ]; - estack_top = estack_bottom -DEBUG_STKSZ +STACK_TOP_MARGIN ; -if (regs->sp >= estack_top && regs->sp <= estack_bottom) + estack_top = (u64 )oist->ist[DEBUG_STACK ]; + estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ; +if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ; -WARN_ONCE (1 ,"do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n" , +WARN_ONCE (1 ,"do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx, irq stack:%Lx-%Lx, exception stack: %Lx-%Lx, ip:%pF)\n" , current->comm, curbase, regs->sp, - irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom, (void *)regs->ip); + irq_stack_bottom, irq_stack_top, + estack_bottom, estack_top, (void *)regs->ip);if (sysctl_panic_on_stackoverflow)panic ("low stack detected by irq handler - check messages\n" );
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Sanitize the top/bottom confusion
x86/irq/64: Sanitize the top/bottom confusion
Commit-ID: df835e7083bee33e98635aca26b39b63ebc6cca7 Gitweb: https://git.kernel.org/tip/df835e7083bee33e98635aca26b39b63ebc6cca7 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:41 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:34:49 +0200
x86/irq/64: Sanitize the top/bottom confusion
On x86, stacks go top to bottom, but the stack overflow check uses it the other way round, which is just confusing. Clean it up and sanitize the warning string a bit.
--- arch/x86/kernel/irq_64.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-)
arch/x86/kernel/irq_64.c +11 -11
@@ -42,7 +42,7 @@ int sysctl_panic_on_stackoverflow;static inline void stack_overflow_check (struct pt_regs *regs) {#ifdef CONFIG_DEBUG_STACKOVERFLOW -#define STACK_TOP_MARGIN 128 +#define STACK_MARGIN 128struct orig_ist *oist;u64 irq_stack_top, irq_stack_bottom;u64 estack_top, estack_bottom;
@@ -51,25 +51,25 @@ static inline void stack_overflow_check(struct pt_regs *regs)if (user_mode (regs))return ; -if (regs->sp >= curbase +sizeof (struct pt_regs ) +STACK_TOP_MARGIN && +if (regs->sp >= curbase +sizeof (struct pt_regs ) +STACK_MARGIN && regs->sp <= curbase +THREAD_SIZE )return ; - irq_stack_bottom = (u64 )__this_cpu_read (irq_stack_ptr); - irq_stack_top = irq_stack_bottom -IRQ_STACK_SIZE +STACK_TOP_MARGIN ; -if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom) + irq_stack_top = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_bottom = irq_stack_top -IRQ_STACK_SIZE +STACK_MARGIN ; +if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ; oist =this_cpu_ptr (&orig_ist); - estack_bottom = (u64 )oist->ist[DEBUG_STACK ]; - estack_top = estack_bottom -DEBUG_STKSZ +STACK_TOP_MARGIN ; -if (regs->sp >= estack_top && regs->sp <= estack_bottom) + estack_top = (u64 )oist->ist[DEBUG_STACK ]; + estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ; +if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ; -WARN_ONCE (1 ,"do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n" , +WARN_ONCE (1 ,"do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx, irq stack:%Lx-%Lx, exception stack: %Lx-%Lx, ip:%pF)\n" , current->comm, curbase, regs->sp, - irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom, (void *)regs->ip); + irq_stack_bottom, irq_stack_top, + estack_bottom, estack_top, (void *)regs->ip);if (sysctl_panic_on_stackoverflow)panic ("low stack detected by irq handler - check messages\n" );
PATCH v3 6/32 x86/idt: Remove unused macro SISTG
In reply to Thomas Gleixnercommit d8ba61ba58c8 ("x86/entry/64: Don't use IST entry for #BP stack") removed the last user but left the macro around.
--- arch/x86/kernel/idt.c | 4 ---- 1 file changed, 4 deletions(-)
arch/x86/kernel/idt.c +0 -4
@@ -45,10 +45,6 @@ struct idt_data {#define ISTG (_vector, _addr, _ist) \ G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) -/* System interrupt gate with interrupt stack */ -#define SISTG (_vector, _addr, _ist) \ - G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS) -/* Task gate */ #define TSKG (_vector, _gdt) \ G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3)
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/idt: Remove unused macro SISTG
x86/idt: Remove unused macro SISTG
Commit-ID: 99d334511b337884cadbdfae28da912a4edb1001 Gitweb: https://git.kernel.org/tip/99d334511b337884cadbdfae28da912a4edb1001 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:42 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:36:19 +0200
x86/idt: Remove unused macro SISTG
Commit
d8ba61ba58c8 ("x86/entry/64: Don't use IST entry for #BP stack")
removed the last user but left the macro around.
--- arch/x86/kernel/idt.c | 4 ---- 1 file changed, 4 deletions(-)
arch/x86/kernel/idt.c +0 -4
@@ -45,10 +45,6 @@ struct idt_data {#define ISTG (_vector, _addr, _ist) \ G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) -/* System interrupt gate with interrupt stack */ -#define SISTG (_vector, _addr, _ist) \ - G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS) -/* Task gate */ #define TSKG (_vector, _gdt) \ G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3)
PATCH v3 7/32 x86/64: Remove stale CURRENT_MASK
In reply to Thomas GleixnerNothing uses that and before people get the wrong ideas, get rid of it.
--- arch/x86/include/asm/page_64_types.h | 1 - 1 file changed, 1 deletion(-)
arch/x86/include/asm/page_64_types.h +0 -1
@@ -14,7 +14,6 @@#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER)#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define CURRENT_MASK (~(THREAD_SIZE - 1))#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/64: Remove stale CURRENT_MASK
x86/64: Remove stale CURRENT_MASK
Commit-ID: 6f36bd8d2e8c221eaaf4ce5b0ebbb11c00b0ac98 Gitweb: https://git.kernel.org/tip/6f36bd8d2e8c221eaaf4ce5b0ebbb11c00b0ac98 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:43 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:38:36 +0200
x86/64: Remove stale CURRENT_MASK
Nothing uses that and before people get the wrong ideas, get rid of it.
--- arch/x86/include/asm/page_64_types.h | 1 - 1 file changed, 1 deletion(-)
arch/x86/include/asm/page_64_types.h +0 -1
@@ -14,7 +14,6 @@#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER)#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define CURRENT_MASK (~(THREAD_SIZE - 1))#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
PATCH v3 8/32 x86/exceptions: Remove unused stack defines on 32bit
In reply to Thomas GleixnerNothing requires those for 32bit builds.
--- arch/x86/include/asm/page_32_types.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
arch/x86/include/asm/page_32_types.h +1 -5
@@ -22,11 +22,7 @@#define THREAD_SIZE_ORDER 1#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define DOUBLEFAULT_STACK 1 -#define NMI_STACK 0 -#define DEBUG_STACK 0 -#define MCE_STACK 0 -#define N_EXCEPTION_STACKS 1 +#define N_EXCEPTION_STACKS 1#ifdef CONFIG_X86_PAE /*
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Remove unused stack defines on 32bit
x86/exceptions: Remove unused stack defines on 32bit
Commit-ID: 30842211506e376b76394a9cb4e6d0c9d258b8d4 Gitweb: https://git.kernel.org/tip/30842211506e376b76394a9cb4e6d0c9d258b8d4 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:44 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:45:29 +0200
x86/exceptions: Remove unused stack defines on 32bit
Nothing requires those for 32bit builds.
--- arch/x86/include/asm/page_32_types.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
arch/x86/include/asm/page_32_types.h +1 -5
@@ -22,11 +22,7 @@#define THREAD_SIZE_ORDER 1#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define DOUBLEFAULT_STACK 1 -#define NMI_STACK 0 -#define DEBUG_STACK 0 -#define MCE_STACK 0 -#define N_EXCEPTION_STACKS 1 +#define N_EXCEPTION_STACKS 1#ifdef CONFIG_X86_PAE /*
PATCH v3 9/32 x86/exceptions: Make IST index zero based
In reply to Thomas GleixnerThe defines for the exception stack (IST) array in the TSS are using the SDM convention IST1 - IST7. That causes all sorts of code to subtract 1 for array indices related to IST. That's confusing at best and does not provide any value.
Make the indices zero based and fixup the usage sites. The only code which needs to adjust the 0 based index is the interrupt descriptor setup which needs to add 1 now.
--- Documentation/x86/kernel-stacks | 8 ++++---- arch/x86/entry/entry_64.S | 4 ++-- arch/x86/include/asm/page_64_types.h | 13 ++++++++----- arch/x86/kernel/cpu/common.c | 4 ++-- arch/x86/kernel/dumpstack_64.c | 14 +++++++------- arch/x86/kernel/idt.c | 15 +++++++++------ arch/x86/kernel/irq_64.c | 2 +- arch/x86/mm/fault.c | 2 +- 8 files changed, 34 insertions(+), 28 deletions(-)
Documentation/x86/kernel-stacks +4 -4
@@ -59,7 +59,7 @@ If that assumption is ever broken then t The currently assigned IST stacks are :- -* DOUBLEFAULT_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_DF. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 8 - Double Fault Exception (#DF).
@@ -68,7 +68,7 @@ The currently assigned IST stacks are :- Using a separate stack allows the kernel to recover from it well enough in many cases to still output an oops. -* NMI_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_NMI. EXCEPTION_STKSZ (PAGE_SIZE). Used for non-maskable interrupts (NMI).
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :- middle of switching stacks. Using IST for NMI events avoids making assumptions about the previous state of the kernel stack. -* DEBUG_STACK. DEBUG_STKSZ +* ESTACK_DB. DEBUG_STKSZ Used for hardware debug interrupts (interrupt 1) and for software debug interrupts (INT3).
@@ -86,7 +86,7 @@ The currently assigned IST stacks are :- avoids making assumptions about the previous state of the kernel stack. -* MCE_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_MCE. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 18 - Machine Check Exception (#MC).
arch/x86/entry/entry_64.S +2 -2
@@ -841,7 +841,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8) /** * idtentry - Generate an IDT entry stub
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=ESTACK_DB idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/page_64_types.h +8 -5
@@ -24,11 +24,14 @@#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define DOUBLEFAULT_STACK 1 -#define NMI_STACK 2 -#define DEBUG_STACK 3 -#define MCE_STACK 4 -#define N_EXCEPTION_STACKS 4/* hw limit: 7 */ +/* +* The index for the tss.ist[] array. The hardware limit is 7 entries. +*/ +#define ESTACK_DF 0 +#define ESTACK_NMI 1 +#define ESTACK_DB 2 +#define ESTACK_MCE 3 +#define N_EXCEPTION_STACKS 4/* * Set __PAGE_OFFSET to the most negative possible address +
arch/x86/kernel/cpu/common.c +2 -2
@@ -516,7 +516,7 @@ DEFINE_PER_CPU(struct cpu_entry_area *,*/ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS ] = { [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [DEBUG_STACK -1 ] =DEBUG_STKSZ + [ESTACK_DB ] =DEBUG_STKSZ };#endif
@@ -1760,7 +1760,7 @@ void cpu_init(void) estacks += exception_stack_sizes[v]; oist->ist[v] = t->x86_tss.ist[v] = (unsigned long )estacks; -if (v ==DEBUG_STACK -1 ) +if (v ==ESTACK_DB )per_cpu (debug_stack_addr, cpu) = (unsigned long )estacks; } }
arch/x86/kernel/dumpstack_64.c +7 -7
@@ -18,16 +18,16 @@#include <asm/stacktrace.h> -static char *exception_stack_names[N_EXCEPTION_STACKS ] = { - [DOUBLEFAULT_STACK -1 ] ="#DF" , - [NMI_STACK -1 ] ="NMI" , - [DEBUG_STACK -1 ] ="#DB" , - [MCE_STACK -1 ] ="#MC" , +static const char *exception_stack_names[N_EXCEPTION_STACKS ] = { + [ESTACK_DF ] ="#DF" , + [ESTACK_NMI ] ="NMI" , + [ESTACK_DB ] ="#DB" , + [ESTACK_MCE ] ="#MC" , }; -static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { +static const unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [DEBUG_STACK -1 ] =DEBUG_STKSZ + [ESTACK_DB ] =DEBUG_STKSZ };const char *stack_type_name (enum stack_type type)
arch/x86/kernel/idt.c +9 -6
@@ -41,9 +41,12 @@ struct idt_data {#define SYSG (_vector, _addr) \ G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS) -/* Interrupt gate with interrupt stack */ +/* +* Interrupt gate with interrupt stack. The _ist index is the index in +* the tss.ist[] array, but for the descriptor it needs to start at 1. +*/ #define ISTG (_vector, _addr, _ist) \ - G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) + G(_vector, _addr, _ist + 1, GATE_INTERRUPT, DPL0, __KERNEL_CS)/* Task gate */ #define TSKG (_vector, _gdt) \
@@ -180,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] _* cpu_init() when the TSS has been initialized. */ static const __initconst struct idt_data ist_idts[] = { -ISTG (X86_TRAP_DB , debug,DEBUG_STACK ), -ISTG (X86_TRAP_NMI , nmi,NMI_STACK ), -ISTG (X86_TRAP_DF , double_fault,DOUBLEFAULT_STACK ), +ISTG (X86_TRAP_DB , debug,ESTACK_DB ), +ISTG (X86_TRAP_NMI , nmi,ESTACK_NMI ), +ISTG (X86_TRAP_DF , double_fault,ESTACK_DF ), #ifdef CONFIG_X86_MCE -ISTG (X86_TRAP_MC , &machine_check,MCE_STACK ), +ISTG (X86_TRAP_MC , &machine_check,ESTACK_MCE ), #endif };
arch/x86/kernel/irq_64.c +1 -1
@@ -61,7 +61,7 @@ static inline void stack_overflow_check(return ; oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[DEBUG_STACK ]; + estack_top = (u64 )oist->ist[ESTACK_DB ]; estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ;if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ;
arch/x86/mm/fault.c +1 -1
@@ -793,7 +793,7 @@ no_context(struct pt_regs *regs, unsigneif (is_vmalloc_addr ((void *)address) && (((unsigned long )tsk->stack -1 - address <PAGE_SIZE ) || address - ((unsigned long )tsk->stack +THREAD_SIZE ) <PAGE_SIZE )) { -unsigned long stack =this_cpu_read (orig_ist.ist[DOUBLEFAULT_STACK ]) -sizeof (void *); +unsigned long stack =this_cpu_read (orig_ist.ist[ESTACK_DF ]) -sizeof (void *);/* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Make IST index zero based
x86/exceptions: Make IST index zero based
Commit-ID: 8f34c5b5afce91d171bb0802631197484cb69b8b Gitweb: https://git.kernel.org/tip/8f34c5b5afce91d171bb0802631197484cb69b8b Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:45 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:48:00 +0200
x86/exceptions: Make IST index zero based
The defines for the exception stack (IST) array in the TSS are using the SDM convention IST1 - IST7. That causes all sorts of code to subtract 1 for array indices related to IST. That's confusing at best and does not provide any value.
Make the indices zero based and fixup the usage sites. The only code which needs to adjust the 0 based index is the interrupt descriptor setup which needs to add 1 now.
--- Documentation/x86/kernel-stacks | 8 ++++---- arch/x86/entry/entry_64.S | 4 ++-- arch/x86/include/asm/page_64_types.h | 13 ++++++++----- arch/x86/kernel/cpu/common.c | 4 ++-- arch/x86/kernel/dumpstack_64.c | 14 +++++++------- arch/x86/kernel/idt.c | 15 +++++++++------ arch/x86/kernel/irq_64.c | 2 +- arch/x86/mm/fault.c | 2 +- 8 files changed, 34 insertions(+), 28 deletions(-)
Documentation/x86/kernel-stacks +4 -4
@@ -59,7 +59,7 @@ If that assumption is ever broken then the stacks will become corrupt. The currently assigned IST stacks are :- -* DOUBLEFAULT_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_DF. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 8 - Double Fault Exception (#DF).
@@ -68,7 +68,7 @@ The currently assigned IST stacks are :- Using a separate stack allows the kernel to recover from it well enough in many cases to still output an oops. -* NMI_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_NMI. EXCEPTION_STKSZ (PAGE_SIZE). Used for non-maskable interrupts (NMI).
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :- middle of switching stacks. Using IST for NMI events avoids making assumptions about the previous state of the kernel stack. -* DEBUG_STACK. DEBUG_STKSZ +* ESTACK_DB. DEBUG_STKSZ Used for hardware debug interrupts (interrupt 1) and for software debug interrupts (INT3).
@@ -86,7 +86,7 @@ The currently assigned IST stacks are :- avoids making assumptions about the previous state of the kernel stack. -* MCE_STACK. EXCEPTION_STKSZ (PAGE_SIZE). +* ESTACK_MCE. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 18 - Machine Check Exception (#MC).
arch/x86/entry/entry_64.S +2 -2
@@ -841,7 +841,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8) /** * idtentry - Generate an IDT entry stub
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=ESTACK_DB idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/page_64_types.h +8 -5
@@ -24,11 +24,14 @@#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define DOUBLEFAULT_STACK 1 -#define NMI_STACK 2 -#define DEBUG_STACK 3 -#define MCE_STACK 4 -#define N_EXCEPTION_STACKS 4/* hw limit: 7 */ +/* +* The index for the tss.ist[] array. The hardware limit is 7 entries. +*/ +#define ESTACK_DF 0 +#define ESTACK_NMI 1 +#define ESTACK_DB 2 +#define ESTACK_MCE 3 +#define N_EXCEPTION_STACKS 4/* * Set __PAGE_OFFSET to the most negative possible address +
arch/x86/kernel/cpu/common.c +2 -2
@@ -516,7 +516,7 @@ DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);*/ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS ] = { [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [DEBUG_STACK -1 ] =DEBUG_STKSZ + [ESTACK_DB ] =DEBUG_STKSZ };#endif
@@ -1760,7 +1760,7 @@ void cpu_init(void) estacks += exception_stack_sizes[v]; oist->ist[v] = t->x86_tss.ist[v] = (unsigned long )estacks; -if (v ==DEBUG_STACK -1 ) +if (v ==ESTACK_DB )per_cpu (debug_stack_addr, cpu) = (unsigned long )estacks; } }
arch/x86/kernel/dumpstack_64.c +7 -7
@@ -18,16 +18,16 @@#include <asm/stacktrace.h> -static char *exception_stack_names[N_EXCEPTION_STACKS ] = { - [DOUBLEFAULT_STACK -1 ] ="#DF" , - [NMI_STACK -1 ] ="NMI" , - [DEBUG_STACK -1 ] ="#DB" , - [MCE_STACK -1 ] ="#MC" , +static const char *exception_stack_names[N_EXCEPTION_STACKS ] = { + [ESTACK_DF ] ="#DF" , + [ESTACK_NMI ] ="NMI" , + [ESTACK_DB ] ="#DB" , + [ESTACK_MCE ] ="#MC" , }; -static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { +static const unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [DEBUG_STACK -1 ] =DEBUG_STKSZ + [ESTACK_DB ] =DEBUG_STKSZ };const char *stack_type_name (enum stack_type type)
arch/x86/kernel/idt.c +9 -6
@@ -41,9 +41,12 @@ struct idt_data {#define SYSG (_vector, _addr) \ G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS) -/* Interrupt gate with interrupt stack */ +/* +* Interrupt gate with interrupt stack. The _ist index is the index in +* the tss.ist[] array, but for the descriptor it needs to start at 1. +*/ #define ISTG (_vector, _addr, _ist) \ - G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) + G(_vector, _addr, _ist + 1, GATE_INTERRUPT, DPL0, __KERNEL_CS)/* Task gate */ #define TSKG (_vector, _gdt) \
@@ -180,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;* cpu_init() when the TSS has been initialized. */ static const __initconst struct idt_data ist_idts[] = { -ISTG (X86_TRAP_DB , debug,DEBUG_STACK ), -ISTG (X86_TRAP_NMI , nmi,NMI_STACK ), -ISTG (X86_TRAP_DF , double_fault,DOUBLEFAULT_STACK ), +ISTG (X86_TRAP_DB , debug,ESTACK_DB ), +ISTG (X86_TRAP_NMI , nmi,ESTACK_NMI ), +ISTG (X86_TRAP_DF , double_fault,ESTACK_DF ), #ifdef CONFIG_X86_MCE -ISTG (X86_TRAP_MC , &machine_check,MCE_STACK ), +ISTG (X86_TRAP_MC , &machine_check,ESTACK_MCE ), #endif };
arch/x86/kernel/irq_64.c +1 -1
@@ -61,7 +61,7 @@ static inline void stack_overflow_check(struct pt_regs *regs)return ; oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[DEBUG_STACK ]; + estack_top = (u64 )oist->ist[ESTACK_DB ]; estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ;if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ;
arch/x86/mm/fault.c +1 -1
@@ -793,7 +793,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,if (is_vmalloc_addr ((void *)address) && (((unsigned long )tsk->stack -1 - address <PAGE_SIZE ) || address - ((unsigned long )tsk->stack +THREAD_SIZE ) <PAGE_SIZE )) { -unsigned long stack =this_cpu_read (orig_ist.ist[DOUBLEFAULT_STACK ]) -sizeof (void *); +unsigned long stack =this_cpu_read (orig_ist.ist[ESTACK_DF ]) -sizeof (void *);/* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but
PATCH v3 10/32 x86/cpu_entry_area: Cleanup setup functions
In reply to Thomas GleixnerNo point in retrieving the entry area pointer over and over. Do it once and use unsigned int for 'cpu' everywhere.
--- arch/x86/mm/cpu_entry_area.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)
arch/x86/mm/cpu_entry_area.c +9 -10
@@ -52,10 +52,10 @@ cea_map_percpu_pages(void *cea_vaddr, vocea_set_pte (cea_vaddr,per_cpu_ptr_to_phys (ptr), prot); } -static void __init percpu_setup_debug_store (int cpu) +static void __init percpu_setup_debug_store (unsigned int cpu) {#ifdef CONFIG_CPU_SUP_INTEL -int npages; +unsigned int npages;void *cea;if (boot_cpu_data.x86_vendor !=X86_VENDOR_INTEL )
@@ -79,8 +79,9 @@ static void __init percpu_setup_debug_st }/* Setup the fixmap mappings only once per-processor */ -static void __init setup_cpu_entry_area (int cpu) +static void __init setup_cpu_entry_area (unsigned int cpu) { +struct cpu_entry_area *cea =get_cpu_entry_area (cpu);#ifdef CONFIG_X86_64 /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ pgprot_t gdt_prot =PAGE_KERNEL_RO ;
@@ -101,10 +102,9 @@ static void __init setup_cpu_entry_area(pgprot_t tss_prot =PAGE_KERNEL ;#endif -cea_set_pte (&get_cpu_entry_area (cpu)->gdt,get_cpu_gdt_paddr (cpu), - gdt_prot); +cea_set_pte (&cea->gdt,get_cpu_gdt_paddr (cpu), gdt_prot); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->entry_stack_page, +cea_map_percpu_pages (&cea->entry_stack_page,per_cpu_ptr (&entry_stack_storage, cpu),1 ,PAGE_KERNEL );
@@ -128,19 +128,18 @@ static void __init setup_cpu_entry_area(BUILD_BUG_ON ((offsetof(struct tss_struct , x86_tss) ^ offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);BUILD_BUG_ON (sizeof (struct tss_struct ) %PAGE_SIZE !=0 ); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->tss, - &per_cpu (cpu_tss_rw, cpu), +cea_map_percpu_pages (&cea->tss, &per_cpu (cpu_tss_rw, cpu),sizeof (struct tss_struct ) /PAGE_SIZE , tss_prot);#ifdef CONFIG_X86_32 -per_cpu (cpu_entry_area, cpu) =get_cpu_entry_area (cpu); +per_cpu (cpu_entry_area, cpu) = cea;#endif #ifdef CONFIG_X86_64 BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 );BUILD_BUG_ON (sizeof (exception_stacks) !=sizeof (((struct cpu_entry_area *)0 )->exception_stacks)); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->exception_stacks, +cea_map_percpu_pages (&cea->exception_stacks, &per_cpu (exception_stacks, cpu),sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL );#endif
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/cpu_entry_area: Cleanup setup functions
x86/cpu_entry_area: Cleanup setup functions
Commit-ID: 881a463cf21dbf83aab2cf6c9a359f34f88c2491 Gitweb: https://git.kernel.org/tip/881a463cf21dbf83aab2cf6c9a359f34f88c2491 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:46 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:50:46 +0200
x86/cpu_entry_area: Cleanup setup functions
No point in retrieving the entry area pointer over and over. Do it once and use unsigned int for 'cpu' everywhere.
--- arch/x86/mm/cpu_entry_area.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)
arch/x86/mm/cpu_entry_area.c +9 -10
@@ -52,10 +52,10 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)cea_set_pte (cea_vaddr,per_cpu_ptr_to_phys (ptr), prot); } -static void __init percpu_setup_debug_store (int cpu) +static void __init percpu_setup_debug_store (unsigned int cpu) {#ifdef CONFIG_CPU_SUP_INTEL -int npages; +unsigned int npages;void *cea;if (boot_cpu_data.x86_vendor !=X86_VENDOR_INTEL )
@@ -79,8 +79,9 @@ static void __init percpu_setup_debug_store(int cpu) }/* Setup the fixmap mappings only once per-processor */ -static void __init setup_cpu_entry_area (int cpu) +static void __init setup_cpu_entry_area (unsigned int cpu) { +struct cpu_entry_area *cea =get_cpu_entry_area (cpu);#ifdef CONFIG_X86_64 /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ pgprot_t gdt_prot =PAGE_KERNEL_RO ;
@@ -101,10 +102,9 @@ static void __init setup_cpu_entry_area(int cpu)pgprot_t tss_prot =PAGE_KERNEL ;#endif -cea_set_pte (&get_cpu_entry_area (cpu)->gdt,get_cpu_gdt_paddr (cpu), - gdt_prot); +cea_set_pte (&cea->gdt,get_cpu_gdt_paddr (cpu), gdt_prot); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->entry_stack_page, +cea_map_percpu_pages (&cea->entry_stack_page,per_cpu_ptr (&entry_stack_storage, cpu),1 ,PAGE_KERNEL );
@@ -128,19 +128,18 @@ static void __init setup_cpu_entry_area(int cpu)BUILD_BUG_ON ((offsetof(struct tss_struct , x86_tss) ^ offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);BUILD_BUG_ON (sizeof (struct tss_struct ) %PAGE_SIZE !=0 ); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->tss, - &per_cpu (cpu_tss_rw, cpu), +cea_map_percpu_pages (&cea->tss, &per_cpu (cpu_tss_rw, cpu),sizeof (struct tss_struct ) /PAGE_SIZE , tss_prot);#ifdef CONFIG_X86_32 -per_cpu (cpu_entry_area, cpu) =get_cpu_entry_area (cpu); +per_cpu (cpu_entry_area, cpu) = cea;#endif #ifdef CONFIG_X86_64 BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 );BUILD_BUG_ON (sizeof (exception_stacks) !=sizeof (((struct cpu_entry_area *)0 )->exception_stacks)); -cea_map_percpu_pages (&get_cpu_entry_area (cpu)->exception_stacks, +cea_map_percpu_pages (&cea->exception_stacks, &per_cpu (exception_stacks, cpu),sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL );#endif
PATCH v3 11/32 x86/exceptions: Add structs for exception stacks
In reply to Thomas GleixnerAt the moment everything assumes a full linear mapping of the various exception stacks. Adding guard pages to the cpu entry area mapping of the exception stacks will break that assumption.
As a preparatory step convert both the real storage and the effective mapping in the cpu entry area from character arrays to structures.
To ensure that both arrays have the same ordering and the same size of the individual stacks fill the members with a macro. The guard size is the only difference between the two resulting structures. For now both have guard size 0 until the preparation of all usage sites is done.
Provide a couple of helper macros which are used in the following conversions.
---
V2 -> V3: Move the guards below the stacks and add a top guard. Fix the
TOP() macro.
--- arch/x86/include/asm/cpu_entry_area.h | 52 ++++++++++++++++++++++++++++++---- arch/x86/kernel/cpu/common.c | 2 - arch/x86/mm/cpu_entry_area.c | 8 +---- 3 files changed, 51 insertions(+), 11 deletions(-)
arch/x86/include/asm/cpu_entry_area.h +47 -5
@@ -7,6 +7,51 @@#include <asm/processor.h> #include <asm/intel_ds.h> +#ifdef CONFIG_X86_64 + +/* Macro to enforce the same ordering and stack sizes */ +#define ESTACKS_MEMBERS (guardsize) \ + char DF_stack_guard[guardsize]; \ + char DF_stack[EXCEPTION_STKSZ]; \ + char NMI_stack_guard[guardsize]; \ + char NMI_stack[EXCEPTION_STKSZ]; \ + char DB_stack_guard[guardsize]; \ + char DB_stack[DEBUG_STKSZ]; \ + char MCE_stack_guard[guardsize]; \ + char MCE_stack[EXCEPTION_STKSZ]; \ + char IST_top_guard[guardsize]; \ + +/* The exception stacks linear storage. No guard pages required */ +struct exception_stacks { + ESTACKS_MEMBERS(0) +}; + +/* +* The effective cpu entry area mapping with guard pages. Guard size is +* zero until the code which makes assumptions about linear mappings is +* cleaned up. +*/ +struct cea_exception_stacks { + ESTACKS_MEMBERS(0) +}; + +#define CEA_ESTACK_SIZE (st) \ + sizeof(((struct cea_exception_stacks *)0)->st## _stack) + +#define CEA_ESTACK_BOT (ceastp, st) \ + ((unsigned long)&(ceastp)->st## _stack) + +#define CEA_ESTACK_TOP (ceastp, st) \ + (CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st)) + +#define CEA_ESTACK_OFFS (st) \ + offsetof(struct cea_exception_stacks, st## _stack) + +#define CEA_ESTACK_PAGES \ + (sizeof(struct cea_exception_stacks) / PAGE_SIZE) + +#endif +/* * cpu_entry_area is a percpu region that contains things needed by the CPU * and early entry/exit code. Real types aren't used for all fields here
@@ -32,12 +77,9 @@ struct cpu_entry_area {#ifdef CONFIG_X86_64 /* -* Exception stacks used for IST entries. -* -* In the future, this should have a separate slot for each stack -* with guard pages between them. +* Exception stacks used for IST entries with guard pages. */ -char exception_stacks[(N_EXCEPTION_STACKS -1 ) *EXCEPTION_STKSZ +DEBUG_STKSZ ]; +struct cea_exception_stacks estacks;#endif #ifdef CONFIG_CPU_SUP_INTEL /*
arch/x86/kernel/cpu/common.c +1 -1
@@ -1754,7 +1754,7 @@ void cpu_init(void)* set up and load the per-CPU TSS */ if (!oist->ist[0 ]) { -char *estacks =get_cpu_entry_area (cpu)->exception_stacks; +char *estacks = (char *)&get_cpu_entry_area (cpu)->estacks;for (v =0 ; v <N_EXCEPTION_STACKS ; v++) { estacks += exception_stack_sizes[v];
arch/x86/mm/cpu_entry_area.c +3 -5
@@ -13,8 +13,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);#ifdef CONFIG_X86_64 -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);#endif struct cpu_entry_area *get_cpu_entry_area (int cpu)
@@ -138,9 +137,8 @@ static void __init setup_cpu_entry_area(#ifdef CONFIG_X86_64 BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 );BUILD_BUG_ON (sizeof (exception_stacks) != -sizeof (((struct cpu_entry_area *)0 )->exception_stacks)); -cea_map_percpu_pages (&cea->exception_stacks, - &per_cpu (exception_stacks, cpu), +sizeof (((struct cpu_entry_area *)0 )->estacks)); +cea_map_percpu_pages (&cea->estacks, &per_cpu (exception_stacks, cpu),sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL );#endif percpu_setup_debug_store (cpu);
Re: [patch V3 11/32] x86/exceptions: Add structs for exception stacks
Quoted 12 lines · Thomas Gleixner
At the moment everything assumes a full linear mapping of the various exception stacks. Adding guard pages to the cpu entry area mapping of the exception stacks will break that assumption.
As a preparatory step convert both the real storage and the effective mapping in the cpu entry area from character arrays to structures.
To ensure that both arrays have the same ordering and the same size of the individual stacks fill the members with a macro. The guard size is the only difference between the two resulting structures. For now both have guard size 0 until the preparation of all usage sites is done.
Quoted 5 lines
Provide a couple of helper macros which are used in the following conversions.
Signed-off-by Thomas Gleixner <[email protected]>---
One comment nit below, but other than that:
Quoted 19 lines
V2 -> V3: Move the guards below the stacks and add a top guard. Fix the
TOP()macro.--- arch/x86/include/asm/cpu_entry_area.h | 52 ++++++++++++++++++++++++++++++---- arch/x86/kernel/cpu/common.c | 2 - arch/x86/mm/cpu_entry_area.c | 8 +---- 3 files changed, 51 insertions(+), 11 deletions(-)arch/x86/include/asm/cpu_entry_area.h +5
-0@@ -7,6 +7,51 @@#include <asm/processor.h> #include <asm/intel_ds.h> +#ifdef CONFIG_X86_64 + +/* Macro to enforce the same ordering and stack sizes */ +#define ESTACKS_MEMBERS (guardsize) \ + char DF_stack_guard[guardsize]; \
arch/x86/include/asm/cpu_entry_area.h line 24
Quoted 10 lines
arch/x86/include/asm/cpu_entry_area.h +10
-0+char DF_stack[EXCEPTION_STKSZ ]; \ +char NMI_stack_guard[guardsize]; \ +char NMI_stack[EXCEPTION_STKSZ ]; \ +char DB_stack_guard[guardsize]; \ +char DB_stack[DEBUG_STKSZ ]; \ +char MCE_stack_guard[guardsize]; \ +char MCE_stack[EXCEPTION_STKSZ ]; \ +char IST_top_guard[guardsize]; \ + +/* The exception stacks linear storage. No guard pages required */
How about s/linear/physical? "linear" is confusing for us Intel wonks (or maybe just me) because in Intel's parlance it means virtual addresses for all intents and purposes. And an apostrophe to show possession would help readability, e.g.:
/* The exception stacks' physical storage. No guard pages required */
Quoted 4 lines
arch/x86/include/asm/cpu_entry_area.h +3
-0+struct exception_stacks { + ESTACKS_MEMBERS(0) +};
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Add structs for exception stacks
In reply to Thomas Gleixnerx86/exceptions: Add structs for exception stacks
Commit-ID: 019b17b3ffe48100e52f609ca1c6ed6e5a40cba1 Gitweb: https://git.kernel.org/tip/019b17b3ffe48100e52f609ca1c6ed6e5a40cba1 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:47 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:55:18 +0200
x86/exceptions: Add structs for exception stacks
At the moment everything assumes a full linear mapping of the various exception stacks. Adding guard pages to the cpu entry area mapping of the exception stacks will break that assumption.
As a preparatory step convert both the real storage and the effective mapping in the cpu entry area from character arrays to structures.
To ensure that both arrays have the same ordering and the same size of the individual stacks fill the members with a macro. The guard size is the only difference between the two resulting structures. For now both have guard size 0 until the preparation of all usage sites is done.
Provide a couple of helper macros which are used in the following conversions.
--- arch/x86/include/asm/cpu_entry_area.h | 52 +++++++++++++++++++++++++++++++---- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/mm/cpu_entry_area.c | 8 ++---- 3 files changed, 51 insertions(+), 11 deletions(-)
arch/x86/include/asm/cpu_entry_area.h +47 -5
@@ -7,6 +7,51 @@#include <asm/processor.h> #include <asm/intel_ds.h> +#ifdef CONFIG_X86_64 + +/* Macro to enforce the same ordering and stack sizes */ +#define ESTACKS_MEMBERS (guardsize) \ + char DF_stack_guard[guardsize]; \ + char DF_stack[EXCEPTION_STKSZ]; \ + char NMI_stack_guard[guardsize]; \ + char NMI_stack[EXCEPTION_STKSZ]; \ + char DB_stack_guard[guardsize]; \ + char DB_stack[DEBUG_STKSZ]; \ + char MCE_stack_guard[guardsize]; \ + char MCE_stack[EXCEPTION_STKSZ]; \ + char IST_top_guard[guardsize]; \ + +/* The exception stacks' physical storage. No guard pages required */ +struct exception_stacks { + ESTACKS_MEMBERS(0) +}; + +/* +* The effective cpu entry area mapping with guard pages. Guard size is +* zero until the code which makes assumptions about linear mappings is +* cleaned up. +*/ +struct cea_exception_stacks { + ESTACKS_MEMBERS(0) +}; + +#define CEA_ESTACK_SIZE (st) \ + sizeof(((struct cea_exception_stacks *)0)->st## _stack) + +#define CEA_ESTACK_BOT (ceastp, st) \ + ((unsigned long)&(ceastp)->st## _stack) + +#define CEA_ESTACK_TOP (ceastp, st) \ + (CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st)) + +#define CEA_ESTACK_OFFS (st) \ + offsetof(struct cea_exception_stacks, st## _stack) + +#define CEA_ESTACK_PAGES \ + (sizeof(struct cea_exception_stacks) / PAGE_SIZE) + +#endif +/* * cpu_entry_area is a percpu region that contains things needed by the CPU * and early entry/exit code. Real types aren't used for all fields here
@@ -32,12 +77,9 @@ struct cpu_entry_area {#ifdef CONFIG_X86_64 /* -* Exception stacks used for IST entries. -* -* In the future, this should have a separate slot for each stack -* with guard pages between them. +* Exception stacks used for IST entries with guard pages. */ -char exception_stacks[(N_EXCEPTION_STACKS -1 ) *EXCEPTION_STKSZ +DEBUG_STKSZ ]; +struct cea_exception_stacks estacks;#endif #ifdef CONFIG_CPU_SUP_INTEL /*
arch/x86/kernel/cpu/common.c +1 -1
@@ -1754,7 +1754,7 @@ void cpu_init(void)* set up and load the per-CPU TSS */ if (!oist->ist[0 ]) { -char *estacks =get_cpu_entry_area (cpu)->exception_stacks; +char *estacks = (char *)&get_cpu_entry_area (cpu)->estacks;for (v =0 ; v <N_EXCEPTION_STACKS ; v++) { estacks += exception_stack_sizes[v];
arch/x86/mm/cpu_entry_area.c +3 -5
@@ -13,8 +13,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);#ifdef CONFIG_X86_64 -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);#endif struct cpu_entry_area *get_cpu_entry_area (int cpu)
@@ -138,9 +137,8 @@ static void __init setup_cpu_entry_area(unsigned int cpu)#ifdef CONFIG_X86_64 BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 );BUILD_BUG_ON (sizeof (exception_stacks) != -sizeof (((struct cpu_entry_area *)0 )->exception_stacks)); -cea_map_percpu_pages (&cea->exception_stacks, - &per_cpu (exception_stacks, cpu), +sizeof (((struct cpu_entry_area *)0 )->estacks)); +cea_map_percpu_pages (&cea->estacks, &per_cpu (exception_stacks, cpu),sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL );#endif percpu_setup_debug_store (cpu);
PATCH v3 12/32 x86/cpu_entry_area: Prepare for IST guard pages
In reply to Thomas GleixnerTo allow guard pages between the IST stacks each stack needs to be mapped individually.
--- arch/x86/mm/cpu_entry_area.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-)
arch/x86/mm/cpu_entry_area.c +30 -7
@@ -77,6 +77,34 @@ static void __init percpu_setup_debug_st#endif } +#ifdef CONFIG_X86_64 + +#define cea_map_stack (name) do { \ + npages = sizeof(estacks->name## _stack) / PAGE_SIZE; \ + cea_map_percpu_pages(cea->estacks.name## _stack, \ + estacks->name## _stack, npages, PAGE_KERNEL); \ + } while (0) + +static void __init percpu_setup_exception_stacks (unsigned int cpu) +{ +struct exception_stacks *estacks =per_cpu_ptr (&exception_stacks, cpu); +struct cpu_entry_area *cea =get_cpu_entry_area (cpu); +unsigned int npages; + +BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); +/* +* The exceptions stack mappings in the per cpu area are protected +* by guard pages so each stack must be mapped separately. +*/ +cea_map_stack (DF ); +cea_map_stack (NMI ); +cea_map_stack (DB ); +cea_map_stack (MCE ); +} +#else +static inline void percpu_setup_exception_stacks (unsigned int cpu) {} +#endif +/* Setup the fixmap mappings only once per-processor */ static void __init setup_cpu_entry_area (unsigned int cpu) {
@@ -134,13 +162,8 @@ static void __init setup_cpu_entry_area(per_cpu (cpu_entry_area, cpu) = cea;#endif -#ifdef CONFIG_X86_64 -BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); -BUILD_BUG_ON (sizeof (exception_stacks) != -sizeof (((struct cpu_entry_area *)0 )->estacks)); -cea_map_percpu_pages (&cea->estacks, &per_cpu (exception_stacks, cpu), -sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL ); -#endif +percpu_setup_exception_stacks (cpu); +percpu_setup_debug_store (cpu); }
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/cpu_entry_area: Prepare for IST guard pages
x86/cpu_entry_area: Prepare for IST guard pages
Commit-ID: a4af767ae59cc579569bbfe49513a0037d5989ee Gitweb: https://git.kernel.org/tip/a4af767ae59cc579569bbfe49513a0037d5989ee Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:48 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 12:58:21 +0200
x86/cpu_entry_area: Prepare for IST guard pages
To allow guard pages between the IST stacks each stack needs to be mapped individually.
--- arch/x86/mm/cpu_entry_area.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-)
arch/x86/mm/cpu_entry_area.c +30 -7
@@ -77,6 +77,34 @@ static void __init percpu_setup_debug_store(unsigned int cpu)#endif } +#ifdef CONFIG_X86_64 + +#define cea_map_stack (name) do { \ + npages = sizeof(estacks->name## _stack) / PAGE_SIZE; \ + cea_map_percpu_pages(cea->estacks.name## _stack, \ + estacks->name## _stack, npages, PAGE_KERNEL); \ + } while (0) + +static void __init percpu_setup_exception_stacks (unsigned int cpu) +{ +struct exception_stacks *estacks =per_cpu_ptr (&exception_stacks, cpu); +struct cpu_entry_area *cea =get_cpu_entry_area (cpu); +unsigned int npages; + +BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); +/* +* The exceptions stack mappings in the per cpu area are protected +* by guard pages so each stack must be mapped separately. +*/ +cea_map_stack (DF ); +cea_map_stack (NMI ); +cea_map_stack (DB ); +cea_map_stack (MCE ); +} +#else +static inline void percpu_setup_exception_stacks (unsigned int cpu) {} +#endif +/* Setup the fixmap mappings only once per-processor */ static void __init setup_cpu_entry_area (unsigned int cpu) {
@@ -134,13 +162,8 @@ static void __init setup_cpu_entry_area(unsigned int cpu)per_cpu (cpu_entry_area, cpu) = cea;#endif -#ifdef CONFIG_X86_64 -BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); -BUILD_BUG_ON (sizeof (exception_stacks) != -sizeof (((struct cpu_entry_area *)0 )->estacks)); -cea_map_percpu_pages (&cea->estacks, &per_cpu (exception_stacks, cpu), -sizeof (exception_stacks) /PAGE_SIZE ,PAGE_KERNEL ); -#endif +percpu_setup_exception_stacks (cpu); +percpu_setup_debug_store (cpu); }
PATCH v3 13/32 x86/cpu_entry_area: Provide exception stack accessor
In reply to Thomas GleixnerStore a pointer to the per cpu entry area exception stack mappings to allow fast retrieval.
Required for converting various places from using the shadow IST array to directly doing address calculations on the actual mapping address.
--- arch/x86/include/asm/cpu_entry_area.h | 4 ++++ arch/x86/mm/cpu_entry_area.c | 4 ++++ 2 files changed, 8 insertions(+)
arch/x86/include/asm/cpu_entry_area.h +4 -0
@@ -98,6 +98,7 @@ struct cpu_entry_area {#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);extern void setup_cpu_entry_areas (void );extern void cea_set_pte (void *cea_vaddr,phys_addr_t pa,pgprot_t flags);
@@ -117,4 +118,7 @@ static inline struct entry_stack *cpu_en return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } +#define __this_cpu_ist_top_va (name) \ + CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name) +#endif
arch/x86/mm/cpu_entry_area.c +4 -0
@@ -14,6 +14,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struc#ifdef CONFIG_X86_64 static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks); +DEFINE_PER_CPU (struct cea_exception_stacks *, cea_exception_stacks);#endif struct cpu_entry_area *get_cpu_entry_area (int cpu)
@@ -92,6 +93,9 @@ static void __init percpu_setup_exceptiounsigned int npages;BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); + +per_cpu (cea_exception_stacks, cpu) = &cea->estacks; +/* * The exceptions stack mappings in the per cpu area are protected * by guard pages so each stack must be mapped separately.
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/cpu_entry_area: Provide exception stack accessor
x86/cpu_entry_area: Provide exception stack accessor
Commit-ID: 7623f37e411156e6e09b95cf5c76e509c5fda640 Gitweb: https://git.kernel.org/tip/7623f37e411156e6e09b95cf5c76e509c5fda640 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:49 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 13:00:22 +0200
x86/cpu_entry_area: Provide exception stack accessor
Store a pointer to the per cpu entry area exception stack mappings to allow fast retrieval.
Required for converting various places from using the shadow IST array to directly doing address calculations on the actual mapping address.
--- arch/x86/include/asm/cpu_entry_area.h | 4 ++++ arch/x86/mm/cpu_entry_area.c | 4 ++++ 2 files changed, 8 insertions(+)
arch/x86/include/asm/cpu_entry_area.h +4 -0
@@ -99,6 +99,7 @@ struct cpu_entry_area {#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);extern void setup_cpu_entry_areas (void );extern void cea_set_pte (void *cea_vaddr,phys_addr_t pa,pgprot_t flags);
@@ -118,4 +119,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu) return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } +#define __this_cpu_ist_top_va (name) \ + CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name) +#endif
arch/x86/mm/cpu_entry_area.c +4 -0
@@ -14,6 +14,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage)#ifdef CONFIG_X86_64 static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks); +DEFINE_PER_CPU (struct cea_exception_stacks *, cea_exception_stacks);#endif struct cpu_entry_area *get_cpu_entry_area (int cpu)
@@ -92,6 +93,9 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)unsigned int npages;BUILD_BUG_ON (sizeof (exception_stacks) %PAGE_SIZE !=0 ); + +per_cpu (cea_exception_stacks, cpu) = &cea->estacks; +/* * The exceptions stack mappings in the per cpu area are protected * by guard pages so each stack must be mapped separately.
PATCH v3 14/32 x86/traps: Use cpu_entry_area instead of orig_ist
In reply to Thomas GleixnerThe orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/mm/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/mm/fault.c +2 -1
@@ -28,6 +28,7 @@#include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ +#include <asm/cpu_entry_area.h> /* exception stack */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h>
@@ -793,7 +794,7 @@ no_context(struct pt_regs *regs, unsigneif (is_vmalloc_addr ((void *)address) && (((unsigned long )tsk->stack -1 - address <PAGE_SIZE ) || address - ((unsigned long )tsk->stack +THREAD_SIZE ) <PAGE_SIZE )) { -unsigned long stack =this_cpu_read (orig_ist.ist[ESTACK_DF ]) -sizeof (void *); +unsigned long stack =__this_cpu_ist_top_va (DF ) -sizeof (void *);/* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/traps: Use cpu_entry_area instead of orig_ist
x86/traps: Use cpu_entry_area instead of orig_ist
Commit-ID: d876b67343a648f3613506c7dbfed088fa0c875b Gitweb: https://git.kernel.org/tip/d876b67343a648f3613506c7dbfed088fa0c875b Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:50 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 13:01:59 +0200
x86/traps: Use cpu_entry_area instead of orig_ist
The orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/mm/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/mm/fault.c +2 -1
@@ -28,6 +28,7 @@#include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ +#include <asm/cpu_entry_area.h> /* exception stack */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h>
@@ -793,7 +794,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,if (is_vmalloc_addr ((void *)address) && (((unsigned long )tsk->stack -1 - address <PAGE_SIZE ) || address - ((unsigned long )tsk->stack +THREAD_SIZE ) <PAGE_SIZE )) { -unsigned long stack =this_cpu_read (orig_ist.ist[ESTACK_DF ]) -sizeof (void *); +unsigned long stack =__this_cpu_ist_top_va (DF ) -sizeof (void *);/* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but
PATCH v3 15/32 x86/irq/64: Use cpu entry area instead of orig_ist
In reply to Thomas GleixnerThe orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/kernel/irq_64.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
arch/x86/kernel/irq_64.c +7 -6
@@ -18,6 +18,8 @@#include <linux/uaccess.h> #include <linux/smp.h> #include <linux/sched/task_stack.h> + +#include <asm/cpu_entry_area.h> #include <asm/io_apic.h> #include <asm/apic.h>
@@ -43,10 +45,9 @@ static inline void stack_overflow_check( {#ifdef CONFIG_DEBUG_STACKOVERFLOW #define STACK_MARGIN 128 -struct orig_ist *oist; -u64 irq_stack_top, irq_stack_bottom; -u64 estack_top, estack_bottom; +u64 irq_stack_top, irq_stack_bottom, estack_top, estack_bottom;u64 curbase = (u64 )task_stack_page (current); +struct cea_exception_stacks *estacks;if (user_mode (regs))return ;
@@ -60,9 +61,9 @@ static inline void stack_overflow_check(if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ; - oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[ESTACK_DB ]; - estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ; + estacks =__this_cpu_read (cea_exception_stacks); + estack_top =CEA_ESTACK_TOP (estacks,DB ); + estack_bottom =CEA_ESTACK_BOT (estacks,DB ) +STACK_MARGIN ;if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ;
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Use cpu entry area instead of orig_ist
x86/irq/64: Use cpu entry area instead of orig_ist
Commit-ID: bf5882abab773afd1277415e2f826b21de28f30d Gitweb: https://git.kernel.org/tip/bf5882abab773afd1277415e2f826b21de28f30d Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:51 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 13:02:48 +0200
x86/irq/64: Use cpu entry area instead of orig_ist
The orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/kernel/irq_64.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
arch/x86/kernel/irq_64.c +7 -6
@@ -18,6 +18,8 @@#include <linux/uaccess.h> #include <linux/smp.h> #include <linux/sched/task_stack.h> + +#include <asm/cpu_entry_area.h> #include <asm/io_apic.h> #include <asm/apic.h>
@@ -43,10 +45,9 @@ static inline void stack_overflow_check(struct pt_regs *regs) {#ifdef CONFIG_DEBUG_STACKOVERFLOW #define STACK_MARGIN 128 -struct orig_ist *oist; -u64 irq_stack_top, irq_stack_bottom; -u64 estack_top, estack_bottom; +u64 irq_stack_top, irq_stack_bottom, estack_top, estack_bottom;u64 curbase = (u64 )task_stack_page (current); +struct cea_exception_stacks *estacks;if (user_mode (regs))return ;
@@ -60,9 +61,9 @@ static inline void stack_overflow_check(struct pt_regs *regs)if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ; - oist =this_cpu_ptr (&orig_ist); - estack_top = (u64 )oist->ist[ESTACK_DB ]; - estack_bottom = estack_top -DEBUG_STKSZ +STACK_MARGIN ; + estacks =__this_cpu_read (cea_exception_stacks); + estack_top =CEA_ESTACK_TOP (estacks,DB ); + estack_bottom =CEA_ESTACK_BOT (estacks,DB ) +STACK_MARGIN ;if (regs->sp >= estack_bottom && regs->sp <= estack_top)return ;
PATCH v3 16/32 x86/dumpstack/64: Use cpu_entry_area instead of orig_ist
In reply to Thomas GleixnerThe orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/kernel/dumpstack_64.c | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-)
arch/x86/kernel/dumpstack_64.c +27 -12
@@ -16,6 +16,7 @@#include <linux/bug.h> #include <linux/nmi.h> +#include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> static const char *exception_stack_names[N_EXCEPTION_STACKS ] = {
@@ -25,11 +26,6 @@ static const char *exception_stack_names [ ESTACK_MCE ] = "#MC", }; -static const unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { - [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [ESTACK_DB ] =DEBUG_STKSZ -}; -const char *stack_type_name (enum stack_type type) {BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 );
@@ -52,25 +48,44 @@ const char *stack_type_name(enum stack_treturn NULL ; } +struct estack_layout { +unsigned int begin; +unsigned int end; +}; + +#define ESTACK_ENTRY (x) { \ + .begin = offsetof(struct cea_exception_stacks, x## _stack), \ + .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ + } + +static const struct estack_layout layout[N_EXCEPTION_STACKS ] = { + [ESTACK_DF ] =ESTACK_ENTRY (DF ), + [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), + [ESTACK_DB ] =ESTACK_ENTRY (DB ), + [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), +}; +static bool in_exception_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin, *end; +unsigned long estacks, begin, end, stk = (unsigned long )stack;struct pt_regs *regs; -unsigned k; +unsigned int k;BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); + estacks = (unsigned long )__this_cpu_read (cea_exception_stacks); +for (k =0 ; k <N_EXCEPTION_STACKS ; k++) { - end = (unsigned long *)raw_cpu_ptr (&orig_ist)->ist[k]; - begin = end - (exception_stack_sizes[k] /sizeof (long )); + begin = estacks + layout[k].begin; + end = estacks + layout[k].end; regs = (struct pt_regs *)end -1 ; -if (stack < begin || stack >= end) +if (stk < begin || stk >= end)continue ; info->type =STACK_TYPE_EXCEPTION + k; - info->begin = begin; - info->end = end; + info->begin = (unsigned long *)begin; + info->end = (unsigned long *)end; info->next_sp = (unsigned long *)regs->sp;return true;
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/dumpstack/64: Use cpu_entry_area instead of orig_ist
x86/dumpstack/64: Use cpu_entry_area instead of orig_ist
Commit-ID: afcd21dad88b68d646e91ed36948117d58b4c197 Gitweb: https://git.kernel.org/tip/afcd21dad88b68d646e91ed36948117d58b4c197 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:52 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 13:05:06 +0200
x86/dumpstack/64: Use cpu_entry_area instead of orig_ist
The orig_ist[] array is a shadow copy of the IST array in the TSS. The reason why it exists is that older kernels used two TSS variants with different pointers into the debug stack. orig_ist[] contains the real starting points.
There is no point anymore to do so because the same information can be retrieved using the base address of the cpu entry area mapping and the offsets of the various exception stacks.
No functional change. Preparation for removing orig_ist.
--- arch/x86/kernel/dumpstack_64.c | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-)
arch/x86/kernel/dumpstack_64.c +27 -12
@@ -16,6 +16,7 @@#include <linux/bug.h> #include <linux/nmi.h> +#include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> static const char *exception_stack_names[N_EXCEPTION_STACKS ] = {
@@ -25,11 +26,6 @@ static const char *exception_stack_names[N_EXCEPTION_STACKS] = { [ ESTACK_MCE ] = "#MC", }; -static const unsigned long exception_stack_sizes[N_EXCEPTION_STACKS ] = { - [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [ESTACK_DB ] =DEBUG_STKSZ -}; -const char *stack_type_name (enum stack_type type) {BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 );
@@ -52,25 +48,44 @@ const char *stack_type_name(enum stack_type type)return NULL ; } +struct estack_layout { +unsigned int begin; +unsigned int end; +}; + +#define ESTACK_ENTRY (x) { \ + .begin = offsetof(struct cea_exception_stacks, x## _stack), \ + .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ + } + +static const struct estack_layout layout[N_EXCEPTION_STACKS ] = { + [ESTACK_DF ] =ESTACK_ENTRY (DF ), + [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), + [ESTACK_DB ] =ESTACK_ENTRY (DB ), + [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), +}; +static bool in_exception_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin, *end; +unsigned long estacks, begin, end, stk = (unsigned long )stack;struct pt_regs *regs; -unsigned k; +unsigned int k;BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); + estacks = (unsigned long )__this_cpu_read (cea_exception_stacks); +for (k =0 ; k <N_EXCEPTION_STACKS ; k++) { - end = (unsigned long *)raw_cpu_ptr (&orig_ist)->ist[k]; - begin = end - (exception_stack_sizes[k] /sizeof (long )); + begin = estacks + layout[k].begin; + end = estacks + layout[k].end; regs = (struct pt_regs *)end -1 ; -if (stack < begin || stack >= end) +if (stk < begin || stk >= end)continue ; info->type =STACK_TYPE_EXCEPTION + k; - info->begin = begin; - info->end = end; + info->begin = (unsigned long *)begin; + info->end = (unsigned long *)end; info->next_sp = (unsigned long *)regs->sp;return true;
PATCH v3 17/32 x86/cpu: Prepare TSS.IST setup for guard pages
In reply to Thomas GleixnerConvert the TSS.IST setup code to use the cpu entry area information directly instead of assuming a linear mapping of the IST stacks.
The store to orig_ist[] is no longer required as there are no users anymore.
This is the last preparatory step for IST guard pages.
--- arch/x86/kernel/cpu/common.c | 35 +++++++---------------------------- 1 file changed, 7 insertions(+), 28 deletions(-)
arch/x86/kernel/cpu/common.c +7 -28
@@ -507,19 +507,6 @@ void load_percpu_segment(int cpu) DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);#endif -#ifdef CONFIG_X86_64 -/* -* Special IST stacks which the CPU switches to when it calls -* an IST-marked descriptor entry. Up to 7 stacks (hardware -* limit), all of them are 4K, except the debug stack which -* is 8K. -*/ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS ] = { - [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [ESTACK_DB ] =DEBUG_STKSZ -}; -#endif -/* Load the original GDT from the per-cpu structure */ void load_direct_gdt (int cpu) {
@@ -1690,17 +1677,14 @@ static void setup_getcpu(int cpu)* initialized (naturally) in the bootstrap process, such as the GDT * and IDT. We reload them nevertheless, this function acts as a * 'CPU state barrier', nothing should get across. -* A lot of state is already set up in PDA init for 64 bit */ #ifdef CONFIG_X86_64 void cpu_init (void ) { -struct orig_ist *oist; +int cpu =raw_smp_processor_id ();struct task_struct *me;struct tss_struct *t; -unsigned long v; -int cpu =raw_smp_processor_id ();int i;wait_for_master_cpu (cpu);
@@ -1715,7 +1699,6 @@ void cpu_init(void)load_ucode_ap (); t = &per_cpu (cpu_tss_rw, cpu); - oist = &per_cpu (orig_ist, cpu);#ifdef CONFIG_NUMA if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1736,12 @@ void cpu_init(void)/* * set up and load the per-CPU TSS */ -if (!oist->ist[0 ]) { -char *estacks = (char *)&get_cpu_entry_area (cpu)->estacks; - -for (v =0 ; v <N_EXCEPTION_STACKS ; v++) { - estacks += exception_stack_sizes[v]; - oist->ist[v] = t->x86_tss.ist[v] = - (unsigned long )estacks; -if (v ==ESTACK_DB ) -per_cpu (debug_stack_addr, cpu) = (unsigned long )estacks; - } +if (!t->x86_tss.ist[0 ]) { + t->x86_tss.ist[ESTACK_DF ] =__this_cpu_ist_top_va (DF ); + t->x86_tss.ist[ESTACK_NMI ] =__this_cpu_ist_top_va (NMI ); + t->x86_tss.ist[ESTACK_DB ] =__this_cpu_ist_top_va (DB ); + t->x86_tss.ist[ESTACK_MCE ] =__this_cpu_ist_top_va (MCE ); +per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[ESTACK_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/cpu: Prepare TSS.IST setup for guard pages
x86/cpu: Prepare TSS.IST setup for guard pages
Commit-ID: f6ef73224a0f0400c3979c8bc68b383f9d2eb9d8 Gitweb: https://git.kernel.org/tip/f6ef73224a0f0400c3979c8bc68b383f9d2eb9d8 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:53 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 14:29:22 +0200
x86/cpu: Prepare TSS.IST setup for guard pages
Convert the TSS.IST setup code to use the cpu entry area information directly instead of assuming a linear mapping of the IST stacks.
The store to orig_ist[] is no longer required as there are no users anymore.
This is the last preparatory step towards IST guard pages.
--- arch/x86/kernel/cpu/common.c | 35 +++++++---------------------------- 1 file changed, 7 insertions(+), 28 deletions(-)
arch/x86/kernel/cpu/common.c +7 -28
@@ -507,19 +507,6 @@ void load_percpu_segment(int cpu) DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);#endif -#ifdef CONFIG_X86_64 -/* -* Special IST stacks which the CPU switches to when it calls -* an IST-marked descriptor entry. Up to 7 stacks (hardware -* limit), all of them are 4K, except the debug stack which -* is 8K. -*/ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS ] = { - [0 ...N_EXCEPTION_STACKS -1 ] =EXCEPTION_STKSZ , - [ESTACK_DB ] =DEBUG_STKSZ -}; -#endif -/* Load the original GDT from the per-cpu structure */ void load_direct_gdt (int cpu) {
@@ -1690,17 +1677,14 @@ static void setup_getcpu(int cpu)* initialized (naturally) in the bootstrap process, such as the GDT * and IDT. We reload them nevertheless, this function acts as a * 'CPU state barrier', nothing should get across. -* A lot of state is already set up in PDA init for 64 bit */ #ifdef CONFIG_X86_64 void cpu_init (void ) { -struct orig_ist *oist; +int cpu =raw_smp_processor_id ();struct task_struct *me;struct tss_struct *t; -unsigned long v; -int cpu =raw_smp_processor_id ();int i;wait_for_master_cpu (cpu);
@@ -1715,7 +1699,6 @@ void cpu_init(void)load_ucode_ap (); t = &per_cpu (cpu_tss_rw, cpu); - oist = &per_cpu (orig_ist, cpu);#ifdef CONFIG_NUMA if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1736,12 @@ void cpu_init(void)/* * set up and load the per-CPU TSS */ -if (!oist->ist[0 ]) { -char *estacks = (char *)&get_cpu_entry_area (cpu)->estacks; - -for (v =0 ; v <N_EXCEPTION_STACKS ; v++) { - estacks += exception_stack_sizes[v]; - oist->ist[v] = t->x86_tss.ist[v] = - (unsigned long )estacks; -if (v ==ESTACK_DB ) -per_cpu (debug_stack_addr, cpu) = (unsigned long )estacks; - } +if (!t->x86_tss.ist[0 ]) { + t->x86_tss.ist[ESTACK_DF ] =__this_cpu_ist_top_va (DF ); + t->x86_tss.ist[ESTACK_NMI ] =__this_cpu_ist_top_va (NMI ); + t->x86_tss.ist[ESTACK_DB ] =__this_cpu_ist_top_va (DB ); + t->x86_tss.ist[ESTACK_MCE ] =__this_cpu_ist_top_va (MCE ); +per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[ESTACK_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
PATCH v3 18/32 x86/cpu: Remove orig_ist array
In reply to Thomas GleixnerAll users gone.
--- arch/x86/include/asm/processor.h | 9 --------- arch/x86/kernel/cpu/common.c | 6 ------ 2 files changed, 15 deletions(-)
arch/x86/include/asm/processor.h +0 -9
@@ -374,16 +374,7 @@ DECLARE_PER_CPU(unsigned long, cpu_curre#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1#endif -/* -* Save the original ist values for checking stack pointers during debugging -*/ -struct orig_ist { -unsigned long ist[7 ]; -}; - #ifdef CONFIG_X86_64 -DECLARE_PER_CPU(struct orig_ist, orig_ist); - union irq_stack_union { char irq_stack[IRQ_STACK_SIZE]; /*
arch/x86/kernel/cpu/common.c +0 -6
@@ -1549,12 +1549,6 @@ void syscall_init(void) X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } -/* -* Copies of the original ist values from the tss are only accessed during -* debugging, no special alignment required. -*/ -DEFINE_PER_CPU(struct orig_ist, orig_ist); - static DEFINE_PER_CPU(unsigned long, debug_stack_addr);DEFINE_PER_CPU (int , debug_stack_usage);
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/cpu: Remove orig_ist array
x86/cpu: Remove orig_ist array
Commit-ID: 4d68c3d0ecd5fcba8876e8a58ac41ffb360de43e Gitweb: https://git.kernel.org/tip/4d68c3d0ecd5fcba8876e8a58ac41ffb360de43e Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:54 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 14:44:17 +0200
x86/cpu: Remove orig_ist array
All users gone.
--- arch/x86/include/asm/processor.h | 9 --------- arch/x86/kernel/cpu/common.c | 6 ------ 2 files changed, 15 deletions(-)
arch/x86/include/asm/processor.h +0 -9
@@ -374,16 +374,7 @@ DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1#endif -/* -* Save the original ist values for checking stack pointers during debugging -*/ -struct orig_ist { -unsigned long ist[7 ]; -}; - #ifdef CONFIG_X86_64 -DECLARE_PER_CPU(struct orig_ist, orig_ist); - union irq_stack_union { char irq_stack[IRQ_STACK_SIZE]; /*
arch/x86/kernel/cpu/common.c +0 -6
@@ -1549,12 +1549,6 @@ void syscall_init(void) X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } -/* -* Copies of the original ist values from the tss are only accessed during -* debugging, no special alignment required. -*/ -DEFINE_PER_CPU(struct orig_ist, orig_ist); - static DEFINE_PER_CPU(unsigned long, debug_stack_addr);DEFINE_PER_CPU (int , debug_stack_usage);
PATCH v3 19/32 x86/exceptions: Disconnect IST index and stack order
In reply to Thomas GleixnerThe entry order of the TSS.IST array and the order of the stack storage/mapping are not required to be the same.
With the upcoming split of the debug stack this is going to fall apart as the number of TSS.IST array entries stays the same while the actual stacks are increasing.
Make them separate so that code like dumpstack can just utilize the mapping order. The IST index is solely required for the actual TSS.IST array initialization.
---
V2 -> V3: s/ISTACK_/ESTACK/
--- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/cpu_entry_area.h | 11 +++++++++++ arch/x86/include/asm/page_64_types.h | 9 ++++----- arch/x86/include/asm/stacktrace.h | 2 ++ arch/x86/kernel/cpu/common.c | 10 +++++----- arch/x86/kernel/idt.c | 8 ++++---- 6 files changed, 27 insertions(+), 15 deletions(-)
arch/x86/entry/entry_64.S +1 -1
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=ESTACK_DB +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/cpu_entry_area.h +11 -0
@@ -35,6 +35,17 @@ struct cea_exception_stacks { ESTACKS_MEMBERS(0) }; +/* +* The exception stack ordering in [cea_]exception_stacks +*/ +enum exception_stack_ordering { +ESTACK_DF , +ESTACK_NMI , +ESTACK_DB , +ESTACK_MCE , +N_EXCEPTION_STACKS +}; +#define CEA_ESTACK_SIZE (st) \ sizeof(((struct cea_exception_stacks *)0)->st## _stack)
arch/x86/include/asm/page_64_types.h +4 -5
@@ -27,11 +27,10 @@/* * The index for the tss.ist[] array. The hardware limit is 7 entries. */ -#define ESTACK_DF 0 -#define ESTACK_NMI 1 -#define ESTACK_DB 2 -#define ESTACK_MCE 3 -#define N_EXCEPTION_STACKS 4 +#define IST_INDEX_DF 0 +#define IST_INDEX_NMI 1 +#define IST_INDEX_DB 2 +#define IST_INDEX_MCE 3/* * Set __PAGE_OFFSET to the most negative possible address +
arch/x86/include/asm/stacktrace.h +2 -0
@@ -9,6 +9,8 @@#include <linux/uaccess.h> #include <linux/ptrace.h> + +#include <asm/cpu_entry_area.h> #include <asm/switch_to.h> enum stack_type {
arch/x86/kernel/cpu/common.c +5 -5
@@ -1731,11 +1731,11 @@ void cpu_init(void)* set up and load the per-CPU TSS */ if (!t->x86_tss.ist[0 ]) { - t->x86_tss.ist[ESTACK_DF ] =__this_cpu_ist_top_va (DF ); - t->x86_tss.ist[ESTACK_NMI ] =__this_cpu_ist_top_va (NMI ); - t->x86_tss.ist[ESTACK_DB ] =__this_cpu_ist_top_va (DB ); - t->x86_tss.ist[ESTACK_MCE ] =__this_cpu_ist_top_va (MCE ); -per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[ESTACK_DB ]; + t->x86_tss.ist[IST_INDEX_DF ] =__this_cpu_ist_top_va (DF ); + t->x86_tss.ist[IST_INDEX_NMI ] =__this_cpu_ist_top_va (NMI ); + t->x86_tss.ist[IST_INDEX_DB ] =__this_cpu_ist_top_va (DB ); + t->x86_tss.ist[IST_INDEX_MCE ] =__this_cpu_ist_top_va (MCE ); +per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[IST_INDEX_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
arch/x86/kernel/idt.c +4 -4
@@ -183,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] _* cpu_init() when the TSS has been initialized. */ static const __initconst struct idt_data ist_idts[] = { -ISTG (X86_TRAP_DB , debug,ESTACK_DB ), -ISTG (X86_TRAP_NMI , nmi,ESTACK_NMI ), -ISTG (X86_TRAP_DF , double_fault,ESTACK_DF ), +ISTG (X86_TRAP_DB , debug,IST_INDEX_DB ), +ISTG (X86_TRAP_NMI , nmi,IST_INDEX_NMI ), +ISTG (X86_TRAP_DF , double_fault,IST_INDEX_DF ), #ifdef CONFIG_X86_MCE -ISTG (X86_TRAP_MC , &machine_check,ESTACK_MCE ), +ISTG (X86_TRAP_MC , &machine_check,IST_INDEX_MCE ), #endif };
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Disconnect IST index and stack order
x86/exceptions: Disconnect IST index and stack order
Commit-ID: 3207426925d2b4da390be8068df1d1c2b36e5918 Gitweb: https://git.kernel.org/tip/3207426925d2b4da390be8068df1d1c2b36e5918 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:55 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:01:09 +0200
x86/exceptions: Disconnect IST index and stack order
The entry order of the TSS.IST array and the order of the stack storage/mapping are not required to be the same.
With the upcoming split of the debug stack this is going to fall apart as the number of TSS.IST array entries stays the same while the actual stacks are increasing.
Make them separate so that code like dumpstack can just utilize the mapping order. The IST index is solely required for the actual TSS.IST array initialization.
--- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/cpu_entry_area.h | 11 +++++++++++ arch/x86/include/asm/page_64_types.h | 9 ++++----- arch/x86/include/asm/stacktrace.h | 2 ++ arch/x86/kernel/cpu/common.c | 10 +++++----- arch/x86/kernel/idt.c | 8 ++++---- 6 files changed, 27 insertions(+), 15 deletions(-)
arch/x86/entry/entry_64.S +1 -1
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=ESTACK_DB +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/cpu_entry_area.h +11 -0
@@ -35,6 +35,17 @@ struct cea_exception_stacks { ESTACKS_MEMBERS(0) }; +/* +* The exception stack ordering in [cea_]exception_stacks +*/ +enum exception_stack_ordering { +ESTACK_DF , +ESTACK_NMI , +ESTACK_DB , +ESTACK_MCE , +N_EXCEPTION_STACKS +}; +#define CEA_ESTACK_SIZE (st) \ sizeof(((struct cea_exception_stacks *)0)->st## _stack)
arch/x86/include/asm/page_64_types.h +4 -5
@@ -27,11 +27,10 @@/* * The index for the tss.ist[] array. The hardware limit is 7 entries. */ -#define ESTACK_DF 0 -#define ESTACK_NMI 1 -#define ESTACK_DB 2 -#define ESTACK_MCE 3 -#define N_EXCEPTION_STACKS 4 +#define IST_INDEX_DF 0 +#define IST_INDEX_NMI 1 +#define IST_INDEX_DB 2 +#define IST_INDEX_MCE 3/* * Set __PAGE_OFFSET to the most negative possible address +
arch/x86/include/asm/stacktrace.h +2 -0
@@ -9,6 +9,8 @@#include <linux/uaccess.h> #include <linux/ptrace.h> + +#include <asm/cpu_entry_area.h> #include <asm/switch_to.h> enum stack_type {
arch/x86/kernel/cpu/common.c +5 -5
@@ -1731,11 +1731,11 @@ void cpu_init(void)* set up and load the per-CPU TSS */ if (!t->x86_tss.ist[0 ]) { - t->x86_tss.ist[ESTACK_DF ] =__this_cpu_ist_top_va (DF ); - t->x86_tss.ist[ESTACK_NMI ] =__this_cpu_ist_top_va (NMI ); - t->x86_tss.ist[ESTACK_DB ] =__this_cpu_ist_top_va (DB ); - t->x86_tss.ist[ESTACK_MCE ] =__this_cpu_ist_top_va (MCE ); -per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[ESTACK_DB ]; + t->x86_tss.ist[IST_INDEX_DF ] =__this_cpu_ist_top_va (DF ); + t->x86_tss.ist[IST_INDEX_NMI ] =__this_cpu_ist_top_va (NMI ); + t->x86_tss.ist[IST_INDEX_DB ] =__this_cpu_ist_top_va (DB ); + t->x86_tss.ist[IST_INDEX_MCE ] =__this_cpu_ist_top_va (MCE ); +per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[IST_INDEX_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
arch/x86/kernel/idt.c +4 -4
@@ -183,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;* cpu_init() when the TSS has been initialized. */ static const __initconst struct idt_data ist_idts[] = { -ISTG (X86_TRAP_DB , debug,ESTACK_DB ), -ISTG (X86_TRAP_NMI , nmi,ESTACK_NMI ), -ISTG (X86_TRAP_DF , double_fault,ESTACK_DF ), +ISTG (X86_TRAP_DB , debug,IST_INDEX_DB ), +ISTG (X86_TRAP_NMI , nmi,IST_INDEX_NMI ), +ISTG (X86_TRAP_DF , double_fault,IST_INDEX_DF ), #ifdef CONFIG_X86_MCE -ISTG (X86_TRAP_MC , &machine_check,ESTACK_MCE ), +ISTG (X86_TRAP_MC , &machine_check,IST_INDEX_MCE ), #endif };
PATCH v3 20/32 x86/exceptions: Enable IST guard pages
In reply to Thomas GleixnerAll usage sites which expected that the exception stacks in the CPU entry area are mapped linearly are fixed up. Enable guard pages between the IST stacks.
--- arch/x86/include/asm/cpu_entry_area.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)
arch/x86/include/asm/cpu_entry_area.h +2 -6
@@ -26,13 +26,9 @@ struct exception_stacks {ESTACKS_MEMBERS (0 ) }; -/* -* The effective cpu entry area mapping with guard pages. Guard size is -* zero until the code which makes assumptions about linear mappings is -* cleaned up. -*/ +/* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(0) + ESTACKS_MEMBERS(PAGE_SIZE) };/*
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Enable IST guard pages
x86/exceptions: Enable IST guard pages
Commit-ID: 1bdb67e5aa2d5d43c48cb7d93393fcba276c9e71 Gitweb: https://git.kernel.org/tip/1bdb67e5aa2d5d43c48cb7d93393fcba276c9e71 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:56 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:05:32 +0200
x86/exceptions: Enable IST guard pages
All usage sites which expected that the exception stacks in the CPU entry area are mapped linearly are fixed up. Enable guard pages between the IST stacks.
--- arch/x86/include/asm/cpu_entry_area.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)
arch/x86/include/asm/cpu_entry_area.h +2 -6
@@ -26,13 +26,9 @@ struct exception_stacks {ESTACKS_MEMBERS (0 ) }; -/* -* The effective cpu entry area mapping with guard pages. Guard size is -* zero until the code which makes assumptions about linear mappings is -* cleaned up. -*/ +/* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(0) + ESTACKS_MEMBERS(PAGE_SIZE) };/*
PATCH v3 21/32 x86/exceptions: Split debug IST stack
In reply to Thomas GleixnerThe debug IST stack is actually two separate debug stacks to handle #DB recursion. This is required because the CPU starts always at top of stack on exception entry, which means on #DB recursion the second #DB would overwrite the stack of the first.
The low level entry code therefore adjusts the top of stack on entry so a secondary #DB starts from a different stack page. But the stack pages are adjacent without a guard page between them.
Split the debug stack into 3 stacks which are separated by guard pages. The 3rd stack is never mapped into the cpu_entry_area and is only there to catch triple #DB nesting:
--- top of DB_stack <- Initial stack
--- end of DB_stack
guard page
--- top of DB1_stack <- Top of stack after entering first #DB
--- end of DB1_stack
guard page
--- top of DB2_stack <- Top of stack after entering second #DB
--- end of DB2_stack
guard page
If DB2 would not act as the final guard hole, a second #DB would point the top of #DB stack to the stack below #DB1 which would be valid and not catch the not so desired triple nesting.
The backing store does not allocate any memory for DB2 and its guard page as it is not going to be mapped into the cpu_entry_area.
- Adjust the low level entry code so it adjusts top of #DB with the offset between the stacks instead of exception stack size.
- Make the dumpstack code aware of the new stacks.
- Adjust the in_debug_stack() implementation and move it into the NMI code where it belongs. As this is NMI hotpath code, it just checks the full area between top of DB_stack and bottom of DB1_stack without checking for the guard page. That's correct because the NMI cannot hit a stackpointer pointing to the guard page between DB and DB1 stack. Even if it would, then the NMI operation still is unaffected, but the resume of the debug exception on the topmost DB stack will crash by touching the guard page.
---
V2 -> V3: Fix off by one in in_debug_stack()
--- Documentation/x86/kernel-stacks | 7 ++++++- arch/x86/entry/entry_64.S | 8 ++++---- arch/x86/include/asm/cpu_entry_area.h | 14 ++++++++++---- arch/x86/include/asm/debugreg.h | 2 -- arch/x86/include/asm/page_64_types.h | 3 --- arch/x86/kernel/asm-offsets_64.c | 2 ++ arch/x86/kernel/cpu/common.c | 11 ----------- arch/x86/kernel/dumpstack_64.c | 12 ++++++++---- arch/x86/kernel/nmi.c | 20 +++++++++++++++++++- arch/x86/mm/cpu_entry_area.c | 4 +++- 10 files changed, 52 insertions(+), 31 deletions(-)
Documentation/x86/kernel-stacks +6 -1
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :- middle of switching stacks. Using IST for NMI events avoids making assumptions about the previous state of the kernel stack. -* ESTACK_DB. DEBUG_STKSZ +* ESTACK_DB. EXCEPTION_STKSZ (PAGE_SIZE). Used for hardware debug interrupts (interrupt 1) and for software debug interrupts (INT3).
@@ -86,6 +86,11 @@ The currently assigned IST stacks are :- avoids making assumptions about the previous state of the kernel stack. + To handle nested #DB correctly there exist two instances of DB stacks. On + #DB entry the IST stackpointer for #DB is switched to the second instance + so a nested #DB starts from a clean stack. The nested #DB switches to + the IST stackpointer to a guard hole to catch triple nesting. + * ESTACK_MCE. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 18 - Machine Check Exception (#MC).
arch/x86/entry/entry_64.S +4 -4
@@ -879,7 +879,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work * @paranoid == 2 is special: the stub will never switch stacks. This is for * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS. */ -.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -925,13 +925,13 @@ ENTRY(\sym) .endif .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + subq $\ist_offset, CPU_TSS_IST(\shift_ist) .endif call \do_sym .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + addq $\ist_offset, CPU_TSS_IST(\shift_ist) .endif /* these procedures expect "no swapgs" flag in ebx */
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/cpu_entry_area.h +10 -4
@@ -10,25 +10,29 @@#ifdef CONFIG_X86_64 /* Macro to enforce the same ordering and stack sizes */ -#define ESTACKS_MEMBERS (guardsize) \ +#define ESTACKS_MEMBERS (guardsize, db2_holesize)\ char DF_stack_guard[guardsize]; \ char DF_stack[EXCEPTION_STKSZ]; \ char NMI_stack_guard[guardsize]; \ char NMI_stack[EXCEPTION_STKSZ]; \ + char DB2_stack_guard[guardsize]; \ + char DB2_stack[db2_holesize]; \ + char DB1_stack_guard[guardsize]; \ + char DB1_stack[EXCEPTION_STKSZ]; \ char DB_stack_guard[guardsize]; \ - char DB_stack[DEBUG_STKSZ]; \ + char DB_stack[EXCEPTION_STKSZ]; \ char MCE_stack_guard[guardsize]; \ char MCE_stack[EXCEPTION_STKSZ]; \ char IST_top_guard[guardsize]; \/* The exception stacks linear storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0) + ESTACKS_MEMBERS(0, 0) };/* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(PAGE_SIZE) + ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ) };/*
@@ -37,6 +41,8 @@ struct cea_exception_stacks {enum exception_stack_ordering {ESTACK_DF ,ESTACK_NMI , +ESTACK_DB2 , +ESTACK_DB1 ,ESTACK_DB ,ESTACK_MCE ,N_EXCEPTION_STACKS
arch/x86/include/asm/debugreg.h +0 -2
@@ -104,11 +104,9 @@ static inline void debug_stack_usage_dec {__this_cpu_dec (debug_stack_usage); } -int is_debug_stack (unsigned long addr);void debug_stack_set_zero (void );void debug_stack_reset (void );#else /* !X86_64 */ -static inline int is_debug_stack (unsigned long addr) {return 0 ; }static inline void debug_stack_set_zero (void ) { }static inline void debug_stack_reset (void ) { }static inline void debug_stack_usage_inc (void ) { }
arch/x86/include/asm/page_64_types.h +0 -3
@@ -18,9 +18,6 @@#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) -#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1) -#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER) -#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
arch/x86/kernel/asm-offsets_64.c +2 -0
@@ -68,6 +68,8 @@ int main(void)#undef ENTRYOFFSET (TSS_ist, tss_struct, x86_tss.ist); +DEFINE (DB_STACK_OFFSET , offsetof(struct cea_exception_stacks , DB_stack) - + offsetof(struct cea_exception_stacks , DB1_stack));BLANK ();#ifdef CONFIG_STACKPROTECTOR
arch/x86/kernel/cpu/common.c +0 -11
@@ -1549,17 +1549,7 @@ void syscall_init(void) X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } -static DEFINE_PER_CPU(unsigned long, debug_stack_addr);DEFINE_PER_CPU (int, debug_stack_usage); - -int is_debug_stack (unsigned long addr) -{ -return __this_cpu_read (debug_stack_usage) || - (addr <=__this_cpu_read (debug_stack_addr) && - addr > (__this_cpu_read (debug_stack_addr) -DEBUG_STKSZ )); -} -NOKPROBE_SYMBOL (is_debug_stack); -DEFINE_PER_CPU (u32, debug_idt_ctr);void debug_stack_set_zero (void )
@@ -1735,7 +1725,6 @@ void cpu_init(void) t->x86_tss.ist[IST_INDEX_NMI ] =__this_cpu_ist_top_va (NMI ); t->x86_tss.ist[IST_INDEX_DB ] =__this_cpu_ist_top_va (DB ); t->x86_tss.ist[IST_INDEX_MCE ] =__this_cpu_ist_top_va (MCE ); -per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[IST_INDEX_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
arch/x86/kernel/dumpstack_64.c +8 -4
@@ -19,16 +19,18 @@#include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> -static const char *exception_stack_names[N_EXCEPTION_STACKS ] = { +static const char *exception_stack_names[] = { [ESTACK_DF ] ="#DF" , [ESTACK_NMI ] ="NMI" , + [ESTACK_DB2 ] ="#DB2" , + [ESTACK_DB1 ] ="#DB1" , [ESTACK_DB ] ="#DB" , [ESTACK_MCE ] ="#MC" , };const char *stack_type_name (enum stack_type type) { -BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); +BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 );if (type ==STACK_TYPE_IRQ )return "IRQ" ;
@@ -58,9 +60,11 @@ struct estack_layout { .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ } -static const struct estack_layout layout[N_EXCEPTION_STACKS ] = { +static const struct estack_layout layout[] = { [ESTACK_DF ] =ESTACK_ENTRY (DF ), [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), + [ESTACK_DB2 ] = { .begin =0 , .end =0 }, + [ESTACK_DB1 ] =ESTACK_ENTRY (DB1 ), [ESTACK_DB ] =ESTACK_ENTRY (DB ), [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), };
@@ -71,7 +75,7 @@ static bool in_exception_stack(unsignedstruct pt_regs *regs;unsigned int k; -BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); +BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 ); estacks = (unsigned long )__this_cpu_read (cea_exception_stacks);
arch/x86/kernel/nmi.c +19 -1
@@ -21,13 +21,14 @@#include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/atomic.h> #include <linux/sched/clock.h> #if defined(CONFIG_EDAC )#include <linux/edac.h> #endif -#include <linux/atomic.h> +#include <asm/cpu_entry_area.h> #include <asm/traps.h> #include <asm/mach_traps.h> #include <asm/nmi.h>
@@ -487,6 +488,23 @@ static DEFINE_PER_CPU(unsigned long, nmi* switch back to the original IDT. */ static DEFINE_PER_CPU(int, update_debug_stack); + +static bool notrace is_debug_stack(unsigned long addr) +{ +struct cea_exception_stacks *cs =__this_cpu_read (cea_exception_stacks); +unsigned long top =CEA_ESTACK_TOP (cs,DB ); +unsigned long bot =CEA_ESTACK_BOT (cs,DB1 ); + +if (__this_cpu_read (debug_stack_usage)) +return true; +/* +* Note, this covers the guard page between DB and DB1 as well to +* avoid two checks. But by all means @addr can never point into +* the guard page. +*/ +return addr >= bot && addr < top; +} +NOKPROBE_SYMBOL (is_debug_stack);#endif dotraplinkage notrace void
arch/x86/mm/cpu_entry_area.c +3 -1
@@ -98,10 +98,12 @@ static void __init percpu_setup_exceptio/* * The exceptions stack mappings in the per cpu area are protected -* by guard pages so each stack must be mapped separately. +* by guard pages so each stack must be mapped separately. DB2 is +* not mapped; it just exists to catch triple nesting of #DB. */ cea_map_stack (DF );cea_map_stack (NMI ); +cea_map_stack (DB1 );cea_map_stack (DB );cea_map_stack (MCE ); }
Re: [patch V3 21/32] x86/exceptions: Split debug IST stack
Quoted 46 lines · Thomas Gleixner
The debug IST stack is actually two separate debug stacks to handle #DB recursion. This is required because the CPU starts always at top of stack on exception entry, which means on #DB recursion the second #DB would overwrite the stack of the first.
The low level entry code therefore adjusts the top of stack on entry so a secondary #DB starts from a different stack page. But the stack pages are adjacent without a guard page between them.
Split the debug stack into 3 stacks which are separated by guard pages. The 3rd stack is never mapped into the
cpu_entry_areaand is only there to catch triple #DB nesting:--- top of
DB_stack<- Initial stack
--- end ofDB_stack
guard page--- top of
DB1_stack<- Top of stack after entering first #DB
--- end ofDB1_stack
guard page--- top of
DB2_stack<- Top of stack after entering second #DB
--- end ofDB2_stack
guard pageIf DB2 would not act as the final guard hole, a second #DB would point the top of #DB stack to the stack below #DB1 which would be valid and not catch the not so desired triple nesting.
The backing store does not allocate any memory for DB2 and its guard page as it is not going to be mapped into the
cpu_entry_area.- Adjust the low level entry code so it adjusts top of #DB with the offset between the stacks instead of exception stack size.
- Make the dumpstack code aware of the new stacks.
- Adjust the
in_debug_stack()implementation and move it into the NMI code where it belongs. As this is NMI hotpath code, it just checks the full area between top ofDB_stackand bottom ofDB1_stackwithout checking for the guard page. That's correct because the NMI cannot hit a stackpointer pointing to the guard page between DB and DB1 stack. Even if it would, then the NMI operation still is unaffected, but the resume of the debug exception on the topmost DB stack will crash by touching the guard page.
Quoted 3 lines
Suggested-by Andy Lutomirski <[email protected]>Signed-off-by Thomas Gleixner <[email protected]>---
One nit below on the docs, otherwise:
Quoted 26 lines
V2 -> V3: Fix off by one in
in_debug_stack()--- Documentation/x86/kernel-stacks | 7 ++++++- arch/x86/entry/entry_64.S | 8 ++++---- arch/x86/include/asm/cpu_entry_area.h | 14 ++++++++++---- arch/x86/include/asm/debugreg.h | 2 -- arch/x86/include/asm/page_64_types.h | 3 --- arch/x86/kernel/asm-offsets_64.c | 2 ++ arch/x86/kernel/cpu/common.c | 11 ----------- arch/x86/kernel/dumpstack_64.c | 12 ++++++++---- arch/x86/kernel/nmi.c | 20 +++++++++++++++++++- arch/x86/mm/cpu_entry_area.c | 4 +++- 10 files changed, 52 insertions(+), 31 deletions(-)Documentation/x86/kernel-stacks +1
-1@@ -76,7 +76,7 @@ The currently assigned IST stacks are :- middle of switching stacks. Using IST for NMI events avoids making assumptions about the previous state of the kernel stack. -* ESTACK_DB. DEBUG_STKSZ +* ESTACK_DB. EXCEPTION_STKSZ (PAGE_SIZE). Used for hardware debug interrupts (interrupt 1) and for software debug interrupts (INT3).
Documentation/x86/kernel-stacks The currently assigned IST stacks are :- · line 91
Quoted 6 lines
Documentation/x86/kernel-stacks +3
-0@@ -86,6 +86,11 @@ The currently assigned IST stacks are :- avoids making assumptions about the previous state of the kernel stack. + To handle nested #DB correctly there exist two instances of DB stacks. On + #DB entry the IST stackpointer for #DB is switched to the second instance + so a nested #DB starts from a clean stack. The nested #DB switches to
Pretty sure the "to" at the end is unwanted.
Quoted 5 lines
Documentation/x86/kernel-stacks +2
-0+ the IST stackpointer to a guard hole to catch triple nesting. + * ESTACK_MCE. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 18 - Machine Check Exception (#MC).
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/exceptions: Split debug IST stack
In reply to Thomas Gleixnerx86/exceptions: Split debug IST stack
Commit-ID: 2a594d4ccf3f10f80b77d71bd3dad10813ac0137 Gitweb: https://git.kernel.org/tip/2a594d4ccf3f10f80b77d71bd3dad10813ac0137 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:57 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:14:28 +0200
x86/exceptions: Split debug IST stack
The debug IST stack is actually two separate debug stacks to handle #DB recursion. This is required because the CPU starts always at top of stack on exception entry, which means on #DB recursion the second #DB would overwrite the stack of the first.
The low level entry code therefore adjusts the top of stack on entry so a secondary #DB starts from a different stack page. But the stack pages are adjacent without a guard page between them.
Split the debug stack into 3 stacks which are separated by guard pages. The 3rd stack is never mapped into the cpu_entry_area and is only there to catch triple #DB nesting:
--- top of DB_stack <- Initial stack
--- end of DB_stack
guard page
--- top of DB1_stack <- Top of stack after entering first #DB
--- end of DB1_stack
guard page
--- top of DB2_stack <- Top of stack after entering second #DB
--- end of DB2_stack
guard page
If DB2 would not act as the final guard hole, a second #DB would point the top of #DB stack to the stack below #DB1 which would be valid and not catch the not so desired triple nesting.
The backing store does not allocate any memory for DB2 and its guard page as it is not going to be mapped into the cpu_entry_area.
- Adjust the low level entry code so it adjusts top of #DB with the offset between the stacks instead of exception stack size.
- Make the dumpstack code aware of the new stacks.
- Adjust the in_debug_stack() implementation and move it into the NMI code where it belongs. As this is NMI hotpath code, it just checks the full area between top of DB_stack and bottom of DB1_stack without checking for the guard page. That's correct because the NMI cannot hit a stackpointer pointing to the guard page between DB and DB1 stack. Even if it would, then the NMI operation still is unaffected, but the resume of the debug exception on the topmost DB stack will crash by touching the guard page.
[ bp: Make exception_stack_names static const char * const ]
--- Documentation/x86/kernel-stacks | 7 ++++++- arch/x86/entry/entry_64.S | 8 ++++---- arch/x86/include/asm/cpu_entry_area.h | 14 ++++++++++---- arch/x86/include/asm/debugreg.h | 2 -- arch/x86/include/asm/page_64_types.h | 3 --- arch/x86/kernel/asm-offsets_64.c | 2 ++ arch/x86/kernel/cpu/common.c | 11 ----------- arch/x86/kernel/dumpstack_64.c | 12 ++++++++---- arch/x86/kernel/nmi.c | 20 +++++++++++++++++++- arch/x86/mm/cpu_entry_area.c | 4 +++- 10 files changed, 52 insertions(+), 31 deletions(-)
Documentation/x86/kernel-stacks +6 -1
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :- middle of switching stacks. Using IST for NMI events avoids making assumptions about the previous state of the kernel stack. -* ESTACK_DB. DEBUG_STKSZ +* ESTACK_DB. EXCEPTION_STKSZ (PAGE_SIZE). Used for hardware debug interrupts (interrupt 1) and for software debug interrupts (INT3).
@@ -86,6 +86,11 @@ The currently assigned IST stacks are :- avoids making assumptions about the previous state of the kernel stack. + To handle nested #DB correctly there exist two instances of DB stacks. On + #DB entry the IST stackpointer for #DB is switched to the second instance + so a nested #DB starts from a clean stack. The nested #DB switches + the IST stackpointer to a guard hole to catch triple nesting. + * ESTACK_MCE. EXCEPTION_STKSZ (PAGE_SIZE). Used for interrupt 18 - Machine Check Exception (#MC).
arch/x86/entry/entry_64.S +4 -4
@@ -879,7 +879,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt * @paranoid == 2 is special: the stub will never switch stacks. This is for * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS. */ -.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -925,13 +925,13 @@ ENTRY(\sym) .endif .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + subq $\ist_offset, CPU_TSS_IST(\shift_ist) .endif call \do_sym .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + addq $\ist_offset, CPU_TSS_IST(\shift_ist) .endif /* these procedures expect "no swapgs" flag in ebx */
@@ -1129,7 +1129,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ hv_stimer0_callback_vector hv_stimer0_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1
arch/x86/include/asm/cpu_entry_area.h +10 -4
@@ -10,25 +10,29 @@#ifdef CONFIG_X86_64 /* Macro to enforce the same ordering and stack sizes */ -#define ESTACKS_MEMBERS (guardsize) \ +#define ESTACKS_MEMBERS (guardsize, db2_holesize)\ char DF_stack_guard[guardsize]; \ char DF_stack[EXCEPTION_STKSZ]; \ char NMI_stack_guard[guardsize]; \ char NMI_stack[EXCEPTION_STKSZ]; \ + char DB2_stack_guard[guardsize]; \ + char DB2_stack[db2_holesize]; \ + char DB1_stack_guard[guardsize]; \ + char DB1_stack[EXCEPTION_STKSZ]; \ char DB_stack_guard[guardsize]; \ - char DB_stack[DEBUG_STKSZ]; \ + char DB_stack[EXCEPTION_STKSZ]; \ char MCE_stack_guard[guardsize]; \ char MCE_stack[EXCEPTION_STKSZ]; \ char IST_top_guard[guardsize]; \/* The exception stacks' physical storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0) + ESTACKS_MEMBERS(0, 0) };/* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(PAGE_SIZE) + ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ) };/*
@@ -37,6 +41,8 @@ struct cea_exception_stacks {enum exception_stack_ordering {ESTACK_DF ,ESTACK_NMI , +ESTACK_DB2 , +ESTACK_DB1 ,ESTACK_DB ,ESTACK_MCE ,N_EXCEPTION_STACKS
arch/x86/include/asm/debugreg.h +0 -2
@@ -104,11 +104,9 @@ static inline void debug_stack_usage_dec(void) {__this_cpu_dec (debug_stack_usage); } -int is_debug_stack (unsigned long addr);void debug_stack_set_zero (void );void debug_stack_reset (void );#else /* !X86_64 */ -static inline int is_debug_stack (unsigned long addr) {return 0 ; }static inline void debug_stack_set_zero (void ) { }static inline void debug_stack_reset (void ) { }static inline void debug_stack_usage_inc (void ) { }
arch/x86/include/asm/page_64_types.h +0 -3
@@ -18,9 +18,6 @@#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) -#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1) -#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER) -#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
arch/x86/kernel/asm-offsets_64.c +2 -0
@@ -68,6 +68,8 @@ int main(void)#undef ENTRYOFFSET (TSS_ist, tss_struct, x86_tss.ist); +DEFINE (DB_STACK_OFFSET , offsetof(struct cea_exception_stacks , DB_stack) - + offsetof(struct cea_exception_stacks , DB1_stack));BLANK ();#ifdef CONFIG_STACKPROTECTOR
arch/x86/kernel/cpu/common.c +0 -11
@@ -1549,17 +1549,7 @@ void syscall_init(void) X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } -static DEFINE_PER_CPU(unsigned long, debug_stack_addr);DEFINE_PER_CPU (int, debug_stack_usage); - -int is_debug_stack (unsigned long addr) -{ -return __this_cpu_read (debug_stack_usage) || - (addr <=__this_cpu_read (debug_stack_addr) && - addr > (__this_cpu_read (debug_stack_addr) -DEBUG_STKSZ )); -} -NOKPROBE_SYMBOL (is_debug_stack); -DEFINE_PER_CPU (u32, debug_idt_ctr);void debug_stack_set_zero (void )
@@ -1735,7 +1725,6 @@ void cpu_init(void) t->x86_tss.ist[IST_INDEX_NMI ] =__this_cpu_ist_top_va (NMI ); t->x86_tss.ist[IST_INDEX_DB ] =__this_cpu_ist_top_va (DB ); t->x86_tss.ist[IST_INDEX_MCE ] =__this_cpu_ist_top_va (MCE ); -per_cpu (debug_stack_addr, cpu) = t->x86_tss.ist[IST_INDEX_DB ]; } t->x86_tss.io_bitmap_base =IO_BITMAP_OFFSET ;
arch/x86/kernel/dumpstack_64.c +8 -4
@@ -19,16 +19,18 @@#include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> -static const char *exception_stack_names[N_EXCEPTION_STACKS ] = { +static const char *const exception_stack_names[] = { [ESTACK_DF ] ="#DF" , [ESTACK_NMI ] ="NMI" , + [ESTACK_DB2 ] ="#DB2" , + [ESTACK_DB1 ] ="#DB1" , [ESTACK_DB ] ="#DB" , [ESTACK_MCE ] ="#MC" , };const char *stack_type_name (enum stack_type type) { -BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); +BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 );if (type ==STACK_TYPE_IRQ )return "IRQ" ;
@@ -58,9 +60,11 @@ struct estack_layout { .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ } -static const struct estack_layout layout[N_EXCEPTION_STACKS ] = { +static const struct estack_layout layout[] = { [ESTACK_DF ] =ESTACK_ENTRY (DF ), [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), + [ESTACK_DB2 ] = { .begin =0 , .end =0 }, + [ESTACK_DB1 ] =ESTACK_ENTRY (DB1 ), [ESTACK_DB ] =ESTACK_ENTRY (DB ), [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), };
@@ -71,7 +75,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)struct pt_regs *regs;unsigned int k; -BUILD_BUG_ON (N_EXCEPTION_STACKS !=4 ); +BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 ); estacks = (unsigned long )__this_cpu_read (cea_exception_stacks);
arch/x86/kernel/nmi.c +19 -1
@@ -21,13 +21,14 @@#include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/atomic.h> #include <linux/sched/clock.h> #if defined(CONFIG_EDAC )#include <linux/edac.h> #endif -#include <linux/atomic.h> +#include <asm/cpu_entry_area.h> #include <asm/traps.h> #include <asm/mach_traps.h> #include <asm/nmi.h>
@@ -487,6 +488,23 @@ static DEFINE_PER_CPU(unsigned long, nmi_cr2);* switch back to the original IDT. */ static DEFINE_PER_CPU(int, update_debug_stack); + +static bool notrace is_debug_stack(unsigned long addr) +{ +struct cea_exception_stacks *cs =__this_cpu_read (cea_exception_stacks); +unsigned long top =CEA_ESTACK_TOP (cs,DB ); +unsigned long bot =CEA_ESTACK_BOT (cs,DB1 ); + +if (__this_cpu_read (debug_stack_usage)) +return true; +/* +* Note, this covers the guard page between DB and DB1 as well to +* avoid two checks. But by all means @addr can never point into +* the guard page. +*/ +return addr >= bot && addr < top; +} +NOKPROBE_SYMBOL (is_debug_stack);#endif dotraplinkage notrace void
arch/x86/mm/cpu_entry_area.c +3 -1
@@ -98,10 +98,12 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)/* * The exceptions stack mappings in the per cpu area are protected -* by guard pages so each stack must be mapped separately. +* by guard pages so each stack must be mapped separately. DB2 is +* not mapped; it just exists to catch triple nesting of #DB. */ cea_map_stack (DF );cea_map_stack (NMI ); +cea_map_stack (DB1 );cea_map_stack (DB );cea_map_stack (MCE ); }
PATCH v3 22/32 x86/dumpstack/64: Speedup in_exception_stack()
In reply to Thomas GleixnerThe current implementation of in_exception_stack() iterates over the exception stacks array. Most of the time this is an useless exercise, but even for the actual use cases (perf and ftrace) it takes at least 2 iterations to get to the NMI stack.
As the exception stacks and the guard pages are page aligned the loop can be avoided completely.
Add a initial check whether the stack pointer is inside the full exception stack area and leave early if not.
Create a lookup table which describes the stack area. The table index is the page offset from the beginning of the exception stacks. So for any given stack pointer the page offset is computed and a lookup in the description table is performed. If it is inside a guard page, return. If not, use the descriptor to fill in the info structure.
The table is filled at compile time and for the !KASAN case the interesting page descriptors exactly fit into a single cache line. Just the last guard page descriptor is in the next cacheline, but that should not be accessed in the regular case.
---
V2: Simplify the macro maze
--- arch/x86/kernel/dumpstack_64.c | 90 +++++++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 35 deletions(-)
arch/x86/kernel/dumpstack_64.c +55 -35
@@ -50,52 +50,72 @@ const char *stack_type_name(enum stack_treturn NULL ; } -struct estack_layout { -unsigned int begin; -unsigned int end; +/** +* struct estack_pages - Page descriptor for exception stacks +* @offs: Offset from the start of the exception stack area +* @size: Size of the exception stack +* @type: Type to store in the stack_info struct +*/ +struct estack_pages { +u32 offs; +u16 size; +u16 type; }; -#define ESTACK_ENTRY (x) { \ - .begin = offsetof(struct cea_exception_stacks, x## _stack), \ - .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ - } - -static const struct estack_layout layout[] = { - [ESTACK_DF ] =ESTACK_ENTRY (DF ), - [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), - [ESTACK_DB2 ] = { .begin =0 , .end =0 }, - [ESTACK_DB1 ] =ESTACK_ENTRY (DB1 ), - [ESTACK_DB ] =ESTACK_ENTRY (DB ), - [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), +#define EPAGERANGE (st) \ + [PFN_DOWN(CEA_ESTACK_OFFS(st)) ... \ + PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = { \ + .offs = CEA_ESTACK_OFFS(st), \ + .size = CEA_ESTACK_SIZE(st), \ + .type = STACK_TYPE_EXCEPTION + ESTACK_ ##st, } + +/* +* Array of exception stack page descriptors. If the stack is larger than +* PAGE_SIZE, all pages covering a particular stack will have the same +* info. The guard pages including the not mapped DB2 stack are zeroed +* out. +*/ +static const +struct estack_pages estack_pages[CEA_ESTACK_PAGES ]____cacheline_aligned = { +EPAGERANGE (DF ), +EPAGERANGE (NMI ), +EPAGERANGE (DB1 ), +EPAGERANGE (DB ), +EPAGERANGE (MCE ), };static bool in_exception_stack (unsigned long *stack,struct stack_info *info) { -unsigned long estacks, begin, end, stk = (unsigned long )stack; +unsigned long begin, end, stk = (unsigned long )stack; +const struct estack_pages *ep;struct pt_regs *regs;unsigned int k;BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 ); - estacks = (unsigned long )__this_cpu_read (cea_exception_stacks); - -for (k =0 ; k <N_EXCEPTION_STACKS ; k++) { - begin = estacks + layout[k].begin; - end = estacks + layout[k].end; - regs = (struct pt_regs *)end -1 ; - -if (stk < begin || stk >= end) -continue ; - - info->type =STACK_TYPE_EXCEPTION + k; - info->begin = (unsigned long *)begin; - info->end = (unsigned long *)end; - info->next_sp = (unsigned long *)regs->sp; - -return true; - } - -return false; + begin = (unsigned long )__this_cpu_read (cea_exception_stacks); + end = begin +sizeof (struct cea_exception_stacks ); +/* Bail if @stack is outside the exception stack area. */ +if (stk < begin || stk >= end) +return false; + +/* Calc page offset from start of exception stacks */ + k = (stk - begin) >>PAGE_SHIFT ; +/* Lookup the page descriptor */ + ep = &estack_pages[k]; +/* Guard page? */ +if (!ep->size) +return false; + + begin += (unsigned long )ep->offs; + end = begin + (unsigned long )ep->size; + regs = (struct pt_regs *)end -1 ; + + info->type = ep->type; + info->begin = (unsigned long *)begin; + info->end = (unsigned long *)end; + info->next_sp = (unsigned long *)regs->sp; +return true; }static bool in_irq_stack (unsigned long *stack,struct stack_info *info)
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/dumpstack/64: Speedup in_exception_stack()
x86/dumpstack/64: Speedup in_exception_stack()
Commit-ID: c450c8f532b63475b30e29bc600c25ab0a4ab282 Gitweb: https://git.kernel.org/tip/c450c8f532b63475b30e29bc600c25ab0a4ab282 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:58 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:16:57 +0200
x86/dumpstack/64: Speedup in_exception_stack()
The current implementation of in_exception_stack() iterates over the exception stacks array. Most of the time this is an useless exercise, but even for the actual use cases (perf and ftrace) it takes at least 2 iterations to get to the NMI stack.
As the exception stacks and the guard pages are page aligned the loop can be avoided completely.
Add a initial check whether the stack pointer is inside the full exception stack area and leave early if not.
Create a lookup table which describes the stack area. The table index is the page offset from the beginning of the exception stacks. So for any given stack pointer the page offset is computed and a lookup in the description table is performed. If it is inside a guard page, return. If not, use the descriptor to fill in the info structure.
The table is filled at compile time and for the !KASAN case the interesting page descriptors exactly fit into a single cache line. Just the last guard page descriptor is in the next cacheline, but that should not be accessed in the regular case.
--- arch/x86/kernel/dumpstack_64.c | 82 ++++++++++++++++++++++++++---------------- 1 file changed, 51 insertions(+), 31 deletions(-)
arch/x86/kernel/dumpstack_64.c +51 -31
@@ -50,52 +50,72 @@ const char *stack_type_name(enum stack_type type)return NULL ; } -struct estack_layout { -unsigned int begin; -unsigned int end; +/** +* struct estack_pages - Page descriptor for exception stacks +* @offs: Offset from the start of the exception stack area +* @size: Size of the exception stack +* @type: Type to store in the stack_info struct +*/ +struct estack_pages { +u32 offs; +u16 size; +u16 type; }; -#define ESTACK_ENTRY (x) { \ - .begin = offsetof(struct cea_exception_stacks, x## _stack), \ - .end = offsetof(struct cea_exception_stacks, x## _stack_guard) \ - } +#define EPAGERANGE (st) \ + [PFN_DOWN(CEA_ESTACK_OFFS(st)) ... \ + PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = { \ + .offs = CEA_ESTACK_OFFS(st), \ + .size = CEA_ESTACK_SIZE(st), \ + .type = STACK_TYPE_EXCEPTION + ESTACK_ ##st, } -static const struct estack_layout layout[] = { - [ESTACK_DF ] =ESTACK_ENTRY (DF ), - [ESTACK_NMI ] =ESTACK_ENTRY (NMI ), - [ESTACK_DB2 ] = { .begin =0 , .end =0 }, - [ESTACK_DB1 ] =ESTACK_ENTRY (DB1 ), - [ESTACK_DB ] =ESTACK_ENTRY (DB ), - [ESTACK_MCE ] =ESTACK_ENTRY (MCE ), +/* +* Array of exception stack page descriptors. If the stack is larger than +* PAGE_SIZE, all pages covering a particular stack will have the same +* info. The guard pages including the not mapped DB2 stack are zeroed +* out. +*/ +static const +struct estack_pages estack_pages[CEA_ESTACK_PAGES ]____cacheline_aligned = { +EPAGERANGE (DF ), +EPAGERANGE (NMI ), +EPAGERANGE (DB1 ), +EPAGERANGE (DB ), +EPAGERANGE (MCE ), };static bool in_exception_stack (unsigned long *stack,struct stack_info *info) { -unsigned long estacks, begin, end, stk = (unsigned long )stack; +unsigned long begin, end, stk = (unsigned long )stack; +const struct estack_pages *ep;struct pt_regs *regs;unsigned int k;BUILD_BUG_ON (N_EXCEPTION_STACKS !=6 ); - estacks = (unsigned long )__this_cpu_read (cea_exception_stacks); - -for (k =0 ; k <N_EXCEPTION_STACKS ; k++) { - begin = estacks + layout[k].begin; - end = estacks + layout[k].end; - regs = (struct pt_regs *)end -1 ; + begin = (unsigned long )__this_cpu_read (cea_exception_stacks); + end = begin +sizeof (struct cea_exception_stacks ); +/* Bail if @stack is outside the exception stack area. */ +if (stk < begin || stk >= end) +return false; -if (stk < begin || stk >= end) -continue ; +/* Calc page offset from start of exception stacks */ + k = (stk - begin) >>PAGE_SHIFT ; +/* Lookup the page descriptor */ + ep = &estack_pages[k]; +/* Guard page? */ +if (!ep->size) +return false; - info->type =STACK_TYPE_EXCEPTION + k; - info->begin = (unsigned long *)begin; - info->end = (unsigned long *)end; - info->next_sp = (unsigned long *)regs->sp; + begin += (unsigned long )ep->offs; + end = begin + (unsigned long )ep->size; + regs = (struct pt_regs *)end -1 ; -return true; - } - -return false; + info->type = ep->type; + info->begin = (unsigned long *)begin; + info->end = (unsigned long *)end; + info->next_sp = (unsigned long *)regs->sp; +return true; }static bool in_irq_stack (unsigned long *stack,struct stack_info *info)
PATCH v3 23/32 x86/irq/32: Define IRQ_STACK_SIZE
In reply to Thomas GleixnerOn 32-bit IRQ_STACK_SIZE is the same as THREAD_SIZE.
To allow sharing struct irq_stack with 32-bit, define IRQ_STACK_SIZE for 32-bit and use of for struct irq_stack.
No functional change.
--- arch/x86/include/asm/page_32_types.h | 2 ++ arch/x86/include/asm/processor.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-)
arch/x86/include/asm/page_32_types.h +2 -0
@@ -22,6 +22,8 @@#define THREAD_SIZE_ORDER 1#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define IRQ_STACK_SIZE THREAD_SIZE +#define N_EXCEPTION_STACKS 1#ifdef CONFIG_X86_PAE
arch/x86/include/asm/processor.h +2 -2
@@ -422,8 +422,8 @@ DECLARE_PER_CPU_ALIGNED(struct stack_can* per-CPU IRQ handling stacks */ struct irq_stack { -u32 stack[THREAD_SIZE /sizeof (u32)]; -}__aligned(THREAD_SIZE) ; +u32 stack[IRQ_STACK_SIZE /sizeof (u32)]; +}__aligned(IRQ_STACK_SIZE) ; DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/32: Define IRQ_STACK_SIZE
x86/irq/32: Define IRQ_STACK_SIZE
Commit-ID: aa641c287b2f7676f6f0064a8351daf08eca6b0a Gitweb: https://git.kernel.org/tip/aa641c287b2f7676f6f0064a8351daf08eca6b0a Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 17:59:59 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:18:36 +0200
x86/irq/32: Define IRQ_STACK_SIZE
On 32-bit IRQ_STACK_SIZE is the same as THREAD_SIZE.
To allow sharing struct irq_stack with 32-bit, define IRQ_STACK_SIZE for 32-bit and use it for struct irq_stack.
No functional change.
--- arch/x86/include/asm/page_32_types.h | 2 ++ arch/x86/include/asm/processor.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-)
arch/x86/include/asm/page_32_types.h +2 -0
@@ -22,6 +22,8 @@#define THREAD_SIZE_ORDER 1#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define IRQ_STACK_SIZE THREAD_SIZE +#define N_EXCEPTION_STACKS 1#ifdef CONFIG_X86_PAE
arch/x86/include/asm/processor.h +2 -2
@@ -422,8 +422,8 @@ DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);* per-CPU IRQ handling stacks */ struct irq_stack { -u32 stack[THREAD_SIZE /sizeof (u32)]; -}__aligned(THREAD_SIZE) ; +u32 stack[IRQ_STACK_SIZE /sizeof (u32)]; +}__aligned(IRQ_STACK_SIZE) ; DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
PATCH v3 24/32 x86/irq/32: Make irq stack a character array
In reply to Thomas GleixnerThere is no reason to have an u32 array in struct irq_stack. The only purpose of the array is to size the struct properly.
Preparatory change for sharing struct irq_stack with 64-bit.
--- arch/x86/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/include/asm/processor.h +1 -1
@@ -422,7 +422,7 @@ DECLARE_PER_CPU_ALIGNED(struct stack_can* per-CPU IRQ handling stacks */ struct irq_stack { -u32 stack[IRQ_STACK_SIZE /sizeof (u32)]; +char stack[IRQ_STACK_SIZE ]; }__aligned(IRQ_STACK_SIZE) ; DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/32: Make irq stack a character array
x86/irq/32: Make irq stack a character array
Commit-ID: 231c4846b106d526fa212b02b37447d3f2fcc99d Gitweb: https://git.kernel.org/tip/231c4846b106d526fa212b02b37447d3f2fcc99d Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:00 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:21:21 +0200
x86/irq/32: Make irq stack a character array
There is no reason to have an u32 array in struct irq_stack. The only purpose of the array is to size the struct properly.
Preparatory change for sharing struct irq_stack with 64-bit.
--- arch/x86/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/include/asm/processor.h +1 -1
@@ -422,7 +422,7 @@ DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);* per-CPU IRQ handling stacks */ struct irq_stack { -u32 stack[IRQ_STACK_SIZE /sizeof (u32)]; +char stack[IRQ_STACK_SIZE ]; }__aligned(IRQ_STACK_SIZE) ; DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
PATCH v3 25/32 x86/irq/32: Rename hard/softirq_stack to hard/softirq_stack_ptr
In reply to Thomas GleixnerThe percpu storage holds a pointer to the stack not the stack itself. Rename it before sharing struct irq_stack with 64-bit.
--- arch/x86/include/asm/processor.h | 4 ++-- arch/x86/kernel/dumpstack_32.c | 4 ++-- arch/x86/kernel/irq_32.c | 19 ++++++++++--------- 3 files changed, 14 insertions(+), 13 deletions(-)
arch/x86/include/asm/processor.h +2 -2
@@ -425,8 +425,8 @@ struct irq_stack {char stack[IRQ_STACK_SIZE ]; } __aligned(IRQ_STACK_SIZE); -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); -DECLARE_PER_CPU(struct irq_stack *, softirq_stack); +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);#endif /* X86_64 */ extern unsigned int fpu_kernel_xstate_size;
arch/x86/kernel/dumpstack_32.c +2 -2
@@ -34,7 +34,7 @@ const char *stack_type_name(enum stack_tstatic bool in_hardirq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin = (unsigned long *)this_cpu_read (hardirq_stack); +unsigned long *begin = (unsigned long *)this_cpu_read (hardirq_stack_ptr);unsigned long *end = begin + (THREAD_SIZE /sizeof (long ));/*
@@ -59,7 +59,7 @@ static bool in_hardirq_stack(unsigned lostatic bool in_softirq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin = (unsigned long *)this_cpu_read (softirq_stack); +unsigned long *begin = (unsigned long *)this_cpu_read (softirq_stack_ptr);unsigned long *end = begin + (THREAD_SIZE /sizeof (long ));/*
arch/x86/kernel/irq_32.c +10 -9
@@ -51,8 +51,8 @@ static inline int check_stack_overflow(vstatic inline void print_stack_overflow (void ) { }#endif -DEFINE_PER_CPU(struct irq_stack *, hardirq_stack); -DEFINE_PER_CPU(struct irq_stack *, softirq_stack); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);static void call_on_stack (void *func,void *stack) {
@@ -76,7 +76,7 @@ static inline int execute_on_irq_stack(iu32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *)current_stack (); - irqstk =__this_cpu_read (hardirq_stack); + irqstk =__this_cpu_read (hardirq_stack_ptr);/* * this is where we switch to the IRQ stack. However, if we are
@@ -113,21 +113,22 @@ void irq_ctx_init(int cpu) {struct irq_stack *irqstk; -if (per_cpu (hardirq_stack, cpu)) +if (per_cpu (hardirq_stack_ptr, cpu))return ; irqstk =page_address (alloc_pages_node (cpu_to_node (cpu),THREADINFO_GFP ,THREAD_SIZE_ORDER )); -per_cpu (hardirq_stack, cpu) = irqstk; +per_cpu (hardirq_stack_ptr, cpu) = irqstk; irqstk =page_address (alloc_pages_node (cpu_to_node (cpu),THREADINFO_GFP ,THREAD_SIZE_ORDER )); -per_cpu (softirq_stack, cpu) = irqstk; +per_cpu (softirq_stack_ptr, cpu) = irqstk; -printk (KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n" , - cpu,per_cpu (hardirq_stack, cpu),per_cpu (softirq_stack, cpu)); +pr_debug ("CPU %u irqstacks, hard=%p soft=%p\n" , + cpu,per_cpu (hardirq_stack_ptr, cpu), +per_cpu (softirq_stack_ptr, cpu)); }void do_softirq_own_stack (void )
@@ -135,7 +136,7 @@ void do_softirq_own_stack(void)struct irq_stack *irqstk;u32 *isp, *prev_esp; - irqstk =__this_cpu_read (softirq_stack); + irqstk =__this_cpu_read (softirq_stack_ptr);/* build the stack frame on the softirq stack */ isp = (u32 *) ((char *)irqstk +sizeof (*irqstk));
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/32: Rename hard/softirq_stack to hard/softirq_stack_ptr
x86/irq/32: Rename hard/softirq_stack to hard/softirq_stack_ptr
Commit-ID: a754fe2b76d1d6bce7069657bba975034f3ad961 Gitweb: https://git.kernel.org/tip/a754fe2b76d1d6bce7069657bba975034f3ad961 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:01 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:24:18 +0200
x86/irq/32: Rename hard/softirq_stack to hard/softirq_stack_ptr
The percpu storage holds a pointer to the stack not the stack itself. Rename it before sharing struct irq_stack with 64-bit.
No functional changes.
--- arch/x86/include/asm/processor.h | 4 ++-- arch/x86/kernel/dumpstack_32.c | 4 ++-- arch/x86/kernel/irq_32.c | 19 ++++++++++--------- 3 files changed, 14 insertions(+), 13 deletions(-)
arch/x86/include/asm/processor.h +2 -2
@@ -425,8 +425,8 @@ struct irq_stack {char stack[IRQ_STACK_SIZE ]; } __aligned(IRQ_STACK_SIZE); -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); -DECLARE_PER_CPU(struct irq_stack *, softirq_stack); +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);#endif /* X86_64 */ extern unsigned int fpu_kernel_xstate_size;
arch/x86/kernel/dumpstack_32.c +2 -2
@@ -34,7 +34,7 @@ const char *stack_type_name(enum stack_type type)static bool in_hardirq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin = (unsigned long *)this_cpu_read (hardirq_stack); +unsigned long *begin = (unsigned long *)this_cpu_read (hardirq_stack_ptr);unsigned long *end = begin + (THREAD_SIZE /sizeof (long ));/*
@@ -59,7 +59,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)static bool in_softirq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *begin = (unsigned long *)this_cpu_read (softirq_stack); +unsigned long *begin = (unsigned long *)this_cpu_read (softirq_stack_ptr);unsigned long *end = begin + (THREAD_SIZE /sizeof (long ));/*
arch/x86/kernel/irq_32.c +10 -9
@@ -51,8 +51,8 @@ static inline int check_stack_overflow(void) { return 0; }static inline void print_stack_overflow (void ) { }#endif -DEFINE_PER_CPU(struct irq_stack *, hardirq_stack); -DEFINE_PER_CPU(struct irq_stack *, softirq_stack); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);static void call_on_stack (void *func,void *stack) {
@@ -76,7 +76,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *)current_stack (); - irqstk =__this_cpu_read (hardirq_stack); + irqstk =__this_cpu_read (hardirq_stack_ptr);/* * this is where we switch to the IRQ stack. However, if we are
@@ -113,21 +113,22 @@ void irq_ctx_init(int cpu) {struct irq_stack *irqstk; -if (per_cpu (hardirq_stack, cpu)) +if (per_cpu (hardirq_stack_ptr, cpu))return ; irqstk =page_address (alloc_pages_node (cpu_to_node (cpu),THREADINFO_GFP ,THREAD_SIZE_ORDER )); -per_cpu (hardirq_stack, cpu) = irqstk; +per_cpu (hardirq_stack_ptr, cpu) = irqstk; irqstk =page_address (alloc_pages_node (cpu_to_node (cpu),THREADINFO_GFP ,THREAD_SIZE_ORDER )); -per_cpu (softirq_stack, cpu) = irqstk; +per_cpu (softirq_stack_ptr, cpu) = irqstk; -printk (KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n" , - cpu,per_cpu (hardirq_stack, cpu),per_cpu (softirq_stack, cpu)); +pr_debug ("CPU %u irqstacks, hard=%p soft=%p\n" , + cpu,per_cpu (hardirq_stack_ptr, cpu), +per_cpu (softirq_stack_ptr, cpu)); }void do_softirq_own_stack (void )
@@ -135,7 +136,7 @@ void do_softirq_own_stack(void)struct irq_stack *irqstk;u32 *isp, *prev_esp; - irqstk =__this_cpu_read (softirq_stack); + irqstk =__this_cpu_read (softirq_stack_ptr);/* build the stack frame on the softirq stack */ isp = (u32 *) ((char *)irqstk +sizeof (*irqstk));
PATCH v3 26/32 x86/irq/64: Rename irq_stack_ptr to hardirq_stack_ptr
In reply to Thomas GleixnerPreparatory patch to share code with 32bit.
--- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/dumpstack_64.c | 2 +- arch/x86/kernel/irq_64.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-)
arch/x86/entry/entry_64.S +1 -1
@@ -431,7 +431,7 @@ END(irq_entries_start) */ movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8) - movq PER_CPU_VAR(irq_stack_ptr), %rsp + movq PER_CPU_VAR(hardirq_stack_ptr), %rsp #ifdef CONFIG_DEBUG_ENTRY /*
arch/x86/include/asm/processor.h +1 -1
@@ -396,7 +396,7 @@ static inline unsigned long cpu_kernelmoreturn (unsigned long )per_cpu (irq_stack_union.gs_base, cpu); } -DECLARE_PER_CPU(char *, irq_stack_ptr); +DECLARE_PER_CPU(char *, hardirq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void);
arch/x86/kernel/cpu/common.c +1 -1
@@ -1510,7 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, cur &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, irq_stack_ptr) = +DEFINE_PER_CPU(char *, hardirq_stack_ptr) =init_per_cpu_var (irq_stack_union.irq_stack) +IRQ_STACK_SIZE ; DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
arch/x86/kernel/dumpstack_64.c +1 -1
@@ -120,7 +120,7 @@ static bool in_exception_stack(unsignedstatic bool in_irq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *end = (unsigned long *)this_cpu_read (irq_stack_ptr); +unsigned long *end = (unsigned long *)this_cpu_read (hardirq_stack_ptr);unsigned long *begin = end - (IRQ_STACK_SIZE /sizeof (long ));/*
arch/x86/kernel/irq_64.c +1 -1
@@ -56,7 +56,7 @@ static inline void stack_overflow_check( regs->sp <= curbase + THREAD_SIZE)return ; - irq_stack_top = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_top = (u64 )__this_cpu_read (hardirq_stack_ptr); irq_stack_bottom = irq_stack_top -IRQ_STACK_SIZE +STACK_MARGIN ;if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ;
arch/x86/kernel/setup_percpu.c +1 -1
@@ -245,7 +245,7 @@ void __init setup_per_cpu_areas(void)early_per_cpu_map (x86_cpu_to_logical_apicid, cpu);#endif #ifdef CONFIG_X86_64 -per_cpu (irq_stack_ptr, cpu) = +per_cpu (hardirq_stack_ptr, cpu) =per_cpu (irq_stack_union.irq_stack, cpu) +IRQ_STACK_SIZE ;#endif
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Rename irq_stack_ptr to hardirq_stack_ptr
x86/irq/64: Rename irq_stack_ptr to hardirq_stack_ptr
Commit-ID: 758a2e312228410f2f5092ade558109e93dc3ee8 Gitweb: https://git.kernel.org/tip/758a2e312228410f2f5092ade558109e93dc3ee8 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:02 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:27:10 +0200
x86/irq/64: Rename irq_stack_ptr to hardirq_stack_ptr
Preparatory patch to share code with 32bit.
No functional changes.
--- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/dumpstack_64.c | 2 +- arch/x86/kernel/irq_64.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-)
arch/x86/entry/entry_64.S +1 -1
@@ -431,7 +431,7 @@ END(irq_entries_start) */ movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8) - movq PER_CPU_VAR(irq_stack_ptr), %rsp + movq PER_CPU_VAR(hardirq_stack_ptr), %rsp #ifdef CONFIG_DEBUG_ENTRY /*
arch/x86/include/asm/processor.h +1 -1
@@ -396,7 +396,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)return (unsigned long )per_cpu (irq_stack_union.gs_base, cpu); } -DECLARE_PER_CPU(char *, irq_stack_ptr); +DECLARE_PER_CPU(char *, hardirq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void);
arch/x86/kernel/cpu/common.c +1 -1
@@ -1510,7 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, irq_stack_ptr) = +DEFINE_PER_CPU(char *, hardirq_stack_ptr) =init_per_cpu_var (irq_stack_union.irq_stack) +IRQ_STACK_SIZE ; DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
arch/x86/kernel/dumpstack_64.c +1 -1
@@ -120,7 +120,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)static bool in_irq_stack (unsigned long *stack,struct stack_info *info) { -unsigned long *end = (unsigned long *)this_cpu_read (irq_stack_ptr); +unsigned long *end = (unsigned long *)this_cpu_read (hardirq_stack_ptr);unsigned long *begin = end - (IRQ_STACK_SIZE /sizeof (long ));/*
arch/x86/kernel/irq_64.c +1 -1
@@ -56,7 +56,7 @@ static inline void stack_overflow_check(struct pt_regs *regs) regs->sp <= curbase + THREAD_SIZE)return ; - irq_stack_top = (u64 )__this_cpu_read (irq_stack_ptr); + irq_stack_top = (u64 )__this_cpu_read (hardirq_stack_ptr); irq_stack_bottom = irq_stack_top -IRQ_STACK_SIZE +STACK_MARGIN ;if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)return ;
arch/x86/kernel/setup_percpu.c +1 -1
@@ -245,7 +245,7 @@ void __init setup_per_cpu_areas(void)early_per_cpu_map (x86_cpu_to_logical_apicid, cpu);#endif #ifdef CONFIG_X86_64 -per_cpu (irq_stack_ptr, cpu) = +per_cpu (hardirq_stack_ptr, cpu) =per_cpu (irq_stack_union.irq_stack, cpu) +IRQ_STACK_SIZE ;#endif
PATCH v3 27/32 x86/irq/32: Invoke irq_ctx_init() from init_IRQ()
In reply to Thomas Gleixnerirq_ctx_init() is invoked from native_init_IRQ() or from xen_init_IRQ() code. There is no reason to have this split. The interrupt stacks must be allocated no matter what.
Invoke it from init_IRQ() before invoking the native or XEN init implementation.
--- arch/x86/kernel/irqinit.c | 4 ++-- drivers/xen/events/events_base.c | 1 - 2 files changed, 2 insertions(+), 3 deletions(-)
arch/x86/kernel/irqinit.c +2 -2
@@ -91,6 +91,8 @@ void __init init_IRQ(void)for (i =0 ; i <nr_legacy_irqs (); i++)per_cpu (vector_irq,0 )[ISA_IRQ_VECTOR (i)] =irq_to_desc (i); +irq_ctx_init (smp_processor_id ()); + x86_init.irqs.intr_init (); }
@@ -104,6 +106,4 @@ void __init native_init_IRQ(void)if (!acpi_ioapic && !of_ioapic &&nr_legacy_irqs ())setup_irq (2 , &irq2); - -irq_ctx_init (smp_processor_id ()); }
drivers/xen/events/events_base.c +0 -1
@@ -1687,7 +1687,6 @@ void __init xen_init_IRQ(void)#ifdef CONFIG_X86 if (xen_pv_domain ()) { -irq_ctx_init (smp_processor_id ());if (xen_initial_domain ())pci_xen_initial_domain (); }
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/32: Invoke irq_ctx_init() from init_IRQ()
x86/irq/32: Invoke irq_ctx_init() from init_IRQ()
Commit-ID: 451f743a64e1cf979f5fe21a1b2a015feb559f72 Gitweb: https://git.kernel.org/tip/451f743a64e1cf979f5fe21a1b2a015feb559f72 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:03 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:30:12 +0200
x86/irq/32: Invoke irq_ctx_init() from init_IRQ()
irq_ctx_init() is invoked from native_init_IRQ() or from xen_init_IRQ() code. There is no reason to have this split. The interrupt stacks must be allocated no matter what.
Invoke it from init_IRQ() before invoking the native or XEN init implementation.
--- arch/x86/kernel/irqinit.c | 4 ++-- drivers/xen/events/events_base.c | 1 - 2 files changed, 2 insertions(+), 3 deletions(-)
arch/x86/kernel/irqinit.c +2 -2
@@ -91,6 +91,8 @@ void __init init_IRQ(void)for (i =0 ; i <nr_legacy_irqs (); i++)per_cpu (vector_irq,0 )[ISA_IRQ_VECTOR (i)] =irq_to_desc (i); +irq_ctx_init (smp_processor_id ()); + x86_init.irqs.intr_init (); }
@@ -104,6 +106,4 @@ void __init native_init_IRQ(void)if (!acpi_ioapic && !of_ioapic &&nr_legacy_irqs ())setup_irq (2 , &irq2); - -irq_ctx_init (smp_processor_id ()); }
drivers/xen/events/events_base.c +0 -1
@@ -1687,7 +1687,6 @@ void __init xen_init_IRQ(void)#ifdef CONFIG_X86 if (xen_pv_domain ()) { -irq_ctx_init (smp_processor_id ());if (xen_initial_domain ())pci_xen_initial_domain (); }
PATCH v3 28/32 x86/irq/32: Handle irq stack allocation failure proper
In reply to Thomas Gleixnerirq_ctx_init() crashes hard on page allocation failures. While that's ok during early boot, it's just wrong in the CPU hotplug bringup code.
Check the page allocation failure and return -ENOMEM and handle it at the call sites. On early boot the only way out is to BUG(), but on CPU hotplug there is no reason to crash, so just abort the operation.
Rename the function to something more sensible while at it.
--- arch/x86/include/asm/irq.h | 4 ++-- arch/x86/include/asm/smp.h | 2 +- arch/x86/kernel/irq_32.c | 34 +++++++++++++++++----------------- arch/x86/kernel/irqinit.c | 2 +- arch/x86/kernel/smpboot.c | 15 ++++++++++++--- arch/x86/xen/smp_pv.c | 4 +++- 6 files changed, 36 insertions(+), 25 deletions(-)
arch/x86/include/asm/irq.h +2 -2
@@ -17,9 +17,9 @@ static inline int irq_canonicalize(int i }#ifdef CONFIG_X86_32 -extern void irq_ctx_init (int cpu); +extern int irq_init_percpu_irqstack (unsigned int cpu);#else -# define irq_ctx_init (cpu) do { } while (0) +static inline int irq_init_percpu_irqstack (unsigned int cpu) {return 0 ; }#endif #define __ARCH_HAS_DO_SOFTIRQ
arch/x86/include/asm/smp.h +1 -1
@@ -131,7 +131,7 @@ void native_smp_prepare_boot_cpu(void);void native_smp_prepare_cpus (unsigned int max_cpus);void calculate_max_logical_packages (void );void native_smp_cpus_done (unsigned int max_cpus); -void common_cpu_up (unsigned int cpunum,struct task_struct *tidle); +int common_cpu_up (unsigned int cpunum,struct task_struct *tidle);int native_cpu_up (unsigned int cpunum,struct task_struct *tidle);int native_cpu_disable (void );int common_cpu_die (unsigned int cpu);
arch/x86/kernel/irq_32.c +17 -17
@@ -107,28 +107,28 @@ static inline int execute_on_irq_stack(i }/* -* allocate per-cpu stacks for hardirq and for softirq processing +* Allocate per-cpu stacks for hardirq and softirq processing */ -void irq_ctx_init (int cpu) +int irq_init_percpu_irqstack (unsigned int cpu) { -struct irq_stack *irqstk; +int node =cpu_to_node (cpu); +struct page *ph, *ps;if (per_cpu (hardirq_stack_ptr, cpu)) -return ; +return 0 ; - irqstk =page_address (alloc_pages_node (cpu_to_node (cpu), -THREADINFO_GFP , -THREAD_SIZE_ORDER )); -per_cpu (hardirq_stack_ptr, cpu) = irqstk; - - irqstk =page_address (alloc_pages_node (cpu_to_node (cpu), -THREADINFO_GFP , -THREAD_SIZE_ORDER )); -per_cpu (softirq_stack_ptr, cpu) = irqstk; - -pr_debug ("CPU %u irqstacks, hard=%p soft=%p\n" , - cpu,per_cpu (hardirq_stack_ptr, cpu), -per_cpu (softirq_stack_ptr, cpu)); + ph =alloc_pages_node (node,THREADINFO_GFP ,THREAD_SIZE_ORDER ); +if (!ph) +return -ENOMEM ; + ps =alloc_pages_node (node,THREADINFO_GFP ,THREAD_SIZE_ORDER ); +if (!ps) { +__free_pages (ph,THREAD_SIZE_ORDER ); +return -ENOMEM ; + } + +per_cpu (hardirq_stack_ptr, cpu) =page_address (ph); +per_cpu (softirq_stack_ptr, cpu) =page_address (ps); +return 0 ; }void do_softirq_own_stack (void )
arch/x86/kernel/irqinit.c +1 -1
@@ -91,7 +91,7 @@ void __init init_IRQ(void)for (i =0 ; i <nr_legacy_irqs (); i++)per_cpu (vector_irq,0 )[ISA_IRQ_VECTOR (i)] =irq_to_desc (i); -irq_ctx_init (smp_processor_id ()); +BUG_ON (irq_init_percpu_irqstack (smp_processor_id ())); x86_init.irqs.intr_init (); }
arch/x86/kernel/smpboot.c +12 -3
@@ -935,20 +935,27 @@ wakeup_cpu_via_init_nmi(int cpu, unsignereturn boot_error; } -void common_cpu_up (unsigned int cpu,struct task_struct *idle) +int common_cpu_up (unsigned int cpu,struct task_struct *idle) { +int ret; +/* Just in case we booted with a single CPU. */ alternatives_enable_smp ();per_cpu (current_task, cpu) = idle; +/* Initialize the interrupt stack(s) */ + ret =irq_init_percpu_irqstack (cpu); +if (ret) +return ret; +#ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ -irq_ctx_init (cpu);per_cpu (cpu_current_top_of_stack, cpu) =task_top_of_stack (idle);#else initial_gs =per_cpu_offset (cpu);#endif +return 0 ; }/*
@@ -1106,7 +1113,9 @@ int native_cpu_up(unsigned int cpu, stru/* the FPU context is blank, nobody can own it */ per_cpu (fpu_fpregs_owner_ctx, cpu) =NULL ; -common_cpu_up (cpu, tidle); + err =common_cpu_up (cpu, tidle); +if (err) +return err; err =do_boot_cpu (apicid, cpu, tidle, &cpu0_nmi_registered);if (err) {
arch/x86/xen/smp_pv.c +3 -1
@@ -361,7 +361,9 @@ static int xen_pv_cpu_up(unsigned int cp {int rc; -common_cpu_up (cpu, idle); + rc =common_cpu_up (cpu, idle); +if (rc) +return rc;xen_setup_runstate_info (cpu);
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/32: Handle irq stack allocation failure proper
x86/irq/32: Handle irq stack allocation failure proper
Commit-ID: 66c7ceb47f628c8bd4f84a6d01c2725ded6a342d Gitweb: https://git.kernel.org/tip/66c7ceb47f628c8bd4f84a6d01c2725ded6a342d Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:04 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:31:42 +0200
x86/irq/32: Handle irq stack allocation failure proper
irq_ctx_init() crashes hard on page allocation failures. While that's ok during early boot, it's just wrong in the CPU hotplug bringup code.
Check the page allocation failure and return -ENOMEM and handle it at the call sites. On early boot the only way out is to BUG(), but on CPU hotplug there is no reason to crash, so just abort the operation.
Rename the function to something more sensible while at it.
--- arch/x86/include/asm/irq.h | 4 ++-- arch/x86/include/asm/smp.h | 2 +- arch/x86/kernel/irq_32.c | 32 ++++++++++++++++---------------- arch/x86/kernel/irqinit.c | 2 +- arch/x86/kernel/smpboot.c | 15 ++++++++++++--- arch/x86/xen/smp_pv.c | 4 +++- 6 files changed, 35 insertions(+), 24 deletions(-)
arch/x86/include/asm/irq.h +2 -2
@@ -17,9 +17,9 @@ static inline int irq_canonicalize(int irq) }#ifdef CONFIG_X86_32 -extern void irq_ctx_init (int cpu); +extern int irq_init_percpu_irqstack (unsigned int cpu);#else -# define irq_ctx_init (cpu) do { } while (0) +static inline int irq_init_percpu_irqstack (unsigned int cpu) {return 0 ; }#endif #define __ARCH_HAS_DO_SOFTIRQ
arch/x86/include/asm/smp.h +1 -1
@@ -131,7 +131,7 @@ void native_smp_prepare_boot_cpu(void);void native_smp_prepare_cpus (unsigned int max_cpus);void calculate_max_logical_packages (void );void native_smp_cpus_done (unsigned int max_cpus); -void common_cpu_up (unsigned int cpunum,struct task_struct *tidle); +int common_cpu_up (unsigned int cpunum,struct task_struct *tidle);int native_cpu_up (unsigned int cpunum,struct task_struct *tidle);int native_cpu_disable (void );int common_cpu_die (unsigned int cpu);
arch/x86/kernel/irq_32.c +16 -16
@@ -107,28 +107,28 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) }/* -* allocate per-cpu stacks for hardirq and for softirq processing +* Allocate per-cpu stacks for hardirq and softirq processing */ -void irq_ctx_init (int cpu) +int irq_init_percpu_irqstack (unsigned int cpu) { -struct irq_stack *irqstk; +int node =cpu_to_node (cpu); +struct page *ph, *ps;if (per_cpu (hardirq_stack_ptr, cpu)) -return ; - - irqstk =page_address (alloc_pages_node (cpu_to_node (cpu), -THREADINFO_GFP , -THREAD_SIZE_ORDER )); -per_cpu (hardirq_stack_ptr, cpu) = irqstk; +return 0 ; - irqstk =page_address (alloc_pages_node (cpu_to_node (cpu), -THREADINFO_GFP , -THREAD_SIZE_ORDER )); -per_cpu (softirq_stack_ptr, cpu) = irqstk; + ph =alloc_pages_node (node,THREADINFO_GFP ,THREAD_SIZE_ORDER ); +if (!ph) +return -ENOMEM ; + ps =alloc_pages_node (node,THREADINFO_GFP ,THREAD_SIZE_ORDER ); +if (!ps) { +__free_pages (ph,THREAD_SIZE_ORDER ); +return -ENOMEM ; + } -pr_debug ("CPU %u irqstacks, hard=%p soft=%p\n" , - cpu,per_cpu (hardirq_stack_ptr, cpu), -per_cpu (softirq_stack_ptr, cpu)); +per_cpu (hardirq_stack_ptr, cpu) =page_address (ph); +per_cpu (softirq_stack_ptr, cpu) =page_address (ps); +return 0 ; }void do_softirq_own_stack (void )
arch/x86/kernel/irqinit.c +1 -1
@@ -91,7 +91,7 @@ void __init init_IRQ(void)for (i =0 ; i <nr_legacy_irqs (); i++)per_cpu (vector_irq,0 )[ISA_IRQ_VECTOR (i)] =irq_to_desc (i); -irq_ctx_init (smp_processor_id ()); +BUG_ON (irq_init_percpu_irqstack (smp_processor_id ())); x86_init.irqs.intr_init (); }
arch/x86/kernel/smpboot.c +12 -3
@@ -935,20 +935,27 @@ out:return boot_error; } -void common_cpu_up (unsigned int cpu,struct task_struct *idle) +int common_cpu_up (unsigned int cpu,struct task_struct *idle) { +int ret; +/* Just in case we booted with a single CPU. */ alternatives_enable_smp ();per_cpu (current_task, cpu) = idle; +/* Initialize the interrupt stack(s) */ + ret =irq_init_percpu_irqstack (cpu); +if (ret) +return ret; +#ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ -irq_ctx_init (cpu);per_cpu (cpu_current_top_of_stack, cpu) =task_top_of_stack (idle);#else initial_gs =per_cpu_offset (cpu);#endif +return 0 ; }/*
@@ -1106,7 +1113,9 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)/* the FPU context is blank, nobody can own it */ per_cpu (fpu_fpregs_owner_ctx, cpu) =NULL ; -common_cpu_up (cpu, tidle); + err =common_cpu_up (cpu, tidle); +if (err) +return err; err =do_boot_cpu (apicid, cpu, tidle, &cpu0_nmi_registered);if (err) {
arch/x86/xen/smp_pv.c +3 -1
@@ -361,7 +361,9 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) {int rc; -common_cpu_up (cpu, idle); + rc =common_cpu_up (cpu, idle); +if (rc) +return rc;xen_setup_runstate_info (cpu);
PATCH v3 29/32 x86/irq/64: Init hardirq_stack_ptr during CPU hotplug
In reply to Thomas GleixnerPreparatory change for distangling the irq stack union as a prerequisite for irq stacks with guard pages.
--- arch/x86/include/asm/irq.h | 4 ---- arch/x86/kernel/cpu/common.c | 4 +--- arch/x86/kernel/irq_64.c | 15 +++++++++++++++ 3 files changed, 16 insertions(+), 7 deletions(-)
arch/x86/include/asm/irq.h +0 -4
@@ -16,11 +16,7 @@ static inline int irq_canonicalize(int ireturn ((irq ==2 ) ?9 : irq); } -#ifdef CONFIG_X86_32 extern int irq_init_percpu_irqstack (unsigned int cpu); -#else -static inline int irq_init_percpu_irqstack (unsigned int cpu) {return 0 ; } -#endif #define __ARCH_HAS_DO_SOFTIRQ
arch/x86/kernel/cpu/common.c +1 -3
@@ -1510,9 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, cur &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, hardirq_stack_ptr) = -init_per_cpu_var (irq_stack_union.irq_stack) +IRQ_STACK_SIZE ; - +DEFINE_PER_CPU(char *, hardirq_stack_ptr); DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;DEFINE_PER_CPU (int, __preempt_count) =INIT_PREEMPT_COUNT ;
arch/x86/kernel/irq_64.c +15 -0
@@ -87,3 +87,18 @@ bool handle_irq(struct irq_desc *desc, sgeneric_handle_irq_desc (desc);return true; } + +static int map_irq_stack (unsigned int cpu) +{ +void *va =per_cpu_ptr (irq_stack_union.irq_stack, cpu); + +per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; +return 0 ; +} + +int irq_init_percpu_irqstack (unsigned int cpu) +{ +if (per_cpu (hardirq_stack_ptr, cpu)) +return 0 ; +return map_irq_stack (cpu); +}
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Init hardirq_stack_ptr during CPU hotplug
x86/irq/64: Init hardirq_stack_ptr during CPU hotplug
Commit-ID: 0ac26104208450d35c4e68754ce0c67b3a4d7802 Gitweb: https://git.kernel.org/tip/0ac26104208450d35c4e68754ce0c67b3a4d7802 Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:05 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:34:21 +0200
x86/irq/64: Init hardirq_stack_ptr during CPU hotplug
Preparatory change for disentangling the irq stack union as a prerequisite for irq stacks with guard pages.
--- arch/x86/include/asm/irq.h | 4 ---- arch/x86/kernel/cpu/common.c | 4 +--- arch/x86/kernel/irq_64.c | 15 +++++++++++++++ 3 files changed, 16 insertions(+), 7 deletions(-)
arch/x86/include/asm/irq.h +0 -4
@@ -16,11 +16,7 @@ static inline int irq_canonicalize(int irq)return ((irq ==2 ) ?9 : irq); } -#ifdef CONFIG_X86_32 extern int irq_init_percpu_irqstack (unsigned int cpu); -#else -static inline int irq_init_percpu_irqstack (unsigned int cpu) {return 0 ; } -#endif #define __ARCH_HAS_DO_SOFTIRQ
arch/x86/kernel/cpu/common.c +1 -3
@@ -1510,9 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, hardirq_stack_ptr) = -init_per_cpu_var (irq_stack_union.irq_stack) +IRQ_STACK_SIZE ; - +DEFINE_PER_CPU(char *, hardirq_stack_ptr); DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;DEFINE_PER_CPU (int, __preempt_count) =INIT_PREEMPT_COUNT ;
arch/x86/kernel/irq_64.c +15 -0
@@ -87,3 +87,18 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)generic_handle_irq_desc (desc);return true; } + +static int map_irq_stack (unsigned int cpu) +{ +void *va =per_cpu_ptr (irq_stack_union.irq_stack, cpu); + +per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; +return 0 ; +} + +int irq_init_percpu_irqstack (unsigned int cpu) +{ +if (per_cpu (hardirq_stack_ptr, cpu)) +return 0 ; +return map_irq_stack (cpu); +}
PATCH v3 30/32 x86/irq/64: Split the IRQ stack into its own pages
In reply to Thomas GleixnerFrom: Andy Lutomirski <[email protected]>
Currently the IRQ stack is hardcoded as the first page of the percpu area, and the stack canary lives on the IRQ stack. The former gets in the way of adding an IRQ stack guard page, and the latter is a potential weakness in the stack canary mechanism.
Split the IRQ stack into its own private percpu pages.
[ tglx: Make 64 and 32 bit share struct irq_stack ]
--- arch/x86/entry/entry_64.S | 4 ++-- arch/x86/include/asm/processor.h | 32 ++++++++++++++------------------ arch/x86/include/asm/stackprotector.h | 6 +++--- arch/x86/kernel/asm-offsets_64.c | 2 +- arch/x86/kernel/cpu/common.c | 8 ++++---- arch/x86/kernel/head_64.S | 2 +- arch/x86/kernel/irq_64.c | 5 ++++- arch/x86/kernel/setup_percpu.c | 5 ----- arch/x86/kernel/vmlinux.lds.S | 7 ++++--- arch/x86/tools/relocs.c | 2 +- arch/x86/xen/xen-head.S | 10 +++++----- 11 files changed, 39 insertions(+), 44 deletions(-)
arch/x86/entry/entry_64.S +2 -2
@@ -298,7 +298,7 @@ ENTRY(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movq TASK_stack_canary(%rsi), %rbx - movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset + movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset #endif #ifdef CONFIG_RETPOLINE
@@ -430,7 +430,7 @@ END(irq_entries_start) * it before we actually move ourselves to the IRQ stack. */ - movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8) + movq \old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8) movq PER_CPU_VAR(hardirq_stack_ptr), %rsp #ifdef CONFIG_DEBUG_ENTRY
arch/x86/include/asm/processor.h +14 -18
@@ -367,6 +367,13 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_#define __KERNEL_TSS_LIMIT \ (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) +/* Per CPU interrupt stacks */ +struct irq_stack { +char stack[IRQ_STACK_SIZE ]; +}__aligned(IRQ_STACK_SIZE) ; + +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +#ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);#else
@@ -375,28 +382,24 @@ DECLARE_PER_CPU(unsigned long, cpu_curre#endif #ifdef CONFIG_X86_64 -union irq_stack_union { -char irq_stack[IRQ_STACK_SIZE ]; +struct fixed_percpu_data {/* * GCC hardcodes the stack canary as %gs:40. Since the * irq_stack is the object at %gs:0, we reserve the bottom * 48 bytes of the irq stack for the canary. */ -struct { -char gs_base[40 ]; -unsigned long stack_canary; - }; +char gs_base[40 ]; +unsigned long stack_canary; }; -DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; -DECLARE_INIT_PER_CPU (irq_stack_union); +DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible; +DECLARE_INIT_PER_CPU (fixed_percpu_data);static inline unsigned long cpu_kernelmode_gs_base (int cpu) { -return (unsigned long )per_cpu (irq_stack_union.gs_base, cpu); +return (unsigned long )per_cpu (fixed_percpu_data.gs_base, cpu); } -DECLARE_PER_CPU(char *, hardirq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void);
@@ -418,14 +421,7 @@ struct stack_canary { }; DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);#endif -/* -* per-CPU IRQ handling stacks -*/ -struct irq_stack { -char stack[IRQ_STACK_SIZE ]; -}__aligned(IRQ_STACK_SIZE) ; - -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +/* Per CPU softirq stack pointer */ DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);#endif /* X86_64 */
arch/x86/include/asm/stackprotector.h +3 -3
@@ -13,7 +13,7 @@* On x86_64, %gs is shared by percpu area and stack canary. All * percpu symbols are zero based and %gs points to the base of percpu * area. The first occupant of the percpu area is always -* irq_stack_union which contains stack_canary at offset 40. Userland +* fixed_percpu_data which contains stack_canary at offset 40. Userland * %gs is always saved and restored on kernel entry and exit using * swapgs, so stack protector doesn't add any complexity there. *
@@ -64,7 +64,7 @@ static __always_inline void boot_init_stu64 tsc;#ifdef CONFIG_X86_64 -BUILD_BUG_ON (offsetof(union irq_stack_union , stack_canary) !=40 ); +BUILD_BUG_ON (offsetof(struct fixed_percpu_data , stack_canary) !=40 );#endif /* * We both use the random pool and the current TSC as a source
@@ -79,7 +79,7 @@ static __always_inline void boot_init_st current->stack_canary = canary;#ifdef CONFIG_X86_64 -this_cpu_write (irq_stack_union.stack_canary, canary); +this_cpu_write (fixed_percpu_data.stack_canary, canary);#else this_cpu_write (stack_canary.canary, canary);#endif
arch/x86/kernel/asm-offsets_64.c +1 -1
@@ -73,7 +73,7 @@ int main(void)BLANK ();#ifdef CONFIG_STACKPROTECTOR -DEFINE (stack_canary_offset, offsetof(union irq_stack_union , stack_canary)); +DEFINE (stack_canary_offset, offsetof(struct fixed_percpu_data , stack_canary));BLANK ();#endif
arch/x86/kernel/cpu/common.c +4 -4
@@ -1498,9 +1498,9 @@ static __init int setup_clearcpuid(char__setup ("clearcpuid=" , setup_clearcpuid);#ifdef CONFIG_X86_64 -DEFINE_PER_CPU_FIRST(union irq_stack_union, - irq_stack_union)__aligned(PAGE_SIZE) __visible; -EXPORT_PER_CPU_SYMBOL_GPL (irq_stack_union); +DEFINE_PER_CPU_FIRST(struct fixed_percpu_data, + fixed_percpu_data)__aligned(PAGE_SIZE) __visible; +EXPORT_PER_CPU_SYMBOL_GPL (fixed_percpu_data);/* * The following percpu variables are hot. Align current_task to
@@ -1510,7 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, cur &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, hardirq_stack_ptr); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;DEFINE_PER_CPU (int, __preempt_count) =INIT_PREEMPT_COUNT ;
arch/x86/kernel/head_64.S +1 -1
@@ -265,7 +265,7 @@ ENDPROC(start_cpu0) GLOBAL(initial_code) .quad x86_64_start_kernel GLOBAL(initial_gs) - .quad INIT_PER_CPU_VAR(irq_stack_union) + .quad INIT_PER_CPU_VAR(fixed_percpu_data) GLOBAL(initial_stack) /* * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
arch/x86/kernel/irq_64.c +4 -1
@@ -23,6 +23,9 @@#include <asm/io_apic.h> #include <asm/apic.h> +DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible; +DECLARE_INIT_PER_CPU (irq_stack_backing_store); +int sysctl_panic_on_stackoverflow;/*
@@ -90,7 +93,7 @@ bool handle_irq(struct irq_desc *desc, sstatic int map_irq_stack (unsigned int cpu) { -void *va =per_cpu_ptr (irq_stack_union.irq_stack, cpu); +void *va =per_cpu_ptr (&irq_stack_backing_store, cpu);per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ;return 0 ;
arch/x86/kernel/setup_percpu.c +0 -5
@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)per_cpu (x86_cpu_to_logical_apicid, cpu) =early_per_cpu_map (x86_cpu_to_logical_apicid, cpu);#endif -#ifdef CONFIG_X86_64 -per_cpu (hardirq_stack_ptr, cpu) = -per_cpu (irq_stack_union.irq_stack, cpu) + -IRQ_STACK_SIZE ; -#endif #ifdef CONFIG_NUMA per_cpu (x86_cpu_to_node_map, cpu) =early_per_cpu_map (x86_cpu_to_node_map, cpu);
arch/x86/kernel/vmlinux.lds.S +4 -3
@@ -403,7 +403,8 @@ SECTIONS */ #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load INIT_PER_CPU(gdt_page); -INIT_PER_CPU(irq_stack_union); +INIT_PER_CPU(fixed_percpu_data); +INIT_PER_CPU(irq_stack_backing_store); /* * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union); "kernel image bigger than KERNEL_IMAGE_SIZE"); #ifdef CONFIG_SMP -. = ASSERT((irq_stack_union == 0), - "irq_stack_union is not at start of per-cpu area"); +. = ASSERT((fixed_percpu_data == 0), + "fixed_percpu_data is not at start of per-cpu area"); #endif #endif /* CONFIG_X86_32 */
arch/x86/tools/relocs.c +1 -1
@@ -738,7 +738,7 @@ static void percpu_init(void)* __per_cpu_load * * The "gold" linker incorrectly associates: -* init_per_cpu__irq_stack_union +* init_per_cpu__fixed_percpu_data * init_per_cpu__gdt_page */ static int is_percpu_sym (ElfW (Sym) *sym,const char *symname)
arch/x86/xen/xen-head.S +5 -5
@@ -40,13 +40,13 @@ ENTRY(startup_xen) #ifdef CONFIG_X86_64 /* Set up %gs. * - * The base of %gs always points to the bottom of the irqstack - * union. If the stack protector canary is enabled, it is - * located at %gs:40. Note that, on SMP, the boot cpu uses - * init data section till per cpu areas are set up. + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx - movq $INIT_PER_CPU_VAR(irq_stack_union),%rax + movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax cdq wrmsr #endif
tip-bot for Andy Lutomirski
merge bot[tip:x86/irq] x86/irq/64: Split the IRQ stack into its own pages
x86/irq/64: Split the IRQ stack into its own pages
Commit-ID: e6401c13093173aad709a5c6de00cf8d692ee786 Gitweb: https://git.kernel.org/tip/e6401c13093173aad709a5c6de00cf8d692ee786 Author: Andy Lutomirski <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:06 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:37:02 +0200
x86/irq/64: Split the IRQ stack into its own pages
Currently, the IRQ stack is hardcoded as the first page of the percpu area, and the stack canary lives on the IRQ stack. The former gets in the way of adding an IRQ stack guard page, and the latter is a potential weakness in the stack canary mechanism.
Split the IRQ stack into its own private percpu pages.
[ tglx: Make 64 and 32 bit share struct irq_stack ]
--- arch/x86/entry/entry_64.S | 4 ++-- arch/x86/include/asm/processor.h | 32 ++++++++++++++------------------ arch/x86/include/asm/stackprotector.h | 6 +++--- arch/x86/kernel/asm-offsets_64.c | 2 +- arch/x86/kernel/cpu/common.c | 8 ++++---- arch/x86/kernel/head_64.S | 2 +- arch/x86/kernel/irq_64.c | 5 ++++- arch/x86/kernel/setup_percpu.c | 5 ----- arch/x86/kernel/vmlinux.lds.S | 7 ++++--- arch/x86/tools/relocs.c | 2 +- arch/x86/xen/xen-head.S | 10 +++++----- 11 files changed, 39 insertions(+), 44 deletions(-)
arch/x86/entry/entry_64.S +2 -2
@@ -298,7 +298,7 @@ ENTRY(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movq TASK_stack_canary(%rsi), %rbx - movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset + movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset #endif #ifdef CONFIG_RETPOLINE
@@ -430,7 +430,7 @@ END(irq_entries_start) * it before we actually move ourselves to the IRQ stack. */ - movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8) + movq \old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8) movq PER_CPU_VAR(hardirq_stack_ptr), %rsp #ifdef CONFIG_DEBUG_ENTRY
arch/x86/include/asm/processor.h +14 -18
@@ -367,6 +367,13 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);#define __KERNEL_TSS_LIMIT \ (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) +/* Per CPU interrupt stacks */ +struct irq_stack { +char stack[IRQ_STACK_SIZE ]; +}__aligned(IRQ_STACK_SIZE) ; + +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +#ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);#else
@@ -375,28 +382,24 @@ DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);#endif #ifdef CONFIG_X86_64 -union irq_stack_union { -char irq_stack[IRQ_STACK_SIZE ]; +struct fixed_percpu_data {/* * GCC hardcodes the stack canary as %gs:40. Since the * irq_stack is the object at %gs:0, we reserve the bottom * 48 bytes of the irq stack for the canary. */ -struct { -char gs_base[40 ]; -unsigned long stack_canary; - }; +char gs_base[40 ]; +unsigned long stack_canary; }; -DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; -DECLARE_INIT_PER_CPU (irq_stack_union); +DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible; +DECLARE_INIT_PER_CPU (fixed_percpu_data);static inline unsigned long cpu_kernelmode_gs_base (int cpu) { -return (unsigned long )per_cpu (irq_stack_union.gs_base, cpu); +return (unsigned long )per_cpu (fixed_percpu_data.gs_base, cpu); } -DECLARE_PER_CPU(char *, hardirq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); extern asmlinkage void ignore_sysret(void);
@@ -418,14 +421,7 @@ struct stack_canary { }; DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);#endif -/* -* per-CPU IRQ handling stacks -*/ -struct irq_stack { -char stack[IRQ_STACK_SIZE ]; -}__aligned(IRQ_STACK_SIZE) ; - -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); +/* Per CPU softirq stack pointer */ DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);#endif /* X86_64 */
arch/x86/include/asm/stackprotector.h +3 -3
@@ -13,7 +13,7 @@* On x86_64, %gs is shared by percpu area and stack canary. All * percpu symbols are zero based and %gs points to the base of percpu * area. The first occupant of the percpu area is always -* irq_stack_union which contains stack_canary at offset 40. Userland +* fixed_percpu_data which contains stack_canary at offset 40. Userland * %gs is always saved and restored on kernel entry and exit using * swapgs, so stack protector doesn't add any complexity there. *
@@ -64,7 +64,7 @@ static __always_inline void boot_init_stack_canary(void)u64 tsc;#ifdef CONFIG_X86_64 -BUILD_BUG_ON (offsetof(union irq_stack_union , stack_canary) !=40 ); +BUILD_BUG_ON (offsetof(struct fixed_percpu_data , stack_canary) !=40 );#endif /* * We both use the random pool and the current TSC as a source
@@ -79,7 +79,7 @@ static __always_inline void boot_init_stack_canary(void) current->stack_canary = canary;#ifdef CONFIG_X86_64 -this_cpu_write (irq_stack_union.stack_canary, canary); +this_cpu_write (fixed_percpu_data.stack_canary, canary);#else this_cpu_write (stack_canary.canary, canary);#endif
arch/x86/kernel/asm-offsets_64.c +1 -1
@@ -73,7 +73,7 @@ int main(void)BLANK ();#ifdef CONFIG_STACKPROTECTOR -DEFINE (stack_canary_offset, offsetof(union irq_stack_union , stack_canary)); +DEFINE (stack_canary_offset, offsetof(struct fixed_percpu_data , stack_canary));BLANK ();#endif
arch/x86/kernel/cpu/common.c +4 -4
@@ -1498,9 +1498,9 @@ static __init int setup_clearcpuid(char *arg)__setup ("clearcpuid=" , setup_clearcpuid);#ifdef CONFIG_X86_64 -DEFINE_PER_CPU_FIRST(union irq_stack_union, - irq_stack_union)__aligned(PAGE_SIZE) __visible; -EXPORT_PER_CPU_SYMBOL_GPL (irq_stack_union); +DEFINE_PER_CPU_FIRST(struct fixed_percpu_data, + fixed_percpu_data)__aligned(PAGE_SIZE) __visible; +EXPORT_PER_CPU_SYMBOL_GPL (fixed_percpu_data);/* * The following percpu variables are hot. Align current_task to
@@ -1510,7 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task;EXPORT_PER_CPU_SYMBOL (current_task); -DEFINE_PER_CPU(char *, hardirq_stack_ptr); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;DEFINE_PER_CPU (int, __preempt_count) =INIT_PREEMPT_COUNT ;
arch/x86/kernel/head_64.S +1 -1
@@ -265,7 +265,7 @@ ENDPROC(start_cpu0) GLOBAL(initial_code) .quad x86_64_start_kernel GLOBAL(initial_gs) - .quad INIT_PER_CPU_VAR(irq_stack_union) + .quad INIT_PER_CPU_VAR(fixed_percpu_data) GLOBAL(initial_stack) /* * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
arch/x86/kernel/irq_64.c +4 -1
@@ -23,6 +23,9 @@#include <asm/io_apic.h> #include <asm/apic.h> +DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible; +DECLARE_INIT_PER_CPU (irq_stack_backing_store); +int sysctl_panic_on_stackoverflow;/*
@@ -90,7 +93,7 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)static int map_irq_stack (unsigned int cpu) { -void *va =per_cpu_ptr (irq_stack_union.irq_stack, cpu); +void *va =per_cpu_ptr (&irq_stack_backing_store, cpu);per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ;return 0 ;
arch/x86/kernel/setup_percpu.c +0 -5
@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)per_cpu (x86_cpu_to_logical_apicid, cpu) =early_per_cpu_map (x86_cpu_to_logical_apicid, cpu);#endif -#ifdef CONFIG_X86_64 -per_cpu (hardirq_stack_ptr, cpu) = -per_cpu (irq_stack_union.irq_stack, cpu) + -IRQ_STACK_SIZE ; -#endif #ifdef CONFIG_NUMA per_cpu (x86_cpu_to_node_map, cpu) =early_per_cpu_map (x86_cpu_to_node_map, cpu);
arch/x86/kernel/vmlinux.lds.S +4 -3
@@ -403,7 +403,8 @@ SECTIONS */ #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load INIT_PER_CPU(gdt_page); -INIT_PER_CPU(irq_stack_union); +INIT_PER_CPU(fixed_percpu_data); +INIT_PER_CPU(irq_stack_backing_store); /* * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union); "kernel image bigger than KERNEL_IMAGE_SIZE"); #ifdef CONFIG_SMP -. = ASSERT((irq_stack_union == 0), - "irq_stack_union is not at start of per-cpu area"); +. = ASSERT((fixed_percpu_data == 0), + "fixed_percpu_data is not at start of per-cpu area"); #endif #endif /* CONFIG_X86_32 */
arch/x86/tools/relocs.c +1 -1
@@ -738,7 +738,7 @@ static void percpu_init(void)* __per_cpu_load * * The "gold" linker incorrectly associates: -* init_per_cpu__irq_stack_union +* init_per_cpu__fixed_percpu_data * init_per_cpu__gdt_page */ static int is_percpu_sym (ElfW (Sym) *sym,const char *symname)
arch/x86/xen/xen-head.S +5 -5
@@ -40,13 +40,13 @@ ENTRY(startup_xen) #ifdef CONFIG_X86_64 /* Set up %gs. * - * The base of %gs always points to the bottom of the irqstack - * union. If the stack protector canary is enabled, it is - * located at %gs:40. Note that, on SMP, the boot cpu uses - * init data section till per cpu areas are set up. + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx - movq $INIT_PER_CPU_VAR(irq_stack_union),%rax + movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax cdq wrmsr #endif
PATCH v3 31/32 x86/irq/64: Remap the IRQ stack with guard pages
In reply to Thomas GleixnerFrom: Andy Lutomirski <[email protected]>
The IRQ stack lives in percpu space, so an IRQ handler that overflows it will overwrite other data structures.
Use vmap() to remap the IRQ stack so that it will have the usual guard pages that vmap/vmalloc allocations have. With this the kernel will panic immediately on an IRQ stack overflow.
[ tglx: Move the map code to a proper place and invoke it only when a CPU
is about to be brought online. No point in installing the map at early boot for all possible CPUs. Fail the CPU bringup if the vmap fails as done for all other preparatory stages in cpu hotplug. ]
--- arch/x86/kernel/irq_64.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+)
arch/x86/kernel/irq_64.c +30 -0
@@ -91,6 +91,35 @@ bool handle_irq(struct irq_desc *desc, sreturn true; } +#ifdef CONFIG_VMAP_STACK +/* +* VMAP the backing store with guard pages +*/ +static int map_irq_stack (unsigned int cpu) +{ +char *stack = (char *)per_cpu_ptr (&irq_stack_backing_store, cpu); +struct page *pages[IRQ_STACK_SIZE /PAGE_SIZE ]; +void *va; +int i; + +for (i =0 ; i <IRQ_STACK_SIZE /PAGE_SIZE ; i++) { +phys_addr_t pa =per_cpu_ptr_to_phys (stack + (i <<PAGE_SHIFT )); + + pages[i] =pfn_to_page (pa >>PAGE_SHIFT ); + } + + va =vmap (pages,IRQ_STACK_SIZE /PAGE_SIZE ,GFP_KERNEL ,PAGE_KERNEL ); +if (!va) +return -ENOMEM ; + +per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; +return 0 ; +} +#else +/* +* If VMAP stacks are disabled due to KASAN, just use the per cpu +* backing store without guard pages. +*/ static int map_irq_stack (unsigned int cpu) {void *va =per_cpu_ptr (&irq_stack_backing_store, cpu);
@@ -98,6 +127,7 @@ static int map_irq_stack(unsigned int cpper_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; return 0; } +#endif int irq_init_percpu_irqstack (unsigned int cpu) {
tip-bot for Andy Lutomirski
merge bot[tip:x86/irq] x86/irq/64: Remap the IRQ stack with guard pages
x86/irq/64: Remap the IRQ stack with guard pages
Commit-ID: 18b7a6bef62de1d598fbff23b52114b7775ecf00 Gitweb: https://git.kernel.org/tip/18b7a6bef62de1d598fbff23b52114b7775ecf00 Author: Andy Lutomirski <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:07 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:40:57 +0200
x86/irq/64: Remap the IRQ stack with guard pages
The IRQ stack lives in percpu space, so an IRQ handler that overflows it will overwrite other data structures.
Use vmap() to remap the IRQ stack so that it will have the usual guard pages that vmap()/vmalloc() allocations have. With this, the kernel will panic immediately on an IRQ stack overflow.
[ tglx: Move the map code to a proper place and invoke it only when a CPU
is about to be brought online. No point in installing the map at early boot for all possible CPUs. Fail the CPU bringup if the vmap() fails as done for all other preparatory stages in CPU hotplug. ]
--- arch/x86/kernel/irq_64.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+)
arch/x86/kernel/irq_64.c +30 -0
@@ -91,6 +91,35 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)return true; } +#ifdef CONFIG_VMAP_STACK +/* +* VMAP the backing store with guard pages +*/ +static int map_irq_stack (unsigned int cpu) +{ +char *stack = (char *)per_cpu_ptr (&irq_stack_backing_store, cpu); +struct page *pages[IRQ_STACK_SIZE /PAGE_SIZE ]; +void *va; +int i; + +for (i =0 ; i <IRQ_STACK_SIZE /PAGE_SIZE ; i++) { +phys_addr_t pa =per_cpu_ptr_to_phys (stack + (i <<PAGE_SHIFT )); + + pages[i] =pfn_to_page (pa >>PAGE_SHIFT ); + } + + va =vmap (pages,IRQ_STACK_SIZE /PAGE_SIZE ,GFP_KERNEL ,PAGE_KERNEL ); +if (!va) +return -ENOMEM ; + +per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; +return 0 ; +} +#else +/* +* If VMAP stacks are disabled due to KASAN, just use the per cpu +* backing store without guard pages. +*/ static int map_irq_stack (unsigned int cpu) {void *va =per_cpu_ptr (&irq_stack_backing_store, cpu);
@@ -98,6 +127,7 @@ static int map_irq_stack(unsigned int cpu)per_cpu (hardirq_stack_ptr, cpu) = va +IRQ_STACK_SIZE ; return 0; } +#endif int irq_init_percpu_irqstack (unsigned int cpu) {
PATCH v3 32/32 x86/irq/64: Remove stack overflow debug code
In reply to Thomas GleixnerAll stack types on x86 64-bit have guard pages now.
So there is no point in executing probabilistic overflow checks as the guard pages are a accurate and reliable overflow prevention.
--- arch/x86/Kconfig | 2 - arch/x86/kernel/irq_64.c | 56 ----------------------------------------------- 2 files changed, 1 insertion(+), 57 deletions(-)
arch/x86/Kconfig +1 -1
@@ -14,6 +14,7 @@ config X86_32 select ARCH_WANT_IPC_PARSE_VERSION select CLKSRC_I8253 select CLONE_BACKWARDS + select HAVE_DEBUG_STACKOVERFLOW select MODULES_USE_ELF_REL select OLD_SIGACTION
@@ -138,7 +139,6 @@ config X86 select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK - select HAVE_DEBUG_STACKOVERFLOW select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS
arch/x86/kernel/irq_64.c +0 -56
64 lines not on this page · raw message
tip-bot for Thomas Gleixner
merge bot[tip:x86/irq] x86/irq/64: Remove stack overflow debug code
x86/irq/64: Remove stack overflow debug code
Commit-ID: 117ed45485413b1977bfc638c32bf5b01d53c62b Gitweb: https://git.kernel.org/tip/117ed45485413b1977bfc638c32bf5b01d53c62b Author: Thomas Gleixner <[email protected]> AuthorDate: Sun, 14 Apr 2019 18:00:08 +0200 Committer: Borislav Petkov <[email protected]> CommitDate: Wed, 17 Apr 2019 15:41:48 +0200
x86/irq/64: Remove stack overflow debug code
All stack types on x86 64-bit have guard pages now.
So there is no point in executing probabilistic overflow checks as the guard pages are a accurate and reliable overflow prevention.
--- arch/x86/Kconfig | 2 +- arch/x86/kernel/irq_64.c | 56 ------------------------------------------------ 2 files changed, 1 insertion(+), 57 deletions(-)
arch/x86/Kconfig +1 -1
@@ -14,6 +14,7 @@ config X86_32 select ARCH_WANT_IPC_PARSE_VERSION select CLKSRC_I8253 select CLONE_BACKWARDS + select HAVE_DEBUG_STACKOVERFLOW select MODULES_USE_ELF_REL select OLD_SIGACTION
@@ -138,7 +139,6 @@ config X86 select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK - select HAVE_DEBUG_STACKOVERFLOW select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS
arch/x86/kernel/irq_64.c +0 -56
64 lines not on this page · raw message