vm: add VM_FAULT_SIGSEGV handling support

commit 33692f27597fcab536d7cbbcc8f52905133e4aa7 upstream.

The core VM already knows about VM_FAULT_SIGBUS, but cannot return a
"you should SIGSEGV" error, because the SIGSEGV case was generally
handled by the caller - usually the architecture fault handler.

That results in lots of duplication - all the architecture fault
handlers end up doing very similar "look up vma, check permissions, do
retries etc" - but it generally works.  However, there are cases where
the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV.

In particular, when accessing the stack guard page, libsigsegv expects a
SIGSEGV.  And it usually got one, because the stack growth is handled by
that duplicated architecture fault handler.

However, when the generic VM layer started propagating the error return
from the stack expansion in commit fee7e49d4514 ("mm: propagate error
from stack expansion even for guard page"), that now exposed the
existing VM_FAULT_SIGBUS result to user space.  And user space really
expected SIGSEGV, not SIGBUS.

To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those
duplicate architecture fault handlers about it.  They all already have
the code to handle SIGSEGV, so it's about just tying that new return
value to the existing code, but it's all a bit annoying.

This is the mindless minimal patch to do this.  A more extensive patch
would be to try to gather up the mostly shared fault handling logic into
one generic helper routine, and long-term we really should do that
cleanup.

Just from this patch, you can generally see that most architectures just
copied (directly or indirectly) the old x86 way of doing things, but in
the meantime that original x86 model has been improved to hold the VM
semaphore for shorter times etc and to handle VM_FAULT_RETRY and other
"newer" things, so it would be a good idea to bring all those
improvements to the generic case and teach other architectures about
them too.

Reported-and-tested-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Jan Engelhardt <jengelh@inai.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots"
Cc: linux-arch@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.2:
 - Adjust filenames, context
 - Drop arc, metag, nios2 and lustre changes
 - For sh, patch both 32-bit and 64-bit implementations to use goto bad_area
 - For s390, pass int_code and trans_exc_code as arguments to do_no_context()
   and do_sigsegv()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
[lizf: Backported to 3.4:
 - adjust context in arch/power/mm/fault.c
 - apply the original change in upstream commit for s390]
Signed-off-by: Zefan Li <lizefan@huawei.com>

27 files changed, 60 insertions, 7 deletions

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 5eecab1a84ef..f153733fb938 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -149,6 +149,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index f7040a1e399f..632b649c7be0 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -136,6 +136,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index b4760d86e1bb..b07c00c01696 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -167,6 +167,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2cfb67..854549617dd2 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -166,6 +166,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 02d29c2a132a..3c820ea4212f 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -162,6 +162,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 		 */
 		if (fault & VM_FAULT_OOM) {
 			goto out_of_memory;
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			goto bad_area;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			signal = SIGBUS;
 			goto bad_area;
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c1d091..06827fc92bbf 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -198,6 +198,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 6b020a8461e7..8646409adf5b 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -146,6 +146,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto map_err;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bus_err;
 		BUG();
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index c38a265846de..c7fe3da48593 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -214,6 +214,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index c14f6dfed995..5c9ba6a536d1 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -155,6 +155,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 90f346f7392d..eb411b3cd7e9 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -255,6 +255,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index a5dce82f864b..162abfbced69 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -163,6 +163,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 18162ce4261e..a9b765a999ef 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -210,6 +210,8 @@ good_area:
 		 */
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bad_area;
 		BUG();
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 08ffcf52a856..3d30a4af627f 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -419,7 +419,11 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		int rc = mm_fault_error(regs, address, fault);
+		int rc;
+
+		if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
+		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			return rc;
 	}
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c
index 641e7273d75a..62f3e4e48a0b 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/platforms/cell/spu_fault.c
@@ -75,7 +75,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
 			goto out_unlock;
-		} else if (*flt & VM_FAULT_SIGBUS) {
+		} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index f2b11ee3fb3a..68ba1bb834bb 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -237,6 +237,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			/* Kernel mode? Handle exceptions or die */
+			if (!user_mode(regs))
+				do_no_context(regs);
+			else
+				do_sigsegv(regs, SEGV_MAPERR);
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!(regs->psw.mask & PSW_MASK_PSTATE))
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 47b600e4b2c5..b3744ca70be6 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -110,6 +110,8 @@ survive:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index e99b104d967a..a4919631ce03 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -206,6 +206,8 @@ good_area:
 			goto out_of_memory;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		BUG();
 	}
 	if (fault & VM_FAULT_MAJOR) {
diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c
index 11c5a18f10ed..92f0df95cf83 100644
--- a/arch/sh/mm/tlbflush_64.c
+++ b/arch/sh/mm/tlbflush_64.c
@@ -194,6 +194,8 @@ good_area:
 			goto out_of_memory;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		BUG();
 	}
 
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index df3155a17991..5c6238d72076 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -300,6 +300,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 1387acafc62c..0dc7b9094a29 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -443,6 +443,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 22e58f51ed23..a362926d513a 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -433,6 +433,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index dafc94715950..f79ffc901d0e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -69,6 +69,8 @@ good_area:
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
 			} else if (fault & VM_FAULT_SIGBUS) {
 				err = -EACCES;
 				goto out;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4a0a2e810b4b..b723f2e09f44 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -887,6 +887,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index b17885a0b508..b3877be25ab3 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -108,6 +108,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dacfd4a31788..ceebf63ef5da 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -841,6 +841,7 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
 #define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
 #define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
+#define VM_FAULT_SIGSEGV 0x0040
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
@@ -848,8 +849,8 @@ static inline int page_mapped(struct page *page)
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_HWPOISON_LARGE)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
+			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
diff --git a/mm/ksm.c b/mm/ksm.c
index 47c885368890..77c71185fb79 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -342,7 +342,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
-	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
 	/*
 	 * We must loop because handle_mm_fault() may back out if there's
 	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
diff --git a/mm/memory.c b/mm/memory.c
index c9c93e238ce4..f573cecf3583 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1787,7 +1787,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 						else
 							return -EFAULT;
 					}
-					if (ret & VM_FAULT_SIGBUS)
+					if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 						return i ? i : -EFAULT;
 					BUG();
 				}
@@ -1891,7 +1891,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return -EHWPOISON;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}