Merge branch 'x86/entry' into ras/core

to fixup conflicts in arch/x86/kernel/cpu/mce/core.c so MCE specific follow
up patches can be applied without creating a horrible merge conflict
afterwards.

1 files changed, 70 insertions, 41 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 84af6c8eecf7..641fc5f3d7dd 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -35,24 +35,24 @@
 
 #include <asm/firmware.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
 #include <asm/kup.h>
+#include <asm/inst.h>
 
 /*
  * Check whether the instruction inst is a store using
  * an update addressing form which will update r1.
  */
-static bool store_updates_sp(unsigned int inst)
+static bool store_updates_sp(struct ppc_inst inst)
 {
 	/* check for 1 in the rA field */
-	if (((inst >> 16) & 0x1f) != 1)
+	if (((ppc_inst_val(inst) >> 16) & 0x1f) != 1)
 		return false;
 	/* check major opcode */
-	switch (inst >> 26) {
+	switch (ppc_inst_primary_opcode(inst)) {
 	case OP_STWU:
 	case OP_STBU:
 	case OP_STHU:
@@ -60,10 +60,10 @@ static bool store_updates_sp(unsigned int inst)
 	case OP_STFDU:
 		return true;
 	case OP_STD:	/* std or stdu */
-		return (inst & 3) == 1;
+		return (ppc_inst_val(inst) & 3) == 1;
 	case OP_31:
 		/* check minor opcode */
-		switch ((inst >> 1) & 0x3ff) {
+		switch ((ppc_inst_val(inst) >> 1) & 0x3ff) {
 		case OP_31_XOP_STDUX:
 		case OP_31_XOP_STWUX:
 		case OP_31_XOP_STBUX:
@@ -108,7 +108,7 @@ static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
 	 * Something tried to access memory that isn't in our memory map..
 	 * Fix it, but check if it's kernel or user first..
 	 */
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return __bad_area_nosemaphore(regs, address, si_code);
 }
@@ -118,9 +118,34 @@ static noinline int bad_area(struct pt_regs *regs, unsigned long address)
 	return __bad_area(regs, address, SEGV_MAPERR);
 }
 
-static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
-				    int pkey)
+#ifdef CONFIG_PPC_MEM_KEYS
+static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
+				    struct vm_area_struct *vma)
 {
+	struct mm_struct *mm = current->mm;
+	int pkey;
+
+	/*
+	 * We don't try to fetch the pkey from page table because reading
+	 * page table without locking doesn't guarantee stable pte value.
+	 * Hence the pkey value that we return to userspace can be different
+	 * from the pkey that actually caused access error.
+	 *
+	 * It does *not* guarantee that the VMA we find here
+	 * was the one that we faulted on.
+	 *
+	 * 1. T1   : mprotect_key(foo, PAGE_SIZE, pkey=4);
+	 * 2. T1   : set AMR to deny access to pkey=4, touches, page
+	 * 3. T1   : faults...
+	 * 4.    T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
+	 * 5. T1   : enters fault handler, takes mmap_lock, etc...
+	 * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
+	 *	     faulted on a pte with its pkey=4.
+	 */
+	pkey = vma_pkey(vma);
+
+	mmap_read_unlock(mm);
+
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
 	 * be caught by the assembly which will restore the non-volatile
@@ -133,6 +158,7 @@ static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
 
 	return 0;
 }
+#endif
 
 static noinline int bad_access(struct pt_regs *regs, unsigned long address)
 {
@@ -255,7 +281,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 	 * expand to 1MB without further checks.
 	 */
 	if (address + 0x100000 < vma->vm_end) {
-		unsigned int __user *nip = (unsigned int __user *)regs->nip;
+		struct ppc_inst __user *nip = (struct ppc_inst __user *)regs->nip;
 		/* get user regs even if this fault is in kernel mode */
 		struct pt_regs *uregs = current->thread.regs;
 		if (uregs == NULL)
@@ -278,9 +304,9 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 
 		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
 		    access_ok(nip, sizeof(*nip))) {
-			unsigned int inst;
+			struct ppc_inst inst;
 
-			if (!probe_user_read(&inst, nip, sizeof(inst)))
+			if (!probe_user_read_inst(&inst, nip))
 				return !store_updates_sp(inst);
 			*must_retry = true;
 		}
@@ -289,8 +315,23 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 	return false;
 }
 
-static bool access_error(bool is_write, bool is_exec,
-			 struct vm_area_struct *vma)
+#ifdef CONFIG_PPC_MEM_KEYS
+static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
+			      struct vm_area_struct *vma)
+{
+	/*
+	 * Make sure to check the VMA so that we do not perform
+	 * faults just to hit a pkey fault as soon as we fill in a
+	 * page. Only called for current mm, hence foreign == 0
+	 */
+	if (!arch_vma_access_permitted(vma, is_write, is_exec, 0))
+		return true;
+
+	return false;
+}
+#endif
+
+static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma)
 {
 	/*
 	 * Allow execution from readable areas if the MMU does not
@@ -483,14 +524,10 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
-	if (error_code & DSISR_KEYFAULT)
-		return bad_key_fault_exception(regs, address,
-					       get_mm_addr_key(mm, address));
-
 	/*
-	 * We want to do this outside mmap_sem, because reading code around nip
+	 * We want to do this outside mmap_lock, because reading code around nip
 	 * can result in fault, which will cause a deadlock when called with
-	 * mmap_sem held
+	 * mmap_lock held
 	 */
 	if (is_user)
 		flags |= FAULT_FLAG_USER;
@@ -502,7 +539,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
-	 * erroneous fault occurring in a code path which already holds mmap_sem
+	 * erroneous fault occurring in a code path which already holds mmap_lock
 	 * we will deadlock attempting to validate the fault against the
 	 * address space.  Luckily the kernel only validly references user
 	 * space from well defined areas of code, which are listed in the
@@ -514,12 +551,12 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * source.  If this is invalid we can skip the address space check,
 	 * thus avoiding the deadlock.
 	 */
-	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+	if (unlikely(!mmap_read_trylock(mm))) {
 		if (!is_user && !search_exception_tables(regs->nip))
 			return bad_area_nosemaphore(regs, address);
 
 retry:
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 	} else {
 		/*
 		 * The above down_read_trylock() might have succeeded in
@@ -543,7 +580,7 @@ retry:
 		if (!must_retry)
 			return bad_area(regs, address);
 
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		if (fault_in_pages_readable((const char __user *)regs->nip,
 					    sizeof(unsigned int)))
 			return bad_area_nosemaphore(regs, address);
@@ -555,6 +592,13 @@ retry:
 		return bad_area(regs, address);
 
 good_area:
+
+#ifdef CONFIG_PPC_MEM_KEYS
+	if (unlikely(access_pkey_error(is_write, is_exec,
+				       (error_code & DSISR_KEYFAULT), vma)))
+		return bad_access_pkey(regs, address, vma);
+#endif /* CONFIG_PPC_MEM_KEYS */
+
 	if (unlikely(access_error(is_write, is_exec, vma)))
 		return bad_access(regs, address);
 
@@ -565,28 +609,13 @@ good_area:
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-#ifdef CONFIG_PPC_MEM_KEYS
-	/*
-	 * we skipped checking for access error due to key earlier.
-	 * Check that using handle_mm_fault error return.
-	 */
-	if (unlikely(fault & VM_FAULT_SIGSEGV) &&
-		!arch_vma_access_permitted(vma, is_write, is_exec, 0)) {
-
-		int pkey = vma_pkey(vma);
-
-		up_read(&mm->mmap_sem);
-		return bad_key_fault_exception(regs, address, pkey);
-	}
-#endif /* CONFIG_PPC_MEM_KEYS */
-
 	major |= fault & VM_FAULT_MAJOR;
 
 	if (fault_signal_pending(fault, regs))
 		return user_mode(regs) ? 0 : SIGBUS;
 
 	/*
-	 * Handle the retry right now, the mmap_sem has been released in that
+	 * Handle the retry right now, the mmap_lock has been released in that
 	 * case.
 	 */
 	if (unlikely(fault & VM_FAULT_RETRY)) {
@@ -596,7 +625,7 @@ good_area:
 		}
 	}
 
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	if (unlikely(fault & VM_FAULT_ERROR))
 		return mm_fault_error(regs, address, fault);