1 files changed, 25 insertions, 34 deletions

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c9cedc0432d2..f07333e86c2f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -36,7 +36,6 @@
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 
@@ -145,6 +144,7 @@ static void show_pte(unsigned long addr)
 	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
 
 	do {
+		p4d_t *p4dp, p4d;
 		pud_t *pudp, pud;
 		pmd_t *pmdp, pmd;
 		pte_t *ptep, pte;
@@ -152,7 +152,13 @@ static void show_pte(unsigned long addr)
 		if (pgd_none(pgd) || pgd_bad(pgd))
 			break;
 
-		pudp = pud_offset(pgdp, addr);
+		p4dp = p4d_offset(pgdp, addr);
+		p4d = READ_ONCE(*p4dp);
+		pr_cont(", p4d=%016llx", p4d_val(p4d));
+		if (p4d_none(p4d) || p4d_bad(p4d))
+			break;
+
+		pudp = pud_offset(p4dp, addr);
 		pud = READ_ONCE(*pudp);
 		pr_cont(", pud=%016llx", pud_val(pud));
 		if (pud_none(pud) || pud_bad(pud))
@@ -398,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADACCESS	0x020000
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
-			   unsigned int mm_flags, unsigned long vm_flags)
+				  unsigned int mm_flags, unsigned long vm_flags,
+				  struct pt_regs *regs)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 
@@ -422,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -444,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	const struct fault_info *inf;
 	struct mm_struct *mm = current->mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned long vm_flags = VM_ACCESS_FLAGS;
 	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
 
@@ -491,11 +498,11 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * validly references user space from well defined areas of the code,
 	 * we can bug out early if this is from code which shouldn't.
 	 */
-	if (!down_read_trylock(&mm->mmap_sem)) {
+	if (!mmap_read_trylock(mm)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->pc))
 			goto no_context;
 retry:
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 	} else {
 		/*
 		 * The above down_read_trylock() might have succeeded in which
@@ -504,14 +511,13 @@ retry:
 		might_sleep();
 #ifdef CONFIG_DEBUG_VM
 		if (!user_mode(regs) && !search_exception_tables(regs->pc)) {
-			up_read(&mm->mmap_sem);
+			mmap_read_unlock(mm);
 			goto no_context;
 		}
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, mm_flags, vm_flags);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -526,31 +532,14 @@ retry:
 			goto retry;
 		}
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/*
 	 * Handle the "normal" (no error) case first.
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS)))) {
-		/*
-		 * Major/minor page fault accounting is only done
-		 * once. If we go through a retry, it is extremely
-		 * likely that the page will be found in page cache at
-		 * that point.
-		 */
-		if (major) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-				      addr);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-				      addr);
-		}
-
+			      VM_FAULT_BADACCESS))))
 		return 0;
-	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
@@ -635,11 +624,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 
 	inf = esr_to_fault_info(esr);
 
-	/*
-	 * Return value ignored as we rely on signal merging.
-	 * Future patches will make this more robust.
-	 */
-	apei_claim_sea(regs);
+	if (user_mode(regs) && apei_claim_sea(regs) == 0) {
+		/*
+		 * APEI claimed this as a firmware-first notification.
+		 * Some processing deferred to task_work before ret_to_user().
+		 */
+		return 0;
+	}
 
 	if (esr & ESR_ELx_FnV)
 		siaddr = NULL;