1 files changed, 86 insertions, 109 deletions

diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28affa9..06e6b4952924 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -13,41 +13,21 @@
  */
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/hardirq.h>
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 #include <asm/io_trapped.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	int ret = 0;
-
-	if (kprobes_built_in() && !user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, trap))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-
 static void
-force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk)
+force_sig_info_fault(int si_signo, int si_code, unsigned long address)
 {
-	siginfo_t info;
-
-	info.si_signo	= si_signo;
-	info.si_errno	= 0;
-	info.si_code	= si_code;
-	info.si_addr	= (void __user *)address;
-
-	force_sig_info(si_signo, &info, tsk);
+	force_sig_fault(si_signo, si_code, (void __user *)address);
 }
 
 /*
@@ -67,12 +47,13 @@ static void show_pte(struct mm_struct *mm, unsigned long addr)
 			pgd = swapper_pg_dir;
 	}
 
-	printk(KERN_ALERT "pgd = %p\n", pgd);
+	pr_alert("pgd = %p\n", pgd);
 	pgd += pgd_index(addr);
-	printk(KERN_ALERT "[%08lx] *pgd=%0*Lx", addr,
-	       (u32)(sizeof(*pgd) * 2), (u64)pgd_val(*pgd));
+	pr_alert("[%08lx] *pgd=%0*llx", addr, (u32)(sizeof(*pgd) * 2),
+		 (u64)pgd_val(*pgd));
 
 	do {
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
@@ -81,33 +62,46 @@ static void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		if (pgd_bad(*pgd)) {
-			printk("(bad)");
+			pr_cont("(bad)");
 			break;
 		}
 
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (PTRS_PER_P4D != 1)
+			pr_cont(", *p4d=%0*Lx", (u32)(sizeof(*p4d) * 2),
+			        (u64)p4d_val(*p4d));
+
+		if (p4d_none(*p4d))
+			break;
+
+		if (p4d_bad(*p4d)) {
+			pr_cont("(bad)");
+			break;
+		}
+
+		pud = pud_offset(p4d, addr);
 		if (PTRS_PER_PUD != 1)
-			printk(", *pud=%0*Lx", (u32)(sizeof(*pud) * 2),
-			       (u64)pud_val(*pud));
+			pr_cont(", *pud=%0*llx", (u32)(sizeof(*pud) * 2),
+				(u64)pud_val(*pud));
 
 		if (pud_none(*pud))
 			break;
 
 		if (pud_bad(*pud)) {
-			printk("(bad)");
+			pr_cont("(bad)");
 			break;
 		}
 
 		pmd = pmd_offset(pud, addr);
 		if (PTRS_PER_PMD != 1)
-			printk(", *pmd=%0*Lx", (u32)(sizeof(*pmd) * 2),
-			       (u64)pmd_val(*pmd));
+			pr_cont(", *pmd=%0*llx", (u32)(sizeof(*pmd) * 2),
+				(u64)pmd_val(*pmd));
 
 		if (pmd_none(*pmd))
 			break;
 
 		if (pmd_bad(*pmd)) {
-			printk("(bad)");
+			pr_cont("(bad)");
 			break;
 		}
 
@@ -116,17 +110,18 @@ static void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pte = pte_offset_kernel(pmd, addr);
-		printk(", *pte=%0*Lx", (u32)(sizeof(*pte) * 2),
-		       (u64)pte_val(*pte));
+		pr_cont(", *pte=%0*llx", (u32)(sizeof(*pte) * 2),
+			(u64)pte_val(*pte));
 	} while (0);
 
-	printk("\n");
+	pr_cont("\n");
 }
 
 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 {
 	unsigned index = pgd_index(address);
 	pgd_t *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -136,8 +131,13 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pgd_present(*pgd_k))
 		return NULL;
 
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (!p4d_present(*p4d_k))
+		return NULL;
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
 	if (!pud_present(*pud_k))
 		return NULL;
 
@@ -208,14 +208,11 @@ show_fault_oops(struct pt_regs *regs, unsigned long address)
 	if (!oops_may_print())
 		return;
 
-	printk(KERN_ALERT "BUG: unable to handle kernel ");
-	if (address < PAGE_SIZE)
-		printk(KERN_CONT "NULL pointer dereference");
-	else
-		printk(KERN_CONT "paging request");
-
-	printk(KERN_CONT " at %08lx\n", address);
-	printk(KERN_ALERT "PC:");
+	pr_alert("BUG: unable to handle kernel %s at %08lx\n",
+		 address < PAGE_SIZE ? "NULL pointer dereference"
+				     : "paging request",
+		 address);
+	pr_alert("PC:");
 	printk_address(regs->pc, 1);
 
 	show_pte(NULL, address);
@@ -241,16 +238,12 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	show_fault_oops(regs, address);
 
 	die("Oops", regs, error_code);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
 }
 
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		       unsigned long address, int si_code)
 {
-	struct task_struct *tsk = current;
-
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs)) {
 		/*
@@ -258,7 +251,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		 */
 		local_irq_enable();
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+		force_sig_info_fault(SIGSEGV, si_code, address);
 
 		return;
 	}
@@ -283,7 +276,7 @@ __bad_area(struct pt_regs *regs, unsigned long error_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);
 
 	__bad_area_nosemaphore(regs, error_code, address, si_code);
 }
@@ -307,42 +300,42 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/* Kernel mode? Handle exceptions or die: */
 	if (!user_mode(regs))
 		no_context(regs, error_code, address);
 
-	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+	force_sig_info_fault(SIGBUS, BUS_ADRERR, address);
 }
 
 static noinline int
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, unsigned int fault)
+	       unsigned long address, vm_fault_t fault)
 {
 	/*
 	 * Pagefault was interrupted by SIGKILL. We have no reason to
 	 * continue pagefault.
 	 */
-	if (fatal_signal_pending(current)) {
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
+	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
 			no_context(regs, error_code, address);
 		return 1;
 	}
 
+	/* Release mmap_lock first if necessary */
+	if (!(fault & VM_FAULT_RETRY))
+		mmap_read_unlock(current->mm);
+
 	if (!(fault & VM_FAULT_ERROR))
 		return 0;
 
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
 		if (!user_mode(regs)) {
-			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address);
 			return 1;
 		}
-		up_read(&current->mm->mmap_sem);
 
 		/*
 		 * We ran out of memory, call the OOM killer, and return the
@@ -353,6 +346,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area(regs, error_code, address);
 		else
 			BUG();
 	}
@@ -375,7 +370,7 @@ static inline int access_error(int error_code, struct vm_area_struct *vma)
 		return 1;
 
 	/* read, not present: */
-	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+	if (unlikely(!vma_is_accessible(vma)))
 		return 1;
 
 	return 0;
@@ -399,10 +394,8 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
-	int fault;
-	int write = error_code & FAULT_CODE_WRITE;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (write ? FAULT_FLAG_WRITE : 0));
+	vm_fault_t fault;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -420,14 +413,14 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	if (unlikely(fault_in_kernel_space(address))) {
 		if (vmalloc_fault(address) >= 0)
 			return;
-		if (notify_page_fault(regs, vec))
+		if (kprobe_page_fault(regs, vec))
 			return;
 
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
-	if (unlikely(notify_page_fault(regs, vec)))
+	if (unlikely(kprobe_page_fault(regs, vec)))
 		return;
 
 	/* Only enable interrupts if they were on before the fault */
@@ -438,29 +431,17 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * with pagefaults disabled then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
 retry:
-	down_read(&mm->mmap_sem);
-
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (unlikely(!vma)) {
-		bad_area(regs, error_code, address);
-		return;
-	}
-	if (likely(vma->vm_start <= address))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
-		bad_area(regs, error_code, address);
-		return;
-	}
-	if (unlikely(expand_stack(vma, address))) {
-		bad_area(regs, error_code, address);
+		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
@@ -468,7 +449,6 @@ retry:
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
 	 */
-good_area:
 	if (unlikely(access_error(error_code, vma))) {
 		bad_area_access_error(regs, error_code, address);
 		return;
@@ -476,39 +456,36 @@ good_area:
 
 	set_thread_fault_code(error_code);
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (error_code & FAULT_CODE_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
 	if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))
 			return;
 
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
-		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			flags |= FAULT_FLAG_TRIED;
-
-			/*
-			 * No need to up_read(&mm->mmap_sem) as we would
-			 * have already released it in __lock_page_or_retry
-			 * in mm/filemap.c.
-			 */
-			goto retry;
-		}
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	if (fault & VM_FAULT_RETRY) {
+		flags |= FAULT_FLAG_TRIED;
+
+		/*
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+		goto retry;
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 }