1 files changed, 292 insertions, 276 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 887f11bcf330..806c74e0d5ab 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -8,11 +9,6 @@
  *  Modified by Cort Dougan and Paul Mackerras.
  *
  *  Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/signal.h>
@@ -21,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/pagemap.h>
 #include <linux/ptrace.h>
@@ -36,69 +33,21 @@
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
 #include <linux/uaccess.h>
+#include <linux/kfence.h>
+#include <linux/pkeys.h>
 
 #include <asm/firmware.h>
+#include <asm/interrupt.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>
 
-static inline bool notify_page_fault(struct pt_regs *regs)
-{
-	bool ret = false;
-
-#ifdef CONFIG_KPROBES
-	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 11))
-			ret = true;
-		preempt_enable();
-	}
-#endif /* CONFIG_KPROBES */
-
-	if (unlikely(debugger_fault_handler(regs)))
-		ret = true;
-
-	return ret;
-}
 
 /*
- * 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)
-{
-	/* check for 1 in the rA field */
-	if (((inst >> 16) & 0x1f) != 1)
-		return false;
-	/* check major opcode */
-	switch (inst >> 26) {
-	case OP_STWU:
-	case OP_STBU:
-	case OP_STHU:
-	case OP_STFSU:
-	case OP_STFDU:
-		return true;
-	case OP_STD:	/* std or stdu */
-		return (inst & 3) == 1;
-	case OP_31:
-		/* check minor opcode */
-		switch ((inst >> 1) & 0x3ff) {
-		case OP_31_XOP_STDUX:
-		case OP_31_XOP_STWUX:
-		case OP_31_XOP_STBUX:
-		case OP_31_XOP_STHUX:
-		case OP_31_XOP_STFSUX:
-		case OP_31_XOP_STFDUX:
-			return true;
-		}
-	}
-	return false;
-}
-/*
  * do_page_fault error handling helpers
  */
 
@@ -123,27 +72,52 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add
 	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
+		      struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct mm_struct *mm = current->mm;
 
 	/*
 	 * 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);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	return __bad_area_nosemaphore(regs, address, si_code);
 }
 
-static noinline int bad_area(struct pt_regs *regs, unsigned long address)
+static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
+				    struct mm_struct *mm,
+				    struct vm_area_struct *vma)
 {
-	return __bad_area(regs, address, SEGV_MAPERR);
-}
+	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);
+
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
-static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
-				    int pkey)
-{
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
 	 * be caught by the assembly which will restore the non-volatile
@@ -157,9 +131,10 @@ static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
 	return 0;
 }
 
-static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+static noinline int bad_access(struct pt_regs *regs, unsigned long address,
+			       struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	return __bad_area(regs, address, SEGV_ACCERR);
+	return __bad_area(regs, address, SEGV_ACCERR, mm, vma);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
@@ -181,13 +156,12 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address,
 		if (fault & VM_FAULT_HWPOISON)
 			lsb = PAGE_SHIFT;
 
-		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb,
-				 current);
+		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
 		return 0;
 	}
 
 #endif
-	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
 	return 0;
 }
 
@@ -223,75 +197,59 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr,
 }
 
 /* Is this a bad kernel fault ? */
-static bool bad_kernel_fault(bool is_exec, unsigned long error_code,
-			     unsigned long address)
+static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
+			     unsigned long address, bool is_write)
 {
-	/* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */
-	if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT |
-				      DSISR_PROTFAULT))) {
-		printk_ratelimited(KERN_CRIT "kernel tried to execute"
-				   " exec-protected page (%lx) -"
-				   "exploit attempt? (uid: %d)\n",
-				   address, from_kuid(&init_user_ns,
-						      current_uid()));
+	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
+
+	if (is_exec) {
+		pr_crit_ratelimited("kernel tried to execute %s page (%lx) - exploit attempt? (uid: %d)\n",
+				    address >= TASK_SIZE ? "exec-protected" : "user",
+				    address,
+				    from_kuid(&init_user_ns, current_uid()));
+
+		// Kernel exec fault is always bad
+		return true;
+	}
+
+	// Kernel fault on kernel address is bad
+	if (address >= TASK_SIZE)
+		return true;
+
+	// Read/write fault blocked by KUAP is bad, it can never succeed.
+	if (bad_kuap_fault(regs, address, is_write)) {
+		pr_crit_ratelimited("Kernel attempted to %s user page (%lx) - exploit attempt? (uid: %d)\n",
+				    str_write_read(is_write), address,
+				    from_kuid(&init_user_ns, current_uid()));
+
+		// Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad
+		if (!search_exception_tables(regs->nip))
+			return true;
+
+		// Read/write fault in a valid region (the exception table search passed
+		// above), but blocked by KUAP is bad, it can never succeed.
+		return WARN(true, "Bug: %s fault blocked by KUAP!", is_write ? "Write" : "Read");
 	}
-	return is_exec || (address >= TASK_SIZE);
+
+	// What's left? Kernel fault on user and allowed by KUAP in the faulting context.
+	return false;
 }
 
-static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
-				struct vm_area_struct *vma, unsigned int flags,
-				bool *must_retry)
+static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
+			      struct vm_area_struct *vma)
 {
 	/*
-	 * N.B. The POWER/Open ABI allows programs to access up to
-	 * 288 bytes below the stack pointer.
-	 * The kernel signal delivery code writes up to about 1.5kB
-	 * below the stack pointer (r1) before decrementing it.
-	 * The exec code can write slightly over 640kB to the stack
-	 * before setting the user r1.  Thus we allow the stack to
-	 * expand to 1MB without further checks.
+	 * 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 (address + 0x100000 < vma->vm_end) {
-		unsigned int __user *nip = (unsigned int __user *)regs->nip;
-		/* get user regs even if this fault is in kernel mode */
-		struct pt_regs *uregs = current->thread.regs;
-		if (uregs == NULL)
-			return true;
-
-		/*
-		 * A user-mode access to an address a long way below
-		 * the stack pointer is only valid if the instruction
-		 * is one which would update the stack pointer to the
-		 * address accessed if the instruction completed,
-		 * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
-		 * (or the byte, halfword, float or double forms).
-		 *
-		 * If we don't check this then any write to the area
-		 * between the last mapped region and the stack will
-		 * expand the stack rather than segfaulting.
-		 */
-		if (address + 2048 >= uregs->gpr[1])
-			return false;
-
-		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
-		    access_ok(nip, sizeof(*nip))) {
-			unsigned int inst;
-			int res;
-
-			pagefault_disable();
-			res = __get_user_inatomic(inst, nip);
-			pagefault_enable();
-			if (!res)
-				return !store_updates_sp(inst);
-			*must_retry = true;
-		}
+	if (!arch_vma_access_permitted(vma, is_write, is_exec, 0))
 		return true;
-	}
+
 	return false;
 }
 
-static bool access_error(bool is_write, bool is_exec,
-			 struct vm_area_struct *vma)
+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
@@ -315,8 +273,18 @@ static bool access_error(bool is_write, bool is_exec,
 		return false;
 	}
 
-	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+	/*
+	 * VM_READ, VM_WRITE and VM_EXEC may imply read permissions, as
+	 * defined in protection_map[].  In that case Read faults can only be
+	 * caused by a PROT_NONE mapping. However a non exec access on a
+	 * VM_EXEC only mapping is invalid anyway, so report it as such.
+	 */
+	if (unlikely(!vma_is_accessible(vma)))
 		return true;
+
+	if ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)
+		return true;
+
 	/*
 	 * We should ideally do the vma pkey access check here. But in the
 	 * fault path, handle_mm_fault() also does the same check. To avoid
@@ -343,7 +311,6 @@ static inline void cmo_account_page_fault(void)
 static inline void cmo_account_page_fault(void) { }
 #endif /* CONFIG_PPC_SMLPAR */
 
-#ifdef CONFIG_PPC_BOOK3S
 static void sanity_check_fault(bool is_write, bool is_user,
 			       unsigned long error_code, unsigned long address)
 {
@@ -351,12 +318,18 @@ static void sanity_check_fault(bool is_write, bool is_user,
 	 * Userspace trying to access kernel address, we get PROTFAULT for that.
 	 */
 	if (is_user && address >= TASK_SIZE) {
+		if ((long)address == -1)
+			return;
+
 		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
 				   current->comm, current->pid, address,
 				   from_kuid(&init_user_ns, current_uid()));
 		return;
 	}
 
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S))
+		return;
+
 	/*
 	 * For hash translation mode, we should never get a
 	 * PROTFAULT. Any update to pte to reduce access will result in us
@@ -391,55 +364,66 @@ static void sanity_check_fault(bool is_write, bool is_user,
 
 	WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 }
-#else
-static void sanity_check_fault(bool is_write, bool is_user,
-			       unsigned long error_code, unsigned long address) { }
-#endif /* CONFIG_PPC_BOOK3S */
 
 /*
  * Define the correct "is_write" bit in error_code based
  * on the processor family
  */
-#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#ifdef CONFIG_BOOKE
 #define page_fault_is_write(__err)	((__err) & ESR_DST)
-#define page_fault_is_bad(__err)	(0)
 #else
 #define page_fault_is_write(__err)	((__err) & DSISR_ISSTORE)
-#if defined(CONFIG_PPC_8xx)
+#endif
+
+#ifdef CONFIG_BOOKE
+#define page_fault_is_bad(__err)	(0)
+#elif defined(CONFIG_PPC_8xx)
 #define page_fault_is_bad(__err)	((__err) & DSISR_NOEXEC_OR_G)
 #elif defined(CONFIG_PPC64)
-#define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_64S)
+static int page_fault_is_bad(unsigned long err)
+{
+	unsigned long flag = DSISR_BAD_FAULT_64S;
+
+	/*
+	 * PAPR+ v2.11 § 14.15.3.4.1 (unreleased)
+	 * If byte 0, bit 3 of pi-attribute-specifier-type in
+	 * ibm,pi-features property is defined, ignore the DSI error
+	 * which is caused by the paste instruction on the
+	 * suspended NX window.
+	 */
+	if (mmu_has_feature(MMU_FTR_NX_DSI))
+		flag &= ~DSISR_BAD_COPYPASTE;
+
+	return err & flag;
+}
 #else
 #define page_fault_is_bad(__err)	((__err) & DSISR_BAD_FAULT_32S)
 #endif
-#endif
 
 /*
  * For 600- and 800-family processors, the error_code parameter is DSISR
- * for a data fault, SRR1 for an instruction fault. For 400-family processors
- * the error_code parameter is ESR for a data fault, 0 for an instruction
- * fault.
- * For 64-bit processors, the error_code parameter is
- *  - DSISR for a non-SLB data access fault,
- *  - SRR1 & 0x08000000 for a non-SLB instruction access fault
- *  - 0 any SLB fault.
+ * for a data fault, SRR1 for an instruction fault.
+ * For 400-family processors the error_code parameter is ESR for a data fault,
+ * 0 for an instruction fault.
+ * For 64-bit processors, the error_code parameter is DSISR for a data access
+ * fault, SRR1 & 0x08000000 for an instruction access fault.
  *
  * The return value is 0 if the fault was handled, or the signal
  * number if this is a kernel fault that can't be handled here.
  */
-static int __do_page_fault(struct pt_regs *regs, unsigned long address,
+static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 			   unsigned long error_code)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
- 	int is_exec = TRAP(regs) == 0x400;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+	int is_exec = TRAP(regs) == INTERRUPT_INST_STORAGE;
 	int is_user = user_mode(regs);
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
-	bool must_retry = false;
+	bool kprobe_fault = kprobe_page_fault(regs, 11);
 
-	if (notify_page_fault(regs))
+	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
 		return 0;
 
 	if (unlikely(page_fault_is_bad(error_code))) {
@@ -455,10 +439,21 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	/*
 	 * The kernel should never take an execute fault nor should it
-	 * take a page fault to a kernel address.
+	 * take a page fault to a kernel address or a page fault to a user
+	 * address outside of dedicated places.
+	 *
+	 * Rather than kfence directly reporting false negatives, search whether
+	 * the NIP belongs to the fixup table for cases where fault could come
+	 * from functions like copy_from_kernel_nofault().
 	 */
-	if (unlikely(!is_user && bad_kernel_fault(is_exec, error_code, address)))
+	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) {
+		if (is_kfence_address((void *)address) &&
+		    !search_exception_tables(instruction_pointer(regs)) &&
+		    kfence_handle_page_fault(address, is_write, regs))
+			return 0;
+
 		return SIGSEGV;
+	}
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
@@ -473,20 +468,14 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 		return bad_area_nosemaphore(regs, address);
 	}
 
-	/* We restore the interrupt state now */
-	if (!arch_irq_disabled_regs(regs))
-		local_irq_enable();
+	interrupt_cond_local_irq_enable(regs);
 
 	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;
@@ -495,174 +484,159 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_exec)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_pkey_error(is_write, is_exec,
+				       (error_code & DSISR_KEYFAULT), vma))) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access_pkey(regs, address, NULL, vma);
+	}
+
+	if (unlikely(access_error(is_write, is_exec, vma))) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access(regs, address, NULL, vma);
+	}
+
+	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
+	if (fault_signal_pending(fault, regs))
+		return user_mode(regs) ? 0 : SIGBUS;
+
+lock_mmap:
+
 	/* 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
-	 * exceptions table.
-	 *
-	 * As the vast majority of faults will be valid we will only perform
-	 * the source reference check when there is a possibility of a deadlock.
-	 * Attempt to lock the address space, if we cannot we then validate the
-	 * source.  If this is invalid we can skip the address space check,
-	 * thus avoiding the deadlock.
+	 * exceptions table. lock_mm_and_find_vma() handles that logic.
 	 */
-	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
-		if (!is_user && !search_exception_tables(regs->nip))
-			return bad_area_nosemaphore(regs, address);
-
 retry:
-		down_read(&mm->mmap_sem);
-	} else {
-		/*
-		 * The above down_read_trylock() might have succeeded in
-		 * which case we'll have missed the might_sleep() from
-		 * down_read():
-		 */
-		might_sleep();
-	}
-
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (unlikely(!vma))
-		return bad_area(regs, address);
-	if (likely(vma->vm_start <= address))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
-		return bad_area(regs, address);
-
-	/* The stack is being expanded, check if it's valid */
-	if (unlikely(bad_stack_expansion(regs, address, vma, flags,
-					 &must_retry))) {
-		if (!must_retry)
-			return bad_area(regs, address);
-
-		up_read(&mm->mmap_sem);
-		if (fault_in_pages_readable((const char __user *)regs->nip,
-					    sizeof(unsigned int)))
-			return bad_area_nosemaphore(regs, address);
-		goto retry;
-	}
+		return bad_area_nosemaphore(regs, address);
 
-	/* Try to expand it */
-	if (unlikely(expand_stack(vma, address)))
-		return bad_area(regs, address);
+	if (unlikely(access_pkey_error(is_write, is_exec,
+				       (error_code & DSISR_KEYFAULT), vma)))
+		return bad_access_pkey(regs, address, mm, vma);
 
-good_area:
 	if (unlikely(access_error(is_write, is_exec, vma)))
-		return bad_access(regs, address);
+		return bad_access(regs, address, mm, vma);
 
 	/*
 	 * 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(vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
-#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);
+	major |= fault & VM_FAULT_MAJOR;
 
-		up_read(&mm->mmap_sem);
-		return bad_key_fault_exception(regs, address, pkey);
-	}
-#endif /* CONFIG_PPC_MEM_KEYS */
+	if (fault_signal_pending(fault, regs))
+		return user_mode(regs) ? 0 : SIGBUS;
 
-	major |= fault & VM_FAULT_MAJOR;
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		goto out;
 
 	/*
-	 * 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)) {
-		/* We retry only once */
-		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			/*
-			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation.
-			 */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			flags |= FAULT_FLAG_TRIED;
-			if (!fatal_signal_pending(current))
-				goto retry;
-		}
-
-		/*
-		 * User mode? Just return to handle the fatal exception otherwise
-		 * return to bad_page_fault
-		 */
-		return is_user ? 0 : SIGBUS;
+		flags |= FAULT_FLAG_TRIED;
+		goto retry;
 	}
 
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
+done:
 	if (unlikely(fault & VM_FAULT_ERROR))
 		return mm_fault_error(regs, address, fault);
 
+out:
 	/*
 	 * Major/minor page fault accounting.
 	 */
-	if (major) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	if (major)
 		cmo_account_page_fault();
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-	}
+
 	return 0;
 }
-NOKPROBE_SYMBOL(__do_page_fault);
+NOKPROBE_SYMBOL(___do_page_fault);
+
+static __always_inline void __do_page_fault(struct pt_regs *regs)
+{
+	long err;
+
+	err = ___do_page_fault(regs, regs->dar, regs->dsisr);
+	if (unlikely(err))
+		bad_page_fault(regs, err);
+}
 
-int do_page_fault(struct pt_regs *regs, unsigned long address,
-		  unsigned long error_code)
+DEFINE_INTERRUPT_HANDLER(do_page_fault)
 {
-	enum ctx_state prev_state = exception_enter();
-	int rc = __do_page_fault(regs, address, error_code);
-	exception_exit(prev_state);
-	return rc;
+	__do_page_fault(regs);
 }
-NOKPROBE_SYMBOL(do_page_fault);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
+void hash__do_page_fault(struct pt_regs *regs)
+{
+	__do_page_fault(regs);
+}
+NOKPROBE_SYMBOL(hash__do_page_fault);
+#endif
 
 /*
  * bad_page_fault is called when we have a bad access from the kernel.
  * It is called from the DSI and ISI handlers in head.S and from some
  * of the procedures in traps.c.
  */
-void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
+static void __bad_page_fault(struct pt_regs *regs, int sig)
 {
-	const struct exception_table_entry *entry;
-
-	/* Are we prepared to handle this fault?  */
-	if ((entry = search_exception_tables(regs->nip)) != NULL) {
-		regs->nip = extable_fixup(entry);
-		return;
-	}
+	int is_write = page_fault_is_write(regs->dsisr);
+	const char *msg;
 
 	/* kernel has accessed a bad area */
 
+	if (regs->dar < PAGE_SIZE)
+		msg = "Kernel NULL pointer dereference";
+	else
+		msg = "Unable to handle kernel data access";
+
 	switch (TRAP(regs)) {
-	case 0x300:
-	case 0x380:
-	case 0xe00:
-		pr_alert("BUG: %s at 0x%08lx\n",
-			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
-			 "Unable to handle kernel data access", regs->dar);
+	case INTERRUPT_DATA_STORAGE:
+	case INTERRUPT_H_DATA_STORAGE:
+		pr_alert("BUG: %s on %s at 0x%08lx\n", msg,
+			 str_write_read(is_write), regs->dar);
+		break;
+	case INTERRUPT_DATA_SEGMENT:
+		pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar);
 		break;
-	case 0x400:
-	case 0x480:
+	case INTERRUPT_INST_STORAGE:
+	case INTERRUPT_INST_SEGMENT:
 		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
 			 regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n");
 		break;
-	case 0x600:
+	case INTERRUPT_ALIGNMENT:
 		pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n",
 			 regs->dar);
 		break;
@@ -679,3 +653,45 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 
 	die("Kernel access of bad area", regs, sig);
 }
+
+void bad_page_fault(struct pt_regs *regs, int sig)
+{
+	const struct exception_table_entry *entry;
+
+	/* Are we prepared to handle this fault?  */
+	entry = search_exception_tables(instruction_pointer(regs));
+	if (entry)
+		instruction_pointer_set(regs, extable_fixup(entry));
+	else
+		__bad_page_fault(regs, sig);
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER(do_bad_page_fault_segv)
+{
+	bad_page_fault(regs, SIGSEGV);
+}
+
+/*
+ * In radix, segment interrupts indicate the EA is not addressable by the
+ * page table geometry, so they are always sent here.
+ *
+ * In hash, this is called if do_slb_fault returns error. Typically it is
+ * because the EA was outside the region allowed by software.
+ */
+DEFINE_INTERRUPT_HANDLER(do_bad_segment_interrupt)
+{
+	int err = regs->result;
+
+	if (err == -EFAULT) {
+		if (user_mode(regs))
+			_exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar);
+		else
+			bad_page_fault(regs, SIGSEGV);
+	} else if (err == -EINVAL) {
+		unrecoverable_exception(regs);
+	} else {
+		BUG();
+	}
+}
+#endif