1 files changed, 103 insertions, 139 deletions

diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 0fd1f0d515ff..95119a5e7761 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -1,49 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Page Fault Handling for ARC (TLB Miss / ProtV)
  *
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/signal.h>
 #include <linux/interrupt.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
-#include <asm/pgalloc.h>
+#include <linux/perf_event.h>
+#include <linux/mm_types.h>
+#include <asm/entry.h>
 #include <asm/mmu.h>
 
-static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address)
+/*
+ * kernel virtual address is required to implement vmalloc/pkmap/fixmap
+ * Refer to asm/processor.h for System Memory Map
+ *
+ * It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
+ * from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
+ */
+noinline static int handle_kernel_vaddr_fault(unsigned long address)
 {
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
 	 */
 	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
-	pgd = pgd_offset_fast(mm, address);
+	pgd = pgd_offset(current->active_mm, address);
 	pgd_k = pgd_offset_k(address);
 
-	if (!pgd_present(*pgd_k))
+	if (pgd_none (*pgd_k))
 		goto bad_area;
+	if (!pgd_present(*pgd))
+		set_pgd(pgd, *pgd_k);
 
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
-	if (!pud_present(*pud_k))
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (p4d_none(*p4d_k))
 		goto bad_area;
+	if (!p4d_present(*p4d))
+		set_p4d(p4d, *p4d_k);
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
+	if (pud_none(*pud_k))
+		goto bad_area;
+	if (!pud_present(*pud))
+		set_pud(pud, *pud_k);
 
 	pmd = pmd_offset(pud, address);
 	pmd_k = pmd_offset(pud_k, address);
-	if (!pmd_present(*pmd_k))
+	if (pmd_none(*pmd_k))
 		goto bad_area;
-
-	set_pmd(pmd, *pmd_k);
+	if (!pmd_present(*pmd))
+		set_pmd(pmd, *pmd_k);
 
 	/* XXX: create the TLB entry here */
 	return 0;
@@ -52,178 +70,124 @@ bad_area:
 	return 1;
 }
 
-void do_page_fault(struct pt_regs *regs, unsigned long address)
+void do_page_fault(unsigned long address, struct pt_regs *regs)
 {
 	struct vm_area_struct *vma = NULL;
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
-	siginfo_t info;
-	int fault, ret;
-	int write = regs->ecr_cause & ECR_C_PROTV_STORE;  /* ST/EX */
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write ? FAULT_FLAG_WRITE : 0);
+	int sig, si_code = SEGV_MAPERR;
+	unsigned int write = 0, exec = 0, mask;
+	vm_fault_t fault = VM_FAULT_SIGSEGV;	/* handle_mm_fault() output */
+	unsigned int flags;			/* handle_mm_fault() input */
 
 	/*
-	 * We fault-in kernel-space virtual memory on-demand. The
-	 * 'reference' page table is init_mm.pgd.
-	 *
 	 * NOTE! We MUST NOT take any locks for this case. We may
 	 * be in an interrupt or a critical region, and should
 	 * only copy the information from the master page table,
 	 * nothing more.
 	 */
-	if (address >= VMALLOC_START && address <= VMALLOC_END) {
-		ret = handle_vmalloc_fault(mm, address);
-		if (unlikely(ret))
-			goto bad_area_nosemaphore;
+	if (address >= VMALLOC_START && !user_mode(regs)) {
+		if (unlikely(handle_kernel_vaddr_fault(address)))
+			goto no_context;
 		else
 			return;
 	}
 
-	info.si_code = SEGV_MAPERR;
-
 	/*
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
+	if (regs->ecr.cause & ECR_C_PROTV_STORE)	/* ST/EX */
+		write = 1;
+	else if ((regs->ecr.vec == ECR_V_PROTV) &&
+	         (regs->ecr.cause == ECR_C_PROTV_INST_FETCH))
+		exec = 1;
+
+	flags = FAULT_FLAG_DEFAULT;
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (write)
+		flags |= FAULT_FLAG_WRITE;
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 retry:
-	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (!vma)
-		goto bad_area;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-	if (expand_stack(vma, address))
-		goto bad_area;
+		goto bad_area_nosemaphore;
 
 	/*
-	 * Ok, we have a good vm_area for this memory access, so
-	 * we can handle it..
+	 * vm_area is good, now check permissions for this memory access
 	 */
-good_area:
-	info.si_code = SEGV_ACCERR;
-
-	/* Handle protection violation, execute on heap or stack */
-
-	if ((regs->ecr_vec == ECR_V_PROTV) &&
-	    (regs->ecr_cause == ECR_C_PROTV_INST_FETCH))
+	mask = VM_READ;
+	if (write)
+		mask = VM_WRITE;
+	if (exec)
+		mask = VM_EXEC;
+
+	if (!(vma->vm_flags & mask)) {
+		si_code = SEGV_ACCERR;
 		goto bad_area;
-
-	if (write) {
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;
-	} else {
-		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
-			goto bad_area;
 	}
 
-survive:
-	/*
-	 * 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 Pagefault was interrupted by SIGKILL, exit page fault "early" */
-	if (unlikely(fatal_signal_pending(current))) {
-		if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
-			up_read(&mm->mmap_sem);
-		if (user_mode(regs))
-			return;
-	}
-
-	if (likely(!(fault & VM_FAULT_ERROR))) {
-		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			/* To avoid updating stats twice for retry case */
-			if (fault & VM_FAULT_MAJOR)
-				tsk->maj_flt++;
-			else
-				tsk->min_flt++;
-
-			if (fault & VM_FAULT_RETRY) {
-				flags &= ~FAULT_FLAG_ALLOW_RETRY;
-				flags |= FAULT_FLAG_TRIED;
-				goto retry;
-			}
-		}
-
-		/* Fault Handled Gracefully */
-		up_read(&mm->mmap_sem);
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return;
 	}
 
-	/* TBD: switch to pagefault_out_of_memory() */
-	if (fault & VM_FAULT_OOM)
-		goto out_of_memory;
-	else if (fault & VM_FAULT_SIGBUS)
-		goto do_sigbus;
-
-	/* no man's land */
-	BUG();
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
 
 	/*
-	 * Something tried to access memory that isn't in our memory map..
-	 * Fix it, but check if it's kernel or user first..
+	 * Fault retry nuances, mmap_lock already relinquished by core mm
 	 */
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+		goto retry;
+	}
+
 bad_area:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 bad_area_nosemaphore:
-	/* User mode accesses just cause a SIGSEGV */
-	if (user_mode(regs)) {
-		tsk->thread.fault_address = address;
-		info.si_signo = SIGSEGV;
-		info.si_errno = 0;
-		/* info.si_code has been set above */
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGSEGV, &info, tsk);
-		return;
-	}
-
-no_context:
-	/* Are we prepared to handle this kernel fault?
-	 *
-	 * (The kernel has valid exception-points in the source
-	 *  when it acesses user-memory. When it fails in one
-	 *  of those points, we find it in a table and do a jump
-	 *  to some fixup code that loads an appropriate error
-	 *  code)
+	/*
+	 * Major/minor page fault accounting
+	 * (in case of retry we only land here once)
 	 */
-	if (fixup_exception(regs))
+	if (likely(!(fault & VM_FAULT_ERROR)))
+		/* Normal return path: fault Handled Gracefully */
 		return;
 
-	die("Oops", regs, address);
-
-out_of_memory:
-	if (is_global_init(tsk)) {
-		yield();
-		goto survive;
-	}
-	up_read(&mm->mmap_sem);
+	if (!user_mode(regs))
+		goto no_context;
 
-	if (user_mode(regs)) {
+	if (fault & VM_FAULT_OOM) {
 		pagefault_out_of_memory();
 		return;
 	}
 
-	goto no_context;
+	if (fault & VM_FAULT_SIGBUS) {
+		sig = SIGBUS;
+		si_code = BUS_ADRERR;
+	}
+	else {
+		sig = SIGSEGV;
+	}
 
-do_sigbus:
-	up_read(&mm->mmap_sem);
+	tsk->thread.fault_address = address;
+	force_sig_fault(sig, si_code, (void __user *)address);
+	return;
 
-	if (!user_mode(regs))
-		goto no_context;
+no_context:
+	if (fixup_exception(regs))
+		return;
 
-	tsk->thread.fault_address = address;
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void __user *)address;
-	force_sig_info(SIGBUS, &info, tsk);
+	die("Oops", regs, address);
 }