1 files changed, 141 insertions, 52 deletions

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index d86f7cebd4a7..04ed6f8acae4 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -15,12 +15,67 @@
 #include <linux/uaccess.h>
 #include <linux/kprobes.h>
 #include <linux/kfence.h>
+#include <linux/entry-common.h>
 
 #include <asm/ptrace.h>
 #include <asm/tlbflush.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/exceptions.h>
+
 #include "../kernel/head.h"
 
+static void show_pte(unsigned long addr)
+{
+	pgd_t *pgdp, pgd;
+	p4d_t *p4dp, p4d;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
+	struct mm_struct *mm = current->mm;
+
+	if (!mm)
+		mm = &init_mm;
+
+	pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n",
+		 current->comm, PAGE_SIZE / SZ_1K, VA_BITS,
+		 mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd));
+
+	pgdp = pgd_offset(mm, addr);
+	pgd = pgdp_get(pgdp);
+	pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd));
+	if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd))
+		goto out;
+
+	p4dp = p4d_offset(pgdp, addr);
+	p4d = p4dp_get(p4dp);
+	pr_cont(", p4d=%016lx", p4d_val(p4d));
+	if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d))
+		goto out;
+
+	pudp = pud_offset(p4dp, addr);
+	pud = pudp_get(pudp);
+	pr_cont(", pud=%016lx", pud_val(pud));
+	if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud))
+		goto out;
+
+	pmdp = pmd_offset(pudp, addr);
+	pmd = pmdp_get(pmdp);
+	pr_cont(", pmd=%016lx", pmd_val(pmd));
+	if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd))
+		goto out;
+
+	ptep = pte_offset_map(pmdp, addr);
+	if (!ptep)
+		goto out;
+
+	pte = ptep_get(ptep);
+	pr_cont(", pte=%016lx", pte_val(pte));
+	pte_unmap(ptep);
+out:
+	pr_cont("\n");
+}
+
 static void die_kernel_fault(const char *msg, unsigned long addr,
 		struct pt_regs *regs)
 {
@@ -30,6 +85,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 		addr);
 
 	bust_spinlocks(0);
+	show_pte(addr);
 	die(regs, "Oops");
 	make_task_dead(SIGKILL);
 }
@@ -60,36 +116,37 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr)
 
 static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
 {
+	if (!user_mode(regs)) {
+		no_context(regs, addr);
+		return;
+	}
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return the userspace
 		 * (which will retry the fault, or kill us if we got oom-killed).
 		 */
-		if (!user_mode(regs)) {
-			no_context(regs, addr);
-			return;
-		}
 		pagefault_out_of_memory();
 		return;
-	} else if (fault & VM_FAULT_SIGBUS) {
+	} else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
 		/* Kernel mode? Handle exceptions or die */
-		if (!user_mode(regs)) {
-			no_context(regs, addr);
-			return;
-		}
 		do_trap(regs, SIGBUS, BUS_ADRERR, addr);
 		return;
+	} else if (fault & VM_FAULT_SIGSEGV) {
+		do_trap(regs, SIGSEGV, SEGV_MAPERR, addr);
+		return;
 	}
+
 	BUG();
 }
 
-static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr)
+static inline void
+bad_area_nosemaphore(struct pt_regs *regs, int code, unsigned long addr)
 {
 	/*
 	 * Something tried to access memory that isn't in our memory map.
 	 * Fix it, but check if it's kernel or user first.
 	 */
-	mmap_read_unlock(mm);
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs)) {
 		do_trap(regs, SIGSEGV, code, addr);
@@ -99,6 +156,15 @@ static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code
 	no_context(regs, addr);
 }
 
+static inline void
+bad_area(struct pt_regs *regs, struct mm_struct *mm, int code,
+	 unsigned long addr)
+{
+	mmap_read_unlock(mm);
+
+	bad_area_nosemaphore(regs, code, addr);
+}
+
 static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr)
 {
 	pgd_t *pgd, *pgd_k;
@@ -126,33 +192,37 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
+	if (pud_leaf(pudp_get(pud_k)))
+		goto flush_tlb;
 
 	/*
 	 * Since the vmalloc area is global, it is unnecessary
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
+	if (pmd_leaf(pmdp_get(pmd_k)))
+		goto flush_tlb;
 
 	/*
 	 * Make sure the actual PTE exists as well to
@@ -161,7 +231,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}
@@ -172,6 +242,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * ordering constraint, not a cache flush; it is
 	 * necessary even after writing invalid entries.
 	 */
+flush_tlb:
 	local_flush_tlb_page(addr);
 }
 
@@ -204,7 +275,7 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
  * This routine handles page faults.  It determines the address and the
  * problem, and then passes it off to one of the appropriate routines.
  */
-asmlinkage void do_page_fault(struct pt_regs *regs)
+void handle_page_fault(struct pt_regs *regs)
 {
 	struct task_struct *tsk;
 	struct vm_area_struct *vma;
@@ -223,6 +294,11 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	if (kprobe_page_fault(regs, cause))
 		return;
 
+	if (user_mode(regs))
+		trace_page_fault_user(addr, regs, cause);
+	else
+		trace_page_fault_kernel(addr, regs, cause);
+
 	/*
 	 * Fault-in kernel-space virtual memory on-demand.
 	 * The 'reference' page table is init_mm.pgd.
@@ -232,26 +308,14 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	 * only copy the information from the master page table,
 	 * nothing more.
 	 */
-	if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
+	if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
+	    unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
 		vmalloc_fault(regs, code, addr);
 		return;
 	}
 
-#ifdef CONFIG_64BIT
-	/*
-	 * Modules in 64bit kernels lie in their own virtual region which is not
-	 * in the vmalloc region, but dealing with page faults in this region
-	 * or the vmalloc region amounts to doing the same thing: checking that
-	 * the mapping exists in init_mm.pgd and updating user page table, so
-	 * just use vmalloc_fault.
-	 */
-	if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) {
-		vmalloc_fault(regs, code, addr);
-		return;
-	}
-#endif
 	/* Enable interrupts if they were enabled in the parent context. */
-	if (likely(regs->status & SR_PIE))
+	if (!regs_irqs_disabled(regs))
 		local_irq_enable();
 
 	/*
@@ -267,10 +331,12 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
-	if (!user_mode(regs) && addr < TASK_SIZE &&
-			unlikely(!(regs->status & SR_SUM)))
-		die_kernel_fault("access to user memory without uaccess routines",
-				addr, regs);
+	if (!user_mode(regs) && addr < TASK_SIZE && unlikely(!(regs->status & SR_SUM))) {
+		if (fixup_exception(regs))
+			return;
+
+		die_kernel_fault("access to user memory without uaccess routines", addr, regs);
+	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
@@ -278,24 +344,45 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 		flags |= FAULT_FLAG_WRITE;
 	else if (cause == EXC_INST_PAGE_FAULT)
 		flags |= FAULT_FLAG_INSTRUCTION;
-retry:
-	mmap_read_lock(mm);
-	vma = find_vma(mm, addr);
-	if (unlikely(!vma)) {
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(cause, vma))) {
+		vma_end_read(vma);
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
 		tsk->thread.bad_cause = cause;
-		bad_area(regs, mm, code, addr);
+		bad_area_nosemaphore(regs, SEGV_ACCERR, addr);
 		return;
 	}
-	if (likely(vma->vm_start <= addr))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
-		tsk->thread.bad_cause = cause;
-		bad_area(regs, mm, code, addr);
+
+	fault = handle_mm_fault(vma, addr, 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)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
 		return;
 	}
-	if (unlikely(expand_stack(vma, addr))) {
+lock_mmap:
+
+retry:
+	vma = lock_mm_and_find_vma(mm, addr, regs);
+	if (unlikely(!vma)) {
 		tsk->thread.bad_cause = cause;
-		bad_area(regs, mm, code, addr);
+		bad_area_nosemaphore(regs, code, addr);
 		return;
 	}
 
@@ -303,7 +390,6 @@ retry:
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it.
 	 */
-good_area:
 	code = SEGV_ACCERR;
 
 	if (unlikely(access_error(cause, vma))) {
@@ -324,8 +410,11 @@ good_area:
 	 * signal first. We do not need to release the mmap_lock because it
 	 * would already be released in __lock_page_or_retry in mm/filemap.c.
 	 */
-	if (fault_signal_pending(fault, regs))
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
 		return;
+	}
 
 	/* The fault is fully completed (including releasing mmap lock) */
 	if (fault & VM_FAULT_COMPLETED)
@@ -344,6 +433,7 @@ good_area:
 
 	mmap_read_unlock(mm);
 
+done:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		tsk->thread.bad_cause = cause;
 		mm_fault_error(regs, addr, fault);
@@ -351,4 +441,3 @@ good_area:
 	}
 	return;
 }
-NOKPROBE_SYMBOL(do_page_fault);