1 files changed, 284 insertions, 187 deletions

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index cf7248e07f43..3ba1d4dde5dd 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -13,24 +13,219 @@
 #include <linux/perf_event.h>
 #include <linux/signal.h>
 #include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/kfence.h>
+#include <linux/entry-common.h>
 
-#include <asm/pgalloc.h>
 #include <asm/ptrace.h>
 #include <asm/tlbflush.h>
 
 #include "../kernel/head.h"
 
+static void die_kernel_fault(const char *msg, unsigned long addr,
+		struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+
+	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", msg,
+		addr);
+
+	bust_spinlocks(0);
+	die(regs, "Oops");
+	make_task_dead(SIGKILL);
+}
+
+static inline void no_context(struct pt_regs *regs, unsigned long addr)
+{
+	const char *msg;
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	if (addr < PAGE_SIZE)
+		msg = "NULL pointer dereference";
+	else {
+		if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs))
+			return;
+
+		msg = "paging request";
+	}
+
+	die_kernel_fault(msg, addr, regs);
+}
+
+static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+{
+	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 | 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;
+	}
+	BUG();
+}
+
+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.
+	 */
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	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;
+	pud_t *pud_k;
+	p4d_t *p4d_k;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+	int index;
+	unsigned long pfn;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs))
+		return do_trap(regs, SIGSEGV, code, addr);
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "tsk->active_mm->pgd" here.
+	 * We might be inside an interrupt in the middle
+	 * of a task switch.
+	 */
+	index = pgd_index(addr);
+	pfn = csr_read(CSR_SATP) & SATP_PPN;
+	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(pgdp_get(pgd_k))) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pgd(pgd, pgdp_get(pgd_k));
+
+	p4d_k = p4d_offset(pgd_k, addr);
+	if (!p4d_present(p4dp_get(p4d_k))) {
+		no_context(regs, addr);
+		return;
+	}
+
+	pud_k = pud_offset(p4d_k, addr);
+	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(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
+	 * catch kernel vmalloc-area accesses to non-mapped
+	 * addresses. If we don't do this, this will just
+	 * silently loop forever.
+	 */
+	pte_k = pte_offset_kernel(pmd_k, addr);
+	if (!pte_present(ptep_get(pte_k))) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * The kernel assumes that TLBs don't cache invalid
+	 * entries, but in RISC-V, SFENCE.VMA specifies an
+	 * ordering constraint, not a cache flush; it is
+	 * necessary even after writing invalid entries.
+	 */
+flush_tlb:
+	local_flush_tlb_page(addr);
+}
+
+static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
+{
+	switch (cause) {
+	case EXC_INST_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_EXEC)) {
+			return true;
+		}
+		break;
+	case EXC_LOAD_PAGE_FAULT:
+		/* Write implies read */
+		if (!(vma->vm_flags & (VM_READ | VM_WRITE))) {
+			return true;
+		}
+		break;
+	case EXC_STORE_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_WRITE)) {
+			return true;
+		}
+		break;
+	default:
+		panic("%s: unhandled cause %lu", __func__, cause);
+	}
+	return false;
+}
+
 /*
  * 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;
 	struct mm_struct *mm;
 	unsigned long addr, cause;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
 	int code = SEGV_MAPERR;
 	vm_fault_t fault;
 
@@ -40,6 +235,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	tsk = current;
 	mm = tsk->mm;
 
+	if (kprobe_page_fault(regs, cause))
+		return;
+
 	/*
 	 * Fault-in kernel-space virtual memory on-demand.
 	 * The 'reference' page table is init_mm.pgd.
@@ -49,60 +247,91 @@ 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)))
-		goto vmalloc_fault;
+	if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
+	    unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
 
 	/* Enable interrupts if they were enabled in the parent context. */
-	if (likely(regs->status & SR_PIE))
+	if (!regs_irqs_disabled(regs))
 		local_irq_enable();
 
 	/*
 	 * If we're in an interrupt, have no user context, or are running
 	 * in an atomic region, then we must not take the fault.
 	 */
-	if (unlikely(faulthandler_disabled() || !mm))
-		goto no_context;
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		tsk->thread.bad_cause = cause;
+		no_context(regs, addr);
+		return;
+	}
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
+	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);
 
+	if (cause == EXC_STORE_PAGE_FAULT)
+		flags |= FAULT_FLAG_WRITE;
+	else if (cause == EXC_INST_PAGE_FAULT)
+		flags |= FAULT_FLAG_INSTRUCTION;
+	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);
+		goto lock_mmap;
+	}
+
+	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;
+	}
+lock_mmap:
+
 retry:
-	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, addr);
-	if (unlikely(!vma))
-		goto bad_area;
-	if (likely(vma->vm_start <= addr))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
-		goto bad_area;
-	if (unlikely(expand_stack(vma, addr)))
-		goto bad_area;
+	vma = lock_mm_and_find_vma(mm, addr, regs);
+	if (unlikely(!vma)) {
+		tsk->thread.bad_cause = cause;
+		bad_area_nosemaphore(regs, code, addr);
+		return;
+	}
 
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it.
 	 */
-good_area:
 	code = SEGV_ACCERR;
 
-	switch (cause) {
-	case EXC_INST_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_EXEC))
-			goto bad_area;
-		break;
-	case EXC_LOAD_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_READ))
-			goto bad_area;
-		break;
-	case EXC_STORE_PAGE_FAULT:
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;
-		flags |= FAULT_FLAG_WRITE;
-		break;
-	default:
-		panic("%s: unhandled cause %lu", __func__, cause);
+	if (unlikely(access_error(cause, vma))) {
+		tsk->thread.bad_cause = cause;
+		bad_area(regs, mm, code, addr);
+		return;
 	}
 
 	/*
@@ -110,173 +339,41 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags, regs);
 
 	/*
 	 * If we need to retry but a fatal signal is pending, handle the
-	 * signal first. We do not need to release the mmap_sem because it
+	 * 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 & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
 		return;
-
-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		if (fault & VM_FAULT_OOM)
-			goto out_of_memory;
-		else if (fault & VM_FAULT_SIGBUS)
-			goto do_sigbus;
-		BUG();
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
-	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, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
-				      1, regs, addr);
-		}
-		if (fault & VM_FAULT_RETRY) {
-			/*
-			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation.
-			 */
-			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;
-		}
-	}
-
-	up_read(&mm->mmap_sem);
-	return;
-
-	/*
-	 * Something tried to access memory that isn't in our memory map.
-	 * Fix it, but check if it's kernel or user first.
-	 */
-bad_area:
-	up_read(&mm->mmap_sem);
-	/* User mode accesses just cause a SIGSEGV */
-	if (user_mode(regs)) {
-		do_trap(regs, SIGSEGV, code, addr);
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
 		return;
-	}
-
-no_context:
-	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs))
-		return;
-
-	/*
-	 * Oops. The kernel tried to access some bad page. We'll have to
-	 * terminate things with extreme prejudice.
-	 */
-	bust_spinlocks(1);
-	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
-		(addr < PAGE_SIZE) ? "NULL pointer dereference" :
-		"paging request", addr);
-	die(regs, "Oops");
-	do_exit(SIGKILL);
-
-	/*
-	 * 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).
-	 */
-out_of_memory:
-	up_read(&mm->mmap_sem);
-	if (!user_mode(regs))
-		goto no_context;
-	pagefault_out_of_memory();
-	return;
-
-do_sigbus:
-	up_read(&mm->mmap_sem);
-	/* Kernel mode? Handle exceptions or die */
-	if (!user_mode(regs))
-		goto no_context;
-	do_trap(regs, SIGBUS, BUS_ADRERR, addr);
-	return;
-
-vmalloc_fault:
-	{
-		pgd_t *pgd, *pgd_k;
-		pud_t *pud, *pud_k;
-		p4d_t *p4d, *p4d_k;
-		pmd_t *pmd, *pmd_k;
-		pte_t *pte_k;
-		int index;
-
-		/* User mode accesses just cause a SIGSEGV */
-		if (user_mode(regs))
-			return do_trap(regs, SIGSEGV, code, addr);
-
-		/*
-		 * Synchronize this task's top level page-table
-		 * with the 'reference' page table.
-		 *
-		 * Do _not_ use "tsk->active_mm->pgd" here.
-		 * We might be inside an interrupt in the middle
-		 * of a task switch.
-		 */
-		index = pgd_index(addr);
-		pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
-		pgd_k = init_mm.pgd + index;
-
-		if (!pgd_present(*pgd_k))
-			goto no_context;
-		set_pgd(pgd, *pgd_k);
-
-		p4d = p4d_offset(pgd, addr);
-		p4d_k = p4d_offset(pgd_k, addr);
-		if (!p4d_present(*p4d_k))
-			goto no_context;
 
-		pud = pud_offset(p4d, addr);
-		pud_k = pud_offset(p4d_k, addr);
-		if (!pud_present(*pud_k))
-			goto no_context;
-
-		/*
-		 * Since the vmalloc area is global, it is unnecessary
-		 * to copy individual PTEs
-		 */
-		pmd = pmd_offset(pud, addr);
-		pmd_k = pmd_offset(pud_k, addr);
-		if (!pmd_present(*pmd_k))
-			goto no_context;
-		set_pmd(pmd, *pmd_k);
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
 
 		/*
-		 * Make sure the actual PTE exists as well to
-		 * catch kernel vmalloc-area accesses to non-mapped
-		 * addresses. If we don't do this, this will just
-		 * silently loop forever.
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
 		 */
-		pte_k = pte_offset_kernel(pmd_k, addr);
-		if (!pte_present(*pte_k))
-			goto no_context;
+		goto retry;
+	}
 
-		/*
-		 * The kernel assumes that TLBs don't cache invalid
-		 * entries, but in RISC-V, SFENCE.VMA specifies an
-		 * ordering constraint, not a cache flush; it is
-		 * necessary even after writing invalid entries.
-		 */
-		local_flush_tlb_page(addr);
+	mmap_read_unlock(mm);
 
+done:
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		tsk->thread.bad_cause = cause;
+		mm_fault_error(regs, addr, fault);
 		return;
 	}
+	return;
 }