1 files changed, 101 insertions, 78 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 971977c438fc..622d12ec7f08 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -19,6 +19,7 @@
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
 #include <linux/mm_types.h>
+#include <linux/mm.h>			/* find_and_lock_vma() */
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -33,6 +34,8 @@
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
 #include <asm/irq_stack.h>
+#include <asm/fred.h>
+#include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -249,7 +252,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
-	if (pmd_large(*pmd_k))
+	if (pmd_leaf(*pmd_k))
 		return 0;
 
 	pte_k = pte_offset_kernel(pmd_k, address);
@@ -318,7 +321,7 @@ static void dump_pagetable(unsigned long address)
 	 * And let's rather not kmap-atomic the pte, just in case
 	 * it's allocated already:
 	 */
-	if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd))
+	if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd))
 		goto out;
 
 	pte = pte_offset_kernel(pmd, address);
@@ -367,7 +370,7 @@ static void dump_pagetable(unsigned long address)
 		goto bad;
 
 	pr_cont("P4D %lx ", p4d_val(*p4d));
-	if (!p4d_present(*p4d) || p4d_large(*p4d))
+	if (!p4d_present(*p4d) || p4d_leaf(*p4d))
 		goto out;
 
 	pud = pud_offset(p4d, address);
@@ -375,7 +378,7 @@ static void dump_pagetable(unsigned long address)
 		goto bad;
 
 	pr_cont("PUD %lx ", pud_val(*pud));
-	if (!pud_present(*pud) || pud_large(*pud))
+	if (!pud_present(*pud) || pud_leaf(*pud))
 		goto out;
 
 	pmd = pmd_offset(pud, address);
@@ -383,7 +386,7 @@ static void dump_pagetable(unsigned long address)
 		goto bad;
 
 	pr_cont("PMD %lx ", pmd_val(*pmd));
-	if (!pmd_present(*pmd) || pmd_large(*pmd))
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
 		goto out;
 
 	pte = pte_offset_kernel(pmd, address);
@@ -546,6 +549,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 		 !(error_code & X86_PF_PROT) ? "not-present page" :
 		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
 		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+		 (error_code & X86_PF_RMP)   ? "RMP violation" :
 					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
@@ -578,6 +582,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 	}
 
 	dump_pagetable(address);
+
+	if (error_code & X86_PF_RMP)
+		snp_dump_hva_rmpentry(address);
 }
 
 static noinline void
@@ -769,6 +776,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address, struct task_struct *tsk)
 {
 	const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
+	/* This is a racy snapshot, but it's better than nothing. */
+	int cpu = raw_smp_processor_id();
 
 	if (!unhandled_signal(tsk, SIGSEGV))
 		return;
@@ -782,20 +791,19 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 
 	print_vma_addr(KERN_CONT " in ", regs->ip);
 
+	/*
+	 * Dump the likely CPU where the fatal segfault happened.
+	 * This can help identify faulty hardware.
+	 */
+	printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu,
+	       topology_core_id(cpu), topology_physical_package_id(cpu));
+
+
 	printk(KERN_CONT "\n");
 
 	show_opcodes(regs, loglvl);
 }
 
-/*
- * The (legacy) vsyscall page is the long page in the kernel portion
- * of the address space that has user-accessible permissions.
- */
-static bool is_vsyscall_vaddr(unsigned long vaddr)
-{
-	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
-}
-
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		       unsigned long address, u32 pkey, int si_code)
@@ -869,12 +877,6 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
 	__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
 }
 
-static noinline void
-bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
-{
-	__bad_area(regs, error_code, address, 0, SEGV_MAPERR);
-}
-
 static inline bool bad_area_access_from_pkeys(unsigned long error_code,
 		struct vm_area_struct *vma)
 {
@@ -1034,21 +1036,21 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address)
 	if (!p4d_present(*p4d))
 		return 0;
 
-	if (p4d_large(*p4d))
+	if (p4d_leaf(*p4d))
 		return spurious_kernel_fault_check(error_code, (pte_t *) p4d);
 
 	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		return 0;
 
-	if (pud_large(*pud))
+	if (pud_leaf(*pud))
 		return spurious_kernel_fault_check(error_code, (pte_t *) pud);
 
 	pmd = pmd_offset(pud, address);
 	if (!pmd_present(*pmd))
 		return 0;
 
-	if (pmd_large(*pmd))
+	if (pmd_leaf(*pmd))
 		return spurious_kernel_fault_check(error_code, (pte_t *) pmd);
 
 	pte = pte_offset_kernel(pmd, address);
@@ -1107,8 +1109,22 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
 				       (error_code & X86_PF_INSTR), foreign))
 		return 1;
 
+	/*
+	 * Shadow stack accesses (PF_SHSTK=1) are only permitted to
+	 * shadow stack VMAs. All other accesses result in an error.
+	 */
+	if (error_code & X86_PF_SHSTK) {
+		if (unlikely(!(vma->vm_flags & VM_SHADOW_STACK)))
+			return 1;
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
+			return 1;
+		return 0;
+	}
+
 	if (error_code & X86_PF_WRITE) {
 		/* write, present and write, not present: */
+		if (unlikely(vma->vm_flags & VM_SHADOW_STACK))
+			return 1;
 		if (unlikely(!(vma->vm_flags & VM_WRITE)))
 			return 1;
 		return 0;
@@ -1283,28 +1299,37 @@ void do_user_addr_fault(struct pt_regs *regs,
 		return;
 	}
 
-	/*
-	 * It's safe to allow irq's after cr2 has been saved and the
-	 * vmalloc fault has been handled.
-	 *
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet:
-	 */
-	if (user_mode(regs)) {
-		local_irq_enable();
-		flags |= FAULT_FLAG_USER;
-	} else {
-		if (regs->flags & X86_EFLAGS_IF)
-			local_irq_enable();
+	/* Legacy check - remove this after verifying that it doesn't trigger */
+	if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
+	local_irq_enable();
+
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+	/*
+	 * Read-only permissions can not be expressed in shadow stack PTEs.
+	 * Treat all shadow stack accesses as WRITE faults. This ensures
+	 * that the MM will prepare everything (e.g., break COW) such that
+	 * maybe_mkwrite() can create a proper shadow stack PTE.
+	 */
+	if (error_code & X86_PF_SHSTK)
+		flags |= FAULT_FLAG_WRITE;
 	if (error_code & X86_PF_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 	if (error_code & X86_PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+	/*
+	 * We set FAULT_FLAG_USER based on the register state, not
+	 * based on X86_PF_USER. User space accesses that cause
+	 * system page faults are still user accesses.
+	 */
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 #ifdef CONFIG_X86_64
 	/*
 	 * Faults in the vsyscall page might need emulation.  The
@@ -1323,51 +1348,43 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 #endif
 
-	/*
-	 * Kernel-mode access to the user address space should only occur
-	 * on well-defined single instructions listed in the exception
-	 * tables.  But, an erroneous kernel fault occurring outside one of
-	 * those areas which also holds mmap_lock might deadlock attempting
-	 * to validate the fault against the address space.
-	 *
-	 * Only do the expensive exception table search when we might be at
-	 * risk of a deadlock.  This happens if we
-	 * 1. Failed to acquire mmap_lock, and
-	 * 2. The access did not originate in userspace.
-	 */
-	if (unlikely(!mmap_read_trylock(mm))) {
-		if (!user_mode(regs) && !search_exception_tables(regs->ip)) {
-			/*
-			 * Fault from code in kernel from
-			 * which we do not expect faults.
-			 */
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
-retry:
-		mmap_read_lock(mm);
-	} else {
-		/*
-		 * The above down_read_trylock() might have succeeded in
-		 * which case we'll have missed the might_sleep() from
-		 * down_read():
-		 */
-		might_sleep();
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(error_code, vma))) {
+		vma_end_read(vma);
+		goto lock_mmap;
 	}
+	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 
-	vma = find_vma(mm, address);
-	if (unlikely(!vma)) {
-		bad_area(regs, error_code, address);
-		return;
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
 	}
-	if (likely(vma->vm_start <= address))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
-		bad_area(regs, error_code, address);
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
 		return;
 	}
-	if (unlikely(expand_stack(vma, address))) {
-		bad_area(regs, error_code, address);
+lock_mmap:
+
+retry:
+	vma = lock_mm_and_find_vma(mm, address, regs);
+	if (unlikely(!vma)) {
+		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
@@ -1375,7 +1392,6 @@ 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, vma);
 		return;
@@ -1408,6 +1424,10 @@ good_area:
 		return;
 	}
 
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
 	/*
 	 * If we need to retry the mmap_lock has already been released,
 	 * and if there is a fatal signal pending there is no guarantee
@@ -1419,6 +1439,7 @@ good_area:
 	}
 
 	mmap_read_unlock(mm);
+done:
 	if (likely(!(fault & VM_FAULT_ERROR)))
 		return;
 
@@ -1495,8 +1516,10 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
-	unsigned long address = read_cr2();
 	irqentry_state_t state;
+	unsigned long address;
+
+	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
 	prefetchw(&current->mm->mmap_lock);