1 files changed, 221 insertions, 81 deletions

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 37b95dff0b07..89993c4be1be 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -31,8 +31,10 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 #include <linux/preempt.h>
+#include <linux/hugetlb.h>
 
 #include <asm/bug.h>
+#include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -42,6 +44,8 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+#include <acpi/ghes.h>
+
 struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr,
 		      struct pt_regs *regs);
@@ -79,19 +83,79 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
 }
 #endif
 
+static void data_abort_decode(unsigned int esr)
+{
+	pr_alert("Data abort info:\n");
+
+	if (esr & ESR_ELx_ISV) {
+		pr_alert("  Access size = %u byte(s)\n",
+			 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+		pr_alert("  SSE = %lu, SRT = %lu\n",
+			 (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+			 (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+		pr_alert("  SF = %lu, AR = %lu\n",
+			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+	} else {
+		pr_alert("  ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+	}
+
+	pr_alert("  CM = %lu, WnR = %lu\n",
+		 (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+		 (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+/*
+ * Decode mem abort information
+ */
+static void mem_abort_decode(unsigned int esr)
+{
+	pr_alert("Mem abort info:\n");
+
+	pr_alert("  Exception class = %s, IL = %u bits\n",
+		 esr_get_class_string(esr),
+		 (esr & ESR_ELx_IL) ? 32 : 16);
+	pr_alert("  SET = %lu, FnV = %lu\n",
+		 (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+		 (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+	pr_alert("  EA = %lu, S1PTW = %lu\n",
+		 (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+		 (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+	if (esr_is_data_abort(esr))
+		data_abort_decode(esr);
+}
+
 /*
- * Dump out the page tables associated with 'addr' in mm 'mm'.
+ * Dump out the page tables associated with 'addr' in the currently active mm.
  */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(unsigned long addr)
 {
+	struct mm_struct *mm;
 	pgd_t *pgd;
 
-	if (!mm)
+	if (addr < TASK_SIZE) {
+		/* TTBR0 */
+		mm = current->active_mm;
+		if (mm == &init_mm) {
+			pr_alert("[%016lx] user address but active_mm is swapper\n",
+				 addr);
+			return;
+		}
+	} else if (addr >= VA_START) {
+		/* TTBR1 */
 		mm = &init_mm;
+	} else {
+		pr_alert("[%016lx] address between user and kernel address ranges\n",
+			 addr);
+		return;
+	}
 
-	pr_alert("pgd = %p\n", mm->pgd);
+	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n",
+		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
+		 VA_BITS, mm->pgd);
 	pgd = pgd_offset(mm, addr);
-	pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));
+	pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
 
 	do {
 		pud_t *pud;
@@ -119,7 +183,6 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	pr_cont("\n");
 }
 
-#ifdef CONFIG_ARM64_HW_AFDBM
 /*
  * This function sets the access flags (dirty, accessed), as well as write
  * permission, and only to a more permissive setting.
@@ -134,40 +197,33 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  unsigned long address, pte_t *ptep,
 			  pte_t entry, int dirty)
 {
-	pteval_t old_pteval;
-	unsigned int tmp;
+	pteval_t old_pteval, pteval;
 
 	if (pte_same(*ptep, entry))
 		return 0;
 
 	/* only preserve the access flags and write permission */
-	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
-
-	/*
-	 * PTE_RDONLY is cleared by default in the asm below, so set it in
-	 * back if necessary (read-only or clean PTE).
-	 */
-	if (!pte_write(entry) || !pte_sw_dirty(entry))
-		pte_val(entry) |= PTE_RDONLY;
+	pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
-	 * hardware update of the access/dirty state.
+	 * hardware update of the access/dirty state. The PTE_RDONLY bit must
+	 * be set to the most permissive (lowest value) of *ptep and entry
+	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
-	asm volatile("//	ptep_set_access_flags\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
-	"	orr	%0, %0, %4		// set flags\n"
-	"	stxr	%w1, %0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+	pte_val(entry) ^= PTE_RDONLY;
+	pteval = READ_ONCE(pte_val(*ptep));
+	do {
+		old_pteval = pteval;
+		pteval ^= PTE_RDONLY;
+		pteval |= pte_val(entry);
+		pteval ^= PTE_RDONLY;
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+	} while (pteval != old_pteval);
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
 }
-#endif
 
 static bool is_el1_instruction_abort(unsigned int esr)
 {
@@ -196,8 +252,8 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
 /*
  * The kernel tried to access some page that wasn't present.
  */
-static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
-			      unsigned int esr, struct pt_regs *regs)
+static void __do_kernel_fault(unsigned long addr, unsigned int esr,
+			      struct pt_regs *regs)
 {
 	const char *msg;
 
@@ -227,7 +283,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
 		 addr);
 
-	show_pte(mm, addr);
+	mem_abort_decode(esr);
+
+	show_pte(addr);
 	die("Oops", regs, esr);
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
@@ -239,18 +297,20 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
  */
 static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 			    unsigned int esr, unsigned int sig, int code,
-			    struct pt_regs *regs)
+			    struct pt_regs *regs, int fault)
 {
 	struct siginfo si;
 	const struct fault_info *inf;
+	unsigned int lsb = 0;
 
 	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
 		inf = esr_to_fault_info(esr);
-		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
+		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x",
 			tsk->comm, task_pid_nr(tsk), inf->name, sig,
 			addr, esr);
-		show_pte(tsk->mm, addr);
-		show_regs(regs);
+		print_vma_addr(KERN_CONT ", in ", regs->pc);
+		pr_cont("\n");
+		__show_regs(regs);
 	}
 
 	tsk->thread.fault_address = addr;
@@ -259,13 +319,23 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	si.si_errno = 0;
 	si.si_code = code;
 	si.si_addr = (void __user *)addr;
+	/*
+	 * Either small page or large page may be poisoned.
+	 * In other words, VM_FAULT_HWPOISON_LARGE and
+	 * VM_FAULT_HWPOISON are mutually exclusive.
+	 */
+	if (fault & VM_FAULT_HWPOISON_LARGE)
+		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+	else if (fault & VM_FAULT_HWPOISON)
+		lsb = PAGE_SHIFT;
+	si.si_addr_lsb = lsb;
+
 	force_sig_info(sig, &si, tsk);
 }
 
 static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->active_mm;
 	const struct fault_info *inf;
 
 	/*
@@ -274,9 +344,9 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 	 */
 	if (user_mode(regs)) {
 		inf = esr_to_fault_info(esr);
-		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs, 0);
 	} else
-		__do_kernel_fault(mm, addr, esr, regs);
+		__do_kernel_fault(addr, esr, regs);
 }
 
 #define VM_FAULT_BADMAP		0x010000
@@ -329,7 +399,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	struct task_struct *tsk;
 	struct mm_struct *mm;
-	int fault, sig, code;
+	int fault, sig, code, major = 0;
 	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
@@ -368,6 +438,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 			die("Accessing user space memory outside uaccess.h routines", regs, esr);
 	}
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -391,24 +463,45 @@ retry:
 	}
 
 	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
+	major |= fault & VM_FAULT_MAJOR;
 
-	/*
-	 * 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
-	 * would already be released in __lock_page_or_retry in mm/filemap.c.
-	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
-		return 0;
+	if (fault & VM_FAULT_RETRY) {
+		/*
+		 * 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 would already be released
+		 * in __lock_page_or_retry in mm/filemap.c.
+		 */
+		if (fatal_signal_pending(current)) {
+			if (!user_mode(regs))
+				goto no_context;
+			return 0;
+		}
+
+		/*
+		 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
+		 * starvation.
+		 */
+		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
+			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			mm_flags |= FAULT_FLAG_TRIED;
+			goto retry;
+		}
+	}
+	up_read(&mm->mmap_sem);
 
 	/*
-	 * 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.
+	 * Handle the "normal" (no error) case first.
 	 */
-
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
+	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
+			      VM_FAULT_BADACCESS)))) {
+		/*
+		 * Major/minor page fault accounting is only done
+		 * once. If we go through a retry, it is extremely
+		 * likely that the page will be found in page cache at
+		 * that point.
+		 */
+		if (major) {
 			tsk->maj_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
 				      addr);
@@ -417,25 +510,9 @@ retry:
 			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.
-			 */
-			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			mm_flags |= FAULT_FLAG_TRIED;
-			goto retry;
-		}
-	}
-
-	up_read(&mm->mmap_sem);
 
-	/*
-	 * Handle the "normal" case first - VM_FAULT_MAJOR
-	 */
-	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS))))
 		return 0;
+	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
@@ -461,6 +538,9 @@ retry:
 		 */
 		sig = SIGBUS;
 		code = BUS_ADRERR;
+	} else if (fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
+		sig = SIGBUS;
+		code = BUS_MCEERR_AR;
 	} else {
 		/*
 		 * Something tried to access memory that isn't in our memory
@@ -471,11 +551,11 @@ retry:
 			SEGV_ACCERR : SEGV_MAPERR;
 	}
 
-	__do_user_fault(tsk, addr, esr, sig, code, regs);
+	__do_user_fault(tsk, addr, esr, sig, code, regs, fault);
 	return 0;
 
 no_context:
-	__do_kernel_fault(mm, addr, esr, regs);
+	__do_kernel_fault(addr, esr, regs);
 	return 0;
 }
 
@@ -522,6 +602,47 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
+/*
+ * This abort handler deals with Synchronous External Abort.
+ * It calls notifiers, and then returns "fault".
+ */
+static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+	struct siginfo info;
+	const struct fault_info *inf;
+	int ret = 0;
+
+	inf = esr_to_fault_info(esr);
+	pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
+		inf->name, esr, addr);
+
+	/*
+	 * Synchronous aborts may interrupt code which had interrupts masked.
+	 * Before calling out into the wider kernel tell the interested
+	 * subsystems.
+	 */
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
+		if (interrupts_enabled(regs))
+			nmi_enter();
+
+		ret = ghes_notify_sea();
+
+		if (interrupts_enabled(regs))
+			nmi_exit();
+	}
+
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code  = 0;
+	if (esr & ESR_ELx_FnV)
+		info.si_addr = NULL;
+	else
+		info.si_addr  = (void __user *)addr;
+	arm64_notify_die("", regs, &info, esr);
+
+	return ret;
+}
+
 static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
@@ -539,22 +660,22 @@ static const struct fault_info fault_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_sea,		SIGBUS,  0,		"level 0 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
@@ -590,6 +711,23 @@ static const struct fault_info fault_info[] = {
 };
 
 /*
+ * Handle Synchronous External Aborts that occur in a guest kernel.
+ *
+ * The return value will be zero if the SEA was successfully handled
+ * and non-zero if there was an error processing the error or there was
+ * no error to process.
+ */
+int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+	int ret = -ENOENT;
+
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
+		ret = ghes_notify_sea();
+
+	return ret;
+}
+
+/*
  * Dispatch a data abort to the relevant handler.
  */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
@@ -604,6 +742,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
 		 inf->name, esr, addr);
 
+	mem_abort_decode(esr);
+
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;