Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The most interesting parts are probably the mm changes from Ryan which
  optimise the creation of the linear mapping at boot and (separately)
  implement write-protect support for userfaultfd.

  Outside of our usual directories, the Kbuild-related changes under
  scripts/ have been acked by Masahiro whilst the drivers/acpi/ parts
  have been acked by Rafael and the addition of cpumask_any_and_but()
  has been acked by Yury.

  ACPI:

   - Support for the Firmware ACPI Control Structure (FACS) signature
     feature which is used to reboot out of hibernation on some systems

  Kbuild:

   - Support for building Flat Image Tree (FIT) images, where the kernel
     Image is compressed alongside a set of devicetree blobs

  Memory management:

   - Optimisation of our early page-table manipulation for creation of
     the linear mapping

   - Support for userfaultfd write protection, which brings along some
     nice cleanups to our handling of invalid but present ptes

   - Extend our use of range TLBI invalidation at EL1

  Perf and PMUs:

   - Ensure that the 'pmu->parent' pointer is correctly initialised by
     PMU drivers

   - Avoid allocating 'cpumask_t' types on the stack in some PMU drivers

   - Fix parsing of the CPU PMU "version" field in assembly code, as it
     doesn't follow the usual architectural rules

   - Add best-effort unwinding support for USER_STACKTRACE

   - Minor driver fixes and cleanups

  Selftests:

   - Minor cleanups to the arm64 selftests (missing NULL check, unused
     variable)

  Miscellaneous:

   - Add a command-line alias for disabling 32-bit application support

   - Add part number for Neoverse-V2 CPUs

   - Minor fixes and cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (64 commits)
  arm64/mm: Fix pud_user_accessible_page() for PGTABLE_LEVELS <= 2
  arm64/mm: Add uffd write-protect support
  arm64/mm: Move PTE_PRESENT_INVALID to overlay PTE_NG
  arm64/mm: Remove PTE_PROT_NONE bit
  arm64/mm: generalize PMD_PRESENT_INVALID for all levels
  arm64: simplify arch_static_branch/_jump function
  arm64: Add USER_STACKTRACE support
  arm64: Add the arm64.no32bit_el0 command line option
  drivers/perf: hisi: hns3: Actually use devm_add_action_or_reset()
  drivers/perf: hisi: hns3: Fix out-of-bound access when valid event group
  drivers/perf: hisi_pcie: Fix out-of-bound access when valid event group
  kselftest: arm64: Add a null pointer check
  arm64: defer clearing DAIF.D
  arm64: assembler: update stale comment for disable_step_tsk
  arm64/sysreg: Update PIE permission encodings
  kselftest/arm64: Remove unused parameters in abi test
  perf/arm-spe: Assign parents for event_source device
  perf/arm-smmuv3: Assign parents for event_source device
  perf/arm-dsu: Assign parents for event_source device
  perf/arm-dmc620: Assign parents for event_source device
  ...

6 files changed, 152 insertions, 116 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index dba8fcec7f33..e0e7b93c16cc 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -26,6 +26,7 @@
 #include <linux/libfdt.h>
 #include <linux/smp.h>
 #include <linux/serial_core.h>
+#include <linux/suspend.h>
 #include <linux/pgtable.h>
 
 #include <acpi/ghes.h>
@@ -227,6 +228,15 @@ done:
 		if (earlycon_acpi_spcr_enable)
 			early_init_dt_scan_chosen_stdout();
 	} else {
+#ifdef CONFIG_HIBERNATION
+		struct acpi_table_header *facs = NULL;
+		acpi_get_table(ACPI_SIG_FACS, 1, &facs);
+		if (facs) {
+			swsusp_hardware_signature =
+				((struct acpi_table_facs *)facs)->hardware_signature;
+			acpi_put_table(facs);
+		}
+#endif
 		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
 		if (IS_ENABLED(CONFIG_ACPI_BGRT))
 			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 6d157f32187b..e8ed5673f481 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -10,94 +10,12 @@
 
 #include <asm/pointer_auth.h>
 
-struct frame_tail {
-	struct frame_tail	__user *fp;
-	unsigned long		lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry_ctx *entry)
-{
-	struct frame_tail buftail;
-	unsigned long err;
-	unsigned long lr;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	lr = ptrauth_strip_user_insn_pac(buftail.lr);
-
-	perf_callchain_store(entry, lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail >= buftail.fp)
-		return NULL;
-
-	return buftail.fp;
-}
-
-#ifdef CONFIG_COMPAT
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct compat_frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct compat_frame_tail {
-	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
-	u32		sp;
-	u32		lr;
-} __attribute__((packed));
-
-static struct compat_frame_tail __user *
-compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry_ctx *entry)
+static bool callchain_trace(void *data, unsigned long pc)
 {
-	struct compat_frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= (struct compat_frame_tail __user *)
-			compat_ptr(buftail.fp))
-		return NULL;
+	struct perf_callchain_entry_ctx *entry = data;
 
-	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+	return perf_callchain_store(entry, pc) == 0;
 }
-#endif /* CONFIG_COMPAT */
 
 void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
@@ -107,35 +25,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 		return;
 	}
 
-	perf_callchain_store(entry, regs->pc);
-
-	if (!compat_user_mode(regs)) {
-		/* AARCH64 mode */
-		struct frame_tail __user *tail;
-
-		tail = (struct frame_tail __user *)regs->regs[29];
-
-		while (entry->nr < entry->max_stack &&
-		       tail && !((unsigned long)tail & 0x7))
-			tail = user_backtrace(tail, entry);
-	} else {
-#ifdef CONFIG_COMPAT
-		/* AARCH32 compat mode */
-		struct compat_frame_tail __user *tail;
-
-		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
-
-		while ((entry->nr < entry->max_stack) &&
-			tail && !((unsigned long)tail & 0x3))
-			tail = compat_user_backtrace(tail, entry);
-#endif
-	}
-}
-
-static bool callchain_trace(void *data, unsigned long pc)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-	return perf_callchain_store(entry, pc) == 0;
+	arch_stack_walk_user(callchain_trace, entry, regs);
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
index aad399796e81..48c1aa456af9 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -108,6 +108,7 @@ static const struct ftr_set_desc pfr0 __prel64_initconst = {
 	.override	= &id_aa64pfr0_override,
 	.fields		= {
 	        FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter),
+		FIELD("el0", ID_AA64PFR0_EL1_EL0_SHIFT, NULL),
 		{}
 	},
 };
@@ -223,6 +224,7 @@ static const struct {
 	{ "nokaslr",			"arm64_sw.nokaslr=1" },
 	{ "rodata=off",			"arm64_sw.rodataoff=1" },
 	{ "arm64.nolva",		"id_aa64mmfr2.varange=0" },
+	{ "arm64.no32bit_el0",		"id_aa64pfr0.el0=1" },
 };
 
 static int __init parse_hexdigit(const char *p, u64 *v)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 65a052bf741f..a096e2451044 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -298,8 +298,15 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	dynamic_scs_init();
 
 	/*
-	 * Unmask SError as soon as possible after initializing earlycon so
-	 * that we can report any SErrors immediately.
+	 * The primary CPU enters the kernel with all DAIF exceptions masked.
+	 *
+	 * We must unmask Debug and SError before preemption or scheduling is
+	 * possible to ensure that these are consistently unmasked across
+	 * threads, and we want to unmask SError as soon as possible after
+	 * initializing earlycon so that we can report any SErrors immediately.
+	 *
+	 * IRQ and FIQ will be unmasked after the root irqchip has been
+	 * detected and initialized.
 	 */
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 4ced34f62dab..31c8b3094dd7 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -264,6 +264,13 @@ asmlinkage notrace void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
+	/*
+	 * Secondary CPUs enter the kernel with all DAIF exceptions masked.
+	 *
+	 * As with setup_arch() we must unmask Debug and SError exceptions, and
+	 * as the root irqchip has already been detected and initialized we can
+	 * unmask IRQ and FIQ at the same time.
+	 */
 	local_daif_restore(DAIF_PROCCTX);
 
 	/*
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 684c26511696..6b3258860377 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -324,3 +324,123 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 	dump_backtrace(NULL, tsk, loglvl);
 	barrier();
 }
+
+/*
+ * The struct defined for userspace stack frame in AARCH64 mode.
+ */
+struct frame_tail {
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+unwind_user_frame(struct frame_tail __user *tail, void *cookie,
+	       stack_trace_consume_fn consume_entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+	unsigned long lr;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	lr = ptrauth_strip_user_insn_pac(buftail.lr);
+
+	if (!consume_entry(cookie, lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp;
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+unwind_compat_user_frame(struct compat_frame_tail __user *tail, void *cookie,
+				stack_trace_consume_fn consume_entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	if (!consume_entry(cookie, buftail.lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
+
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+					const struct pt_regs *regs)
+{
+	if (!consume_entry(cookie, regs->pc))
+		return;
+
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+		while (tail && !((unsigned long)tail & 0x7))
+			tail = unwind_user_frame(tail, cookie, consume_entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+		while (tail && !((unsigned long)tail & 0x3))
+			tail = unwind_compat_user_frame(tail, cookie, consume_entry);
+#endif
+	}
+}