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

Pull arm64 fixes from Catalin Marinas:

 - Avoid writing an uninitialised stack variable to POR_EL0 on sigreturn
   if the poe_context record is absent

 - Reserve one more page for the early 4K-page kernel mapping to cover
   the extra [_text, _stext) split introduced by the non-executable
   read-only mapping

 - Force the arch_local_irq_*() wrappers to be __always_inline so that
   noinstr entry and idle paths cannot call out-of-line, instrumentable
   copies

 - Fix potential sign extension in the arm64 SCS unwinder's DWARF
   advance_loc4 decoding

 - Tolerate arm64 ACPI platforms with only WFI and no deeper PSCI idle
   states, restoring cpuidle registration on such systems

 - Include the UAPI <asm/ptrace.h> header in the arm64 GCS libc test
   rather than carrying a duplicate struct user_gcs definition (the
   original #ifdef NT_ARM_GCS was wrong to cover the structure
   definition as it would be masked out if the toolchain defined it)

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: signal: Preserve POR_EL0 if poe_context is missing
  arm64: Reserve an extra page for early kernel mapping
  kselftest/arm64: Include <asm/ptrace.h> for user_gcs definition
  ACPI: arm64: cpuidle: Tolerate platforms with no deep PSCI idle states
  arm64/irqflags: __always_inline the arch_local_irq_*() helpers
  arm64/scs: Fix potential sign extension issue of advance_loc4

Author: torvalds

arch/arm64/include/asm/irqflags.h

@@ -40,7 +40,7 @@ static __always_inline void __pmr_local_irq_enable(void)
 	barrier();
 }
 
-static inline void arch_local_irq_enable(void)
+static __always_inline void arch_local_irq_enable(void)
 {
 	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_enable();
@@ -68,7 +68,7 @@ static __always_inline void __pmr_local_irq_disable(void)
 	barrier();
 }
 
-static inline void arch_local_irq_disable(void)
+static __always_inline void arch_local_irq_disable(void)
 {
 	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_disable();
@@ -90,7 +90,7 @@ static __always_inline unsigned long __pmr_local_save_flags(void)
 /*
  * Save the current interrupt enable state.
  */
-static inline unsigned long arch_local_save_flags(void)
+static __always_inline unsigned long arch_local_save_flags(void)
 {
 	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_save_flags();
@@ -109,7 +109,7 @@ static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags)
 	return flags != GIC_PRIO_IRQON;
 }
 
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
+static __always_inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled_flags(flags);
@@ -128,7 +128,7 @@ static __always_inline bool __pmr_irqs_disabled(void)
 	return __pmr_irqs_disabled_flags(__pmr_local_save_flags());
 }
 
-static inline bool arch_irqs_disabled(void)
+static __always_inline bool arch_irqs_disabled(void)
 {
 	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled();
@@ -160,7 +160,7 @@ static __always_inline unsigned long __pmr_local_irq_save(void)
 	return flags;
 }
 
-static inline unsigned long arch_local_irq_save(void)
+static __always_inline unsigned long arch_local_irq_save(void)
 {
 	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_irq_save();
@@ -187,7 +187,7 @@ static __always_inline void __pmr_local_irq_restore(unsigned long flags)
 /*
  * restore saved IRQ state
  */
-static inline void arch_local_irq_restore(unsigned long flags)
+static __always_inline void arch_local_irq_restore(unsigned long flags)
 {
 	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_restore(flags);

arch/arm64/include/asm/kernel-pgtable.h

@@ -68,7 +68,12 @@
 #define KERNEL_SEGMENT_COUNT	5
 
 #if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN
-#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1)
+/*
+ * KERNEL_SEGMENT_COUNT counts the permanent kernel VMAs. The early mapping
+ * has one additional split, [_text, _stext). Reserve one more page for the
+ * SWAPPER_BLOCK_SIZE-unaligned boundaries.
+ */
+#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 2)
 /*
  * The initial ID map consists of the kernel image, mapped as two separate
  * segments, and may appear misaligned wrt the swapper block size. This means

arch/arm64/kernel/pi/patch-scs.c

@@ -196,9 +196,9 @@ static int scs_handle_fde_frame(const struct eh_frame *frame,
 			loc += *opcode++ * code_alignment_factor;
 			loc += (*opcode++ << 8) * code_alignment_factor;
 			loc += (*opcode++ << 16) * code_alignment_factor;
-			loc += (*opcode++ << 24) * code_alignment_factor;
+			loc += ((u64)*opcode++ << 24) * code_alignment_factor;
 			size -= 4;
-		break;
+			break;
 
 		case DW_CFA_def_cfa:
 		case DW_CFA_offset_extended:

arch/arm64/kernel/signal.c

@@ -67,20 +67,45 @@ struct rt_sigframe_user_layout {
 	unsigned long end_offset;
 };
 
+#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
+#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
+
 /*
  * Holds any EL0-controlled state that influences unprivileged memory accesses.
  * This includes both accesses done in userspace and uaccess done in the kernel.
  *
  * This state needs to be carefully managed to ensure that it doesn't cause
  * uaccess to fail when setting up the signal frame, and the signal handler
  * itself also expects a well-defined state when entered.
+ *
+ * The struct should be zero-initialised. Its members should only be accessed
+ * via the accessors below. __valid_fields tracks which of the fields are valid
+ * (have been set to some value).
  */
 struct user_access_state {
-	u64 por_el0;
+	unsigned int __valid_fields;
+	u64 __por_el0;
 };
 
-#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
-#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
+#define UA_STATE_HAS_POR_EL0	BIT(0)
+
+static void set_ua_state_por_el0(struct user_access_state *ua_state,
+				 u64 por_el0)
+{
+	ua_state->__por_el0 = por_el0;
+	ua_state->__valid_fields |= UA_STATE_HAS_POR_EL0;
+}
+
+static int get_ua_state_por_el0(const struct user_access_state *ua_state,
+				u64 *por_el0)
+{
+	if (ua_state->__valid_fields & UA_STATE_HAS_POR_EL0) {
+		*por_el0 = ua_state->__por_el0;
+		return 0;
+	}
+
+	return -ENOENT;
+}
 
 /*
  * Save the user access state into ua_state and reset it to disable any
@@ -94,7 +119,7 @@ static void save_reset_user_access_state(struct user_access_state *ua_state)
 		for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
 			por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX);
 
-		ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
+		set_ua_state_por_el0(ua_state, read_sysreg_s(SYS_POR_EL0));
 		write_sysreg_s(por_enable_all, SYS_POR_EL0);
 		/*
 		 * No ISB required as we can tolerate spurious Overlay faults -
@@ -122,8 +147,10 @@ static void set_handler_user_access_state(void)
  */
 static void restore_user_access_state(const struct user_access_state *ua_state)
 {
-	if (system_supports_poe())
-		write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
+	u64 por_el0;
+
+	if (get_ua_state_por_el0(ua_state, &por_el0) == 0)
+		write_sysreg_s(por_el0, SYS_POR_EL0);
 }
 
 static void init_user_layout(struct rt_sigframe_user_layout *user)
@@ -333,11 +360,16 @@ static int restore_fpmr_context(struct user_ctxs *user)
 static int preserve_poe_context(struct poe_context __user *ctx,
 				const struct user_access_state *ua_state)
 {
-	int err = 0;
+	int err;
+	u64 por_el0;
+
+	err = get_ua_state_por_el0(ua_state, &por_el0);
+	if (WARN_ON_ONCE(err))
+		return err;
 
 	__put_user_error(POE_MAGIC, &ctx->head.magic, err);
 	__put_user_error(sizeof(*ctx), &ctx->head.size, err);
-	__put_user_error(ua_state->por_el0, &ctx->por_el0, err);
+	__put_user_error(por_el0, &ctx->por_el0, err);
 
 	return err;
 }
@@ -353,7 +385,7 @@ static int restore_poe_context(struct user_ctxs *user,
 
 	__get_user_error(por_el0, &(user->poe->por_el0), err);
 	if (!err)
-		ua_state->por_el0 = por_el0;
+		set_ua_state_por_el0(ua_state, por_el0);
 
 	return err;
 }
@@ -1095,7 +1127,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
-	struct user_access_state ua_state;
+	struct user_access_state ua_state = {};
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
@@ -1507,7 +1539,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 {
 	struct rt_sigframe_user_layout user;
 	struct rt_sigframe __user *frame;
-	struct user_access_state ua_state;
+	struct user_access_state ua_state = {};
 	int err = 0;
 
 	fpsimd_save_and_flush_current_state();

drivers/acpi/arm64/cpuidle.c

@@ -16,7 +16,7 @@
 
 static int psci_acpi_cpu_init_idle(unsigned int cpu)
 {
-	int i, count;
+	int i;
 	struct acpi_lpi_state *lpi;
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 
@@ -30,14 +30,10 @@ static int psci_acpi_cpu_init_idle(unsigned int cpu)
 	if (!psci_ops.cpu_suspend)
 		return -EOPNOTSUPP;
 
-	count = pr->power.count - 1;
-	if (count <= 0)
-		return -ENODEV;
-
-	for (i = 0; i < count; i++) {
+	for (i = 1; i < pr->power.count; i++) {
 		u32 state;
 
-		lpi = &pr->power.lpi_states[i + 1];
+		lpi = &pr->power.lpi_states[i];
 		/*
 		 * Only bits[31:0] represent a PSCI power_state while
 		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification

tools/testing/selftests/arm64/gcs/gcs-util.h

@@ -18,12 +18,6 @@
 
 #ifndef NT_ARM_GCS
 #define NT_ARM_GCS 0x410
-
-struct user_gcs {
-	__u64 features_enabled;
-	__u64 features_locked;
-	__u64 gcspr_el0;
-};
 #endif
 
 /* Shadow Stack/Guarded Control Stack interface */

tools/testing/selftests/arm64/gcs/libc-gcs.c

@@ -16,6 +16,7 @@
 
 #include <asm/hwcap.h>
 #include <asm/mman.h>
+#include <asm/ptrace.h>
 
 #include <linux/compiler.h>