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

Pull arm64 updates from Catalin Marinas:

 - Expose tag address bits in siginfo. The original arm64 ABI did not
   expose any of the bits 63:56 of a tagged address in siginfo. In the
   presence of user ASAN or MTE, this information may be useful. The
   implementation is generic to other architectures supporting tags
   (like SPARC ADI, subject to wiring up the arch code). The user will
   have to opt in via sigaction(SA_EXPOSE_TAGBITS) so that the extra
   bits, if available, become visible in si_addr.

 - Default to 32-bit wide ZONE_DMA. Previously, ZONE_DMA was set to the
   lowest 1GB to cope with the Raspberry Pi 4 limitations, to the
   detriment of other platforms. With these changes, the kernel scans
   the Device Tree dma-ranges and the ACPI IORT information before
   deciding on a smaller ZONE_DMA.

 - Strengthen READ_ONCE() to acquire when CONFIG_LTO=y. When building
   with LTO, there is an increased risk of the compiler converting an
   address dependency headed by a READ_ONCE() invocation into a control
   dependency and consequently allowing for harmful reordering by the
   CPU.

 - Add CPPC FFH support using arm64 AMU counters.

 - set_fs() removal on arm64. This renders the User Access Override
   (UAO) ARMv8 feature unnecessary.

 - Perf updates: PMU driver for the ARM DMC-620 memory controller, sysfs
   identifier file for SMMUv3, stop event counters support for i.MX8MP,
   enable the perf events-based hard lockup detector.

 - Reorganise the kernel VA space slightly so that 52-bit VA
   configurations can use more virtual address space.

 - Improve the robustness of the arm64 memory offline event notifier.

 - Pad the Image header to 64K following the EFI header definition
   updated recently to increase the section alignment to 64K.

 - Support CONFIG_CMDLINE_EXTEND on arm64.

 - Do not use tagged PC in the kernel (TCR_EL1.TBID1==1), freeing up 8
   bits for PtrAuth.

 - Switch to vmapped shadow call stacks.

 - Miscellaneous clean-ups.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (78 commits)
  perf/imx_ddr: Add system PMU identifier for userspace
  bindings: perf: imx-ddr: add compatible string
  arm64: Fix build failure when HARDLOCKUP_DETECTOR_PERF is enabled
  arm64: mte: fix prctl(PR_GET_TAGGED_ADDR_CTRL) if TCF0=NONE
  arm64: mark __system_matches_cap as __maybe_unused
  arm64: uaccess: remove vestigal UAO support
  arm64: uaccess: remove redundant PAN toggling
  arm64: uaccess: remove addr_limit_user_check()
  arm64: uaccess: remove set_fs()
  arm64: uaccess cleanup macro naming
  arm64: uaccess: split user/kernel routines
  arm64: uaccess: refactor __{get,put}_user
  arm64: uaccess: simplify __copy_user_flushcache()
  arm64: uaccess: rename privileged uaccess routines
  arm64: sdei: explicitly simulate PAN/UAO entry
  arm64: sdei: move uaccess logic to arch/arm64/
  arm64: head.S: always initialize PSTATE
  arm64: head.S: cleanup SCTLR_ELx initialization
  arm64: head.S: rename el2_setup -> init_kernel_el
  arm64: add C wrappers for SET_PSTATE_*()
  ...

9 files changed, 108 insertions, 59 deletions

diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 20a32120bb88..1a12baa58e40 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -38,6 +38,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
 const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
 						const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
+phys_addr_t acpi_iort_dma_get_max_cpu_address(void);
 #else
 static inline void acpi_iort_init(void) { }
 static inline u32 iort_msi_map_id(struct device *dev, u32 id)
@@ -55,6 +56,9 @@ static inline const struct iommu_ops *iort_iommu_configure_id(
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 { return 0; }
+
+static inline phys_addr_t acpi_iort_dma_get_max_cpu_address(void)
+{ return PHYS_ADDR_MAX; }
 #endif
 
 #endif /* __ACPI_IORT_H__ */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fb3bf696c05e..9d0c454d23cd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -354,26 +354,6 @@ enum zone_type {
 	 * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
 	 * platforms may need both zones as they support peripherals with
 	 * different DMA addressing limitations.
-	 *
-	 * Some examples:
-	 *
-	 *  - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the
-	 *    rest of the lower 4G.
-	 *
-	 *  - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on
-	 *    the specific device.
-	 *
-	 *  - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the
-	 *    lower 4G.
-	 *
-	 *  - powerpc only uses ZONE_DMA, the size, up to 2G, may vary
-	 *    depending on the specific device.
-	 *
-	 *  - s390 uses ZONE_DMA fixed to the lower 2G.
-	 *
-	 *  - ia64 and riscv only use ZONE_DMA32.
-	 *
-	 *  - parisc uses neither.
 	 */
 #ifdef CONFIG_ZONE_DMA
 	ZONE_DMA,
diff --git a/include/linux/of.h b/include/linux/of.h
index 5d51891cbf1a..9ed5b8532c30 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -558,6 +558,8 @@ int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
+phys_addr_t of_dma_get_max_cpu_address(struct device_node *np);
+
 #else /* CONFIG_OF */
 
 static inline void of_core_init(void)
@@ -995,6 +997,11 @@ static inline int of_map_id(struct device_node *np, u32 id,
 	return -EINVAL;
 }
 
+static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np)
+{
+	return PHYS_ADDR_MAX;
+}
+
 #define of_match_ptr(_ptr)	NULL
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 505480217cf1..bf7966776c55 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,6 +163,8 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
+bool arm_pmu_irq_is_nmi(void);
+
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);
diff --git a/include/linux/scs.h b/include/linux/scs.h
index 6dec390cf154..18122d9e17ff 100644
--- a/include/linux/scs.h
+++ b/include/linux/scs.h
@@ -15,24 +15,18 @@
 
 #ifdef CONFIG_SHADOW_CALL_STACK
 
-/*
- * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit
- * architecture) provided ~40% safety margin on stack usage while keeping
- * memory allocation overhead reasonable.
- */
-#define SCS_SIZE		SZ_1K
+#define SCS_ORDER		0
+#define SCS_SIZE		(PAGE_SIZE << SCS_ORDER)
 #define GFP_SCS			(GFP_KERNEL | __GFP_ZERO)
 
 /* An illegal pointer value to mark the end of the shadow stack. */
 #define SCS_END_MAGIC		(0x5f6UL + POISON_POINTER_DELTA)
 
-/* Allocate a static per-CPU shadow stack */
-#define DEFINE_SCS(name)						\
-	DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name)	\
-
 #define task_scs(tsk)		(task_thread_info(tsk)->scs_base)
 #define task_scs_sp(tsk)	(task_thread_info(tsk)->scs_sp)
 
+void *scs_alloc(int node);
+void scs_free(void *s);
 void scs_init(void);
 int scs_prepare(struct task_struct *tsk, int node);
 void scs_release(struct task_struct *tsk);
@@ -61,6 +55,8 @@ static inline bool task_scs_end_corrupted(struct task_struct *tsk)
 
 #else /* CONFIG_SHADOW_CALL_STACK */
 
+static inline void *scs_alloc(int node) { return NULL; }
+static inline void scs_free(void *s) {}
 static inline void scs_init(void) {}
 static inline void scs_task_reset(struct task_struct *tsk) {}
 static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; }
diff --git a/include/linux/signal.h b/include/linux/signal.h
index b256f9c65661..205526c4003a 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -469,4 +469,18 @@ struct seq_file;
 extern void render_sigset_t(struct seq_file *, const char *, sigset_t *);
 #endif
 
+#ifndef arch_untagged_si_addr
+/*
+ * Given a fault address and a signal and si_code which correspond to the
+ * _sigfault union member, returns the address that must appear in si_addr if
+ * the signal handler does not have SA_EXPOSE_TAGBITS enabled in sa_flags.
+ */
+static inline void __user *arch_untagged_si_addr(void __user *addr,
+						 unsigned long sig,
+						 unsigned long si_code)
+{
+	return addr;
+}
+#endif
+
 #endif /* _LINUX_SIGNAL_H */
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index f8a90ae9c6ec..68e06c75c5b2 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -68,4 +68,16 @@ struct ksignal {
 	int sig;
 };
 
+#ifndef __ARCH_UAPI_SA_FLAGS
+#ifdef SA_RESTORER
+#define __ARCH_UAPI_SA_FLAGS	SA_RESTORER
+#else
+#define __ARCH_UAPI_SA_FLAGS	0
+#endif
+#endif
+
+#define UAPI_SA_FLAGS                                                          \
+	(SA_NOCLDSTOP | SA_NOCLDWAIT | SA_SIGINFO | SA_ONSTACK | SA_RESTART |  \
+	 SA_NODEFER | SA_RESETHAND | SA_EXPOSE_TAGBITS | __ARCH_UAPI_SA_FLAGS)
+
 #endif /* _LINUX_SIGNAL_TYPES_H */
diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h
index e9304c95ceea..fe929e7b77ca 100644
--- a/include/uapi/asm-generic/signal-defs.h
+++ b/include/uapi/asm-generic/signal-defs.h
@@ -4,6 +4,69 @@
 
 #include <linux/compiler.h>
 
+/*
+ * SA_FLAGS values:
+ *
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_SIGINFO delivers the signal with SIGINFO structs.
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_UNSUPPORTED is a flag bit that will never be supported. Kernels from
+ * before the introduction of SA_UNSUPPORTED did not clear unknown bits from
+ * sa_flags when read using the oldact argument to sigaction and rt_sigaction,
+ * so this bit allows flag bit support to be detected from userspace while
+ * allowing an old kernel to be distinguished from a kernel that supports every
+ * flag bit.
+ * SA_EXPOSE_TAGBITS exposes an architecture-defined set of tag bits in
+ * siginfo.si_addr.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#ifndef SA_NOCLDSTOP
+#define SA_NOCLDSTOP	0x00000001
+#endif
+#ifndef SA_NOCLDWAIT
+#define SA_NOCLDWAIT	0x00000002
+#endif
+#ifndef SA_SIGINFO
+#define SA_SIGINFO	0x00000004
+#endif
+/* 0x00000008 used on alpha, mips, parisc */
+/* 0x00000010 used on alpha, parisc */
+/* 0x00000020 used on alpha, parisc, sparc */
+/* 0x00000040 used on alpha, parisc */
+/* 0x00000080 used on parisc */
+/* 0x00000100 used on sparc */
+/* 0x00000200 used on sparc */
+#define SA_UNSUPPORTED	0x00000400
+#define SA_EXPOSE_TAGBITS	0x00000800
+/* 0x00010000 used on mips */
+/* 0x01000000 used on x86 */
+/* 0x02000000 used on x86 */
+/*
+ * New architectures should not define the obsolete
+ *	SA_RESTORER	0x04000000
+ */
+#ifndef SA_ONSTACK
+#define SA_ONSTACK	0x08000000
+#endif
+#ifndef SA_RESTART
+#define SA_RESTART	0x10000000
+#endif
+#ifndef SA_NODEFER
+#define SA_NODEFER	0x40000000
+#endif
+#ifndef SA_RESETHAND
+#define SA_RESETHAND	0x80000000
+#endif
+
+#define SA_NOMASK	SA_NODEFER
+#define SA_ONESHOT	SA_RESETHAND
+
 #ifndef SIG_BLOCK
 #define SIG_BLOCK          0	/* for blocking signals */
 #endif
diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h
index 5c716a952cbe..f634822906e4 100644
--- a/include/uapi/asm-generic/signal.h
+++ b/include/uapi/asm-generic/signal.h
@@ -52,35 +52,6 @@
 #define SIGRTMAX	_NSIG
 #endif
 
-/*
- * SA_FLAGS values:
- *
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_RESETHAND clears the handler when the signal is delivered.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_NODEFER prevents the current signal from being masked in the handler.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP	0x00000001
-#define SA_NOCLDWAIT	0x00000002
-#define SA_SIGINFO	0x00000004
-#define SA_ONSTACK	0x08000000
-#define SA_RESTART	0x10000000
-#define SA_NODEFER	0x40000000
-#define SA_RESETHAND	0x80000000
-
-#define SA_NOMASK	SA_NODEFER
-#define SA_ONESHOT	SA_RESETHAND
-
-/*
- * New architectures should not define the obsolete
- *	SA_RESTORER	0x04000000
- */
-
 #if !defined MINSIGSTKSZ || !defined SIGSTKSZ
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192