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

Pull arm64 updates from Will Deacon:
 "The highlights this time are support for dynamically enabling and
  disabling Clang's Shadow Call Stack at boot and a long-awaited
  optimisation to the way in which we handle the SVE register state on
  system call entry to avoid taking unnecessary traps from userspace.

  Summary:

  ACPI:
   - Enable FPDT support for boot-time profiling
   - Fix CPU PMU probing to work better with PREEMPT_RT
   - Update SMMUv3 MSI DeviceID parsing to latest IORT spec
   - APMT support for probing Arm CoreSight PMU devices

  CPU features:
   - Advertise new SVE instructions (v2.1)
   - Advertise range prefetch instruction
   - Advertise CSSC ("Common Short Sequence Compression") scalar
     instructions, adding things like min, max, abs, popcount
   - Enable DIT (Data Independent Timing) when running in the kernel
   - More conversion of system register fields over to the generated
     header

  CPU misfeatures:
   - Workaround for Cortex-A715 erratum #2645198

  Dynamic SCS:
   - Support for dynamic shadow call stacks to allow switching at
     runtime between Clang's SCS implementation and the CPU's pointer
     authentication feature when it is supported (complete with scary
     DWARF parser!)

  Tracing and debug:
   - Remove static ftrace in favour of, err, dynamic ftrace!
   - Seperate 'struct ftrace_regs' from 'struct pt_regs' in core ftrace
     and existing arch code
   - Introduce and implement FTRACE_WITH_ARGS on arm64 to replace the
     old FTRACE_WITH_REGS
   - Extend 'crashkernel=' parameter with default value and fallback to
     placement above 4G physical if initial (low) allocation fails

  SVE:
   - Optimisation to avoid disabling SVE unconditionally on syscall
     entry and just zeroing the non-shared state on return instead

  Exceptions:
   - Rework of undefined instruction handling to avoid serialisation on
     global lock (this includes emulation of user accesses to the ID
     registers)

  Perf and PMU:
   - Support for TLP filters in Hisilicon's PCIe PMU device
   - Support for the DDR PMU present in Amlogic Meson G12 SoCs
   - Support for the terribly-named "CoreSight PMU" architecture from
     Arm (and Nvidia's implementation of said architecture)

  Misc:
   - Tighten up our boot protocol for systems with memory above 52 bits
     physical
   - Const-ify static keys to satisty jump label asm constraints
   - Trivial FFA driver cleanups in preparation for v1.1 support
   - Export the kernel_neon_* APIs as GPL symbols
   - Harden our instruction generation routines against instrumentation
   - A bunch of robustness improvements to our arch-specific selftests
   - Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (151 commits)
  arm64: kprobes: Return DBG_HOOK_ERROR if kprobes can not handle a BRK
  arm64: kprobes: Let arch do_page_fault() fix up page fault in user handler
  arm64: Prohibit instrumentation on arch_stack_walk()
  arm64:uprobe fix the uprobe SWBP_INSN in big-endian
  arm64: alternatives: add __init/__initconst to some functions/variables
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  kselftest/arm64: Allow epoll_wait() to return more than one result
  kselftest/arm64: Don't drain output while spawning children
  kselftest/arm64: Hold fp-stress children until they're all spawned
  arm64/sysreg: Remove duplicate definitions from asm/sysreg.h
  arm64/sysreg: Convert ID_DFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_DFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_AFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_MMFR5_EL1 to automatic generation
  arm64/sysreg: Convert MVFR2_EL1 to automatic generation
  arm64/sysreg: Convert MVFR1_EL1 to automatic generation
  arm64/sysreg: Convert MVFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR2_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR0_EL1 to automatic generation
  ...

7 files changed, 231 insertions, 14 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3dc5824141cd..c8ab800652b5 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1027,14 +1027,19 @@
  * keep any .init_array.* sections.
  * https://bugs.llvm.org/show_bug.cgi?id=46478
  */
+#ifdef CONFIG_UNWIND_TABLES
+#define DISCARD_EH_FRAME
+#else
+#define DISCARD_EH_FRAME	*(.eh_frame)
+#endif
 #if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
 # ifdef CONFIG_CONSTRUCTORS
 #  define SANITIZER_DISCARDS						\
-	*(.eh_frame)
+	DISCARD_EH_FRAME
 # else
 #  define SANITIZER_DISCARDS						\
 	*(.init_array) *(.init_array.*)					\
-	*(.eh_frame)
+	DISCARD_EH_FRAME
 # endif
 #else
 # define SANITIZER_DISCARDS
diff --git a/include/linux/acpi_apmt.h b/include/linux/acpi_apmt.h
new file mode 100644
index 000000000000..40bd634d082f
--- /dev/null
+++ b/include/linux/acpi_apmt.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * ARM CoreSight PMU driver.
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
+ *
+ */
+
+#ifndef __ACPI_APMT_H__
+#define __ACPI_APMT_H__
+
+#include <linux/acpi.h>
+
+#ifdef CONFIG_ACPI_APMT
+void acpi_apmt_init(void);
+#else
+static inline void acpi_apmt_init(void) { }
+#endif /* CONFIG_ACPI_APMT */
+
+#endif /* __ACPI_APMT_H__ */
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 5f02d2e6b9d9..c87aeecaa9b2 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -11,6 +11,89 @@
 #include <linux/types.h>
 #include <linux/uuid.h>
 
+#define FFA_SMC(calling_convention, func_num)				\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, (calling_convention),	\
+			   ARM_SMCCC_OWNER_STANDARD, (func_num))
+
+#define FFA_SMC_32(func_num)	FFA_SMC(ARM_SMCCC_SMC_32, (func_num))
+#define FFA_SMC_64(func_num)	FFA_SMC(ARM_SMCCC_SMC_64, (func_num))
+
+#define FFA_ERROR			FFA_SMC_32(0x60)
+#define FFA_SUCCESS			FFA_SMC_32(0x61)
+#define FFA_INTERRUPT			FFA_SMC_32(0x62)
+#define FFA_VERSION			FFA_SMC_32(0x63)
+#define FFA_FEATURES			FFA_SMC_32(0x64)
+#define FFA_RX_RELEASE			FFA_SMC_32(0x65)
+#define FFA_RXTX_MAP			FFA_SMC_32(0x66)
+#define FFA_FN64_RXTX_MAP		FFA_SMC_64(0x66)
+#define FFA_RXTX_UNMAP			FFA_SMC_32(0x67)
+#define FFA_PARTITION_INFO_GET		FFA_SMC_32(0x68)
+#define FFA_ID_GET			FFA_SMC_32(0x69)
+#define FFA_MSG_POLL			FFA_SMC_32(0x6A)
+#define FFA_MSG_WAIT			FFA_SMC_32(0x6B)
+#define FFA_YIELD			FFA_SMC_32(0x6C)
+#define FFA_RUN				FFA_SMC_32(0x6D)
+#define FFA_MSG_SEND			FFA_SMC_32(0x6E)
+#define FFA_MSG_SEND_DIRECT_REQ		FFA_SMC_32(0x6F)
+#define FFA_FN64_MSG_SEND_DIRECT_REQ	FFA_SMC_64(0x6F)
+#define FFA_MSG_SEND_DIRECT_RESP	FFA_SMC_32(0x70)
+#define FFA_FN64_MSG_SEND_DIRECT_RESP	FFA_SMC_64(0x70)
+#define FFA_MEM_DONATE			FFA_SMC_32(0x71)
+#define FFA_FN64_MEM_DONATE		FFA_SMC_64(0x71)
+#define FFA_MEM_LEND			FFA_SMC_32(0x72)
+#define FFA_FN64_MEM_LEND		FFA_SMC_64(0x72)
+#define FFA_MEM_SHARE			FFA_SMC_32(0x73)
+#define FFA_FN64_MEM_SHARE		FFA_SMC_64(0x73)
+#define FFA_MEM_RETRIEVE_REQ		FFA_SMC_32(0x74)
+#define FFA_FN64_MEM_RETRIEVE_REQ	FFA_SMC_64(0x74)
+#define FFA_MEM_RETRIEVE_RESP		FFA_SMC_32(0x75)
+#define FFA_MEM_RELINQUISH		FFA_SMC_32(0x76)
+#define FFA_MEM_RECLAIM			FFA_SMC_32(0x77)
+#define FFA_MEM_OP_PAUSE		FFA_SMC_32(0x78)
+#define FFA_MEM_OP_RESUME		FFA_SMC_32(0x79)
+#define FFA_MEM_FRAG_RX			FFA_SMC_32(0x7A)
+#define FFA_MEM_FRAG_TX			FFA_SMC_32(0x7B)
+#define FFA_NORMAL_WORLD_RESUME		FFA_SMC_32(0x7C)
+
+/*
+ * For some calls it is necessary to use SMC64 to pass or return 64-bit values.
+ * For such calls FFA_FN_NATIVE(name) will choose the appropriate
+ * (native-width) function ID.
+ */
+#ifdef CONFIG_64BIT
+#define FFA_FN_NATIVE(name)	FFA_FN64_##name
+#else
+#define FFA_FN_NATIVE(name)	FFA_##name
+#endif
+
+/* FFA error codes. */
+#define FFA_RET_SUCCESS            (0)
+#define FFA_RET_NOT_SUPPORTED      (-1)
+#define FFA_RET_INVALID_PARAMETERS (-2)
+#define FFA_RET_NO_MEMORY          (-3)
+#define FFA_RET_BUSY               (-4)
+#define FFA_RET_INTERRUPTED        (-5)
+#define FFA_RET_DENIED             (-6)
+#define FFA_RET_RETRY              (-7)
+#define FFA_RET_ABORTED            (-8)
+
+/* FFA version encoding */
+#define FFA_MAJOR_VERSION_MASK	GENMASK(30, 16)
+#define FFA_MINOR_VERSION_MASK	GENMASK(15, 0)
+#define FFA_MAJOR_VERSION(x)	((u16)(FIELD_GET(FFA_MAJOR_VERSION_MASK, (x))))
+#define FFA_MINOR_VERSION(x)	((u16)(FIELD_GET(FFA_MINOR_VERSION_MASK, (x))))
+#define FFA_PACK_VERSION_INFO(major, minor)			\
+	(FIELD_PREP(FFA_MAJOR_VERSION_MASK, (major)) |		\
+	 FIELD_PREP(FFA_MINOR_VERSION_MASK, (minor)))
+#define FFA_VERSION_1_0		FFA_PACK_VERSION_INFO(1, 0)
+
+/**
+ * FF-A specification mentions explicitly about '4K pages'. This should
+ * not be confused with the kernel PAGE_SIZE, which is the translation
+ * granule kernel is configured and may be one among 4K, 16K and 64K.
+ */
+#define FFA_PAGE_SIZE		SZ_4K
+
 /* FFA Bus/Device/Driver related */
 struct ffa_device {
 	int vm_id;
@@ -161,11 +244,11 @@ struct ffa_mem_region_attributes {
 	 */
 #define FFA_MEM_RETRIEVE_SELF_BORROWER	BIT(0)
 	u8 flag;
-	u32 composite_off;
 	/*
 	 * Offset in bytes from the start of the outer `ffa_memory_region` to
 	 * an `struct ffa_mem_region_addr_range`.
 	 */
+	u32 composite_off;
 	u64 reserved;
 };
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 62557d4bffc2..99f1146614c0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -37,9 +37,10 @@ extern void ftrace_boot_snapshot(void);
 static inline void ftrace_boot_snapshot(void) { }
 #endif
 
-#ifdef CONFIG_FUNCTION_TRACER
 struct ftrace_ops;
 struct ftrace_regs;
+
+#ifdef CONFIG_FUNCTION_TRACER
 /*
  * If the arch's mcount caller does not support all of ftrace's
  * features, then it must call an indirect function that
@@ -110,12 +111,11 @@ struct ftrace_regs {
 #define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
 
 /*
- * ftrace_instruction_pointer_set() is to be defined by the architecture
- * if to allow setting of the instruction pointer from the ftrace_regs
- * when HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports
- * live kernel patching.
+ * ftrace_regs_set_instruction_pointer() is to be defined by the architecture
+ * if to allow setting of the instruction pointer from the ftrace_regs when
+ * HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports live kernel patching.
  */
-#define ftrace_instruction_pointer_set(fregs, ip) do { } while (0)
+#define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
@@ -126,6 +126,35 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs
 	return arch_ftrace_get_regs(fregs);
 }
 
+/*
+ * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs.
+ * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs.
+ */
+static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs)
+{
+	if (IS_ENABLED(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS))
+		return true;
+
+	return ftrace_get_regs(fregs) != NULL;
+}
+
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+#define ftrace_regs_get_instruction_pointer(fregs) \
+	instruction_pointer(ftrace_get_regs(fregs))
+#define ftrace_regs_get_argument(fregs, n) \
+	regs_get_kernel_argument(ftrace_get_regs(fregs), n)
+#define ftrace_regs_get_stack_pointer(fregs) \
+	kernel_stack_pointer(ftrace_get_regs(fregs))
+#define ftrace_regs_return_value(fregs) \
+	regs_return_value(ftrace_get_regs(fregs))
+#define ftrace_regs_set_return_value(fregs, ret) \
+	regs_set_return_value(ftrace_get_regs(fregs), ret)
+#define ftrace_override_function_with_return(fregs) \
+	override_function_with_return(ftrace_get_regs(fregs))
+#define ftrace_regs_query_register_offset(name) \
+	regs_query_register_offset(name)
+#endif
+
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct ftrace_regs *fregs);
 
@@ -427,9 +456,7 @@ static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsi
 {
 	return -ENODEV;
 }
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
-#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /*
  * This must be implemented by the architecture.
  * It is the way the ftrace direct_ops helper, when called
@@ -443,9 +470,9 @@ static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsi
  * the return from the trampoline jump to the direct caller
  * instead of going back to the function it just traced.
  */
-static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs,
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 						 unsigned long addr) { }
-#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifdef CONFIG_STACK_TRACER
 
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 0356cb6a215d..0c15c5b7f801 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -174,7 +174,6 @@ void kvm_host_pmu_init(struct arm_pmu *pmu);
 
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
-struct arm_pmu *armpmu_alloc_atomic(void);
 void armpmu_free(struct arm_pmu *pmu);
 int armpmu_register(struct arm_pmu *pmu);
 int armpmu_request_irq(int irq, int cpu);
diff --git a/include/linux/scs.h b/include/linux/scs.h
index 18122d9e17ff..4ab5bdc898cf 100644
--- a/include/linux/scs.h
+++ b/include/linux/scs.h
@@ -53,6 +53,22 @@ static inline bool task_scs_end_corrupted(struct task_struct *tsk)
 	return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC;
 }
 
+DECLARE_STATIC_KEY_FALSE(dynamic_scs_enabled);
+
+static inline bool scs_is_dynamic(void)
+{
+	if (!IS_ENABLED(CONFIG_DYNAMIC_SCS))
+		return false;
+	return static_branch_likely(&dynamic_scs_enabled);
+}
+
+static inline bool scs_is_enabled(void)
+{
+	if (!IS_ENABLED(CONFIG_DYNAMIC_SCS))
+		return true;
+	return scs_is_dynamic();
+}
+
 #else /* CONFIG_SHADOW_CALL_STACK */
 
 static inline void *scs_alloc(int node) { return NULL; }
@@ -62,6 +78,8 @@ static inline void scs_task_reset(struct task_struct *tsk) {}
 static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; }
 static inline void scs_release(struct task_struct *tsk) {}
 static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; }
+static inline bool scs_is_enabled(void) { return false; }
+static inline bool scs_is_dynamic(void) { return false; }
 
 #endif /* CONFIG_SHADOW_CALL_STACK */
 
diff --git a/include/soc/amlogic/meson_ddr_pmu.h b/include/soc/amlogic/meson_ddr_pmu.h
new file mode 100644
index 000000000000..4a33e4ab8ada
--- /dev/null
+++ b/include/soc/amlogic/meson_ddr_pmu.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Amlogic, Inc. All rights reserved.
+ */
+
+#ifndef __MESON_DDR_PMU_H__
+#define __MESON_DDR_PMU_H__
+
+#define MAX_CHANNEL_NUM		8
+
+enum {
+	ALL_CHAN_COUNTER_ID,
+	CHAN1_COUNTER_ID,
+	CHAN2_COUNTER_ID,
+	CHAN3_COUNTER_ID,
+	CHAN4_COUNTER_ID,
+	CHAN5_COUNTER_ID,
+	CHAN6_COUNTER_ID,
+	CHAN7_COUNTER_ID,
+	CHAN8_COUNTER_ID,
+	COUNTER_MAX_ID,
+};
+
+struct dmc_info;
+
+struct dmc_counter {
+	u64 all_cnt;	/* The count of all requests come in/out ddr controller */
+	union {
+		u64 all_req;
+		struct {
+			u64 all_idle_cnt;
+			u64 all_16bit_cnt;
+		};
+	};
+	u64 channel_cnt[MAX_CHANNEL_NUM]; /* To save a DMC bandwidth-monitor channel counter */
+};
+
+struct dmc_hw_info {
+	void (*enable)(struct dmc_info *info);
+	void (*disable)(struct dmc_info *info);
+	/* Bind an axi line to a bandwidth-monitor channel */
+	void (*set_axi_filter)(struct dmc_info *info, int axi_id, int chann);
+	int (*irq_handler)(struct dmc_info *info,
+			   struct dmc_counter *counter);
+	void (*get_counters)(struct dmc_info *info,
+			     struct dmc_counter *counter);
+
+	int dmc_nr;			/* The number of dmc controller */
+	int chann_nr;			/* The number of dmc bandwidth monitor channels */
+	struct attribute **fmt_attr;
+	const u64 capability[2];
+};
+
+struct dmc_info {
+	const struct dmc_hw_info *hw_info;
+
+	void __iomem *ddr_reg[4];
+	unsigned long timer_value;	/* Timer value in TIMER register */
+	void __iomem *pll_reg;
+	int irq_num;			/* irq vector number */
+};
+
+int meson_ddr_pmu_create(struct platform_device *pdev);
+int meson_ddr_pmu_remove(struct platform_device *pdev);
+
+#endif /* __MESON_DDR_PMU_H__ */