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

Pull arm64 updates from Catalin Marinas:

 - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that
   Linux needs to save/restore

 - Include TPIDR2 in the signal context and add the corresponding
   kselftests

 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time

 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64

 - Permit EFI boot with MMU and caches on. Instead of cleaning the
   entire loaded kernel image to the PoC and disabling the MMU and
   caches before branching to the kernel bare metal entry point, leave
   the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of
   all of system RAM to populate the initial page tables

 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values)

 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure

 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice

 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone

 - Further arm64 sysreg conversion and some fixes

 - arm64 kselftest fixes and improvements

 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation

 - Pseudo-NMI code generation optimisations

 - Minor fixes for SME and TPIDR2 handling

 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable,
   replace strtobool() to kstrtobool() in the cpufeature.c code, apply
   dynamic shadow call stack in two passes, intercept pfn changes in
   set_pte_at() without the required break-before-make sequence, attempt
   to dump all instructions on unhandled kernel faults

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits)
  arm64: fix .idmap.text assertion for large kernels
  kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests
  kselftest/arm64: Copy whole EXTRA context
  arm64: kprobes: Drop ID map text from kprobes blacklist
  perf: arm_spe: Print the version of SPE detected
  perf: arm_spe: Add support for SPEv1.2 inverted event filtering
  perf: Add perf_event_attr::config3
  arm64/sme: Fix __finalise_el2 SMEver check
  drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable
  arm64/signal: Only read new data when parsing the ZT context
  arm64/signal: Only read new data when parsing the ZA context
  arm64/signal: Only read new data when parsing the SVE context
  arm64/signal: Avoid rereading context frame sizes
  arm64/signal: Make interface for restore_fpsimd_context() consistent
  arm64/signal: Remove redundant size validation from parse_user_sigframe()
  arm64/signal: Don't redundantly verify FPSIMD magic
  arm64/cpufeature: Use helper macros to specify hwcaps
  arm64/cpufeature: Always use symbolic name for feature value in hwcaps
  arm64/sysreg: Initial unsigned annotations for ID registers
  arm64/sysreg: Initial annotation of signed ID registers
  ...

5 files changed, 45 insertions, 10 deletions

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 56467f86a27c..4a3bd114a24f 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -76,12 +76,6 @@
 #endif
 
 /*
- *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute
- *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute
- */
-#define __cold                          __attribute__((__cold__))
-
-/*
  * Note the long name.
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index dea5bf5bd09c..690c7c826fbf 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -79,6 +79,33 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 /* Attributes */
 #include <linux/compiler_attributes.h>
 
+#if CONFIG_FUNCTION_ALIGNMENT > 0
+#define __function_aligned		__aligned(CONFIG_FUNCTION_ALIGNMENT)
+#else
+#define __function_aligned
+#endif
+
+/*
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute
+ *
+ * When -falign-functions=N is in use, we must avoid the cold attribute as
+ * contemporary versions of GCC drop the alignment for cold functions. Worse,
+ * GCC can implicitly mark callees of cold functions as cold themselves, so
+ * it's not sufficient to add __function_aligned here as that will not ensure
+ * that callees are correctly aligned.
+ *
+ * See:
+ *
+ *   https://lore.kernel.org/lkml/Y77%2FqVgvaJidFpYt@FVFF77S0Q05N
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c9
+ */
+#if !defined(CONFIG_CC_IS_GCC) || (CONFIG_FUNCTION_ALIGNMENT == 0)
+#define __cold				__attribute__((__cold__))
+#else
+#define __cold
+#endif
+
 /* Builtins */
 
 /*
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 99f1146614c0..366c730beaa3 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -39,6 +39,7 @@ static inline void ftrace_boot_snapshot(void) { }
 
 struct ftrace_ops;
 struct ftrace_regs;
+struct dyn_ftrace;
 
 #ifdef CONFIG_FUNCTION_TRACER
 /*
@@ -57,6 +58,9 @@ void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 			       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #endif
+extern const struct ftrace_ops ftrace_nop_ops;
+extern const struct ftrace_ops ftrace_list_ops;
+struct ftrace_ops *ftrace_find_unique_ops(struct dyn_ftrace *rec);
 #endif /* CONFIG_FUNCTION_TRACER */
 
 /* Main tracing buffer and events set up */
@@ -391,8 +395,6 @@ struct ftrace_func_entry {
 	unsigned long direct; /* for direct lookup only */
 };
 
-struct dyn_ftrace;
-
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 extern int ftrace_direct_func_count;
 int register_ftrace_direct(unsigned long ip, unsigned long addr);
@@ -563,6 +565,8 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  IPMODIFY - the record allows for the IP address to be changed.
  *  DISABLED - the record is not ready to be touched yet
  *  DIRECT   - there is a direct function to call
+ *  CALL_OPS - the record can use callsite-specific ops
+ *  CALL_OPS_EN - the function is set up to use callsite-specific ops
  *
  * When a new ftrace_ops is registered and wants a function to save
  * pt_regs, the rec->flags REGS is set. When the function has been
@@ -580,9 +584,11 @@ enum {
 	FTRACE_FL_DISABLED	= (1UL << 25),
 	FTRACE_FL_DIRECT	= (1UL << 24),
 	FTRACE_FL_DIRECT_EN	= (1UL << 23),
+	FTRACE_FL_CALL_OPS	= (1UL << 22),
+	FTRACE_FL_CALL_OPS_EN	= (1UL << 21),
 };
 
-#define FTRACE_REF_MAX_SHIFT	23
+#define FTRACE_REF_MAX_SHIFT	21
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
 
 #define ftrace_rec_count(rec)	((rec)->flags & FTRACE_REF_MAX)
@@ -820,7 +826,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \
+	defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
  * @rec: the call site record (e.g. mcount/fentry)
@@ -833,6 +840,9 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
  * what we expect it to be, and then on success of the compare,
  * it should write to the location.
  *
+ * When using call ops, this is called when the associated ops change, even
+ * when (addr == old_addr).
+ *
  * The code segment at @rec->ip should be a caller to @old_addr
  *
  * Return must be:
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 4c6a8fa5e7ed..68de6f4c4eee 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -434,6 +434,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_PAC_ENABLED_KEYS	0x40a	/* arm64 ptr auth enabled keys (prctl()) */
 #define NT_ARM_SSVE	0x40b		/* ARM Streaming SVE registers */
 #define NT_ARM_ZA	0x40c		/* ARM SME ZA registers */
+#define NT_ARM_ZT	0x40d		/* ARM SME ZT registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ccb7f5dad59b..37675437b768 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -374,6 +374,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
 #define PERF_ATTR_SIZE_VER6	120	/* add: aux_sample_size */
 #define PERF_ATTR_SIZE_VER7	128	/* add: sig_data */
+#define PERF_ATTR_SIZE_VER8	136	/* add: config3 */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -515,6 +516,8 @@ struct perf_event_attr {
 	 * truncated accordingly on 32 bit architectures.
 	 */
 	__u64	sig_data;
+
+	__u64	config3; /* extension of config2 */
 };
 
 /*