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

Pull arm64 fixes from Will Deacon:
 "The critical one here is a fix for fpsimd register corruption across
  signals which was introduced by the SVE support code (the register
  files overlap), but the others are worth having as well.

  Summary:

   - Fix FP register corruption when SVE is not available or in use

   - Fix out-of-tree module build failure when CONFIG_ARM64_MODULE_PLTS=y

   - Missing 'const' generating errors with LTO builds

   - Remove unsupported events from Cortex-A73 PMU description

   - Removal of stale and incorrect comments"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: context: Fix comments and remove pointless smp_wmb()
  arm64: cpu_ops: Add missing 'const' qualifiers
  arm64: perf: remove unsupported events for Cortex-A73
  arm64: fpsimd: Fix failure to restore FPSIMD state after signals
  arm64: pgd: Mark pgd_cache as __ro_after_init
  arm64: ftrace: emit ftrace-mod.o contents through code
  arm64: module-plts: factor out PLT generation code for ftrace
  arm64: mm: cleanup stale AIVIVT references

arch/arm64/Makefile

@@ -83,9 +83,6 @@ endif
 
 ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
 KBUILD_LDFLAGS_MODULE	+= -T $(srctree)/arch/arm64/kernel/module.lds
-ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-KBUILD_LDFLAGS_MODULE	+= $(objtree)/arch/arm64/kernel/ftrace-mod.o
-endif
 endif
 
 # Default value

arch/arm64/include/asm/cacheflush.h

@@ -38,7 +38,7 @@
  *
  *	See Documentation/cachetlb.txt for more information. Please note that
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
- *	VIPT or ASID-tagged VIVT I-cache.
+ *	VIPT I-cache.
  *
  *	flush_cache_mm(mm)
  *

arch/arm64/include/asm/module.h

@@ -32,7 +32,7 @@ struct mod_arch_specific {
 	struct mod_plt_sec	init;
 
 	/* for CONFIG_DYNAMIC_FTRACE */
-	void			*ftrace_trampoline;
+	struct plt_entry 	*ftrace_trampoline;
 };
 #endif
 
@@ -45,4 +45,48 @@ extern u64 module_alloc_base;
 #define module_alloc_base	((u64)_etext - MODULES_VSIZE)
 #endif
 
+struct plt_entry {
+	/*
+	 * A program that conforms to the AArch64 Procedure Call Standard
+	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+	 * IP1 (x17) may be inserted at any branch instruction that is
+	 * exposed to a relocation that supports long branches. Since that
+	 * is exactly what we are dealing with here, we are free to use x16
+	 * as a scratch register in the PLT veneers.
+	 */
+	__le32	mov0;	/* movn	x16, #0x....			*/
+	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
+	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
+	__le32	br;	/* br	x16				*/
+};
+
+static inline struct plt_entry get_plt_entry(u64 val)
+{
+	/*
+	 * MOVK/MOVN/MOVZ opcode:
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
+	 * +--------+------------+--------+-----------+-------------+---------+
+	 *
+	 * Rd     := 0x10 (x16)
+	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
+	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
+	 * sf     := 1 (64-bit variant)
+	 */
+	return (struct plt_entry){
+		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
+		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
+		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
+		cpu_to_le32(0xd61f0200)
+	};
+}
+
+static inline bool plt_entries_equal(const struct plt_entry *a,
+				     const struct plt_entry *b)
+{
+	return a->mov0 == b->mov0 &&
+	       a->mov1 == b->mov1 &&
+	       a->mov2 == b->mov2;
+}
+
 #endif /* __ASM_MODULE_H */

arch/arm64/kernel/Makefile

@@ -61,6 +61,3 @@ extra-y					+= $(head-y) vmlinux.lds
 ifeq ($(CONFIG_DEBUG_EFI),y)
 AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\""
 endif
-
-# will be included by each individual module but not by the core kernel itself
-extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o

arch/arm64/kernel/cpu_ops.c

@@ -31,13 +31,13 @@ extern const struct cpu_operations cpu_psci_ops;
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
 	&smp_spin_table_ops,
 	&cpu_psci_ops,
 	NULL,
 };
 
-static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
+static const struct cpu_operations *const acpi_supported_cpu_ops[] __initconst = {
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
 	&acpi_parking_protocol_ops,
 #endif
@@ -47,7 +47,7 @@ static const struct cpu_operations *acpi_supported_cpu_ops[] __initconst = {
 
 static const struct cpu_operations * __init cpu_get_ops(const char *name)
 {
-	const struct cpu_operations **ops;
+	const struct cpu_operations *const *ops;
 
 	ops = acpi_disabled ? dt_supported_cpu_ops : acpi_supported_cpu_ops;
 

arch/arm64/kernel/fpsimd.c

@@ -1026,10 +1026,10 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
 
 	local_bh_disable();
 
-	if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
-		current->thread.fpsimd_state = *state;
+	current->thread.fpsimd_state = *state;
+	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		fpsimd_to_sve(current);
-	}
+
 	task_fpsimd_load();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {

arch/arm64/kernel/ftrace-mod.S

-/*
- * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-	.section	".text.ftrace_trampoline", "ax"
-	.align		3
-0:	.quad		0
-__ftrace_trampoline:
-	ldr		x16, 0b
-	br		x16
-ENDPROC(__ftrace_trampoline)

arch/arm64/kernel/ftrace.c

@@ -76,7 +76,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		unsigned long *trampoline;
+		struct plt_entry trampoline;
 		struct module *mod;
 
 		/*
@@ -104,22 +104,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
 		 */
-		trampoline = (unsigned long *)mod->arch.ftrace_trampoline;
-		if (trampoline[0] != addr) {
-			if (trampoline[0] != 0) {
+		trampoline = get_plt_entry(addr);
+		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+				       &trampoline)) {
+			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+					       &(struct plt_entry){})) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}
 
 			/* point the trampoline to our ftrace entry point */
 			module_disable_ro(mod);
-			trampoline[0] = addr;
+			*mod->arch.ftrace_trampoline = trampoline;
 			module_enable_ro(mod, true);
 
 			/* update trampoline before patching in the branch */
 			smp_wmb();
 		}
-		addr = (unsigned long)&trampoline[1];
+		addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */

arch/arm64/kernel/module-plts.c

@@ -11,21 +11,6 @@
 #include <linux/module.h>
 #include <linux/sort.h>
 
-struct plt_entry {
-	/*
-	 * A program that conforms to the AArch64 Procedure Call Standard
-	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
-	 * IP1 (x17) may be inserted at any branch instruction that is
-	 * exposed to a relocation that supports long branches. Since that
-	 * is exactly what we are dealing with here, we are free to use x16
-	 * as a scratch register in the PLT veneers.
-	 */
-	__le32	mov0;	/* movn	x16, #0x....			*/
-	__le32	mov1;	/* movk	x16, #0x...., lsl #16		*/
-	__le32	mov2;	/* movk	x16, #0x...., lsl #32		*/
-	__le32	br;	/* br	x16				*/
-};
-
 static bool in_init(const struct module *mod, void *loc)
 {
 	return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
@@ -40,33 +25,14 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
 	int i = pltsec->plt_num_entries;
 	u64 val = sym->st_value + rela->r_addend;
 
-	/*
-	 * MOVK/MOVN/MOVZ opcode:
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
-	 * +--------+------------+--------+-----------+-------------+---------+
-	 *
-	 * Rd     := 0x10 (x16)
-	 * hw     := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32)
-	 * opc    := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ)
-	 * sf     := 1 (64-bit variant)
-	 */
-	plt[i] = (struct plt_entry){
-		cpu_to_le32(0x92800010 | (((~val      ) & 0xffff)) << 5),
-		cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5),
-		cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5),
-		cpu_to_le32(0xd61f0200)
-	};
+	plt[i] = get_plt_entry(val);
 
 	/*
 	 * Check if the entry we just created is a duplicate. Given that the
 	 * relocations are sorted, this will be the last entry we allocated.
 	 * (if one exists).
 	 */
-	if (i > 0 &&
-	    plt[i].mov0 == plt[i - 1].mov0 &&
-	    plt[i].mov1 == plt[i - 1].mov1 &&
-	    plt[i].mov2 == plt[i - 1].mov2)
+	if (i > 0 && plt_entries_equal(plt + i, plt + i - 1))
 		return (u64)&plt[i - 1];
 
 	pltsec->plt_num_entries++;
@@ -154,6 +120,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
+	Elf_Shdr *tramp = NULL;
 	int i;
 
 	/*
@@ -165,6 +132,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			mod->arch.core.plt = sechdrs + i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
 			mod->arch.init.plt = sechdrs + i;
+		else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) &&
+			 !strcmp(secstrings + sechdrs[i].sh_name,
+				 ".text.ftrace_trampoline"))
+			tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
@@ -215,5 +186,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	mod->arch.init.plt_num_entries = 0;
 	mod->arch.init.plt_max_entries = init_plts;
 
+	if (tramp) {
+		tramp->sh_type = SHT_NOBITS;
+		tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+		tramp->sh_addralign = __alignof__(struct plt_entry);
+		tramp->sh_size = sizeof(struct plt_entry);
+	}
+
 	return 0;
 }

arch/arm64/kernel/module.lds

 SECTIONS {
 	.plt (NOLOAD) : { BYTE(0) }
 	.init.plt (NOLOAD) : { BYTE(0) }
+	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
 }

arch/arm64/kernel/perf_event.c

@@ -262,12 +262,6 @@ static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 
 	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
 	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
-
-	[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
-	[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
 };
 
 static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

arch/arm64/mm/context.c

@@ -96,12 +96,6 @@ static void flush_context(unsigned int cpu)
 
 	set_reserved_asid_bits();
 
-	/*
-	 * Ensure the generation bump is observed before we xchg the
-	 * active_asids.
-	 */
-	smp_wmb();
-
 	for_each_possible_cpu(i) {
 		asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
 		/*
@@ -117,7 +111,10 @@ static void flush_context(unsigned int cpu)
 		per_cpu(reserved_asids, i) = asid;
 	}
 
-	/* Queue a TLB invalidate and flush the I-cache if necessary. */
+	/*
+	 * Queue a TLB invalidation for each CPU to perform on next
+	 * context-switch
+	 */
 	cpumask_setall(&tlb_flush_pending);
 }
 
@@ -202,11 +199,18 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	asid = atomic64_read(&mm->context.id);
 
 	/*
-	 * The memory ordering here is subtle. We rely on the control
-	 * dependency between the generation read and the update of
-	 * active_asids to ensure that we are synchronised with a
-	 * parallel rollover (i.e. this pairs with the smp_wmb() in
-	 * flush_context).
+	 * The memory ordering here is subtle.
+	 * If our ASID matches the current generation, then we update
+	 * our active_asids entry with a relaxed xchg. Racing with a
+	 * concurrent rollover means that either:
+	 *
+	 * - We get a zero back from the xchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated generation.
+	 *
+	 * - We get a valid ASID back from the xchg, which means the
+	 *   relaxed xchg in flush_context will treat us as reserved
+	 *   because atomic RmWs are totally ordered for a given location.
 	 */
 	if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
 	    && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))

arch/arm64/mm/pgd.c

@@ -26,7 +26,7 @@
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 
-static struct kmem_cache *pgd_cache;
+static struct kmem_cache *pgd_cache __ro_after_init;
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {