15 files changed, 76 insertions, 98 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 8265dd790895..067baace74a0 100644
--- a/arch/arm64/kernel/Makefile
+++ b/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
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 65f42d257414..2a752cb2a0f3 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart)
 	mrs	x12, sctlr_el1
 	ldr	x13, =SCTLR_ELx_FLAGS
 	bic	x12, x12, x13
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x12
 	isb
 
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index d16978213c5b..ea001241bdd4 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/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;
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c5ba0097887f..a73a5928f09b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -145,7 +145,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 4e6ad355bd05..6b9736c3fb56 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -96,6 +96,7 @@ ENTRY(entry)
 	mrs	x0, sctlr_el2
 	bic	x0, x0, #1 << 0	// clear SCTLR.M
 	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	pre_disable_mmu_workaround
 	msr	sctlr_el2, x0
 	isb
 	b	2f
@@ -103,6 +104,7 @@ ENTRY(entry)
 	mrs	x0, sctlr_el1
 	bic	x0, x0, #1 << 0	// clear SCTLR.M
 	bic	x0, x0, #1 << 2	// clear SCTLR.C
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x0
 	isb
 2:
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 143b3e72c25e..fae81f7964b4 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -114,7 +114,12 @@
  *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
  *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
  */
-static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+struct fpsimd_last_state_struct {
+	struct fpsimd_state *st;
+	bool sve_in_use;
+};
+
+static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
 
 /* Default VL for tasks that don't set it explicitly: */
 static int sve_default_vl = -1;
@@ -905,7 +910,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 		 */
 		struct fpsimd_state *st = &next->thread.fpsimd_state;
 
-		if (__this_cpu_read(fpsimd_last_state) == st
+		if (__this_cpu_read(fpsimd_last_state.st) == st
 		    && st->cpu == smp_processor_id())
 			clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE);
 		else
@@ -992,6 +997,21 @@ void fpsimd_signal_preserve_current_state(void)
 }
 
 /*
+ * Associate current's FPSIMD context with this cpu
+ * Preemption must be disabled when calling this function.
+ */
+static void fpsimd_bind_to_cpu(void)
+{
+	struct fpsimd_last_state_struct *last =
+		this_cpu_ptr(&fpsimd_last_state);
+	struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+	last->st = st;
+	last->sve_in_use = test_thread_flag(TIF_SVE);
+	st->cpu = smp_processor_id();
+}
+
+/*
  * Load the userland FPSIMD state of 'current' from memory, but only if the
  * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
  * state of 'current'
@@ -1004,11 +1024,8 @@ void fpsimd_restore_current_state(void)
 	local_bh_disable();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
-
 		task_fpsimd_load();
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
+		fpsimd_bind_to_cpu();
 	}
 
 	local_bh_enable();
@@ -1026,18 +1043,14 @@ 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.user_fpsimd = state->user_fpsimd;
+	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)) {
-		struct fpsimd_state *st = &current->thread.fpsimd_state;
+	task_fpsimd_load();
 
-		__this_cpu_write(fpsimd_last_state, st);
-		st->cpu = smp_processor_id();
-	}
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_bind_to_cpu();
 
 	local_bh_enable();
 }
@@ -1052,7 +1065,7 @@ void fpsimd_flush_task_state(struct task_struct *t)
 
 static inline void fpsimd_flush_cpu_state(void)
 {
-	__this_cpu_write(fpsimd_last_state, NULL);
+	__this_cpu_write(fpsimd_last_state.st, NULL);
 }
 
 /*
@@ -1065,14 +1078,10 @@ static inline void fpsimd_flush_cpu_state(void)
 #ifdef CONFIG_ARM64_SVE
 void sve_flush_cpu_state(void)
 {
-	struct fpsimd_state *const fpstate = __this_cpu_read(fpsimd_last_state);
-	struct task_struct *tsk;
-
-	if (!fpstate)
-		return;
+	struct fpsimd_last_state_struct const *last =
+		this_cpu_ptr(&fpsimd_last_state);
 
-	tsk = container_of(fpstate, struct task_struct, thread.fpsimd_state);
-	if (test_tsk_thread_flag(tsk, TIF_SVE))
+	if (last->st && last->sve_in_use)
 		fpsimd_flush_cpu_state();
 }
 #endif /* CONFIG_ARM64_SVE */
@@ -1267,7 +1276,7 @@ static inline void fpsimd_pm_init(void) { }
 #ifdef CONFIG_HOTPLUG_CPU
 static int fpsimd_cpu_dead(unsigned int cpu)
 {
-	per_cpu(fpsimd_last_state, cpu) = NULL;
+	per_cpu(fpsimd_last_state.st, cpu) = NULL;
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/ftrace-mod.S b/arch/arm64/kernel/ftrace-mod.S
deleted file mode 100644
index 00c4025be4ff..000000000000
--- a/arch/arm64/kernel/ftrace-mod.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * 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)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index c13b1fca0e5b..50986e388d2b 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/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 */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 67e86a0f57ac..e3cb9fbf96b6 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -750,6 +750,7 @@ __primary_switch:
 	 * to take into account by discarding the current kernel mapping and
 	 * creating a new one.
 	 */
+	pre_disable_mmu_workaround
 	msr	sctlr_el1, x20			// disable the MMU
 	isb
 	bl	__create_page_tables		// recreate kernel mapping
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 749f81779420..74bb56f656ef 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -28,6 +28,7 @@
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/smp.h>
+#include <linux/uaccess.h>
 
 #include <asm/compat.h>
 #include <asm/current.h>
@@ -36,7 +37,6 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
-#include <asm/uaccess.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index d05dbe658409..ea640f92fe5a 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/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;
 }
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
index f7c9781a9d48..22e36a21c113 100644
--- a/arch/arm64/kernel/module.lds
+++ b/arch/arm64/kernel/module.lds
@@ -1,4 +1,5 @@
 SECTIONS {
 	.plt (NOLOAD) : { BYTE(0) }
 	.init.plt (NOLOAD) : { BYTE(0) }
+	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
 }
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9eaef51f83ff..3affca3dd96a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/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]
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index b2adcce7bc18..6b7dcf4310ac 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -314,6 +314,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	clear_tsk_thread_flag(p, TIF_SVE);
 	p->thread.sve_state = NULL;
 
+	/*
+	 * In case p was allocated the same task_struct pointer as some
+	 * other recently-exited task, make sure p is disassociated from
+	 * any cpu that may have run that now-exited task recently.
+	 * Otherwise we could erroneously skip reloading the FPSIMD
+	 * registers for p.
+	 */
+	fpsimd_flush_task_state(p);
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index ce704a4aeadd..f407e422a720 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel)
 	mrs	x0, sctlr_el2
 	ldr	x1, =SCTLR_ELx_FLAGS
 	bic	x0, x0, x1
+	pre_disable_mmu_workaround
 	msr	sctlr_el2, x0
 	isb
 1: