21 files changed, 226 insertions, 243 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 151f28521f1e..a561cbb91d4d 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
-ifneq ($(CONFIG_COMPAT_VDSO), y)
 obj-$(CONFIG_COMPAT)			+= sigreturn32.o
-endif
 obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ad06d6802d2e..79728bfb5351 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 	{},
 };
 
@@ -470,12 +472,7 @@ static bool
 has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
 			       int scope)
 {
-	u32 midr = read_cpuid_id();
-	/* Cortex-A76 r0p0 - r3p1 */
-	struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1);
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode();
+	return is_affected_midr_range_list(entry, scope) && is_kernel_in_hyp_mode();
 }
 #endif
 
@@ -726,6 +723,8 @@ static const struct midr_range erratum_1418040_list[] = {
 	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
 	/* Neoverse-N1 r0p0 to r3p1 */
 	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
 	{},
 };
 #endif
@@ -770,11 +769,23 @@ static const struct midr_range erratum_speculative_at_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1530923
 	/* Cortex A55 r0p0 to r2p0 */
 	MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0),
+	/* Kryo4xx Silver (rdpe => r1p0) */
+	MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 	{},
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+static const struct midr_range erratum_1463225[] = {
+	/* Cortex-A76 r0p0 - r3p1 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -914,6 +925,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.capability = ARM64_WORKAROUND_1463225,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_cortex_a76_erratum_1463225,
+		.midr_range_list = erratum_1463225,
 	},
 #endif
 #ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4ae41670c2e6..9fae0efc80c1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1290,6 +1290,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
@@ -1406,6 +1408,8 @@ static bool cpu_has_broken_dbm(void)
 	static const struct midr_range cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1024718
 		MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0),  // A55 r0p0 -r1p0
+		/* Kryo4xx Silver (rdpe => r1p0) */
+		MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 		{},
 	};
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 5df49366e9ab..7310a4f7f993 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -391,17 +394,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3dbdf9752b11..d3be9dbf5490 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -57,7 +57,7 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
 	/*
 	 * The CPU masked interrupts, and we are leaving them masked during
 	 * do_debug_exception(). Update PMR as if we had called
-	 * local_mask_daif().
+	 * local_daif_mask().
 	 */
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5304d193c79d..35de8ba60e3d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -126,8 +126,10 @@ alternative_else_nop_endif
 	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
-	// This macro corrupts x0-x3. It is the caller's duty
-	// to save/restore them if required.
+	/*
+	 * This macro corrupts x0-x3. It is the caller's duty  to save/restore
+	 * them if required.
+	 */
 	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
@@ -167,13 +169,28 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	.if	\regsize == 32
+	/*
+	 * If we're returning from a 32-bit task on a system affected by
+	 * 1418040 then re-enable userspace access to the virtual counter.
+	 */
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
 	msr	sp_el0, tsk
 
-	// Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
-	// when scheduling.
+	/*
+	 * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
+	 * when scheduling.
+	 */
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
@@ -320,6 +337,14 @@ alternative_else_nop_endif
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
@@ -331,21 +356,6 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if_not ARM64_WORKAROUND_1418040
-	b	4f
-alternative_else_nop_endif
-	/*
-	 * if (x22.mode32 == cntkctl_el1.el0vcten)
-	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
-	 */
-	mrs	x1, cntkctl_el1
-	eon	x0, x1, x22, lsr #3
-	tbz	x0, #1, 4f
-	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x1
-4:
-#endif
 	scs_save tsk, x0
 
 	/* No kernel C function calls after this as user keys are set. */
@@ -377,11 +387,11 @@ alternative_else_nop_endif
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	5f
+	bne	4f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-5:
+4:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac612146e..666b225aeb3a 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d1c95dcf1d78..5290f17a4d80 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 
 void *alloc_insn_page(void)
 {
-	void *page;
-
-	page = vmalloc_exec(PAGE_SIZE);
-	if (page) {
-		set_memory_ro((unsigned long)page, 1);
-		set_vm_flush_reset_perms(page);
-	}
-
-	return page;
+	return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 /* arm kprobe: install breakpoint in text */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68b7f34a08f5..1e02e98e68dd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1811,19 +1811,42 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	unsigned long saved_reg;
 
 	/*
-	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
-	 * used to denote syscall entry/exit:
+	 * We have some ABI weirdness here in the way that we handle syscall
+	 * exit stops because we indicate whether or not the stop has been
+	 * signalled from syscall entry or syscall exit by clobbering a general
+	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+	 * and restoring its old value after the stop. This means that:
+	 *
+	 * - Any writes by the tracer to this register during the stop are
+	 *   ignored/discarded.
+	 *
+	 * - The actual value of the register is not available during the stop,
+	 *   so the tracer cannot save it and restore it later.
+	 *
+	 * - Syscall stops behave differently to seccomp and pseudo-step traps
+	 *   (the latter do not nobble any registers).
 	 */
 	regno = (is_compat_task() ? 12 : 7);
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1833,12 +1856,12 @@ int syscall_trace_enter(struct pt_regs *regs)
 	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 		if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
-			return -1;
+			return NO_SYSCALL;
 	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing() == -1)
-		return -1;
+		return NO_SYSCALL;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
@@ -1851,12 +1874,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1934,8 +1959,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 801d56cdf701..3b4f31f35e45 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -800,7 +800,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -824,14 +823,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 82feca6f7052..2f507f565c48 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
 		/* Set up sigreturn pointer */
-#ifdef CONFIG_COMPAT_VDSO
-		void *vdso_base = current->mm->context.vdso;
-		void *vdso_trampoline;
-
-		if (ka->sa.sa_flags & SA_SIGINFO) {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_arm);
-			}
-		} else {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_arm);
-			}
-		}
-
-		retcode = ptr_to_compat(vdso_trampoline) + thumb;
-#else
 		unsigned int idx = thumb << 1;
 
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = (unsigned long)current->mm->context.vdso +
+		retcode = (unsigned long)current->mm->context.sigpage +
 			  (idx << 2) + thumb;
-#endif
 	}
 
 	regs->regs[0]	= usig;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f5b868292f5..5f0c04863d2c 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,21 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	user_exit();
 
 	if (has_syscall_work(flags)) {
-		/* set default errno for user-issued syscall(-1) */
+		/*
+		 * The de-facto standard way to skip a system call using ptrace
+		 * is to set the system call to -1 (NO_SYSCALL) and set x0 to a
+		 * suitable error code for consumption by userspace. However,
+		 * this cannot be distinguished from a user-issued syscall(-1)
+		 * and so we must set x0 to -ENOSYS here in case the tracer doesn't
+		 * issue the skip and we fall into trace_exit with x0 preserved.
+		 *
+		 * This is slightly odd because it also means that if a tracer
+		 * sets the system call number to -1 but does not initialise x0,
+		 * then x0 will be preserved for all system calls apart from a
+		 * user-issued syscall(-1). However, requesting a skip and not
+		 * setting the return value is unlikely to do anything sensible
+		 * anyway.
+		 */
 		if (scno == NO_SYSCALL)
 			regs->regs[0] = -ENOSYS;
 		scno = syscall_trace_enter(regs);
@@ -139,7 +156,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 4e016574bd91..e546df0efefb 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -191,15 +191,12 @@ enum aarch32_map {
 #ifdef CONFIG_COMPAT_VDSO
 	AA32_MAP_VVAR,
 	AA32_MAP_VDSO,
-#else
-	AA32_MAP_SIGPAGE
 #endif
+	AA32_MAP_SIGPAGE
 };
 
 static struct page *aarch32_vectors_page __ro_after_init;
-#ifndef CONFIG_COMPAT_VDSO
 static struct page *aarch32_sig_page __ro_after_init;
-#endif
 
 static struct vm_special_mapping aarch32_vdso_maps[] = {
 	[AA32_MAP_VECTORS] = {
@@ -214,12 +211,11 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
-#else
+#endif /* CONFIG_COMPAT_VDSO */
 	[AA32_MAP_SIGPAGE] = {
 		.name	= "[sigpage]", /* ABI */
 		.pages	= &aarch32_sig_page,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -242,27 +238,11 @@ static int aarch32_alloc_kuser_vdso_page(void)
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
-	int ret;
-
-	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
-	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
-
-	ret = __vdso_init(VDSO_ABI_AA32);
-	if (ret)
-		return ret;
-
-	return aarch32_alloc_kuser_vdso_page();
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+static int aarch32_alloc_sigpage(void)
 {
 	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
 	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
 	unsigned long sigpage;
-	int ret;
 
 	sigpage = get_zeroed_page(GFP_ATOMIC);
 	if (!sigpage)
@@ -271,18 +251,34 @@ static int __aarch32_alloc_vdso_pages(void)
 	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
 	aarch32_sig_page = virt_to_page(sigpage);
 	flush_dcache_page(aarch32_sig_page);
+	return 0;
+}
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret)
-		free_page(sigpage);
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
 
-	return ret;
+	return __vdso_init(VDSO_ABI_AA32);
 }
 #endif /* CONFIG_COMPAT_VDSO */
 
 static int __init aarch32_alloc_vdso_pages(void)
 {
-	return __aarch32_alloc_vdso_pages();
+	int ret;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __aarch32_alloc_vdso_pages();
+	if (ret)
+		return ret;
+#endif
+
+	ret = aarch32_alloc_sigpage();
+	if (ret)
+		return ret;
+
+	return aarch32_alloc_kuser_vdso_page();
 }
 arch_initcall(aarch32_alloc_vdso_pages);
 
@@ -305,7 +301,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	return PTR_ERR_OR_ZERO(ret);
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 static int aarch32_sigreturn_setup(struct mm_struct *mm)
 {
 	unsigned long addr;
@@ -328,12 +323,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	if (IS_ERR(ret))
 		goto out;
 
-	mm->context.vdso = (void *)addr;
+	mm->context.sigpage = (void *)addr;
 
 out:
 	return PTR_ERR_OR_ZERO(ret);
 }
-#endif /* !CONFIG_COMPAT_VDSO */
 
 int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
@@ -352,10 +346,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 				       mm,
 				       bprm,
 				       uses_interp);
-#else
-	ret = aarch32_sigreturn_setup(mm);
+	if (ret)
+		goto out;
 #endif /* CONFIG_COMPAT_VDSO */
 
+	ret = aarch32_sigreturn_setup(mm);
 out:
 	mmap_write_unlock(mm);
 	return ret;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 556d424c6f52..45d5cfe46429 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
 # potential future proofing if we end up with internal calls to the exported
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
-ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-		-Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
+	     -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n	\
+	     $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
 KBUILD_CFLAGS			+= $(DISABLE_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 620a3ef837b7..0e18729abc3b 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -18,29 +18,40 @@
 
 	.text
 
+/*
+ * NOTE!!!  You may notice that all of the .cfi directives in this file have
+ * been commented out. This is because they have been shown to trigger segfaults
+ * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread
+ * cleanup handlers during the thread cancellation dance. By omitting the
+ * directives, we trigger an arm64-specific fallback path in the unwinder which
+ * recognises the signal frame and restores many of the registers directly from
+ * the sigcontext. Re-enabling the cfi directives here therefore needs to be
+ * much more comprehensive to reduce the risk of further regressions.
+ */
+
 /* Ensure that the mysterious NOP can be associated with a function. */
-	.cfi_startproc
+//	.cfi_startproc
 
 /*
- * .cfi_signal_frame causes the corresponding Frame Description Entry in the
- * .eh_frame section to be annotated as a signal frame. This allows DWARF
- * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits
- * unwinding out of the signal trampoline without the need for the mysterious
- * NOP.
+ * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in
+ * the .eh_frame section to be annotated as a signal frame. This allows DWARF
+ * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify
+ * the next frame using the unmodified return address instead of subtracting 1,
+ * which may yield the wrong FDE.
  */
-	.cfi_signal_frame
+//	.cfi_signal_frame
 
 /*
  * Tell the unwinder where to locate the frame record linking back to the
- * interrupted context. We don't provide unwind info for registers other
- * than the frame pointer and the link register here; in practice, this
- * is sufficient for unwinding in C/C++ based runtimes and the values in
- * the sigcontext may have been modified by this point anyway. Debuggers
+ * interrupted context. We don't provide unwind info for registers other than
+ * the frame pointer and the link register here; in practice, this is likely to
+ * be insufficient for unwinding in C/C++ based runtimes, especially without a
+ * means to restore the stack pointer. Thankfully, unwinders and debuggers
  * already have baked-in strategies for attempting to unwind out of signals.
  */
-	.cfi_def_cfa    x29, 0
-	.cfi_offset     x29, 0 * 8
-	.cfi_offset     x30, 1 * 8
+//	.cfi_def_cfa    x29, 0
+//	.cfi_offset     x29, 0 * 8
+//	.cfi_offset     x30, 1 * 8
 
 /*
  * This mysterious NOP is required for some unwinders (e.g. libc++) that
@@ -51,16 +62,19 @@
 	nop	// Mysterious NOP
 
 /*
- * GDB relies on being able to identify the sigreturn instruction sequence to
- * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START()
- * here, as it will emit a BTI C instruction and break the unwinder. Thankfully,
- * this function is only ever called from a RET and so omitting the landing pad
- * is perfectly fine.
+ * GDB, libgcc and libunwind rely on being able to identify the sigreturn
+ * instruction sequence to unwind from signal handlers. We cannot, therefore,
+ * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the
+ * unwinder. Thankfully, this function is only ever called from a RET and so
+ * omitting the landing pad is perfectly fine.
  */
 SYM_CODE_START(__kernel_rt_sigreturn)
+//	PLEASE DO NOT MODIFY
 	mov	x8, #__NR_rt_sigreturn
+//	PLEASE DO NOT MODIFY
 	svc	#0
-	.cfi_endproc
+//	PLEASE DO NOT MODIFY
+//	.cfi_endproc
 SYM_CODE_END(__kernel_rt_sigreturn)
 
 emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 7ea1e827e505..5139a5f19256 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit))
 COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
 
 CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT))
 CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
 ifneq ($(COMPAT_GCC_TOOLCHAIN),)
 CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)
@@ -140,7 +140,6 @@ hostprogs := $(munge)
 
 c-obj-vdso := note.o
 c-obj-vdso-gettimeofday := vgettimeofday.o
-asm-obj-vdso := sigreturn.o
 
 ifneq ($(c-gettimeofday-y),)
 VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
deleted file mode 100644
index b0091064c3d6..000000000000
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This file provides both A32 and T32 versions, in accordance with the
- * arm sigreturn code.
- *
- * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to
- * understand some of the craziness in here.
- *
- * Copyright (C) 2018 ARM Limited
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-	.text
-
-	.arm
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_arm)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_arm)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_arm)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_arm)
-
-	.thumb
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_thumb)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_thumb)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_thumb)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index a3944927eaeb..337d03522048 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -64,19 +64,7 @@ VERSION
 		__vdso_clock_gettime;
 		__vdso_gettimeofday;
 		__vdso_clock_getres;
-		__kernel_sigreturn_arm;
-		__kernel_sigreturn_thumb;
-		__kernel_rt_sigreturn_arm;
-		__kernel_rt_sigreturn_thumb;
 		__vdso_clock_gettime64;
 	local: *;
 	};
 }
-
-/*
- * Make the sigreturn code visible to the kernel.
- */
-VDSO_compat_sigreturn_arm	= __kernel_sigreturn_arm;
-VDSO_compat_sigreturn_thumb	= __kernel_sigreturn_thumb;
-VDSO_compat_rt_sigreturn_arm	= __kernel_rt_sigreturn_arm;
-VDSO_compat_rt_sigreturn_thumb	= __kernel_rt_sigreturn_thumb;
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6827da7f3aa5..5423ffe0a987 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -165,9 +165,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(SEGMENT_ALIGN);
 	__inittext_end = .;