1 files changed, 94 insertions, 58 deletions

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index aacf2f5559a8..044a7d7f1f6a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -40,6 +40,7 @@
 #include <linux/percpu.h>
 #include <linux/thread_info.h>
 #include <linux/prctl.h>
+#include <linux/stacktrace.h>
 
 #include <asm/alternative.h>
 #include <asm/compat.h>
@@ -110,8 +111,7 @@ void machine_power_off(void)
 {
 	local_irq_disable();
 	smp_send_stop();
-	if (pm_power_off)
-		pm_power_off();
+	do_kernel_power_off();
 }
 
 /*
@@ -249,6 +249,8 @@ void show_regs(struct pt_regs *regs)
 static void tls_thread_flush(void)
 {
 	write_sysreg(0, tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(0, SYS_TPIDR2_EL0);
 
 	if (is_compat_task()) {
 		current->thread.uw.tp_value = 0;
@@ -277,10 +279,6 @@ void flush_thread(void)
 	flush_tagged_addr_state();
 }
 
-void release_thread(struct task_struct *dead_task)
-{
-}
-
 void arch_release_task_struct(struct task_struct *tsk)
 {
 	fpsimd_release_task(tsk);
@@ -297,16 +295,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	/*
 	 * Detach src's sve_state (if any) from dst so that it does not
-	 * get erroneously used or freed prematurely.  dst's sve_state
+	 * get erroneously used or freed prematurely.  dst's copies
 	 * will be allocated on demand later on if dst uses SVE.
 	 * For consistency, also clear TIF_SVE here: this could be done
 	 * later in copy_process(), but to avoid tripping up future
-	 * maintainers it is best not to leave TIF_SVE and sve_state in
+	 * maintainers it is best not to leave TIF flags and buffers in
 	 * an inconsistent state, even temporarily.
 	 */
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	/*
+	 * In the unlikely event that we create a new thread with ZA
+	 * enabled we should retain the ZA state so duplicate it here.
+	 * This may be shortly freed if we exec() or if CLONE_SETTLS
+	 * but it's simpler to do it here. To avoid confusing the rest
+	 * of the code ensure that we have a sve_state allocated
+	 * whenever za_state is allocated.
+	 */
+	if (thread_za_enabled(&src->thread)) {
+		dst->thread.sve_state = kzalloc(sve_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.sve_state)
+			return -ENOMEM;
+		dst->thread.za_state = kmemdup(src->thread.za_state,
+					       za_state_size(src),
+					       GFP_KERNEL);
+		if (!dst->thread.za_state) {
+			kfree(dst->thread.sve_state);
+			dst->thread.sve_state = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		dst->thread.za_state = NULL;
+		clear_tsk_thread_flag(dst, TIF_SME);
+	}
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 
@@ -315,9 +339,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long stack_start = args->stack;
+	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
@@ -333,7 +359,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	ptrauth_thread_init_kernel(p);
 
-	if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
+	if (likely(!args->fn)) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
 
@@ -342,6 +368,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		 * out-of-sync with the saved value.
 		 */
 		*task_user_tls(p) = read_sysreg(tpidr_el0);
+		if (system_supports_tpidr2())
+			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 
 		if (stack_start) {
 			if (is_compat_thread(task_thread_info(p)))
@@ -352,10 +380,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 		/*
 		 * If a TLS pointer was passed to clone, use it for the new
-		 * thread.
+		 * thread.  We also reset TPIDR2 if it's in use.
 		 */
-		if (clone_flags & CLONE_SETTLS)
+		if (clone_flags & CLONE_SETTLS) {
 			p->thread.uw.tp_value = tls;
+			p->thread.tpidr2_el0 = 0;
+		}
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy
@@ -367,8 +397,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
 
-		p->thread.cpu_context.x19 = stack_start;
-		p->thread.cpu_context.x20 = stk_sz;
+		p->thread.cpu_context.x19 = (unsigned long)args->fn;
+		p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;
@@ -386,6 +416,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 void tls_preserve_current_state(void)
 {
 	*task_user_tls(current) = read_sysreg(tpidr_el0);
+	if (system_supports_tpidr2() && !is_compat_task())
+		current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 }
 
 static void tls_thread_switch(struct task_struct *next)
@@ -398,6 +430,8 @@ static void tls_thread_switch(struct task_struct *next)
 		write_sysreg(0, tpidrro_el0);
 
 	write_sysreg(*task_user_tls(next), tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
 }
 
 /*
@@ -439,34 +473,26 @@ static void entry_task_switch(struct task_struct *next)
 
 /*
  * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
- * Assuming the virtual counter is enabled at the beginning of times:
- *
- * - disable access when switching from a 64bit task to a 32bit task
- * - enable access when switching from a 32bit task to a 64bit task
+ * Ensure access is disabled when switching to a 32bit task, ensure
+ * access is enabled when switching to a 64bit task.
  */
-static void erratum_1418040_thread_switch(struct task_struct *prev,
-					  struct task_struct *next)
+static void erratum_1418040_thread_switch(struct task_struct *next)
 {
-	bool prev32, next32;
-	u64 val;
-
-	if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040))
+	if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) ||
+	    !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
 		return;
 
-	prev32 = is_compat_thread(task_thread_info(prev));
-	next32 = is_compat_thread(task_thread_info(next));
-
-	if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
-		return;
-
-	val = read_sysreg(cntkctl_el1);
-
-	if (!next32)
-		val |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+	if (is_compat_thread(task_thread_info(next)))
+		sysreg_clear_set(cntkctl_el1, ARCH_TIMER_USR_VCT_ACCESS_EN, 0);
 	else
-		val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN;
+		sysreg_clear_set(cntkctl_el1, 0, ARCH_TIMER_USR_VCT_ACCESS_EN);
+}
 
-	write_sysreg(val, cntkctl_el1);
+static void erratum_1418040_new_exec(void)
+{
+	preempt_disable();
+	erratum_1418040_thread_switch(current);
+	preempt_enable();
 }
 
 /*
@@ -490,7 +516,8 @@ void update_sctlr_el1(u64 sctlr)
 /*
  * Thread switching.
  */
-__notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
+__notrace_funcgraph __sched
+struct task_struct *__switch_to(struct task_struct *prev,
 				struct task_struct *next)
 {
 	struct task_struct *last;
@@ -501,7 +528,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
 	ssbs_thread_switch(next);
-	erratum_1418040_thread_switch(prev, next);
+	erratum_1418040_thread_switch(next);
 	ptrauth_thread_switch_user(next);
 
 	/*
@@ -528,36 +555,43 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	return last;
 }
 
+struct wchan_info {
+	unsigned long	pc;
+	int		count;
+};
+
+static bool get_wchan_cb(void *arg, unsigned long pc)
+{
+	struct wchan_info *wchan_info = arg;
+
+	if (!in_sched_functions(pc)) {
+		wchan_info->pc = pc;
+		return false;
+	}
+	return wchan_info->count++ < 16;
+}
+
 unsigned long __get_wchan(struct task_struct *p)
 {
-	struct stackframe frame;
-	unsigned long stack_page, ret = 0;
-	int count = 0;
+	struct wchan_info wchan_info = {
+		.pc = 0,
+		.count = 0,
+	};
 
-	stack_page = (unsigned long)try_get_task_stack(p);
-	if (!stack_page)
+	if (!try_get_task_stack(p))
 		return 0;
 
-	start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p));
+	arch_stack_walk(get_wchan_cb, &wchan_info, p, NULL);
 
-	do {
-		if (unwind_frame(p, &frame))
-			goto out;
-		if (!in_sched_functions(frame.pc)) {
-			ret = frame.pc;
-			goto out;
-		}
-	} while (count++ < 16);
-
-out:
 	put_task_stack(p);
-	return ret;
+
+	return wchan_info.pc;
 }
 
 unsigned long arch_align_stack(unsigned long sp)
 {
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() & ~PAGE_MASK;
+		sp -= prandom_u32_max(PAGE_SIZE);
 	return sp & ~0xf;
 }
 
@@ -611,6 +645,7 @@ void arch_setup_new_exec(void)
 	current->mm->context.flags = mmflags;
 	ptrauth_thread_init_user();
 	mte_thread_init_user();
+	erratum_1418040_new_exec();
 
 	if (task_spec_ssb_noexec(current)) {
 		arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,
@@ -633,7 +668,8 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 		return -EINVAL;
 
 	if (system_supports_mte())
-		valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
+		valid_mask |= PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC \
+			| PR_MTE_TAG_MASK;
 
 	if (arg & ~valid_mask)
 		return -EINVAL;