Merge tag 'v6.1-rc8' into efi/next

Linux 6.1-rc8

6 files changed, 167 insertions, 17 deletions

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b9eda3fcbd6d..186abd146eaf 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -404,6 +404,19 @@ handle_syscall_trace_exit:
 
 #ifdef CONFIG_VMAP_STACK
 handle_kernel_stack_overflow:
+	/*
+	 * Takes the psuedo-spinlock for the shadow stack, in case multiple
+	 * harts are concurrently overflowing their kernel stacks.  We could
+	 * store any value here, but since we're overflowing the kernel stack
+	 * already we only have SP to use as a scratch register.  So we just
+	 * swap in the address of the spinlock, as that's definately non-zero.
+	 *
+	 * Pairs with a store_release in handle_bad_stack().
+	 */
+1:	la sp, spin_shadow_stack
+	REG_AMOSWAP_AQ sp, sp, (sp)
+	bnez sp, 1b
+
 	la sp, shadow_stack
 	addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE
 
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index ee79e6839b86..2d139b724bc8 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -15,6 +15,8 @@
 #include <linux/compiler.h>	/* For unreachable() */
 #include <linux/cpu.h>		/* For cpu_down() */
 #include <linux/reboot.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
 
 /*
  * kexec_image_info - Print received image details
@@ -138,20 +140,35 @@ void machine_shutdown(void)
 #endif
 }
 
-/* Override the weak function in kernel/panic.c */
-void crash_smp_send_stop(void)
+static void machine_kexec_mask_interrupts(void)
 {
-	static int cpus_stopped;
+	unsigned int i;
+	struct irq_desc *desc;
 
-	/*
-	 * This function can be called twice in panic path, but obviously
-	 * we execute this only once.
-	 */
-	if (cpus_stopped)
-		return;
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int ret;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		/*
+		 * First try to remove the active state. If this
+		 * fails, try to EOI the interrupt.
+		 */
+		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+		    chip->irq_eoi)
+			chip->irq_eoi(&desc->irq_data);
 
-	smp_send_stop();
-	cpus_stopped = 1;
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
 }
 
 /*
@@ -169,6 +186,8 @@ machine_crash_shutdown(struct pt_regs *regs)
 	crash_smp_send_stop();
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
 	pr_info("Starting crashdump kernel...\n");
 }
 
@@ -195,6 +214,11 @@ machine_kexec(struct kimage *image)
 	void *control_code_buffer = page_address(image->control_code_page);
 	riscv_kexec_method kexec_method = NULL;
 
+#ifdef CONFIG_SMP
+	WARN(smp_crash_stop_failed(),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
+#endif
+
 	if (image->type != KEXEC_TYPE_CRASH)
 		kexec_method = control_code_buffer;
 	else
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 67ec1fadcfe2..86acd690d529 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -322,10 +322,11 @@ subsys_initcall(topology_init);
 
 void free_initmem(void)
 {
-	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
-		set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end),
-				  IS_ENABLED(CONFIG_64BIT) ?
-					set_memory_rw : set_memory_rw_nx);
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
+		set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx);
+		if (IS_ENABLED(CONFIG_64BIT))
+			set_kernel_memory(__init_begin, __init_end, set_memory_nx);
+	}
 
 	free_initmem_default(POISON_FREE_INITMEM);
 }
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 760a64518c58..8c3b59f1f9b8 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -12,6 +12,7 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/kexec.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
@@ -22,11 +23,13 @@
 #include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
 
 enum ipi_message_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CPU_STOP,
+	IPI_CPU_CRASH_STOP,
 	IPI_IRQ_WORK,
 	IPI_TIMER,
 	IPI_MAX
@@ -71,6 +74,32 @@ static void ipi_stop(void)
 		wait_for_interrupt();
 }
 
+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+
+static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+	crash_save_cpu(regs, cpu);
+
+	atomic_dec(&waiting_for_crash_ipi);
+
+	local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_has_hotplug(cpu))
+		cpu_ops[cpu]->cpu_stop();
+#endif
+
+	for(;;)
+		wait_for_interrupt();
+}
+#else
+static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+	unreachable();
+}
+#endif
+
 static const struct riscv_ipi_ops *ipi_ops __ro_after_init;
 
 void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
@@ -124,8 +153,9 @@ void arch_irq_work_raise(void)
 
 void handle_IPI(struct pt_regs *regs)
 {
-	unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits;
-	unsigned long *stats = ipi_data[smp_processor_id()].stats;
+	unsigned int cpu = smp_processor_id();
+	unsigned long *pending_ipis = &ipi_data[cpu].bits;
+	unsigned long *stats = ipi_data[cpu].stats;
 
 	riscv_clear_ipi();
 
@@ -154,6 +184,10 @@ void handle_IPI(struct pt_regs *regs)
 			ipi_stop();
 		}
 
+		if (ops & (1 << IPI_CPU_CRASH_STOP)) {
+			ipi_cpu_crash_stop(cpu, get_irq_regs());
+		}
+
 		if (ops & (1 << IPI_IRQ_WORK)) {
 			stats[IPI_IRQ_WORK]++;
 			irq_work_run();
@@ -176,6 +210,7 @@ static const char * const ipi_names[] = {
 	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
 	[IPI_CALL_FUNC]		= "Function call interrupts",
 	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
 	[IPI_IRQ_WORK]		= "IRQ work interrupts",
 	[IPI_TIMER]		= "Timer broadcast interrupts",
 };
@@ -235,6 +270,64 @@ void smp_send_stop(void)
 			   cpumask_pr_args(cpu_online_mask));
 }
 
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * The number of CPUs online, not counting this CPU (which may not be
+ * fully online and so not counted in num_online_cpus()).
+ */
+static inline unsigned int num_other_online_cpus(void)
+{
+	unsigned int this_cpu_online = cpu_online(smp_processor_id());
+
+	return num_online_cpus() - this_cpu_online;
+}
+
+void crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+	cpumask_t mask;
+	unsigned long timeout;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	cpus_stopped = 1;
+
+	/*
+	 * If this cpu is the only one alive at this point in time, online or
+	 * not, there are no stop messages to be sent around, so just back out.
+	 */
+	if (num_other_online_cpus() == 0)
+		return;
+
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+
+	atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
+
+	pr_crit("SMP: stopping secondary CPUs\n");
+	send_ipi_mask(&mask, IPI_CPU_CRASH_STOP);
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+		udelay(1);
+
+	if (atomic_read(&waiting_for_crash_ipi) > 0)
+		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+			cpumask_pr_args(&mask));
+}
+
+bool smp_crash_stop_failed(void)
+{
+	return (atomic_read(&waiting_for_crash_ipi) > 0);
+}
+#endif
+
 void smp_send_reschedule(int cpu)
 {
 	send_ipi_single(cpu, IPI_RESCHEDULE);
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index f3e96d60a2ff..7abd8e4c4df6 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -221,11 +221,29 @@ asmlinkage unsigned long get_overflow_stack(void)
 		OVERFLOW_STACK_SIZE;
 }
 
+/*
+ * A pseudo spinlock to protect the shadow stack from being used by multiple
+ * harts concurrently.  This isn't a real spinlock because the lock side must
+ * be taken without a valid stack and only a single register, it's only taken
+ * while in the process of panicing anyway so the performance and error
+ * checking a proper spinlock gives us doesn't matter.
+ */
+unsigned long spin_shadow_stack;
+
 asmlinkage void handle_bad_stack(struct pt_regs *regs)
 {
 	unsigned long tsk_stk = (unsigned long)current->stack;
 	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
 
+	/*
+	 * We're done with the shadow stack by this point, as we're on the
+	 * overflow stack.  Tell any other concurrent overflowing harts that
+	 * they can proceed with panicing by releasing the pseudo-spinlock.
+	 *
+	 * This pairs with an amoswap.aq in handle_kernel_stack_overflow.
+	 */
+	smp_store_release(&spin_shadow_stack, 0);
+
 	console_verbose();
 
 	pr_emerg("Insufficient stack space to handle exception!\n");
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index db6548509bb3..06e6b27f3bcc 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -17,6 +17,7 @@ vdso-syms += flush_icache
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ccflags-y := -fno-stack-protector
+ccflags-y += -DDISABLE_BRANCH_PROFILING
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)