Merge branch 'lsk/kdump/for-v4.9' into linux-linaro-lsk-v4.9

6 files changed, 316 insertions, 11 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7d66bba..6a7384e 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -50,6 +50,7 @@ arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
+arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
new file mode 100644
index 0000000..f46d57c
--- /dev/null
+++ b/arch/arm64/kernel/crash_dump.c
@@ -0,0 +1,71 @@
+/*
+ * Routines for doing kexec-based kdump
+ *
+ * Copyright (C) 2017 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@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/crash_dump.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/uaccess.h>
+#include <asm/memory.h>
+
+/**
+ * copy_oldmem_page() - copy one page from old kernel memory
+ * @pfn: page frame number to be copied
+ * @buf: buffer where the copied page is placed
+ * @csize: number of bytes to copy
+ * @offset: offset in bytes into the page
+ * @userbuf: if set, @buf is in a user address space
+ *
+ * This function copies one page from old kernel memory into buffer pointed by
+ * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
+ * copied or negative error in case of failure.
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
+			 size_t csize, unsigned long offset,
+			 int userbuf)
+{
+	void *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+	if (!vaddr)
+		return -ENOMEM;
+
+	if (userbuf) {
+		if (copy_to_user((char __user *)buf, vaddr + offset, csize)) {
+			memunmap(vaddr);
+			return -EFAULT;
+		}
+	} else {
+		memcpy(buf, vaddr + offset, csize);
+	}
+
+	memunmap(vaddr);
+
+	return csize;
+}
+
+/**
+ * elfcorehdr_read - read from ELF core header
+ * @buf: buffer where the data is placed
+ * @csize: number of bytes to read
+ * @ppos: address in the memory
+ *
+ * This function reads @count bytes from elf core header which exists
+ * on crash dump kernel's memory.
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+	return count;
+}
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index d55a7b0..4b10dc1 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -28,6 +28,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/irqflags.h>
+#include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
@@ -105,7 +106,8 @@ int pfn_is_nosave(unsigned long pfn)
 	unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
 	unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);
 
-	return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+	return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)) ||
+		crash_is_nosave(pfn);
 }
 
 void notrace save_processor_state(void)
@@ -289,6 +291,9 @@ int swsusp_arch_suspend(void)
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
+		/* make the crash dump kernel image visible/saveable */
+		crash_prepare_suspend();
+
 		sleep_cpu = smp_processor_id();
 		ret = swsusp_save();
 	} else {
@@ -300,6 +305,9 @@ int swsusp_arch_suspend(void)
 		if (el2_reset_needed())
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
 
+		/* make the crash dump kernel image protected again */
+		crash_post_resume();
+
 		/*
 		 * Tell the hibernation core that we've just restored
 		 * the memory
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index bc96c8a..481f54a 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -9,12 +9,19 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <linux/page-flags.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
 #include <asm/mmu_context.h>
+#include <asm/page.h>
 
 #include "cpu-reset.h"
 
@@ -22,8 +29,6 @@
 extern const unsigned char arm64_relocate_new_kernel[];
 extern const unsigned long arm64_relocate_new_kernel_size;
 
-static unsigned long kimage_start;
-
 /**
  * kexec_image_info - For debugging output.
  */
@@ -64,8 +69,6 @@ void machine_kexec_cleanup(struct kimage *kimage)
  */
 int machine_kexec_prepare(struct kimage *kimage)
 {
-	kimage_start = kimage->start;
-
 	kexec_image_info(kimage);
 
 	if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
@@ -144,11 +147,15 @@ void machine_kexec(struct kimage *kimage)
 {
 	phys_addr_t reboot_code_buffer_phys;
 	void *reboot_code_buffer;
+	bool in_kexec_crash = (kimage == kexec_crash_image);
+	bool stuck_cpus = cpus_are_stuck_in_kernel();
 
 	/*
 	 * New cpus may have become stuck_in_kernel after we loaded the image.
 	 */
-	BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1));
+	BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1)));
+	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
 
 	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
@@ -183,7 +190,7 @@ void machine_kexec(struct kimage *kimage)
 	kexec_list_flush(kimage);
 
 	/* Flush the new image if already in place. */
-	if (kimage->head & IND_DONE)
+	if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE))
 		kexec_segment_flush(kimage);
 
 	pr_info("Bye!\n");
@@ -200,13 +207,158 @@ void machine_kexec(struct kimage *kimage)
 	 * relocation is complete.
 	 */
 
-	cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head,
-		kimage_start, 0);
+	cpu_soft_restart(kimage != kexec_crash_image,
+		reboot_code_buffer_phys, kimage->head, kimage->start, 0);
 
 	BUG(); /* Should never get here. */
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	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);
+
+		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);
+	}
+}
+
+/**
+ * machine_crash_shutdown - shutdown non-crashing cpus and save registers
+ */
 void machine_crash_shutdown(struct pt_regs *regs)
 {
-	/* Empty routine needed to avoid build errors. */
+	local_irq_disable();
+
+	/* shutdown non-crashing cpus */
+	smp_send_crash_stop();
+
+	/* for crashing cpu */
+	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
+	pr_info("Starting crashdump kernel...\n");
+}
+
+void arch_kexec_protect_crashkres(void)
+{
+	int i;
+
+	kexec_segment_flush(kexec_crash_image);
+
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		set_memory_valid(
+			__phys_to_virt(kexec_crash_image->segment[i].mem),
+			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0);
+}
+
+void arch_kexec_unprotect_crashkres(void)
+{
+	int i;
+
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		set_memory_valid(
+			__phys_to_virt(kexec_crash_image->segment[i].mem),
+			kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1);
+}
+
+#ifdef CONFIG_HIBERNATION
+/*
+ * To preserve the crash dump kernel image, the relevant memory segments
+ * should be mapped again around the hibernation.
+ */
+void crash_prepare_suspend(void)
+{
+	if (kexec_crash_image)
+		arch_kexec_unprotect_crashkres();
+}
+
+void crash_post_resume(void)
+{
+	if (kexec_crash_image)
+		arch_kexec_protect_crashkres();
+}
+
+/*
+ * crash_is_nosave
+ *
+ * Return true only if a page is part of reserved memory for crash dump kernel,
+ * but does not hold any data of loaded kernel image.
+ *
+ * Note that all the pages in crash dump kernel memory have been initially
+ * marked as Reserved in kexec_reserve_crashkres_pages().
+ *
+ * In hibernation, the pages which are Reserved and yet "nosave" are excluded
+ * from the hibernation iamge. crash_is_nosave() does thich check for crash
+ * dump kernel and will reduce the total size of hibernation image.
+ */
+
+bool crash_is_nosave(unsigned long pfn)
+{
+	int i;
+	phys_addr_t addr;
+
+	if (!crashk_res.end)
+		return false;
+
+	/* in reserved memory? */
+	addr = __pfn_to_phys(pfn);
+	if ((addr < crashk_res.start) || (crashk_res.end < addr))
+		return false;
+
+	if (!kexec_crash_image)
+		return true;
+
+	/* not part of loaded kernel image? */
+	for (i = 0; i < kexec_crash_image->nr_segments; i++)
+		if (addr >= kexec_crash_image->segment[i].mem &&
+				addr < (kexec_crash_image->segment[i].mem +
+					kexec_crash_image->segment[i].memsz))
+			return false;
+
+	return true;
+}
+
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+	unsigned long addr;
+	struct page *page;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
+		page = phys_to_page(addr);
+		ClearPageReserved(page);
+		free_reserved_page(page);
+	}
+}
+#endif /* CONFIG_HIBERNATION */
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_NUMBER(VA_BITS);
+	/* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+	vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+						kimage_voffset);
+	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+						PHYS_OFFSET);
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index a53f52a..e4e2a5a 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -31,7 +31,6 @@
 #include <linux/screen_info.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
-#include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
@@ -224,6 +223,12 @@ static void __init request_standard_resources(void)
 		if (kernel_data.start >= res->start &&
 		    kernel_data.end <= res->end)
 			request_resource(res, &kernel_data);
+#ifdef CONFIG_KEXEC_CORE
+		/* Userspace will find "Crash kernel" region in /proc/iomem. */
+		if (crashk_res.end && crashk_res.start >= res->start &&
+		    crashk_res.end <= res->end)
+			request_resource(res, &crashk_res);
+#endif
 	}
 }
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index cb87234..11f2890 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -37,6 +37,7 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/kexec.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -74,6 +75,7 @@ enum ipi_msg_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CPU_STOP,
+	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
 	IPI_WAKEUP
@@ -753,6 +755,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
@@ -827,6 +830,29 @@ static void ipi_cpu_stop(unsigned int cpu)
 		cpu_relax();
 }
 
+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+#endif
+
+static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+#ifdef CONFIG_KEXEC_CORE
+	crash_save_cpu(regs, cpu);
+
+	atomic_dec(&waiting_for_crash_ipi);
+
+	local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu]->cpu_die)
+		cpu_ops[cpu]->cpu_die(cpu);
+#endif
+
+	/* just in case */
+	cpu_park_loop();
+#endif
+}
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -857,6 +883,15 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+	case IPI_CPU_CRASH_STOP:
+		if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
+			irq_enter();
+			ipi_cpu_crash_stop(cpu, regs);
+
+			unreachable();
+		}
+		break;
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
 		irq_enter();
@@ -929,6 +964,39 @@ void smp_send_stop(void)
 			   cpumask_pr_args(cpu_online_mask));
 }
 
+#ifdef CONFIG_KEXEC_CORE
+void smp_send_crash_stop(void)
+{
+	cpumask_t mask;
+	unsigned long timeout;
+
+	if (num_online_cpus() == 1)
+		return;
+
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+
+	pr_crit("SMP: stopping secondary CPUs\n");
+	smp_cross_call(&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_warning("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
+
 /*
  * not supported here
  */