arm64 kexec kernel patches v11

index b51f2cc..3b46501 100644
@@ -1,5 +1,5 @@
 /*
- * Based on arch/arm/include/asm/assembler.h
+ * Based on arch/arm/include/asm/assembler.h, arch/arm/mm/proc-macros.S
  *
  * Copyright (C) 1996-2000 Russell King
  * Copyright (C) 2012 ARM Ltd.

@@ -23,6 +23,8 @@
 #ifndef __ASM_ASSEMBLER_H
 #define __ASM_ASSEMBLER_H
 
+#include <asm/asm-offsets.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 

@@ -193,4 +195,48 @@ lr	.req	x30		// link register
 	str	\src, [\tmp, :lo12:\sym]
 	.endm
 
+/*
+ * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
+ */
+	.macro	vma_vm_mm, rd, rn
+	ldr	\rd, [\rn, #VMA_VM_MM]
+	.endm
+
+/*
+ * mmid - get context id from mm pointer (mm->context.id)
+ */
+	.macro	mmid, rd, rn
+	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+	.endm
+
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ */
+	.macro	dcache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	and	\tmp, \tmp, #0xf		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
+ */
+	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
+#ifndef CONFIG_ARM64_VA_BITS_48
+	ldr_l	\tmpreg, idmap_t0sz
+	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+#endif
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */

index 7a5df52..eb10368 100644
@@ -18,6 +18,33 @@
 #ifndef __ASM__VIRT_H
 #define __ASM__VIRT_H
 
+/*
+ * The arm64 hcall implementation uses the ISS field of the ESR_EL2 register to
+ * specify the hcall type.  The exception handlers are allowed to use registers
+ * x17 and x18 in their implementation.  Any routine issuing an hcall must not
+ * expect these registers to be preserved.
+ */
+
+/*
+ * HVC_CALL_HYP - Execute a hyp routine.
+ */
+
+#define HVC_CALL_HYP 0
+
+/*
+ * HVC_GET_VECTORS - Return the value of the vbar_el2 register.
+ */
+
+#define HVC_GET_VECTORS 1
+
+/*
+ * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
+ *
+ * @x0: Physical address of the new vector table.
+ */
+
+#define HVC_SET_VECTORS 2
+
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 

index eb10368..3070096 100644
@@ -45,6 +45,19 @@
 
 #define HVC_SET_VECTORS 2
 
+/*
+ * HVC_CALL_FUNC - Execute a function at EL2.
+ *
+ * @x0: Physical address of the function to be executed.
+ * @x1: Passed as the first argument to the function.
+ * @x2: Passed as the second argument to the function.
+ * @x3: Passed as the third argument to the function.
+ *
+ * The called function must preserve the contents of register x18.
+ */
+
+#define HVC_CALL_FUNC 3
+
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 

index c4072d9..4c6a38c 100644
@@ -211,6 +211,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
+static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+					phys_addr_t phys_idmap_start)
+{
+	/*
+	 * TODO
+	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
+	 */
+}
+
 static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 {
 	return 0;

@@ -223,7 +232,6 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
-static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

index 405aa18..dc6fadf 100644
@@ -66,6 +66,7 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
+phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

149 lines not on this page · raw message

index 6984342..69b4a33 100644
@@ -1644,6 +1644,11 @@ phys_addr_t kvm_get_idmap_vector(void)
 	return hyp_idmap_vector;
 }
 
+phys_addr_t kvm_get_idmap_start(void)
+{
+	return hyp_idmap_start;
+}
+
 int kvm_mmu_init(void)
 {
 	int err;

index ed03968..e86421a 100644
@@ -220,6 +220,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
 struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
+void kvm_call_reset(phys_addr_t boot_pgd_ptr, phys_addr_t phys_idmap_start);
 void force_vm_exit(const cpumask_t *mask);
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 

@@ -244,7 +245,20 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 		     hyp_stack_ptr, vector_ptr);
 }
 
-static inline void kvm_arch_hardware_disable(void) {}
+static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+					phys_addr_t phys_idmap_start)
+{
+	/*
+	 * Call reset code, and switch back to stub hyp vectors.
+	 */
+	kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
+}
+
+struct vgic_sr_vectors {
+	void	*save_vgic;
+	void	*restore_vgic;
+};
+
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

index 6150567..ff5a087 100644
@@ -98,6 +98,7 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
+phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

index 3070096..bca79f9 100644
@@ -58,9 +58,18 @@
 
 #define HVC_CALL_FUNC 3
 
+/*
+ * HVC_RESET_CPU - Reset cpu in EL2 to initial state.
+ *
+ * @x0: entry address in trampoline code in va
+ * @x1: identical mapping page table in pa
+ */
+
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 
+#define HVC_RESET_CPU 4
+
 #ifndef __ASSEMBLY__
 
 /*

new file mode 100644
index 0000000..79816b6
@@ -0,0 +1,22 @@
+/*
+ * cpu reset routines
+ *
+ * Copyright (C) 2015 Huawei Futurewei Technologies.
+ *
+ * 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.
+ */
+
+#if !defined(_ARM64_CPU_RESET_H)
+#define _ARM64_CPU_RESET_H
+
+#include <asm/virt.h>
+
+void __attribute__((noreturn)) cpu_reset(unsigned long el2_switch,
+	unsigned long entry, unsigned long arg0, unsigned long arg1);
+void __attribute__((noreturn)) cpu_soft_restart(phys_addr_t cpu_reset,
+	unsigned long el2_switch, unsigned long entry, unsigned long arg0,
+	unsigned long arg1);
+
+#endif

index 0302087..79fcfb0 100644
@@ -28,6 +28,7 @@ typedef struct {
 #define ASID(mm)	((mm)->context.id & 0xffff)
 
 extern void paging_init(void);
+extern void setup_mm_for_reboot(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,

index 9211b85..8cffad9 100644
@@ -461,6 +461,17 @@ void __init paging_init(void)
 }
 
 /*
+ * Enable the identity mapping to allow the MMU disabling.
+ */
+void setup_mm_for_reboot(void)
+{
+	cpu_set_reserved_ttbr0();
+	flush_tlb_all();
+	cpu_set_idmap_tcr_t0sz();
+	cpu_switch_mm(idmap_pg_dir, &init_mm);
+}
+
+/*
  * Check whether a kernel address is valid (derived from arch/x86/).
  */
 int kern_addr_valid(unsigned long addr)

48 lines not on this page · raw message

152 lines not on this page · raw message

index 99048e5..ccec467 100644
@@ -39,6 +39,7 @@
 #define KEXEC_ARCH_SH      (42 << 16)
 #define KEXEC_ARCH_MIPS_LE (10 << 16)
 #define KEXEC_ARCH_MIPS    ( 8 << 16)
+#define KEXEC_ARCH_ARM64   (183 << 16)
 
 /* The artificial cap on the number of segments passed to kexec_load. */
 #define KEXEC_SEGMENT_MAX 16

index 8b990b8..da28a26 100644
@@ -25,6 +25,48 @@ extern const unsigned long arm64_relocate_new_kernel_size;
 
 static unsigned long kimage_start;
 
+/**
+ * kexec_is_dtb - Helper routine to check the device tree header signature.
+ */
+static bool kexec_is_dtb(const void *dtb)
+{
+	__be32 magic;
+
+	return get_user(magic, (__be32 *)dtb) ? false :
+		(be32_to_cpu(magic) == OF_DT_HEADER);
+}
+
+/**
+ * kexec_image_info - For debugging output.
+ */
+#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
+static void _kexec_image_info(const char *func, int line,
+	const struct kimage *kimage)
+{
+	unsigned long i;
+
+#if !defined(DEBUG)
+	return;
+#endif
+	pr_devel("%s:%d:\n", func, line);
+	pr_devel("  kexec kimage info:\n");
+	pr_devel("    type:        %d\n", kimage->type);
+	pr_devel("    start:       %lx\n", kimage->start);
+	pr_devel("    head:        %lx\n", kimage->head);
+	pr_devel("    nr_segments: %lu\n", kimage->nr_segments);
+
+	for (i = 0; i < kimage->nr_segments; i++) {
+		pr_devel("      segment[%lu]: %016lx - %016lx, %lx bytes, %lu pages%s\n",
+			i,
+			kimage->segment[i].mem,
+			kimage->segment[i].mem + kimage->segment[i].memsz,
+			kimage->segment[i].memsz,
+			kimage->segment[i].memsz /  PAGE_SIZE,
+			(kexec_is_dtb(kimage->segment[i].buf) ?
+				", dtb segment" : ""));
+	}
+}
+
 void machine_kexec_cleanup(struct kimage *kimage)
 {
 	/* Empty routine needed to avoid build errors. */

@@ -38,6 +80,8 @@ void machine_kexec_cleanup(struct kimage *kimage)
 int machine_kexec_prepare(struct kimage *kimage)
 {
 	kimage_start = kimage->start;
+	kexec_image_info(kimage);
+
 	return 0;
 }
 

@@ -107,6 +151,25 @@ void machine_kexec(struct kimage *kimage)
 	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
 
+	kexec_image_info(kimage);
+
+	pr_devel("%s:%d: control_code_page:        %p\n", __func__, __LINE__,
+		kimage->control_code_page);
+	pr_devel("%s:%d: reboot_code_buffer_phys:  %pa\n", __func__, __LINE__,
+		&reboot_code_buffer_phys);
+	pr_devel("%s:%d: reboot_code_buffer:       %p\n", __func__, __LINE__,
+		reboot_code_buffer);
+	pr_devel("%s:%d: relocate_new_kernel:      %p\n", __func__, __LINE__,
+		arm64_relocate_new_kernel);
+	pr_devel("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
+		__func__, __LINE__, arm64_relocate_new_kernel_size,
+		arm64_relocate_new_kernel_size);
+
+	pr_devel("%s:%d: kimage_head:              %lx\n", __func__, __LINE__,
+		kimage->head);
+	pr_devel("%s:%d: kimage_start:             %lx\n", __func__, __LINE__,
+		kimage_start);
+
 	/*
 	 * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
 	 * after the kernel is shut down.

index 2322479..9d085ac 100644
@@ -32,7 +32,6 @@
 #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>

@@ -337,6 +336,12 @@ static void __init request_standard_resources(void)
 		    kernel_data.end <= res->end)
 			request_resource(res, &kernel_data);
 	}
+
+#ifdef CONFIG_KEXEC
+	/* User space tools will find "Crash kernel" region in /proc/iomem. */
+	if (crashk_res.end)
+		insert_resource(&iomem_resource, &crashk_res);
+#endif
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD

72 lines not on this page · raw message

index 46d63cd..555a955 100644
@@ -30,6 +30,8 @@
 
 #if !defined(__ASSEMBLY__)
 
+extern bool in_crash_kexec;
+
 /**
  * crash_setup_regs() - save registers for the panic kernel
  *

@@ -40,7 +42,37 @@
 static inline void crash_setup_regs(struct pt_regs *newregs,
 				    struct pt_regs *oldregs)
 {
-	/* Empty routine needed to avoid build errors. */
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		__asm__ __volatile__ (
+			"stp	 x0,   x1, [%3, #16 *  0]\n"
+			"stp	 x2,   x3, [%3, #16 *  1]\n"
+			"stp	 x4,   x5, [%3, #16 *  2]\n"
+			"stp	 x6,   x7, [%3, #16 *  3]\n"
+			"stp	 x8,   x9, [%3, #16 *  4]\n"
+			"stp	x10,  x11, [%3, #16 *  5]\n"
+			"stp	x12,  x13, [%3, #16 *  6]\n"
+			"stp	x14,  x15, [%3, #16 *  7]\n"
+			"stp	x16,  x17, [%3, #16 *  8]\n"
+			"stp	x18,  x19, [%3, #16 *  9]\n"
+			"stp	x20,  x21, [%3, #16 * 10]\n"
+			"stp	x22,  x23, [%3, #16 * 11]\n"
+			"stp	x24,  x25, [%3, #16 * 12]\n"
+			"stp	x26,  x27, [%3, #16 * 13]\n"
+			"stp	x28,  x29, [%3, #16 * 14]\n"
+			"str	x30,	   [%3, #16 * 15]\n"
+			"mov	%0, sp\n"
+			"adr	%1, 1f\n"
+			"mrs	%2, spsr_el1\n"
+		"1:"
+			: "=r" (newregs->sp),
+			  "=r" (newregs->pc),
+			  "=r" (newregs->pstate)
+			: "r"  (&newregs->regs)
+			: "memory"
+		);
+	}
 }
 
 #endif /* !defined(__ASSEMBLY__) */

index da28a26..d2d7e90 100644
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/of_fdt.h>
 #include <linux/slab.h>

@@ -23,6 +24,7 @@
 extern const unsigned char arm64_relocate_new_kernel[];
 extern const unsigned long arm64_relocate_new_kernel_size;
 
+bool in_crash_kexec;
 static unsigned long kimage_start;
 
 /**

@@ -203,13 +205,38 @@ void machine_kexec(struct kimage *kimage)
 	 */
 
 	cpu_soft_restart(virt_to_phys(cpu_reset),
-		is_hyp_mode_available(),
+		in_crash_kexec ? 0 : is_hyp_mode_available(),
 		reboot_code_buffer_phys, kimage->head, kimage_start);
 
 	BUG(); /* Should never get here. */
 }
 
+/**
+ * machine_crash_shutdown - shutdown non-boot cpus and save registers
+ */
 void machine_crash_shutdown(struct pt_regs *regs)
 {
-	/* Empty routine needed to avoid build errors. */
+	struct pt_regs dummy_regs;
+	int cpu;
+
+	local_irq_disable();
+
+	in_crash_kexec = true;
+
+	/*
+	 * clear and initialize the per-cpu info. This is necessary
+	 * because, otherwise, slots for offline cpus would never be
+	 * filled up. See smp_send_stop().
+	 */
+	memset(&dummy_regs, 0, sizeof(dummy_regs));
+	for_each_possible_cpu(cpu)
+		crash_save_cpu(&dummy_regs, cpu);
+
+	/* shutdown non-boot cpus */
+	smp_send_stop();
+
+	/* for boot cpu */
+	crash_save_cpu(regs, smp_processor_id());
+
+	pr_info("Starting crashdump kernel...\n");
 }

index dbdaacd..88aec66 100644
@@ -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>

@@ -54,6 +55,8 @@
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
+#include "cpu-reset.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 

@@ -679,8 +682,12 @@ static DEFINE_RAW_SPINLOCK(stop_lock);
 /*
  * ipi_cpu_stop - handle IPI from smp_send_stop()
  */
-static void ipi_cpu_stop(unsigned int cpu)
+static void ipi_cpu_stop(unsigned int cpu, struct pt_regs *regs)
 {
+#ifdef CONFIG_KEXEC
+	/* printing messages may slow down the shutdown. */
+	if (!in_crash_kexec)
+#endif
 	if (system_state == SYSTEM_BOOTING ||
 	    system_state == SYSTEM_RUNNING) {
 		raw_spin_lock(&stop_lock);

@@ -693,6 +700,11 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 	local_irq_disable();
 
+#ifdef CONFIG_KEXEC
+	if (in_crash_kexec)
+		crash_save_cpu(regs, cpu);
+#endif /* CONFIG_KEXEC */
+
 	while (1)
 		cpu_relax();
 }

@@ -723,7 +735,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 	case IPI_CPU_STOP:
 		irq_enter();
-		ipi_cpu_stop(cpu);
+		ipi_cpu_stop(cpu, regs);
 		irq_exit();
 		break;
 

71 lines not on this page · raw message

index f33f201..ff8eeb4 100644
@@ -35,6 +35,7 @@
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
 #include <linux/kexec.h>
+#include <linux/crash_dump.h>
 
 #include <asm/fixmap.h>
 #include <asm/memory.h>

@@ -116,6 +117,31 @@ static void __init reserve_crashkernel(void)
 }
 #endif /* CONFIG_KEXEC */
 
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * reserve_elfcorehdr() - reserves memory for elf core header
+ *
+ * This function reserves elf core header given in "elfcorehdr=" kernel
+ * command line parameter. This region contains all the information about
+ * primary kernel's core image and is used by a dump capture kernel to
+ * access the system memory on primary kernel.
+ */
+static void __init reserve_elfcorehdr(void)
+{
+	if (!elfcorehdr_size)
+		return;
+
+	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+		pr_warn("elfcorehdr is overlapped\n");
+		return;
+	}
+
+	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+	pr_info("Reserving %lldKB of memory at %lldMB for elfcorehdr\n",
+		elfcorehdr_size >> 10, elfcorehdr_addr >> 20);
+}
+#endif /* CONFIG_CRASH_DUMP */
 /*
  * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
  * currently assumes that for memory starting above 4G, 32-bit devices will

@@ -223,6 +249,9 @@ void __init arm64_memblock_init(void)
 #ifdef CONFIG_KEXEC
 	reserve_crashkernel();
 #endif
+#ifdef CONFIG_CRASH_DUMP
+	reserve_elfcorehdr();
+#endif
 
 	early_init_fdt_scan_reserved_mem();
 

index d2d7e90..482aae7 100644
@@ -148,7 +148,13 @@ void machine_kexec(struct kimage *kimage)
 	phys_addr_t reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
-	BUG_ON(num_online_cpus() > 1);
+	if (num_online_cpus() > 1) {
+		if (in_crash_kexec)
+			pr_warn("kdump might fail because %d cpus are still online\n",
+					num_online_cpus());
+		else
+			BUG();
+	}
 
 	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);