Unverified Commit e53d2818 authored by Nick Kossifidis's avatar Nick Kossifidis Committed by Palmer Dabbelt
Browse files

RISC-V: Add kdump support



This patch adds support for kdump, the kernel will reserve a
region for the crash kernel and jump there on panic. In order
for userspace tools (kexec-tools) to prepare the crash kernel
kexec image, we also need to expose some information on
/proc/iomem for the memory regions used by the kernel and for
the region reserved for crash kernel. Note that on userspace
the device tree is used to determine the system's memory
layout so the "System RAM" on /proc/iomem is ignored.

I tested this on riscv64 qemu and works as expected, you may
test it by triggering a crash through /proc/sysrq_trigger:

echo c > /proc/sysrq_trigger

Signed-off-by: default avatarNick Kossifidis <mick@ics.forth.gr>
Signed-off-by: default avatarPalmer Dabbelt <palmerdabbelt@google.com>
parent ffe0e526
......@@ -81,4 +81,10 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
#endif /* CONFIG_MMU */
#define ELF_CORE_COPY_REGS(dest, regs) \
do { \
*(struct user_regs_struct *)&(dest) = \
*(struct user_regs_struct *)regs; \
} while (0);
#endif /* _ASM_RISCV_ELF_H */
......@@ -23,11 +23,16 @@
#define KEXEC_ARCH KEXEC_ARCH_RISCV
extern void riscv_crash_save_regs(struct pt_regs *newregs);
static inline void
crash_setup_regs(struct pt_regs *newregs,
struct pt_regs *oldregs)
{
/* Dummy implementation for now */
if (oldregs)
memcpy(newregs, oldregs, sizeof(struct pt_regs));
else
riscv_crash_save_regs(newregs);
}
......@@ -40,10 +45,12 @@ struct kimage_arch {
const extern unsigned char riscv_kexec_relocate[];
const extern unsigned int riscv_kexec_relocate_size;
typedef void (*riscv_kexec_do_relocate)(unsigned long first_ind_entry,
unsigned long jump_addr,
unsigned long fdt_addr,
unsigned long hartid,
unsigned long va_pa_off);
typedef void (*riscv_kexec_method)(unsigned long first_ind_entry,
unsigned long jump_addr,
unsigned long fdt_addr,
unsigned long hartid,
unsigned long va_pa_off);
extern riscv_kexec_method riscv_kexec_norelocate;
#endif
......@@ -58,7 +58,7 @@ obj-$(CONFIG_SMP) += cpu_ops_sbi.o
endif
obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_KEXEC) += kexec_relocate.o machine_kexec.o
obj-$(CONFIG_KEXEC) += kexec_relocate.o crash_save_regs.o machine_kexec.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
......
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020 FORTH-ICS/CARV
* Nick Kossifidis <mick@ics.forth.gr>
*/
#include <asm/asm.h> /* For RISCV_* and REG_* macros */
#include <asm/csr.h> /* For CSR_* macros */
#include <asm/asm-offsets.h> /* For offsets on pt_regs */
#include <linux/linkage.h> /* For SYM_* macros */
.section ".text"
SYM_CODE_START(riscv_crash_save_regs)
REG_S ra, PT_RA(a0) /* x1 */
REG_S sp, PT_SP(a0) /* x2 */
REG_S gp, PT_GP(a0) /* x3 */
REG_S tp, PT_TP(a0) /* x4 */
REG_S t0, PT_T0(a0) /* x5 */
REG_S t1, PT_T1(a0) /* x6 */
REG_S t2, PT_T2(a0) /* x7 */
REG_S s0, PT_S0(a0) /* x8/fp */
REG_S s1, PT_S1(a0) /* x9 */
REG_S a0, PT_A0(a0) /* x10 */
REG_S a1, PT_A1(a0) /* x11 */
REG_S a2, PT_A2(a0) /* x12 */
REG_S a3, PT_A3(a0) /* x13 */
REG_S a4, PT_A4(a0) /* x14 */
REG_S a5, PT_A5(a0) /* x15 */
REG_S a6, PT_A6(a0) /* x16 */
REG_S a7, PT_A7(a0) /* x17 */
REG_S s2, PT_S2(a0) /* x18 */
REG_S s3, PT_S3(a0) /* x19 */
REG_S s4, PT_S4(a0) /* x20 */
REG_S s5, PT_S5(a0) /* x21 */
REG_S s6, PT_S6(a0) /* x22 */
REG_S s7, PT_S7(a0) /* x23 */
REG_S s8, PT_S8(a0) /* x24 */
REG_S s9, PT_S9(a0) /* x25 */
REG_S s10, PT_S10(a0) /* x26 */
REG_S s11, PT_S11(a0) /* x27 */
REG_S t3, PT_T3(a0) /* x28 */
REG_S t4, PT_T4(a0) /* x29 */
REG_S t5, PT_T5(a0) /* x30 */
REG_S t6, PT_T6(a0) /* x31 */
csrr t1, CSR_STATUS
csrr t2, CSR_EPC
csrr t3, CSR_TVAL
csrr t4, CSR_CAUSE
REG_S t1, PT_STATUS(a0)
REG_S t2, PT_EPC(a0)
REG_S t3, PT_BADADDR(a0)
REG_S t4, PT_CAUSE(a0)
ret
SYM_CODE_END(riscv_crash_save_regs)
......@@ -151,7 +151,73 @@ SYM_CODE_START(riscv_kexec_relocate)
SYM_CODE_END(riscv_kexec_relocate)
riscv_kexec_relocate_end:
.section ".rodata"
/* Used for jumping to crashkernel */
.section ".text"
SYM_CODE_START(riscv_kexec_norelocate)
/*
* s0: (const) Phys address to jump to
* s1: (const) Phys address of the FDT image
* s2: (const) The hartid of the current hart
* s3: (const) va_pa_offset, used when switching MMU off
*/
mv s0, a1
mv s1, a2
mv s2, a3
mv s3, a4
/* Disable / cleanup interrupts */
csrw CSR_SIE, zero
csrw CSR_SIP, zero
/* Switch to physical addressing */
la s4, 1f
sub s4, s4, s3
csrw CSR_STVEC, s4
csrw CSR_SATP, zero
.align 2
1:
/* Pass the arguments to the next kernel / Cleanup*/
mv a0, s2
mv a1, s1
mv a2, s0
/* Cleanup */
mv a3, zero
mv a4, zero
mv a5, zero
mv a6, zero
mv a7, zero
mv s0, zero
mv s1, zero
mv s2, zero
mv s3, zero
mv s4, zero
mv s5, zero
mv s6, zero
mv s7, zero
mv s8, zero
mv s9, zero
mv s10, zero
mv s11, zero
mv t0, zero
mv t1, zero
mv t2, zero
mv t3, zero
mv t4, zero
mv t5, zero
mv t6, zero
csrw CSR_SEPC, zero
csrw CSR_SCAUSE, zero
csrw CSR_SSCRATCH, zero
jalr zero, a2, 0
SYM_CODE_END(riscv_kexec_norelocate)
.section ".rodata"
SYM_DATA(riscv_kexec_relocate_size,
.long riscv_kexec_relocate_end - riscv_kexec_relocate)
......@@ -59,11 +59,6 @@ machine_kexec_prepare(struct kimage *image)
kexec_image_info(image);
if (image->type == KEXEC_TYPE_CRASH) {
pr_warn("Loading a crash kernel is unsupported for now.\n");
return -EINVAL;
}
/* Find the Flattened Device Tree and save its physical address */
for (i = 0; i < image->nr_segments; i++) {
if (image->segment[i].memsz <= sizeof(fdt))
......@@ -85,17 +80,21 @@ machine_kexec_prepare(struct kimage *image)
}
/* Copy the assembler code for relocation to the control page */
control_code_buffer = page_address(image->control_code_page);
control_code_buffer_sz = page_size(image->control_code_page);
if (unlikely(riscv_kexec_relocate_size > control_code_buffer_sz)) {
pr_err("Relocation code doesn't fit within a control page\n");
return -EINVAL;
}
memcpy(control_code_buffer, riscv_kexec_relocate,
riscv_kexec_relocate_size);
if (image->type != KEXEC_TYPE_CRASH) {
control_code_buffer = page_address(image->control_code_page);
control_code_buffer_sz = page_size(image->control_code_page);
/* Mark the control page executable */
set_memory_x((unsigned long) control_code_buffer, 1);
if (unlikely(riscv_kexec_relocate_size > control_code_buffer_sz)) {
pr_err("Relocation code doesn't fit within a control page\n");
return -EINVAL;
}
memcpy(control_code_buffer, riscv_kexec_relocate,
riscv_kexec_relocate_size);
/* Mark the control page executable */
set_memory_x((unsigned long) control_code_buffer, 1);
}
return 0;
}
......@@ -147,6 +146,9 @@ void machine_shutdown(void)
void
machine_crash_shutdown(struct pt_regs *regs)
{
crash_save_cpu(regs, smp_processor_id());
machine_shutdown();
pr_info("Starting crashdump kernel...\n");
}
/**
......@@ -169,7 +171,12 @@ machine_kexec(struct kimage *image)
unsigned long this_hart_id = raw_smp_processor_id();
unsigned long fdt_addr = internal->fdt_addr;
void *control_code_buffer = page_address(image->control_code_page);
riscv_kexec_do_relocate do_relocate = control_code_buffer;
riscv_kexec_method kexec_method = NULL;
if (image->type != KEXEC_TYPE_CRASH)
kexec_method = control_code_buffer;
else
kexec_method = (riscv_kexec_method) &riscv_kexec_norelocate;
pr_notice("Will call new kernel at %08lx from hart id %lx\n",
jump_addr, this_hart_id);
......@@ -180,7 +187,7 @@ machine_kexec(struct kimage *image)
/* Jump to the relocation code */
pr_notice("Bye...\n");
do_relocate(first_ind_entry, jump_addr, fdt_addr,
this_hart_id, va_pa_offset);
kexec_method(first_ind_entry, jump_addr, fdt_addr,
this_hart_id, va_pa_offset);
unreachable();
}
......@@ -20,6 +20,7 @@
#include <linux/swiotlb.h>
#include <linux/smp.h>
#include <linux/efi.h>
#include <linux/crash_dump.h>
#include <asm/cpu_ops.h>
#include <asm/early_ioremap.h>
......@@ -160,6 +161,14 @@ static void __init init_resources(void)
if (ret < 0)
goto error;
#ifdef CONFIG_KEXEC_CORE
if (crashk_res.start != crashk_res.end) {
ret = add_resource(&iomem_resource, &crashk_res);
if (ret < 0)
goto error;
}
#endif
for_each_reserved_mem_region(region) {
res = &mem_res[res_idx--];
......@@ -252,7 +261,6 @@ void __init setup_arch(char **cmdline_p)
efi_init();
setup_bootmem();
paging_init();
init_resources();
#if IS_ENABLED(CONFIG_BUILTIN_DTB)
unflatten_and_copy_device_tree();
#else
......@@ -263,6 +271,7 @@ void __init setup_arch(char **cmdline_p)
#endif
misc_mem_init();
init_resources();
sbi_init();
if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
......
......@@ -2,6 +2,8 @@
/*
* Copyright (C) 2012 Regents of the University of California
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
* Copyright (C) 2020 FORTH-ICS/CARV
* Nick Kossifidis <mick@ics.forth.gr>
*/
#include <linux/init.h>
......@@ -14,6 +16,7 @@
#include <linux/libfdt.h>
#include <linux/set_memory.h>
#include <linux/dma-map-ops.h>
#include <linux/crash_dump.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
......@@ -658,6 +661,71 @@ void mark_rodata_ro(void)
}
#endif
#ifdef CONFIG_KEXEC_CORE
/*
* reserve_crashkernel() - reserves memory for crash kernel
*
* This function reserves memory area given in "crashkernel=" kernel command
* line parameter. The memory reserved is used by dump capture kernel when
* primary kernel is crashing.
*/
static void __init reserve_crashkernel(void)
{
unsigned long long crash_base = 0;
unsigned long long crash_size = 0;
unsigned long search_start = memblock_start_of_DRAM();
unsigned long search_end = memblock_end_of_DRAM();
int ret = 0;
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base);
if (ret || !crash_size)
return;
crash_size = PAGE_ALIGN(crash_size);
if (crash_base == 0) {
/*
* Current riscv boot protocol requires 2MB alignment for
* RV64 and 4MB alignment for RV32 (hugepage size)
*/
crash_base = memblock_find_in_range(search_start, search_end,
crash_size, PMD_SIZE);
if (crash_base == 0) {
pr_warn("crashkernel: couldn't allocate %lldKB\n",
crash_size >> 10);
return;
}
} else {
/* User specifies base address explicitly. */
if (!memblock_is_region_memory(crash_base, crash_size)) {
pr_warn("crashkernel: requested region is not memory\n");
return;
}
if (memblock_is_region_reserved(crash_base, crash_size)) {
pr_warn("crashkernel: requested region is reserved\n");
return;
}
if (!IS_ALIGNED(crash_base, PMD_SIZE)) {
pr_warn("crashkernel: requested region is misaligned\n");
return;
}
}
memblock_reserve(crash_base, crash_size);
pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
crash_base, crash_base + crash_size, crash_size >> 20);
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
}
#endif /* CONFIG_KEXEC_CORE */
void __init paging_init(void)
{
setup_vm_final();
......@@ -670,6 +738,9 @@ void __init misc_mem_init(void)
arch_numa_init();
sparse_init();
zone_sizes_init();
#ifdef CONFIG_KEXEC_CORE
reserve_crashkernel();
#endif
memblock_dump_all();
}
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment