RISC-V: Add kexec/kdump support

index 05669c87a..778dc191c 100644
@@ -42,6 +42,7 @@
 #define KEXEC_ARCH_MIPS_LE (10 << 16)
 #define KEXEC_ARCH_MIPS    ( 8 << 16)
 #define KEXEC_ARCH_AARCH64 (183 << 16)
+#define KEXEC_ARCH_RISCV   (243 << 16)
 
 /* The artificial cap on the number of segments passed to kexec_load. */
 #define KEXEC_SEGMENT_MAX 16

49 lines not on this page · raw message

186 lines not on this page · raw message

index f8f15332c..030554bab 100644
@@ -60,6 +60,7 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices);
  * also add "System RAM" regions for compatibility with other
  * archs, and the rest of the known regions for completeness.
  */
+static struct resource kimage_res = { .name = "Kernel image", };
 static struct resource code_res = { .name = "Kernel code", };
 static struct resource data_res = { .name = "Kernel data", };
 static struct resource rodata_res = { .name = "Kernel rodata", };

@@ -80,45 +81,54 @@ static int __init add_resource(struct resource *parent,
 	return 1;
 }
 
-static int __init add_kernel_resources(struct resource *res)
+static int __init add_kernel_resources(void)
 {
 	int ret = 0;
 
 	/*
 	 * The memory region of the kernel image is continuous and
-	 * was reserved on setup_bootmem, find it here and register
-	 * it as a resource, then register the various segments of
-	 * the image as child nodes
+	 * was reserved on setup_bootmem, register it here as a
+	 * resource, with the various segments of the image as
+	 * child nodes.
 	 */
-	if (!(res->start <= code_res.start && res->end >= data_res.end))
-		return 0;
 
-	res->name = "Kernel image";
-	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	code_res.start = __pa_symbol(_text);
+	code_res.end = __pa_symbol(_etext) - 1;
+	code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	/*
-	 * We removed a part of this region on setup_bootmem so
-	 * we need to expand the resource for the bss to fit in.
-	 */
-	res->end = bss_res.end;
+	rodata_res.start = __pa_symbol(__start_rodata);
+	rodata_res.end = __pa_symbol(__end_rodata) - 1;
+	rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	data_res.start = __pa_symbol(_data);
+	data_res.end = __pa_symbol(_edata) - 1;
+	data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	bss_res.start = __pa_symbol(__bss_start);
+	bss_res.end = __pa_symbol(__bss_stop) - 1;
+	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	kimage_res.start = code_res.start;
+	kimage_res.end = bss_res.end;
+	kimage_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	ret = add_resource(&iomem_resource, res);
+	ret = add_resource(&iomem_resource, &kimage_res);
 	if (ret < 0)
 		return ret;
 
-	ret = add_resource(res, &code_res);
+	ret = add_resource(&kimage_res, &code_res);
 	if (ret < 0)
 		return ret;
 
-	ret = add_resource(res, &rodata_res);
+	ret = add_resource(&kimage_res, &rodata_res);
 	if (ret < 0)
 		return ret;
 
-	ret = add_resource(res, &data_res);
+	ret = add_resource(&kimage_res, &data_res);
 	if (ret < 0)
 		return ret;
 
-	ret = add_resource(res, &bss_res);
+	ret = add_resource(&kimage_res, &bss_res);
 
 	return ret;
 }

@@ -129,54 +139,42 @@ static void __init init_resources(void)
 	struct resource *res = NULL;
 	struct resource *mem_res = NULL;
 	size_t mem_res_sz = 0;
-	int ret = 0, i = 0;
-
-	code_res.start = __pa_symbol(_text);
-	code_res.end = __pa_symbol(_etext) - 1;
-	code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-
-	rodata_res.start = __pa_symbol(__start_rodata);
-	rodata_res.end = __pa_symbol(__end_rodata) - 1;
-	rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-
-	data_res.start = __pa_symbol(_data);
-	data_res.end = __pa_symbol(_edata) - 1;
-	data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-
-	bss_res.start = __pa_symbol(__bss_start);
-	bss_res.end = __pa_symbol(__bss_stop) - 1;
-	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	int num_resources = 0, res_idx = 0;
+	int ret = 0;
 
 	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
-	mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt + 1) * sizeof(*mem_res);
+	num_resources = memblock.memory.cnt + memblock.reserved.cnt + 1;
+	res_idx = num_resources - 1;
+
+	mem_res_sz = num_resources * sizeof(*mem_res);
 	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
 	if (!mem_res)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
+
 	/*
 	 * Start by adding the reserved regions, if they overlap
 	 * with /memory regions, insert_resource later on will take
 	 * care of it.
 	 */
+	ret = add_kernel_resources();
+	if (ret < 0)
+		goto error;
+
 	for_each_reserved_mem_region(region) {
-		res = &mem_res[i++];
+		res = &mem_res[res_idx--];
 
 		res->name = "Reserved";
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
 
-		ret = add_kernel_resources(res);
-		if (ret < 0)
-			goto error;
-		else if (ret)
-			continue;
-
 		/*
 		 * Ignore any other reserved regions within
 		 * system memory.
 		 */
 		if (memblock_is_memory(res->start)) {
-			memblock_free((phys_addr_t) res, sizeof(struct resource));
+			/* Re-use this pre-allocated resource */
+			res_idx++;
 			continue;
 		}
 

@@ -187,7 +185,7 @@ static void __init init_resources(void)
 
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
-		res = &mem_res[i++];
+		res = &mem_res[res_idx--];
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";

@@ -205,6 +203,9 @@ static void __init init_resources(void)
 			goto error;
 	}
 
+	/* Clean-up any unused pre-allocated resources */
+	mem_res_sz = (num_resources - res_idx + 1) * sizeof(*mem_res);
+	memblock_free((phys_addr_t) mem_res, mem_res_sz);
 	return;
 
  error:

index 5c725e1df..f4b490cd0 100644
@@ -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 */

index 86e6e4922..1e9541019 100644
@@ -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

73 lines not on this page · raw message

index 030554bab..31866dce9 100644
@@ -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))

95 lines not on this page · raw message

46 lines not on this page · raw message

index 31866dce9..ff398a3d8 100644
@@ -66,6 +66,9 @@ static struct resource code_res = { .name = "Kernel code", };
 static struct resource data_res = { .name = "Kernel data", };
 static struct resource rodata_res = { .name = "Kernel rodata", };
 static struct resource bss_res = { .name = "Kernel bss", };
+#ifdef CONFIG_CRASH_DUMP
+static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
+#endif
 
 static int __init add_resource(struct resource *parent,
 				struct resource *res)

@@ -169,6 +172,15 @@ static void __init init_resources(void)
 	}
 #endif
 
+#ifdef CONFIG_CRASH_DUMP
+	if (elfcorehdr_size > 0) {
+		elfcorehdr_res.start = elfcorehdr_addr;
+		elfcorehdr_res.end = elfcorehdr_addr + elfcorehdr_size - 1;
+		elfcorehdr_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+		add_resource(&iomem_resource, &elfcorehdr_res);
+	}
+#endif
+
 	for_each_reserved_mem_region(region) {
 		res = &mem_res[res_idx--];
 

index 8b2b85a57..9c048fccb 100644
@@ -13,6 +13,7 @@
 #include <linux/swap.h>
 #include <linux/sizes.h>
 #include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/libfdt.h>
 #include <linux/set_memory.h>
 #include <linux/dma-map-ops.h>

@@ -605,6 +606,18 @@ static void __init reserve_crashkernel(void)
 
 	int ret = 0;
 
+	/*
+	 * Don't reserve a region for a crash kernel on a crash kernel
+	 * since it doesn't make much sense and we have limited memory
+	 * resources.
+	 */
+#ifdef CONFIG_CRASH_DUMP
+	if (is_kdump_kernel()) {
+		pr_info("crashkernel: ignoring reservation request\n");
+		return;
+	}
+#endif
+
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
 	if (ret || !crash_size)

@@ -653,6 +666,26 @@ static void __init reserve_crashkernel(void)
 }
 #endif /* CONFIG_KEXEC_CORE */
 
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * We keep track of the ELF core header of the crashed
+ * kernel with a reserved-memory region with compatible
+ * string "linux,elfcorehdr". Here we register a callback
+ * to populate elfcorehdr_addr/size when this region is
+ * present. Note that this region will be marked as
+ * reserved once we call early_init_fdt_scan_reserved_mem()
+ * later on.
+ */
+static int elfcore_hdr_setup(struct reserved_mem *rmem)
+{
+	elfcorehdr_addr = rmem->base;
+	elfcorehdr_size = rmem->size;
+	return 0;
+}
+
+RESERVEDMEM_OF_DECLARE(elfcorehdr, "linux,elfcorehdr", elfcore_hdr_setup);
+#endif
+
 void __init paging_init(void)
 {
 	setup_vm_final();