powerpc/kexec_file: Setup backup region for kdump kernel

Though kdump kernel boots from loaded address, the first 64KB of it is
copied down to real 0. So, setup a backup region and let purgatory
copy the first 64KB of crashed kernel into this backup region before
booting into kdump kernel. Update reserve map with backup region and
crashed kernel's memory to avoid kdump kernel from accidentially using
that memory.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/159602294718.575379.16216507537038008623.stgit@hbathini

5 files changed, 159 insertions, 7 deletions

diff --git a/arch/powerpc/include/asm/crashdump-ppc64.h b/arch/powerpc/include/asm/crashdump-ppc64.h
new file mode 100644
index 000000000000..68d9717cc5ee
--- /dev/null
+++ b/arch/powerpc/include/asm/crashdump-ppc64.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_POWERPC_CRASHDUMP_PPC64_H
+#define _ASM_POWERPC_CRASHDUMP_PPC64_H
+
+/*
+ * Backup region - first 64KB of System RAM
+ *
+ * If ever the below macros are to be changed, please be judicious.
+ * The implicit assumptions are:
+ *     - start, end & size are less than UINT32_MAX.
+ *     - start & size are at least 8 byte aligned.
+ *
+ * For implementation details: arch/powerpc/purgatory/trampoline_64.S
+ */
+#define BACKUP_SRC_START	0
+#define BACKUP_SRC_END		0xffff
+#define BACKUP_SRC_SIZE		(BACKUP_SRC_END - BACKUP_SRC_START + 1)
+
+#endif /* __ASM_POWERPC_CRASHDUMP_PPC64_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 639f31e13593..807bb58ed8fa 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -105,6 +105,9 @@ extern const struct kexec_file_ops kexec_elf64_ops;
 struct kimage_arch {
 	struct crash_mem *exclude_ranges;
 
+	unsigned long backup_start;
+	void *backup_buf;
+
 #ifdef CONFIG_IMA_KEXEC
 	phys_addr_t ima_buffer_addr;
 	size_t ima_buffer_size;
@@ -120,6 +123,10 @@ int setup_new_fdt(const struct kimage *image, void *fdt,
 int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size);
 
 #ifdef CONFIG_PPC64
+struct kexec_buf;
+
+int load_crashdump_segments_ppc64(struct kimage *image,
+				  struct kexec_buf *kbuf);
 int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
 			  const void *fdt, unsigned long kernel_load_addr,
 			  unsigned long fdt_load_addr);
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index 64c15a5a280b..76e2fc7e6dc3 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -68,6 +68,15 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 
 	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
+	/* Load additional segments needed for panic kernel */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = load_crashdump_segments_ppc64(image, &kbuf);
+		if (ret) {
+			pr_err("Failed to load kdump kernel segments\n");
+			goto out;
+		}
+	}
+
 	if (initrd != NULL) {
 		kbuf.buffer = initrd;
 		kbuf.bufsz = kbuf.memsz = initrd_len;
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index f94660874765..a81bffb72cc5 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -20,8 +20,10 @@
 #include <linux/of_device.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/drmem.h>
 #include <asm/kexec_ranges.h>
+#include <asm/crashdump-ppc64.h>
 
 struct umem_info {
 	u64 *buf;		/* data buffer for usable-memory property */
@@ -606,6 +608,70 @@ out:
 }
 
 /**
+ * load_backup_segment - Locate a memory hole to place the backup region.
+ * @image:               Kexec image.
+ * @kbuf:                Buffer contents and memory parameters.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf)
+{
+	void *buf;
+	int ret;
+
+	/*
+	 * Setup a source buffer for backup segment.
+	 *
+	 * A source buffer has no meaning for backup region as data will
+	 * be copied from backup source, after crash, in the purgatory.
+	 * But as load segment code doesn't recognize such segments,
+	 * setup a dummy source buffer to keep it happy for now.
+	 */
+	buf = vzalloc(BACKUP_SRC_SIZE);
+	if (!buf)
+		return -ENOMEM;
+
+	kbuf->buffer = buf;
+	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
+	kbuf->bufsz = kbuf->memsz = BACKUP_SRC_SIZE;
+	kbuf->top_down = false;
+
+	ret = kexec_add_buffer(kbuf);
+	if (ret) {
+		vfree(buf);
+		return ret;
+	}
+
+	image->arch.backup_buf = buf;
+	image->arch.backup_start = kbuf->mem;
+	return 0;
+}
+
+/**
+ * load_crashdump_segments_ppc64 - Initialize the additional segements needed
+ *                                 to load kdump kernel.
+ * @image:                         Kexec image.
+ * @kbuf:                          Buffer contents and memory parameters.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int load_crashdump_segments_ppc64(struct kimage *image,
+				  struct kexec_buf *kbuf)
+{
+	int ret;
+
+	/* Load backup segment - first 64K bytes of the crashing kernel */
+	ret = load_backup_segment(image, kbuf);
+	if (ret) {
+		pr_err("Failed to load backup segment\n");
+		return ret;
+	}
+	pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem);
+
+	return 0;
+}
+
+/**
  * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
  *                         variables and call setup_purgatory() to initialize
  *                         common global variable.
@@ -643,6 +709,11 @@ int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
 			goto out;
 	}
 
+	/* Tell purgatory where to look for backup region */
+	ret = kexec_purgatory_get_set_symbol(image, "backup_start",
+					     &image->arch.backup_start,
+					     sizeof(image->arch.backup_start),
+					     false);
 out:
 	if (ret)
 		pr_err("Failed to setup purgatory symbols");
@@ -674,7 +745,7 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 
 	/*
 	 * Restrict memory usage for kdump kernel by setting up
-	 * usable memory ranges.
+	 * usable memory ranges and memory reserve map.
 	 */
 	if (image->type == KEXEC_TYPE_CRASH) {
 		ret = get_usable_memory_ranges(&umem);
@@ -687,13 +758,26 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 			goto out;
 		}
 
-		/* Ensure we don't touch crashed kernel's memory */
-		ret = fdt_add_mem_rsv(fdt, 0, crashk_res.start);
+		/*
+		 * Ensure we don't touch crashed kernel's memory except the
+		 * first 64K of RAM, which will be backed up.
+		 */
+		ret = fdt_add_mem_rsv(fdt, BACKUP_SRC_END + 1,
+				      crashk_res.start - BACKUP_SRC_SIZE);
 		if (ret) {
 			pr_err("Error reserving crash memory: %s\n",
 			       fdt_strerror(ret));
 			goto out;
 		}
+
+		/* Ensure backup region is not used by kdump/capture kernel */
+		ret = fdt_add_mem_rsv(fdt, image->arch.backup_start,
+				      BACKUP_SRC_SIZE);
+		if (ret) {
+			pr_err("Error reserving memory for backup: %s\n",
+			       fdt_strerror(ret));
+			goto out;
+		}
 	}
 
 out:
@@ -800,5 +884,8 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
 	kfree(image->arch.exclude_ranges);
 	image->arch.exclude_ranges = NULL;
 
+	vfree(image->arch.backup_buf);
+	image->arch.backup_buf = NULL;
+
 	return kexec_image_post_load_cleanup_default(image);
 }
diff --git a/arch/powerpc/purgatory/trampoline_64.S b/arch/powerpc/purgatory/trampoline_64.S
index a5a83c3f53e6..b567da56dde1 100644
--- a/arch/powerpc/purgatory/trampoline_64.S
+++ b/arch/powerpc/purgatory/trampoline_64.S
@@ -10,6 +10,7 @@
  */
 
 #include <asm/asm-compat.h>
+#include <asm/crashdump-ppc64.h>
 
 	.machine ppc64
 	.balign 256
@@ -43,14 +44,39 @@ master:
 	mr	%r17,%r3	/* save cpu id to r17 */
 	mr	%r15,%r4	/* save physical address in reg15 */
 
+	/* Work out where we're running */
+	bcl	20, 31, 0f
+0:	mflr	%r18
+
+	/*
+	 * Copy BACKUP_SRC_SIZE bytes from BACKUP_SRC_START to
+	 * backup_start 8 bytes at a time.
+	 *
+	 * Use r3 = dest, r4 = src, r5 = size, r6 = count
+	 */
+	ld	%r3, (backup_start - 0b)(%r18)
+	cmpdi	%cr0, %r3, 0
+	beq	.Lskip_copy	/* skip if there is no backup region */
+	lis	%r5, BACKUP_SRC_SIZE@h
+	ori	%r5, %r5, BACKUP_SRC_SIZE@l
+	cmpdi	%cr0, %r5, 0
+	beq	.Lskip_copy	/* skip if copy size is zero */
+	lis	%r4, BACKUP_SRC_START@h
+	ori	%r4, %r4, BACKUP_SRC_START@l
+	li	%r6, 0
+.Lcopy_loop:
+	ldx	%r0, %r6, %r4
+	stdx	%r0, %r6, %r3
+	addi	%r6, %r6, 8
+	cmpld	%cr0, %r6, %r5
+	blt	.Lcopy_loop
+
+.Lskip_copy:
 	or	%r3,%r3,%r3	/* ok now to high priority, lets boot */
 	lis	%r6,0x1
 	mtctr	%r6		/* delay a bit for slaves to catch up */
 	bdnz	.		/* before we overwrite 0-100 again */
 
-	bl	0f		/* Work out where we're running */
-0:	mflr	%r18
-
 	/* load device-tree address */
 	ld	%r3, (dt_offset - 0b)(%r18)
 	mr	%r16,%r3	/* save dt address in reg16 */
@@ -89,7 +115,6 @@ master:
 
 	rfid			/* update MSR and start kernel */
 
-
 	.balign 8
 	.globl kernel
 kernel:
@@ -102,6 +127,11 @@ dt_offset:
 	.8byte  0x0
 	.size dt_offset, . - dt_offset
 
+	.balign 8
+	.globl backup_start
+backup_start:
+	.8byte  0x0
+	.size backup_start, . - backup_start
 
 	.data
 	.balign 8