powerpc/crash: add crash memory hotplug support

Extend the arch crash hotplug handler, as introduced by the patch title
("powerpc: add crash CPU hotplug support"), to also support memory
add/remove events.

Elfcorehdr describes the memory of the crash kernel to capture the
kernel; hence, it needs to be updated if memory resources change due to
memory add/remove events. Therefore, arch_crash_handle_hotplug_event()
is updated to recreate the elfcorehdr and replace it with the previous
one on memory add/remove events.

The memblock list is used to prepare the elfcorehdr. In the case of
memory hot remove, the memblock list is updated after the arch crash
hotplug handler is triggered, as depicted in Figure 1. Thus, the
hot-removed memory is explicitly removed from the crash memory ranges
to ensure that the memory ranges added to elfcorehdr do not include the
hot-removed memory.

    Memory remove
          |
          v
    Offline pages
          |
          v
 Initiate memory notify call <----> crash hotplug handler
 chain for MEM_OFFLINE event
          |
          v
 Update memblock list

 	Figure 1

There are two system calls, `kexec_file_load` and `kexec_load`, used to
load the kdump image. A few changes have been made to ensure that the
kernel can safely update the elfcorehdr component of the kdump image for
both system calls.

For the kexec_file_load syscall, kdump image is prepared in the kernel.
To support an increasing number of memory regions, the elfcorehdr is
built with extra buffer space to ensure that it can accommodate
additional memory ranges in future.

For the kexec_load syscall, the elfcorehdr is updated only if the
KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag is passed to the kernel by the
kexec tool. Passing this flag to the kernel indicates that the
elfcorehdr is built to accommodate additional memory ranges and the
elfcorehdr segment is not considered for SHA calculation, making it safe
to update.

The changes related to this feature are kept under the CRASH_HOTPLUG
config, and it is enabled by default.

Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240326055413.186534-7-sourabhjain@linux.ibm.com

1 files changed, 94 insertions, 1 deletions

diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index 8938a19af12f..21b193e938a3 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -17,6 +17,7 @@
 #include <linux/irq.h>
 #include <linux/types.h>
 #include <linux/libfdt.h>
+#include <linux/memory.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
@@ -25,6 +26,7 @@
 #include <asm/setjmp.h>
 #include <asm/debug.h>
 #include <asm/interrupt.h>
+#include <asm/kexec_ranges.h>
 
 /*
  * The primary CPU waits a while for all secondary CPUs to enter. This is to
@@ -398,6 +400,94 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 #undef pr_fmt
 #define pr_fmt(fmt) "crash hp: " fmt
 
+/*
+ * Advertise preferred elfcorehdr size to userspace via
+ * /sys/kernel/crash_elfcorehdr_size sysfs interface.
+ */
+unsigned int arch_crash_get_elfcorehdr_size(void)
+{
+	unsigned long phdr_cnt;
+
+	/* A program header for possible CPUs + vmcoreinfo */
+	phdr_cnt = num_possible_cpus() + 1;
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES;
+
+	return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr));
+}
+
+/**
+ * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old
+ *			       elfcorehdr in the kexec segment array.
+ * @image: the active struct kimage
+ * @mn: struct memory_notify data handler
+ */
+static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn)
+{
+	int ret;
+	struct crash_mem *cmem = NULL;
+	struct kexec_segment *ksegment;
+	void *ptr, *mem, *elfbuf = NULL;
+	unsigned long elfsz, memsz, base_addr, size;
+
+	ksegment = &image->segment[image->elfcorehdr_index];
+	mem = (void *) ksegment->mem;
+	memsz = ksegment->memsz;
+
+	ret = get_crash_memory_ranges(&cmem);
+	if (ret) {
+		pr_err("Failed to get crash mem range\n");
+		return;
+	}
+
+	/*
+	 * The hot unplugged memory is part of crash memory ranges,
+	 * remove it here.
+	 */
+	if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) {
+		base_addr = PFN_PHYS(mn->start_pfn);
+		size = mn->nr_pages * PAGE_SIZE;
+		ret = remove_mem_range(&cmem, base_addr, size);
+		if (ret) {
+			pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n");
+			goto out;
+		}
+	}
+
+	ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz);
+	if (ret) {
+		pr_err("Failed to prepare elf header\n");
+		goto out;
+	}
+
+	/*
+	 * It is unlikely that kernel hit this because elfcorehdr kexec
+	 * segment (memsz) is built with addition space to accommodate growing
+	 * number of crash memory ranges while loading the kdump kernel. It is
+	 * Just to avoid any unforeseen case.
+	 */
+	if (elfsz > memsz) {
+		pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz);
+		goto out;
+	}
+
+	ptr = __va(mem);
+	if (ptr) {
+		/* Temporarily invalidate the crash image while it is replaced */
+		xchg(&kexec_crash_image, NULL);
+
+		/* Replace the old elfcorehdr with newly prepared elfcorehdr */
+		memcpy((void *)ptr, elfbuf, elfsz);
+
+		/* The crash image is now valid once again */
+		xchg(&kexec_crash_image, image);
+	}
+out:
+	kvfree(cmem);
+	if (elfbuf)
+		kvfree(elfbuf);
+}
+
 /**
  * get_fdt_index - Loop through the kexec segment array and find
  *		   the index of the FDT segment.
@@ -478,6 +568,8 @@ int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
  */
 void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
 {
+	struct memory_notify *mn;
+
 	switch (image->hp_action) {
 	case KEXEC_CRASH_HP_REMOVE_CPU:
 		return;
@@ -488,7 +580,8 @@ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
 
 	case KEXEC_CRASH_HP_REMOVE_MEMORY:
 	case KEXEC_CRASH_HP_ADD_MEMORY:
-		pr_info_once("Crash update is not supported for memory hotplug\n");
+		mn = (struct memory_notify *)arg;
+		update_crash_elfcorehdr(image, mn);
 		return;
 	default:
 		pr_warn_once("Unknown hotplug action\n");