[PATCH v7 6/8] powerpc/crash: add crash CPU hotplug support

Sourabh Jain sourabhjain at linux.ibm.com
Sun Jan 15 07:02:04 PST 2023


Introduce powerpc crash hotplug handler to update the necessary kexec
segments on CPU/Memory hotplug events. A common crash hotplug handler is
triggered from generic infrastructure for both CPU/Memory hot un/plugged
events but in this patch, only CPU hot un/plugged events are introduced.
The memory hotplug support is added in upcoming patches.

The elfcorehdr segment is used to exchange the CPU and other dump related
information between the kernels. Ideally, the elfcorehdr segment needs to
be recreated on CPU hotplug events to reflect the changes. But on PowerPC
elfcorehdr is built with all possible CPUs instead of just online CPUs
hence no elfcorehdr segment update/recreation is needed.

In addition to elfcorehdr there is one more kexec segment that holds CPU
data FDT (Flattened Device Tree). To boot the PowerPC kernel the crashing
CPU has to be part of the FDT segment. If the kdump kernel doesn't find
the crashing CPU in the FDT segment, it fails to boot.

The only action needed on PowerPC to handle the crash CPU hotplug event
is to add hot added CPUs in the FDT segment to avoid kdump kernel boot
failure in case the system crashes on hot added CPU.

So for the CPU hot add events, the FDT segment is updated with hot added
CPU and Since there is no need to remove the hot unplugged CPUs from the
FDT segment hence no action taken on CPU hot remove event in PowerPC arch
crash hotplug handler.

To accommodate a growing number of CPUs, FDT is built with additional
buffer space to ensure that it can hold all possible CPUs.

The changes done here will also work for kexec_load system call given
that the kexec tool builds the FDT segment with additional space to
accommodate all possible CPUs as it is done for kexec_file_load system
call in the kernel.

Since memory crash hotplug support is not there yet the crash hotplug
handler simply warns the user and returns.

Signed-off-by: Sourabh Jain <sourabhjain at linux.ibm.com>
---
 arch/powerpc/include/asm/kexec.h |  4 ++
 arch/powerpc/kexec/core_64.c     | 43 ++++++++++++++++++++
 arch/powerpc/kexec/elf_64.c      | 69 +++++++++++++++++++++++++++++++-
 3 files changed, 114 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 5a322c1737661..e7cd4fd2becf5 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -106,6 +106,10 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges);
 #if defined(CONFIG_CRASH_HOTPLUG)
 int machine_kexec_post_load(struct kimage *image);
 #define machine_kexec_post_load machine_kexec_post_load
+
+void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
 #endif
 #endif
 
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 3d4fe1aa6f761..7748b633c20fa 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -570,6 +570,49 @@ int update_cpus_node(void *fdt)
 	return ret;
 }
 
+#if defined(CONFIG_CRASH_HOTPLUG)
+/**
+ * arch_crash_hotplug_handler() - Handle hotplug kexec segements changes FDT, elfcorehdr
+ * @image: the active struct kimage
+ * @hp_action: the hot un/plug action being handled
+ *
+ * To accurately reflect CPU hot un/plug changes, the FDT must be updated with the
+ * new list of CPUs.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action)
+{
+	void *fdt;
+
+	/* No action needed for CPU hot-unplug */
+	if (hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
+		return;
+
+	/* crash update on memory hotplug is not support yet */
+	if (hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY || hp_action == KEXEC_CRASH_HP_ADD_MEMORY) {
+		pr_info_once("crash hp: crash update is not supported with memory hotplug\n");
+		return;
+	}
+
+	/* Must have valid FDT index */
+	if (image->arch.fdt_index < 0) {
+		pr_err("crash hp: unable to locate FDT segment");
+		return;
+	}
+
+	fdt = __va((void *)image->segment[image->arch.fdt_index].mem);
+
+	/* Temporarily invalidate the crash image while it is replaced */
+	xchg(&kexec_crash_image, NULL);
+
+	/* update FDT to refelect changes to CPU resrouces */
+	if (update_cpus_node(fdt))
+		pr_err("crash hp: failed to update crash FDT");
+
+	/* The crash image is now valid once again */
+	xchg(&kexec_crash_image, image);
+}
+#endif
+
 #ifdef CONFIG_PPC_64S_HASH_MMU
 /* Values we need to export to the second kernel via the device tree. */
 static unsigned long htab_base;
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index 2a17f171661f1..c9dfd6d7660ed 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -24,6 +24,64 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
+#include <asm/kvm_book3s_asm.h>
+
+#if defined(CONFIG_CRASH_HOTPLUG)
+/**
+ * get_cpu_node_sz() - Calculate the space needed to store a CPU device
+ * type node in FDT. The calculation is done based on the existing CPU node
+ * in unflatten device tree. Loop through all the properties of the very
+ * first CPU type device node found in unflatten device tree and returns
+ * the sum of the property length and property string size of all properties
+ * of a CPU node.
+ */
+static int get_cpu_node_sz(void)
+{
+	struct device_node *dn;
+	struct property *pp;
+	int cpu_node_size = 0;
+
+	dn = of_find_node_by_type(NULL, "cpu");
+
+	if (!dn) {
+		pr_warn("Unable to locate cpu device_type node.\n");
+		return 0;
+	}
+
+	/* Every node in FDT starts with FDT_BEGIN_NODE and ends with
+	 * FDT_END_NODE that takes one byte each.
+	 */
+	cpu_node_size = 2;
+
+	for_each_property_of_node(dn, pp) {
+		/**
+		 * For each property add two bytes extra. One for string null
+		 * character for property name and other for FDT property start
+		 * tag FDT_PROP.
+		 */
+		cpu_node_size += pp->length + strlen(pp->name) + 2;
+	}
+	return cpu_node_size;
+}
+
+/*
+ * get_crash_fdt_mem_sz() - calcuate mem size for crash kernel FDT
+ * @fdt: pointer to crash kernel FDT
+ *
+ * Calculate the buffer space needed to accommodate more CPU nodes in
+ * crash FDT post capture kernel load due to CPU hotplug events.
+ */
+static unsigned int get_crash_fdt_mem_sz(void *fdt)
+{
+	int fdt_cpu_nodes_sz, offline_cpu_cnt;
+
+	offline_cpu_cnt = (num_possible_cpus() - num_present_cpus()) / MAX_SMT_THREADS;
+	fdt_cpu_nodes_sz = get_cpu_node_sz() * offline_cpu_cnt;
+
+	return fdt_totalsize(fdt) + fdt_cpu_nodes_sz;
+}
+#endif
+
 static void *elf64_load(struct kimage *image, char *kernel_buf,
 			unsigned long kernel_len, char *initrd,
 			unsigned long initrd_len, char *cmdline,
@@ -119,15 +177,22 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	fdt_pack(fdt);
 
 	kbuf.buffer = fdt;
-	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
+	kbuf.bufsz = fdt_totalsize(fdt);
 	kbuf.buf_align = PAGE_SIZE;
 	kbuf.top_down = true;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 
 #if defined(CONFIG_CRASH_HOTPLUG)
 	image->arch.fdt_index = image->nr_segments;
+	if (image->type == KEXEC_TYPE_CRASH) {
+		kbuf.memsz = get_crash_fdt_mem_sz(fdt);
+		fdt_set_totalsize(fdt, kbuf.memsz);
+		image->arch.fdt_index = image->nr_segments;
+	} else
 #endif
-	kbuf.memsz = fdt_totalsize(fdt);
+	{
+		kbuf.memsz = fdt_totalsize(fdt);
+	}
 
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
-- 
2.39.0




More information about the kexec mailing list