powerpc/crash: add crash CPU hotplug support

Due to CPU/Memory hotplug or online/offline events, the elfcorehdr
(which describes the CPUs and memory of the crashed kernel) and FDT
(Flattened Device Tree) of kdump image becomes outdated. Consequently,
attempting dump collection with an outdated elfcorehdr or FDT can lead
to failed or inaccurate dump collection.

Going forward, CPU hotplug or online/offline events are referred as
CPU/Memory add/remove events.

The current solution to address the above issue involves monitoring the
CPU/Memory add/remove events in userspace using udev rules and whenever
there are changes in CPU and memory resources, the entire kdump image
is loaded again. The kdump image includes kernel, initrd, elfcorehdr,
FDT, purgatory. Given that only elfcorehdr and FDT get outdated due to
CPU/Memory add/remove events, reloading the entire kdump image is
inefficient. More importantly, kdump remains inactive for a substantial
amount of time until the kdump reload completes.

To address the aforementioned issue, commit 2472627561 ("crash: add
generic infrastructure for crash hotplug support") added a generic
infrastructure that allows architectures to selectively update the kdump
image component during CPU or memory add/remove events within the kernel
itself.

In the event of a CPU or memory add/remove events, the generic crash
hotplug event handler, `crash_handle_hotplug_event()`, is triggered. It
then acquires the necessary locks to update the kdump image and invokes
the architecture-specific crash hotplug handler,
`arch_crash_handle_hotplug_event()`, to update the required kdump image
components.

This patch adds crash hotplug handler for PowerPC and enable support to
update the kdump image on CPU add/remove events. Support for memory
add/remove events is added in a subsequent patch with the title
"powerpc: add crash memory hotplug support"

As mentioned earlier, only the elfcorehdr and FDT kdump image components
need to be updated in the event of CPU or memory add/remove events.
However, on PowerPC architecture crash hotplug handler only updates the
FDT to enable crash hotplug support for CPU add/remove events. Here's
why.

The elfcorehdr on PowerPC is built with possible CPUs, and thus, it does
not need an update on CPU add/remove events. On the other hand, the FDT
needs to be updated on CPU add events to include the newly added CPU. If
the FDT is not updated and the kernel crashes on a newly added CPU, the
kdump kernel will fail to boot due to the unavailability of the crashing
CPU in the FDT. During the early boot, it is expected that the boot CPU
must be a part of the FDT; otherwise, the kernel will raise a BUG and
fail to boot. For more information, refer to commit 36ae37e343
("powerpc: Make boot_cpuid common between 32 and 64-bit"). Since it is
okay to have an offline CPU in the kdump FDT, no action is taken in case
of CPU removal.

There are two system calls, `kexec_file_load` and `kexec_load`, used to
load the kdump image. Few changes have been made to ensure kernel can
safely update the FDT of kdump image loaded using both system calls.

For kexec_file_load syscall the kdump image is prepared in kernel. So to
support an increasing number of CPUs, the FDT is constructed with extra
buffer space to ensure it can accommodate a possible number of CPU
nodes. Additionally, a call to fdt_pack (which trims the unused space
once the FDT is prepared) is avoided if this feature is enabled.

For the kexec_load syscall, the FDT is updated only if the
KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag is passed to the kernel by
userspace (kexec tools). When userspace passes this flag to the kernel,
it indicates that the FDT is built to accommodate possible CPUs, and the
FDT segment is excluded from 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/20240326055413.186534-6-sourabhjain@linux.ibm.com

arch/powerpc/Kconfig

@@ -686,6 +686,10 @@ config ARCH_SELECTS_CRASH_DUMP
 	depends on CRASH_DUMP
 	select RELOCATABLE if PPC64 || 44x || PPC_85xx
 
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+	def_bool y
+	depends on PPC64
+
 config FA_DUMP
 	bool "Firmware-assisted dump"
 	depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)

arch/powerpc/include/asm/kexec.h

@@ -135,6 +135,14 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 		ppc_save_regs(newregs);
 }
 
+#ifdef CONFIG_CRASH_HOTPLUG
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
+#endif /* CONFIG_CRASH_HOTPLUG */
+
 extern int crashing_cpu;
 extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
 extern void crash_ipi_callback(struct pt_regs *regs);

arch/powerpc/kexec/crash.c

@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/types.h>
+#include <linux/libfdt.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
@@ -392,3 +393,105 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(1, 0);
 }
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/**
+ * get_fdt_index - Loop through the kexec segment array and find
+ *		   the index of the FDT segment.
+ * @image: a pointer to kexec_crash_image
+ *
+ * Returns the index of FDT segment in the kexec segment array
+ * if found; otherwise -1.
+ */
+static int get_fdt_index(struct kimage *image)
+{
+	void *ptr;
+	unsigned long mem;
+	int i, fdt_index = -1;
+
+	/* Find the FDT segment index in kexec segment array. */
+	for (i = 0; i < image->nr_segments; i++) {
+		mem = image->segment[i].mem;
+		ptr = __va(mem);
+
+		if (ptr && fdt_magic(ptr) == FDT_MAGIC) {
+			fdt_index = i;
+			break;
+		}
+	}
+
+	return fdt_index;
+}
+
+/**
+ * update_crash_fdt - updates the cpus node of the crash FDT.
+ *
+ * @image: a pointer to kexec_crash_image
+ */
+static void update_crash_fdt(struct kimage *image)
+{
+	void *fdt;
+	int fdt_index;
+
+	fdt_index = get_fdt_index(image);
+	if (fdt_index < 0) {
+		pr_err("Unable to locate FDT segment.\n");
+		return;
+	}
+
+	fdt = __va((void *)image->segment[fdt_index].mem);
+
+	/* Temporarily invalidate the crash image while it is replaced */
+	xchg(&kexec_crash_image, NULL);
+
+	/* update FDT to reflect changes in CPU resources */
+	if (update_cpus_node(fdt))
+		pr_err("Failed to update crash FDT");
+
+	/* The crash image is now valid once again */
+	xchg(&kexec_crash_image, image);
+}
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+#ifdef CONFIG_KEXEC_FILE
+	if (image->file_mode)
+		return 1;
+#endif
+	return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT;
+}
+
+/**
+ * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the
+ *				     necessary kexec segments based on the hotplug event.
+ * @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case.
+ *
+ * Update the kdump image based on the type of hotplug event, represented by image->hp_action.
+ * CPU add: Update the FDT segment to include the newly added CPU.
+ * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs
+ *	       part of the FDT.
+ * Memory add/remove: No action is taken as this is not yet supported.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
+{
+	switch (image->hp_action) {
+	case KEXEC_CRASH_HP_REMOVE_CPU:
+		return;
+
+	case KEXEC_CRASH_HP_ADD_CPU:
+		update_crash_fdt(image);
+		break;
+
+	case KEXEC_CRASH_HP_REMOVE_MEMORY:
+	case KEXEC_CRASH_HP_ADD_MEMORY:
+		pr_info_once("Crash update is not supported for memory hotplug\n");
+		return;
+	default:
+		pr_warn_once("Unknown hotplug action\n");
+	}
+}
+#endif /* CONFIG_CRASH_HOTPLUG */

arch/powerpc/kexec/elf_64.c

@@ -116,7 +116,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out_free_fdt;
 
-	fdt_pack(fdt);
+	if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH)
+		fdt_pack(fdt);
 
 	kbuf.buffer = fdt;
 	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);

arch/powerpc/kexec/file_load_64.c

@@ -30,6 +30,7 @@
 #include <asm/iommu.h>
 #include <asm/prom.h>
 #include <asm/plpks.h>
+#include <asm/cputhreads.h>
 
 struct umem_info {
 	__be64 *buf;		/* data buffer for usable-memory property */
@@ -789,6 +790,9 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image)
 	unsigned int cpu_nodes, extra_size = 0;
 	struct device_node *dn;
 	u64 usm_entries;
+#ifdef CONFIG_CRASH_HOTPLUG
+	unsigned int possible_cpu_nodes;
+#endif
 
 	if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH)
 		return 0;
@@ -816,6 +820,19 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image)
 	if (cpu_nodes > boot_cpu_node_count)
 		extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
 
+#ifdef CONFIG_CRASH_HOTPLUG
+	/*
+	 * Make sure enough space is reserved to accommodate possible CPU nodes
+	 * in the crash FDT. This allows packing possible CPU nodes which are
+	 * not yet present in the system without regenerating the entire FDT.
+	 */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		possible_cpu_nodes = num_possible_cpus() / threads_per_core;
+		if (possible_cpu_nodes > cpu_nodes)
+			extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size();
+	}
+#endif
+
 	return extra_size;
 }