Merge branch 'topic/kdump-hotplug' into next

Merge our topic branch containing kdump hotplug changes, more detail from the
original cover letter:

Commit 247262756121 ("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.

This patch series adds crash hotplug handler for PowerPC and enable
support to update the kdump image on CPU/Memory add/remove events.

Among the 6 patches in this series, the first two patches make changes
to the generic crash hotplug handler to assist PowerPC in adding support
for this feature. The last four patches add support for this feature.

The following section outlines the problem addressed by this patch
series, along with the current solution, its shortcomings, and the
proposed resolution.

Problem:
========
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(Flattened Device Tree) of kdump image becomes outdated.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attempting dump collection with an outdated elfcorehdr or FDT can lead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.

Existing solution and its shortcoming:
======================================
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 Given that only elfcorehdr and FDT get outdated due to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.

Proposed solution:
==================
Instead of initiating a full kdump image reload from userspace on
CPU/Memory hotplug and online/offline events, the proposed solution aims
to update only the necessary kdump image component within the kernel
itself.

1 files changed, 36 insertions, 278 deletions

diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 1bc65de6174f..925a69ad2468 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/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 */
@@ -48,83 +49,6 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 };
 
 /**
- * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
- *                             regions like opal/rtas, tce-table, initrd,
- *                             kernel, htab which should be avoided while
- *                             setting up kexec load segments.
- * @mem_ranges:                Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_initrd_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_htab_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_kernel_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* exclude memory ranges should be sorted for easy lookup */
-	sort_memory_ranges(*mem_ranges, true);
-out:
-	if (ret)
-		pr_err("Failed to setup exclude memory ranges\n");
-	return ret;
-}
-
-/**
- * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
- *                              memory regions that should be added to the
- *                              memory reserve map to ensure the region is
- *                              protected from any mischief.
- * @mem_ranges:                 Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup reserved memory ranges\n");
-	return ret;
-}
-
-/**
  * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
  *                              in the memory regions between buf_min & buf_max
  *                              for the buffer. If found, sets kbuf->mem.
@@ -323,119 +247,6 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
 
 #ifdef CONFIG_CRASH_DUMP
 /**
- * get_usable_memory_ranges - Get usable memory ranges. This list includes
- *                            regions like crashkernel, opal/rtas & tce-table,
- *                            that kdump kernel could use.
- * @mem_ranges:               Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_usable_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	/*
-	 * Early boot failure observed on guests when low memory (first memory
-	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
-	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
-	 * Also, crashed kernel's memory must be added to reserve map to
-	 * avoid kdump kernel from using it.
-	 */
-	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup usable memory ranges\n");
-	return ret;
-}
-
-/**
- * get_crash_memory_ranges - Get crash memory ranges. This list includes
- *                           first/crashing kernel's memory regions that
- *                           would be exported via an elfcore.
- * @mem_ranges:              Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
-{
-	phys_addr_t base, end;
-	struct crash_mem *tmem;
-	u64 i;
-	int ret;
-
-	for_each_mem_range(i, &base, &end) {
-		u64 size = end - base;
-
-		/* Skip backup memory region, which needs a separate entry */
-		if (base == BACKUP_SRC_START) {
-			if (size > BACKUP_SRC_SIZE) {
-				base = BACKUP_SRC_END + 1;
-				size -= BACKUP_SRC_SIZE;
-			} else
-				continue;
-		}
-
-		ret = add_mem_range(mem_ranges, base, size);
-		if (ret)
-			goto out;
-
-		/* Try merging adjacent ranges before reallocation attempt */
-		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
-			sort_memory_ranges(*mem_ranges, true);
-	}
-
-	/* Reallocate memory ranges if there is no space to split ranges */
-	tmem = *mem_ranges;
-	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
-		tmem = realloc_mem_ranges(mem_ranges);
-		if (!tmem)
-			goto out;
-	}
-
-	/* Exclude crashkernel region */
-	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
-	if (ret)
-		goto out;
-
-	/*
-	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
-	 *        regions are exported to save their context at the time of
-	 *        crash, they should actually be backed up just like the
-	 *        first 64K bytes of memory.
-	 */
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* create a separate program header for the backup region */
-	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
-	if (ret)
-		goto out;
-
-	sort_memory_ranges(*mem_ranges, false);
-out:
-	if (ret)
-		pr_err("Failed to setup crash memory ranges\n");
-	return ret;
-}
-
-/**
  * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries
  * @um_info:                  Usable memory buffer and ranges info.
  * @cnt:                      No. of entries to accommodate.
@@ -784,6 +595,23 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
 	}
 }
 
+static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem)
+{
+#if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG)
+	unsigned int extra_sz = 0;
+
+	if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM)
+		pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES);
+	else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES)
+		pr_warn("Configured crash mem ranges may not be enough\n");
+	else
+		extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr);
+
+	return extra_sz;
+#endif
+	return 0;
+}
+
 /**
  * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr
  *                           segment needed to load kdump kernel.
@@ -815,7 +643,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 
 	kbuf->buffer = headers;
 	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
-	kbuf->bufsz = kbuf->memsz = headers_sz;
+	kbuf->bufsz = headers_sz;
+	kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
 	kbuf->top_down = false;
 
 	ret = kexec_add_buffer(kbuf);
@@ -979,6 +808,9 @@ 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;
@@ -1006,6 +838,19 @@ 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;
 }
 
@@ -1028,93 +873,6 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 	return extra_size + kdump_extra_fdt_size_ppc64(image);
 }
 
-/**
- * add_node_props - Reads node properties from device node structure and add
- *                  them to fdt.
- * @fdt:            Flattened device tree of the kernel
- * @node_offset:    offset of the node to add a property at
- * @dn:             device node pointer
- *
- * Returns 0 on success, negative errno on error.
- */
-static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
-{
-	int ret = 0;
-	struct property *pp;
-
-	if (!dn)
-		return -EINVAL;
-
-	for_each_property_of_node(dn, pp) {
-		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
-		if (ret < 0) {
-			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
-			return ret;
-		}
-	}
-	return ret;
-}
-
-/**
- * update_cpus_node - Update cpus node of flattened device tree using of_root
- *                    device node.
- * @fdt:              Flattened device tree of the kernel.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int update_cpus_node(void *fdt)
-{
-	struct device_node *cpus_node, *dn;
-	int cpus_offset, cpus_subnode_offset, ret = 0;
-
-	cpus_offset = fdt_path_offset(fdt, "/cpus");
-	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
-		pr_err("Malformed device tree: error reading /cpus node: %s\n",
-		       fdt_strerror(cpus_offset));
-		return cpus_offset;
-	}
-
-	if (cpus_offset > 0) {
-		ret = fdt_del_node(fdt, cpus_offset);
-		if (ret < 0) {
-			pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
-			return -EINVAL;
-		}
-	}
-
-	/* Add cpus node to fdt */
-	cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
-	if (cpus_offset < 0) {
-		pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
-		return -EINVAL;
-	}
-
-	/* Add cpus node properties */
-	cpus_node = of_find_node_by_path("/cpus");
-	ret = add_node_props(fdt, cpus_offset, cpus_node);
-	of_node_put(cpus_node);
-	if (ret < 0)
-		return ret;
-
-	/* Loop through all subnodes of cpus and add them to fdt */
-	for_each_node_by_type(dn, "cpu") {
-		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
-		if (cpus_subnode_offset < 0) {
-			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
-			       fdt_strerror(cpus_subnode_offset));
-			ret = cpus_subnode_offset;
-			goto out;
-		}
-
-		ret = add_node_props(fdt, cpus_subnode_offset, dn);
-		if (ret < 0)
-			goto out;
-	}
-out:
-	of_node_put(dn);
-	return ret;
-}
-
 static int copy_property(void *fdt, int node_offset, const struct device_node *dn,
 			 const char *propname)
 {