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(Flattened Device Tree) of kdump image becomes outdated.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attempting dump collection with an outdated elfcorehdr or FDT can lead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 Given that only elfcorehdr and FDT get outdated due to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, 303 insertions, 9 deletions

diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index 33b780049aaf..3702b0bdab14 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -20,9 +20,13 @@
 #include <linux/kexec.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/crash_core.h>
 #include <asm/sections.h>
 #include <asm/kexec_ranges.h>
+#include <asm/crashdump-ppc64.h>
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * get_max_nr_ranges - Get the max no. of ranges crash_mem structure
  *                     could hold, given the size allocated for it.
@@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
 	return __add_mem_range(mem_ranges, base, size);
 }
 
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
+
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range(s) to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_tce_mem_ranges(struct crash_mem **mem_ranges)
+static int add_tce_mem_ranges(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn = NULL;
 	int ret = 0;
@@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_initrd_mem_range(struct crash_mem **mem_ranges)
+static int add_initrd_mem_range(struct crash_mem **mem_ranges)
 {
 	u64 base, end;
 	int ret;
@@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
 	return ret;
 }
 
-#ifdef CONFIG_PPC_64S_HASH_MMU
 /**
  * add_htab_mem_range - Adds htab range to the given memory ranges list,
  *                      if it exists
@@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_htab_mem_range(struct crash_mem **mem_ranges)
+static int add_htab_mem_range(struct crash_mem **mem_ranges)
 {
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
 	if (!htab_address)
 		return 0;
 
 	return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
-}
+#else
+	return 0;
 #endif
+}
 
 /**
  * add_kernel_mem_range - Adds kernel text region to the given
@@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_kernel_mem_range(struct crash_mem **mem_ranges)
+static int add_kernel_mem_range(struct crash_mem **mem_ranges)
 {
 	return add_mem_range(mem_ranges, 0, __pa(_end));
 }
+#endif /* CONFIG_KEXEC_FILE */
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * add_rtas_mem_range - Adds RTAS region to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_rtas_mem_range(struct crash_mem **mem_ranges)
+static int add_rtas_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u32 base, size;
@@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_opal_mem_range(struct crash_mem **mem_ranges)
+static int add_opal_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u64 base, size;
@@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
 	of_node_put(dn);
 	return ret;
 }
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
 
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w
  *                           to the given memory ranges list.
@@ -382,7 +396,7 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
+static int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 {
 	int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0;
 	struct device_node *root = of_find_node_by_path("/");
@@ -412,3 +426,283 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 
 	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.
+ */
+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;
+}
+
+/**
+ * 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.
+ */
+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;
+}
+
+#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.
+ */
+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;
+}
+#endif /* CONFIG_CRASH_DUMP */
+#endif /* CONFIG_KEXEC_FILE */
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * 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.
+ */
+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;
+}
+
+/**
+ * remove_mem_range - Removes the given memory range from the range list.
+ * @mem_ranges:    Range list to remove the memory range to.
+ * @base:          Base address of the range to remove.
+ * @size:          Size of the memory range to remove.
+ *
+ * (Re)allocates memory, if needed.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
+{
+	u64 end;
+	int ret = 0;
+	unsigned int i;
+	u64 mstart, mend;
+	struct crash_mem *mem_rngs = *mem_ranges;
+
+	if (!size)
+		return 0;
+
+	/*
+	 * Memory range are stored as start and end address, use
+	 * the same format to do remove operation.
+	 */
+	end = base + size - 1;
+
+	for (i = 0; i < mem_rngs->nr_ranges; i++) {
+		mstart = mem_rngs->ranges[i].start;
+		mend = mem_rngs->ranges[i].end;
+
+		/*
+		 * Memory range to remove is not part of this range entry
+		 * in the memory range list
+		 */
+		if (!(base >= mstart && end <= mend))
+			continue;
+
+		/*
+		 * Memory range to remove is equivalent to this entry in the
+		 * memory range list. Remove the range entry from the list.
+		 */
+		if (base == mstart && end == mend) {
+			for (; i < mem_rngs->nr_ranges - 1; i++) {
+				mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start;
+				mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end;
+			}
+			mem_rngs->nr_ranges--;
+			goto out;
+		}
+		/*
+		 * Start address of the memory range to remove and the
+		 * current memory range entry in the list is same. Just
+		 * move the start address of the current memory range
+		 * entry in the list to end + 1.
+		 */
+		else if (base == mstart) {
+			mem_rngs->ranges[i].start = end + 1;
+			goto out;
+		}
+		/*
+		 * End address of the memory range to remove and the
+		 * current memory range entry in the list is same.
+		 * Just move the end address of the current memory
+		 * range entry in the list to base - 1.
+		 */
+		else if (end == mend)  {
+			mem_rngs->ranges[i].end = base - 1;
+			goto out;
+		}
+		/*
+		 * Memory range to remove is not at the edge of current
+		 * memory range entry. Split the current memory entry into
+		 * two half.
+		 */
+		else {
+			mem_rngs->ranges[i].end = base - 1;
+			size = mem_rngs->ranges[i].end - end;
+			ret = add_mem_range(mem_ranges, end + 1, size);
+		}
+	}
+out:
+	return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */