powerpc/kexec_file: Avoid stomping memory used by special regions

crashkernel region could have an overlap with special memory regions
like OPAL, RTAS, TCE table & such. These regions are referred to as
excluded memory ranges. Setup these ranges during image probe in order
to avoid them while finding the buffer for different kdump segments.
Override arch_kexec_locate_mem_hole() to locate a memory hole taking
these ranges into account.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Reviewed-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/159602281047.575379.6636807148335160795.stgit@hbathini

5 files changed, 539 insertions, 4 deletions

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 9b3feef55aaa..639f31e13593 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -100,14 +100,16 @@ void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_co
 #ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_elf64_ops;
 
-#ifdef CONFIG_IMA_KEXEC
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
+	struct crash_mem *exclude_ranges;
+
+#ifdef CONFIG_IMA_KEXEC
 	phys_addr_t ima_buffer_addr;
 	size_t ima_buffer_size;
-};
 #endif
+};
 
 int setup_purgatory(struct kimage *image, const void *slave_code,
 		    const void *fdt, unsigned long kernel_load_addr,
@@ -125,6 +127,7 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 			unsigned long initrd_load_addr,
 			unsigned long initrd_len, const char *cmdline);
 #endif /* CONFIG_PPC64 */
+
 #endif /* CONFIG_KEXEC_FILE */
 
 #else /* !CONFIG_KEXEC_CORE */
diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h
index 35ae31a7a4de..7a90000f8d15 100644
--- a/arch/powerpc/include/asm/kexec_ranges.h
+++ b/arch/powerpc/include/asm/kexec_ranges.h
@@ -7,5 +7,19 @@
 void sort_memory_ranges(struct crash_mem *mrngs, bool merge);
 struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges);
 int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
+int add_tce_mem_ranges(struct crash_mem **mem_ranges);
+int add_initrd_mem_range(struct crash_mem **mem_ranges);
+#ifdef CONFIG_PPC_BOOK3S_64
+int add_htab_mem_range(struct crash_mem **mem_ranges);
+#else
+static inline int add_htab_mem_range(struct crash_mem **mem_ranges)
+{
+	return 0;
+}
+#endif
+int add_kernel_mem_range(struct crash_mem **mem_ranges);
+int add_rtas_mem_range(struct crash_mem **mem_ranges);
+int add_opal_mem_range(struct crash_mem **mem_ranges);
+int add_reserved_mem_ranges(struct crash_mem **mem_ranges);
 
 #endif /* _ASM_POWERPC_KEXEC_RANGES_H */
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index 23ad04ccaf8e..64c15a5a280b 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -46,6 +46,14 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out;
 
+	if (image->type == KEXEC_TYPE_CRASH) {
+		/* min & max buffer values for kdump case */
+		kbuf.buf_min = pbuf.buf_min = crashk_res.start;
+		kbuf.buf_max = pbuf.buf_max =
+				((crashk_res.end < ppc64_rma_size) ?
+				 crashk_res.end : (ppc64_rma_size - 1));
+	}
+
 	ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr);
 	if (ret)
 		goto out;
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 3e9ac5f216b0..d09c7724efa8 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -17,6 +17,8 @@
 #include <linux/kexec.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <asm/kexec_ranges.h>
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 	&kexec_elf64_ops,
@@ -24,6 +26,254 @@ 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;
+}
+
+/**
+ * __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.
+ * @kbuf:                       Buffer contents and memory parameters.
+ * @buf_min:                    Minimum address for the buffer.
+ * @buf_max:                    Maximum address for the buffer.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
+				      u64 buf_min, u64 buf_max)
+{
+	int ret = -EADDRNOTAVAIL;
+	phys_addr_t start, end;
+	u64 i;
+
+	for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE,
+			       MEMBLOCK_NONE, &start, &end, NULL) {
+		/*
+		 * memblock uses [start, end) convention while it is
+		 * [start, end] here. Fix the off-by-one to have the
+		 * same convention.
+		 */
+		end -= 1;
+
+		if (start > buf_max)
+			continue;
+
+		/* Memory hole not found */
+		if (end < buf_min)
+			break;
+
+		/* Adjust memory region based on the given range */
+		if (start < buf_min)
+			start = buf_min;
+		if (end > buf_max)
+			end = buf_max;
+
+		start = ALIGN(start, kbuf->buf_align);
+		if (start < end && (end - start + 1) >= kbuf->memsz) {
+			/* Suitable memory range found. Set kbuf->mem */
+			kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1,
+					       kbuf->buf_align);
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
+ *                                  suitable buffer with top down approach.
+ * @kbuf:                           Buffer contents and memory parameters.
+ * @buf_min:                        Minimum address for the buffer.
+ * @buf_max:                        Maximum address for the buffer.
+ * @emem:                           Exclude memory ranges.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
+					  u64 buf_min, u64 buf_max,
+					  const struct crash_mem *emem)
+{
+	int i, ret = 0, err = -EADDRNOTAVAIL;
+	u64 start, end, tmin, tmax;
+
+	tmax = buf_max;
+	for (i = (emem->nr_ranges - 1); i >= 0; i--) {
+		start = emem->ranges[i].start;
+		end = emem->ranges[i].end;
+
+		if (start > tmax)
+			continue;
+
+		if (end < tmax) {
+			tmin = (end < buf_min ? buf_min : end + 1);
+			ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
+			if (!ret)
+				return 0;
+		}
+
+		tmax = start - 1;
+
+		if (tmax < buf_min) {
+			ret = err;
+			break;
+		}
+		ret = 0;
+	}
+
+	if (!ret) {
+		tmin = buf_min;
+		ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
+	}
+	return ret;
+}
+
+/**
+ * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole
+ *                               in the memory regions between buf_min & buf_max
+ *                               for the buffer. If found, sets kbuf->mem.
+ * @kbuf:                        Buffer contents and memory parameters.
+ * @buf_min:                     Minimum address for the buffer.
+ * @buf_max:                     Maximum address for the buffer.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
+				       u64 buf_min, u64 buf_max)
+{
+	int ret = -EADDRNOTAVAIL;
+	phys_addr_t start, end;
+	u64 i;
+
+	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+			   MEMBLOCK_NONE, &start, &end, NULL) {
+		/*
+		 * memblock uses [start, end) convention while it is
+		 * [start, end] here. Fix the off-by-one to have the
+		 * same convention.
+		 */
+		end -= 1;
+
+		if (end < buf_min)
+			continue;
+
+		/* Memory hole not found */
+		if (start > buf_max)
+			break;
+
+		/* Adjust memory region based on the given range */
+		if (start < buf_min)
+			start = buf_min;
+		if (end > buf_max)
+			end = buf_max;
+
+		start = ALIGN(start, kbuf->buf_align);
+		if (start < end && (end - start + 1) >= kbuf->memsz) {
+			/* Suitable memory range found. Set kbuf->mem */
+			kbuf->mem = start;
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
+ *                                   suitable buffer with bottom up approach.
+ * @kbuf:                            Buffer contents and memory parameters.
+ * @buf_min:                         Minimum address for the buffer.
+ * @buf_max:                         Maximum address for the buffer.
+ * @emem:                            Exclude memory ranges.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
+					   u64 buf_min, u64 buf_max,
+					   const struct crash_mem *emem)
+{
+	int i, ret = 0, err = -EADDRNOTAVAIL;
+	u64 start, end, tmin, tmax;
+
+	tmin = buf_min;
+	for (i = 0; i < emem->nr_ranges; i++) {
+		start = emem->ranges[i].start;
+		end = emem->ranges[i].end;
+
+		if (end < tmin)
+			continue;
+
+		if (start > tmin) {
+			tmax = (start > buf_max ? buf_max : start - 1);
+			ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
+			if (!ret)
+				return 0;
+		}
+
+		tmin = end + 1;
+
+		if (tmin > buf_max) {
+			ret = err;
+			break;
+		}
+		ret = 0;
+	}
+
+	if (!ret) {
+		tmax = buf_max;
+		ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
+	}
+	return ret;
+}
+
+/**
  * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
  *                         variables and call setup_purgatory() to initialize
  *                         common global variable.
@@ -68,6 +318,67 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 }
 
 /**
+ * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal,
+ *                              tce-table, reserved-ranges & such (exclude
+ *                              memory ranges) as they can't be used for kexec
+ *                              segment buffer. Sets kbuf->mem when a suitable
+ *                              memory hole is found.
+ * @kbuf:                       Buffer contents and memory parameters.
+ *
+ * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
+{
+	struct crash_mem **emem;
+	u64 buf_min, buf_max;
+	int ret;
+
+	/*
+	 * Use the generic kexec_locate_mem_hole for regular
+	 * kexec_file_load syscall
+	 */
+	if (kbuf->image->type != KEXEC_TYPE_CRASH)
+		return kexec_locate_mem_hole(kbuf);
+
+	/* Look up the exclude ranges list while locating the memory hole */
+	emem = &(kbuf->image->arch.exclude_ranges);
+	if (!(*emem) || ((*emem)->nr_ranges == 0)) {
+		pr_warn("No exclude range list. Using the default locate mem hole method\n");
+		return kexec_locate_mem_hole(kbuf);
+	}
+
+	/* Segments for kdump kernel should be within crashkernel region */
+	buf_min = (kbuf->buf_min < crashk_res.start ?
+		   crashk_res.start : kbuf->buf_min);
+	buf_max = (kbuf->buf_max > crashk_res.end ?
+		   crashk_res.end : kbuf->buf_max);
+
+	if (buf_min > buf_max) {
+		pr_err("Invalid buffer min and/or max values\n");
+		return -EINVAL;
+	}
+
+	if (kbuf->top_down)
+		ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
+						     *emem);
+	else
+		ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
+						      *emem);
+
+	/* Add the buffer allocated to the exclude list for the next lookup */
+	if (!ret) {
+		add_mem_range(emem, kbuf->mem, kbuf->memsz);
+		sort_memory_ranges(*emem, true);
+	} else {
+		pr_err("Failed to locate memory buffer of size %lu\n",
+		       kbuf->memsz);
+	}
+	return ret;
+}
+
+/**
  * arch_kexec_kernel_image_probe - Does additional handling needed to setup
  *                                 kexec segments.
  * @image:                         kexec image being loaded.
@@ -79,9 +390,31 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 				  unsigned long buf_len)
 {
-	/* We don't support crash kernels yet. */
-	if (image->type == KEXEC_TYPE_CRASH)
+	if (image->type == KEXEC_TYPE_CRASH) {
+		int ret;
+
+		/* Get exclude memory ranges needed for setting up kdump segments */
+		ret = get_exclude_memory_ranges(&(image->arch.exclude_ranges));
+		if (ret)
+			pr_err("Failed to setup exclude memory ranges for buffer lookup\n");
+		/* Return this until all changes for panic kernel are in */
 		return -EOPNOTSUPP;
+	}
 
 	return kexec_image_probe_default(image, buf, buf_len);
 }
+
+/**
+ * arch_kimage_file_post_load_cleanup - Frees up all the allocations done
+ *                                      while loading the image.
+ * @image:                              kexec image being loaded.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	kfree(image->arch.exclude_ranges);
+	image->arch.exclude_ranges = NULL;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index dc3ce036f416..6b81c852feab 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -233,3 +233,180 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
 
 	return __add_mem_range(mem_ranges, base, size);
 }
+
+/**
+ * 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)
+{
+	struct device_node *dn = NULL;
+	int ret = 0;
+
+	for_each_node_by_type(dn, "pci") {
+		u64 base;
+		u32 size;
+
+		ret = of_property_read_u64(dn, "linux,tce-base", &base);
+		ret |= of_property_read_u32(dn, "linux,tce-size", &size);
+		if (ret) {
+			/*
+			 * It is ok to have pci nodes without tce. So, ignore
+			 * property does not exist error.
+			 */
+			if (ret == -EINVAL) {
+				ret = 0;
+				continue;
+			}
+			break;
+		}
+
+		ret = add_mem_range(mem_ranges, base, size);
+		if (ret)
+			break;
+	}
+
+	of_node_put(dn);
+	return ret;
+}
+
+/**
+ * add_initrd_mem_range - Adds initrd range to the given memory ranges list,
+ *                        if the initrd was retained.
+ * @mem_ranges:           Range list to add the memory range to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int add_initrd_mem_range(struct crash_mem **mem_ranges)
+{
+	u64 base, end;
+	int ret;
+
+	/* This range means something, only if initrd was retained */
+	if (!strstr(saved_command_line, "retain_initrd"))
+		return 0;
+
+	ret = of_property_read_u64(of_chosen, "linux,initrd-start", &base);
+	ret |= of_property_read_u64(of_chosen, "linux,initrd-end", &end);
+	if (!ret)
+		ret = add_mem_range(mem_ranges, base, end - base + 1);
+
+	return ret;
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/**
+ * add_htab_mem_range - Adds htab range to the given memory ranges list,
+ *                      if it exists
+ * @mem_ranges:         Range list to add the memory range to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int add_htab_mem_range(struct crash_mem **mem_ranges)
+{
+	if (!htab_address)
+		return 0;
+
+	return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
+}
+#endif
+
+/**
+ * add_kernel_mem_range - Adds kernel text 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_kernel_mem_range(struct crash_mem **mem_ranges)
+{
+	return add_mem_range(mem_ranges, 0, __pa(_end));
+}
+
+/**
+ * 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)
+{
+	struct device_node *dn;
+	u32 base, size;
+	int ret = 0;
+
+	dn = of_find_node_by_path("/rtas");
+	if (!dn)
+		return 0;
+
+	ret = of_property_read_u32(dn, "linux,rtas-base", &base);
+	ret |= of_property_read_u32(dn, "rtas-size", &size);
+	if (!ret)
+		ret = add_mem_range(mem_ranges, base, size);
+
+	of_node_put(dn);
+	return ret;
+}
+
+/**
+ * add_opal_mem_range - Adds OPAL 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_opal_mem_range(struct crash_mem **mem_ranges)
+{
+	struct device_node *dn;
+	u64 base, size;
+	int ret;
+
+	dn = of_find_node_by_path("/ibm,opal");
+	if (!dn)
+		return 0;
+
+	ret = of_property_read_u64(dn, "opal-base-address", &base);
+	ret |= of_property_read_u64(dn, "opal-runtime-size", &size);
+	if (!ret)
+		ret = add_mem_range(mem_ranges, base, size);
+
+	of_node_put(dn);
+	return ret;
+}
+
+/**
+ * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w
+ *                           to the given memory ranges list.
+ * @mem_ranges:              Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
+{
+	int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0;
+	const __be32 *prop;
+
+	prop = of_get_property(of_root, "reserved-ranges", &len);
+	if (!prop)
+		return 0;
+
+	n_mem_addr_cells = of_n_addr_cells(of_root);
+	n_mem_size_cells = of_n_size_cells(of_root);
+	cells = n_mem_addr_cells + n_mem_size_cells;
+
+	/* Each reserved range is an (address,size) pair */
+	for (i = 0; i < (len / (sizeof(u32) * cells)); i++) {
+		u64 base, size;
+
+		base = of_read_number(prop + (i * cells), n_mem_addr_cells);
+		size = of_read_number(prop + (i * cells) + n_mem_addr_cells,
+				      n_mem_size_cells);
+
+		ret = add_mem_range(mem_ranges, base, size);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}