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

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 */

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 */

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;

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;
+}