[PATCH v15 5/6] x86/boot: Parse SRAT address from RSDP and store immovable memory

[Chao Fan]

SRAT should be parsed by RSDP to fix the conflict between KASLR and
memory-hotremove, then find the immovable memory regions and store
them in an array called immovable_mem[]. With immovable_mem[], KASLR
can avoid to extract kernel to specific regions.

Since 'RANDOMIZE_BASE' && 'MEMORY_HOTREMOVE' is needed, introduce
'CONFIG_EARLY_SRAT_PARSE' to make ifdeffery clear.

Signed-off-by: Chao Fan <fanc.fnst@xxxxxxxxxxxxxx>
---
 arch/x86/Kconfig                  |  12 +++
 arch/x86/boot/compressed/Makefile |   2 +
 arch/x86/boot/compressed/acpi.c   | 138 ++++++++++++++++++++++++++++++
 arch/x86/boot/compressed/kaslr.c  |   4 -
 arch/x86/boot/compressed/misc.h   |  19 ++++
 5 files changed, 171 insertions(+), 4 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba7e3464ee92..c1457609f2e3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2149,6 +2149,18 @@ config X86_NEED_RELOCS
 	def_bool y
 	depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
 
+config EARLY_SRAT_PARSE
+	bool "EARLY SRAT parsing"
+	def_bool y
+	depends on RANDOMIZE_BASE && MEMORY_HOTREMOVE
+	help
+	  This option enables early SRAT parsing in compressed boot stage
+	  so that memory hot-remove ranges do not overlap with KASLR
+	  chosen ranges. Kernel won't be extracted in hot-removable
+	  memory, so that make sure memory-hotremove works well with
+	  KASLR enabled.
+	  Say Y if you want to use both KASLR and memory-hotremove.
+
 config PHYSICAL_ALIGN
 	hex "Alignment value to which kernel should be aligned"
 	default "0x200000"
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 466f66c8a7f8..23491d74939d 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -84,6 +84,8 @@ ifdef CONFIG_X86_64
 	vmlinux-objs-y += $(obj)/pgtable_64.o
 endif
 
+vmlinux-objs-$(CONFIG_EARLY_SRAT_PARSE) += $(obj)/acpi.o
+
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
 vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index e9dd84f459ed..f7a9e9cbd254 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -5,6 +5,7 @@
 #include "../string.h"
 
 #include <linux/acpi.h>
+#include <linux/numa.h>
 #include <linux/efi.h>
 #include <asm/efi.h>
 
@@ -14,6 +15,19 @@
  */
 #define MAX_HEX_ADDRESS_STRING_LEN 19
 
+/*
+ * Longest parameter of 'acpi=' in cmldine is 'copy_dsdt', so max length
+ * is 10, which contains '\0' for termination.
+ */
+#define MAX_ACPI_ARG_LENGTH 10
+
+/*
+ * Information of immovable memory regions.
+ * Max amount of memory regions is MAX_NUMNODES*2, so need such array
+ * to place immovable memory regions if all of the memory is immovable.
+ */
+struct mem_vector immovable_mem[MAX_NUMNODES*2];
+
 static acpi_physical_address get_acpi_rsdp(void)
 {
 #ifdef CONFIG_KEXEC
@@ -197,3 +211,127 @@ static acpi_physical_address bios_get_rsdp_addr(void)
 	}
 	return 0;
 }
+
+/* Determine RSDP, based on acpi_os_get_root_pointer(). */
+static acpi_physical_address get_rsdp_addr(void)
+{
+	acpi_physical_address pa;
+
+	pa = get_acpi_rsdp();
+
+	if (!pa)
+		pa = efi_get_rsdp_addr();
+
+	if (!pa)
+		pa = bios_get_rsdp_addr();
+
+	return pa;
+}
+
+/* Compute SRAT address from RSDP. */
+static struct acpi_table_header *get_acpi_srat_table(void)
+{
+	acpi_physical_address acpi_table;
+	acpi_physical_address root_table;
+	struct acpi_table_header *header;
+	struct acpi_table_rsdp *rsdp;
+	u32 num_entries;
+	char arg[10];
+	u8 *entry;
+	u32 size;
+	u32 len;
+
+	rsdp = (struct acpi_table_rsdp *)(long)get_rsdp_addr();
+	if (!rsdp)
+		return NULL;
+
+	/* Get RSDT or XSDT from RSDP. */
+	if (!(cmdline_find_option("acpi", arg, sizeof(arg)) == 4 &&
+	    !strncmp(arg, "rsdt", 4)) &&
+	    rsdp->xsdt_physical_address &&
+	    rsdp->revision > 1) {
+		root_table = rsdp->xsdt_physical_address;
+		size = ACPI_XSDT_ENTRY_SIZE;
+	} else {
+		root_table = rsdp->rsdt_physical_address;
+		size = ACPI_RSDT_ENTRY_SIZE;
+	}
+
+	/* Get ACPI root table from RSDT or XSDT.*/
+	if (!root_table)
+		return NULL;
+	header = (struct acpi_table_header *)(long)root_table;
+
+	len = header->length;
+	if (len < sizeof(struct acpi_table_header) + size)
+		return NULL;
+
+	num_entries = (u32)((len - sizeof(struct acpi_table_header)) / size);
+	entry = ACPI_ADD_PTR(u8, header, sizeof(struct acpi_table_header));
+
+	while (num_entries--) {
+		u64 address64;
+
+		if (size == ACPI_RSDT_ENTRY_SIZE)
+			acpi_table =  *ACPI_CAST_PTR(u32, entry);
+		else {
+			address64 = *(u64 *)entry;
+			acpi_table = address64;
+		}
+
+		if (acpi_table) {
+			header = (struct acpi_table_header *)(long)acpi_table;
+
+			if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_SRAT))
+				return header;
+		}
+		entry += size;
+	}
+	return NULL;
+}
+
+/*
+ * According to ACPI table, filter the immovable memory regions
+ * and store them in immovable_mem[].
+ */
+void get_immovable_mem(void)
+{
+	struct acpi_table_header *table_header;
+	struct acpi_subtable_header *table;
+	struct acpi_srat_mem_affinity *ma;
+	char arg[MAX_ACPI_ARG_LENGTH];
+	unsigned long table_end;
+	int i = 0;
+
+	if (cmdline_find_option("acpi", arg, sizeof(arg)) == 3 &&
+	    !strncmp(arg, "off", 3))
+		return;
+
+	table_header = get_acpi_srat_table();
+	if (!table_header)
+		return;
+
+	table_end = (unsigned long)table_header + table_header->length;
+	table = (struct acpi_subtable_header *)
+		((unsigned long)table_header + sizeof(struct acpi_table_srat));
+
+	while (((unsigned long)table) +
+		       sizeof(struct acpi_subtable_header) < table_end) {
+		if (table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) {
+			ma = (struct acpi_srat_mem_affinity *)table;
+			if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)) {
+				immovable_mem[i].start = ma->base_address;
+				immovable_mem[i].size = ma->length;
+				i++;
+			}
+
+			if (i >= MAX_NUMNODES*2) {
+				debug_putstr("Too many immovable memory regions, aborting.\n");
+				return;
+			}
+		}
+		table = (struct acpi_subtable_header *)
+			((unsigned long)table + table->length);
+	}
+	num_immovable_mem = i;
+}
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 9ed9709d9947..b251572e77af 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -87,10 +87,6 @@ static unsigned long get_boot_seed(void)
 #define KASLR_COMPRESSED_BOOT
 #include "../../lib/kaslr.c"
 
-struct mem_vector {
-	unsigned long long start;
-	unsigned long long size;
-};
 
 /* Only supporting at most 4 unusable memmap regions with kaslr */
 #define MAX_MEMMAP_REGIONS	4
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index a1d5918765f3..b49748366a5b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -77,6 +77,11 @@ void choose_random_location(unsigned long input,
 			    unsigned long *output,
 			    unsigned long output_size,
 			    unsigned long *virt_addr);
+struct mem_vector {
+	unsigned long long start;
+	unsigned long long size;
+};
+
 /* cpuflags.c */
 bool has_cpuflag(int flag);
 #else
@@ -116,3 +121,17 @@ static inline void console_init(void)
 void set_sev_encryption_mask(void);
 
 #endif
+
+/* acpi.c */
+#ifdef CONFIG_RANDOMIZE_BASE
+/* Amount of immovable memory regions */
+int num_immovable_mem;
+#endif
+
+#ifdef CONFIG_EARLY_SRAT_PARSE
+void get_immovable_mem(void);
+#else
+static void get_immovable_mem(void)
+{
+}
+#endif
-- 
2.20.1