Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Ingo Molnar:
 "The main changes are KASL related fixes and cleanups: in particular we
  now exclude certain physical memory ranges as KASLR randomization
  targets that have proven to be unreliable (early-)RAM on some firmware
  versions"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot/KASLR: Work around firmware bugs by excluding EFI_BOOT_SERVICES_* and EFI_LOADER_* from KASLR's choice
  x86/boot/KASLR: Prefer mirrored memory regions for the kernel physical address
  efi: Introduce efi_early_memdesc_ptr to get pointer to memmap descriptor
  x86/boot/KASLR: Rename process_e820_entry() into process_mem_region()
  x86/boot/KASLR: Switch to pass struct mem_vector to process_e820_entry()
  x86/boot/KASLR: Wrap e820 entries walking code into new function process_e820_entries()

4 files changed, 145 insertions, 30 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c3e869eaef0c..e007887a33b0 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -767,7 +767,7 @@ static efi_status_t setup_e820(struct boot_params *params,
 		m |= (u64)efi->efi_memmap_hi << 32;
 #endif
 
-		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
+		d = efi_early_memdesc_ptr(m, efi->efi_memdesc_size, i);
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
 		case EFI_RUNTIME_SERVICES_CODE:
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 91f27ab970ef..17818ba6906f 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -37,7 +37,9 @@
 #include <linux/uts.h>
 #include <linux/utsname.h>
 #include <linux/ctype.h>
+#include <linux/efi.h>
 #include <generated/utsrelease.h>
+#include <asm/efi.h>
 
 /* Macros used by the included decompressor code below. */
 #define STATIC
@@ -479,35 +481,31 @@ static unsigned long slots_fetch_random(void)
 	return 0;
 }
 
-static void process_e820_entry(struct boot_e820_entry *entry,
+static void process_mem_region(struct mem_vector *entry,
 			       unsigned long minimum,
 			       unsigned long image_size)
 {
 	struct mem_vector region, overlap;
 	struct slot_area slot_area;
 	unsigned long start_orig, end;
-	struct boot_e820_entry cur_entry;
-
-	/* Skip non-RAM entries. */
-	if (entry->type != E820_TYPE_RAM)
-		return;
+	struct mem_vector cur_entry;
 
 	/* On 32-bit, ignore entries entirely above our maximum. */
-	if (IS_ENABLED(CONFIG_X86_32) && entry->addr >= KERNEL_IMAGE_SIZE)
+	if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE)
 		return;
 
 	/* Ignore entries entirely below our minimum. */
-	if (entry->addr + entry->size < minimum)
+	if (entry->start + entry->size < minimum)
 		return;
 
 	/* Ignore entries above memory limit */
-	end = min(entry->size + entry->addr, mem_limit);
-	if (entry->addr >= end)
+	end = min(entry->size + entry->start, mem_limit);
+	if (entry->start >= end)
 		return;
-	cur_entry.addr = entry->addr;
-	cur_entry.size = end - entry->addr;
+	cur_entry.start = entry->start;
+	cur_entry.size = end - entry->start;
 
-	region.start = cur_entry.addr;
+	region.start = cur_entry.start;
 	region.size = cur_entry.size;
 
 	/* Give up if slot area array is full. */
@@ -521,8 +519,8 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 		/* Potentially raise address to meet alignment needs. */
 		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
 
-		/* Did we raise the address above this e820 region? */
-		if (region.start > cur_entry.addr + cur_entry.size)
+		/* Did we raise the address above the passed in memory entry? */
+		if (region.start > cur_entry.start + cur_entry.size)
 			return;
 
 		/* Reduce size by any delta from the original address. */
@@ -562,31 +560,126 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 	}
 }
 
-static unsigned long find_random_phys_addr(unsigned long minimum,
-					   unsigned long image_size)
+#ifdef CONFIG_EFI
+/*
+ * Returns true if mirror region found (and must have been processed
+ * for slots adding)
+ */
+static bool
+process_efi_entries(unsigned long minimum, unsigned long image_size)
 {
+	struct efi_info *e = &boot_params->efi_info;
+	bool efi_mirror_found = false;
+	struct mem_vector region;
+	efi_memory_desc_t *md;
+	unsigned long pmap;
+	char *signature;
+	u32 nr_desc;
 	int i;
-	unsigned long addr;
 
-	/* Check if we had too many memmaps. */
-	if (memmap_too_large) {
-		debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
-		return 0;
+	signature = (char *)&e->efi_loader_signature;
+	if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) &&
+	    strncmp(signature, EFI64_LOADER_SIGNATURE, 4))
+		return false;
+
+#ifdef CONFIG_X86_32
+	/* Can't handle data above 4GB at this time */
+	if (e->efi_memmap_hi) {
+		warn("EFI memmap is above 4GB, can't be handled now on x86_32. EFI should be disabled.\n");
+		return false;
 	}
+	pmap =  e->efi_memmap;
+#else
+	pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32));
+#endif
 
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+	nr_desc = e->efi_memmap_size / e->efi_memdesc_size;
+	for (i = 0; i < nr_desc; i++) {
+		md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i);
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			efi_mirror_found = true;
+			break;
+		}
+	}
+
+	for (i = 0; i < nr_desc; i++) {
+		md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i);
+
+		/*
+		 * Here we are more conservative in picking free memory than
+		 * the EFI spec allows:
+		 *
+		 * According to the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also
+		 * free memory and thus available to place the kernel image into,
+		 * but in practice there's firmware where using that memory leads
+		 * to crashes.
+		 *
+		 * Only EFI_CONVENTIONAL_MEMORY is guaranteed to be free.
+		 */
+		if (md->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (efi_mirror_found &&
+		    !(md->attribute & EFI_MEMORY_MORE_RELIABLE))
+			continue;
+
+		region.start = md->phys_addr;
+		region.size = md->num_pages << EFI_PAGE_SHIFT;
+		process_mem_region(&region, minimum, image_size);
+		if (slot_area_index == MAX_SLOT_AREA) {
+			debug_putstr("Aborted EFI scan (slot_areas full)!\n");
+			break;
+		}
+	}
+	return true;
+}
+#else
+static inline bool
+process_efi_entries(unsigned long minimum, unsigned long image_size)
+{
+	return false;
+}
+#endif
+
+static void process_e820_entries(unsigned long minimum,
+				 unsigned long image_size)
+{
+	int i;
+	struct mem_vector region;
+	struct boot_e820_entry *entry;
 
 	/* Verify potential e820 positions, appending to slots list. */
 	for (i = 0; i < boot_params->e820_entries; i++) {
-		process_e820_entry(&boot_params->e820_table[i], minimum,
-				   image_size);
+		entry = &boot_params->e820_table[i];
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+		region.start = entry->addr;
+		region.size = entry->size;
+		process_mem_region(&region, minimum, image_size);
 		if (slot_area_index == MAX_SLOT_AREA) {
 			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
 			break;
 		}
 	}
+}
+
+static unsigned long find_random_phys_addr(unsigned long minimum,
+					   unsigned long image_size)
+{
+	/* Check if we had too many memmaps. */
+	if (memmap_too_large) {
+		debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n");
+		return 0;
+	}
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	if (process_efi_entries(minimum, image_size))
+		return slots_fetch_random();
 
+	process_e820_entries(minimum, image_size);
 	return slots_fetch_random();
 }
 
@@ -645,7 +738,7 @@ void choose_random_location(unsigned long input,
 	 */
 	min_addr = min(*output, 512UL << 20);
 
-	/* Walk e820 and find a random address. */
+	/* Walk available memory entries to find a random address. */
 	random_addr = find_random_phys_addr(min_addr, output_size);
 	if (!random_addr) {
 		warn("Physical KASLR disabled: no suitable memory region!");
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index b0184360efc6..50a9cab5a834 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -205,7 +205,7 @@ again:
 		unsigned long m = (unsigned long)map;
 		u64 start, end;
 
-		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+		desc = efi_early_memdesc_ptr(m, desc_size, i);
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
@@ -298,7 +298,7 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 		unsigned long m = (unsigned long)map;
 		u64 start, end;
 
-		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+		desc = efi_early_memdesc_ptr(m, desc_size, i);
 
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8269bcb8ccf7..a686ca9a7e5c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1020,6 +1020,28 @@ extern int efi_memattr_init(void);
 extern int efi_memattr_apply_permissions(struct mm_struct *mm,
 					 efi_memattr_perm_setter fn);
 
+/*
+ * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor
+ * @map: the start of efi memmap
+ * @desc_size: the size of space for each EFI memmap descriptor
+ * @n: the index of efi memmap descriptor
+ *
+ * EFI boot service provides the GetMemoryMap() function to get a copy of the
+ * current memory map which is an array of memory descriptors, each of
+ * which describes a contiguous block of memory. It also gets the size of the
+ * map, and the size of each descriptor, etc.
+ *
+ * Note that per section 6.2 of UEFI Spec 2.6 Errata A, the returned size of
+ * each descriptor might not be equal to sizeof(efi_memory_memdesc_t),
+ * since efi_memory_memdesc_t may be extended in the future. Thus the OS
+ * MUST use the returned size of the descriptor to find the start of each
+ * efi_memory_memdesc_t in the memory map array. This should only be used
+ * during bootup since for_each_efi_memory_desc_xxx() is available after the
+ * kernel initializes the EFI subsystem to set up struct efi_memory_map.
+ */
+#define efi_early_memdesc_ptr(map, desc_size, n)			\
+	(efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size)))
+
 /* Iterate through an efi_memory_map */
 #define for_each_efi_memory_desc_in_map(m, md)				   \
 	for ((md) = (m)->map;						   \