x86/boot/KASLR: Restrict kernel to be randomized in mirror regions

Currently KASLR will parse all e820 entries of RAM type and add all candidate position into slots array. Then we will choose one slot randomly as the new position which kernel will be decompressed into and run at.

On system with EFI enabled, e820 memory regions are coming from EFI memory regions by combining adjacent regions. While these EFI memory regions have more attributes to mark their different use. Mirror attribute is such kind. The physical memory region whose descriptors in EFI memory map has EFI_MEMORY_MORE_RELIABLE attribute (bit: 16) are mirrored. The address range mirroring feature of kernel arranges such mirror region into normal zone and other region into movable zone. And with mirroring feature enabled, the code and date of kernel can only be located in more reliable mirror region. However, the current KASLR code doesn't check EFI memory entries, and could choose new position in non-mirrored region. This will break the functionality of the address range mirroring feature.

So if EFI is detected, iterate EFI memory map and pick the mirror region to process for adding candidate of randomization slot. If EFI is disabled or no mirror region found, still process e820 memory map.

Signed-off-by Baoquan He <[email protected]>

---
v6->v7:
Ingo pointed out several incorrect line break issues and unclear description of patch log. Correct them and rewrite patch log.

And also rewrite the EFI warning message that if EFI memmap is above 4G in 32bit system since 32bit system can not handle data above 4G at kernel decompression stage. This is suggested by Ingo too.

v5->v6:
Code style issue fix according to Kees's comment.

This is based on tip/x86/boot, patch 1,2,3/4 in v5 post has been put into tip/x86/boot now.

 arch/x86/boot/compressed/kaslr.c | 68 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 66 insertions(+), 2 deletions(-)

arch/x86/boot/compressed/kaslr.c +40 -0

index 99c7194f7ea6..e1dd59ea8a8f 100644
@@ -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

@@ -558,6 +560,65 @@ static void process_mem_region(struct mem_vector *entry,
 	}
 }
 
+#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;
+
+	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
+
+	nr_desc = e->efi_memmap_size / e->efi_memdesc_size;
+	for (i = 0; i < nr_desc; i++) {
+		md = (efi_memory_desc_t *)(pmap + (i * e->efi_memdesc_size));
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			region.start = md->phys_addr;

Quoted 11 lines

arch/x86/boot/compressed/kaslr.c +10 -0

+	pmap =  e->efi_memmap;
+#else
+	pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32));
+#endif
+
+	nr_desc = e->efi_memmap_size / e->efi_memdesc_size;
+	for (i = 0; i < nr_desc; i++) {
+		md = (efi_memory_desc_t *)(pmap + (i * e->efi_memdesc_size));
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			region.start = md->phys_addr;

arch/x86/boot/compressed/kaslr.c static void process_mem_region(struct mem_vector *entry, · line 610

Quoted 10 lines

arch/x86/boot/compressed/kaslr.c +10 -0

+			region.size = md->num_pages << EFI_PAGE_SHIFT;
+			process_mem_region(&region, minimum, image_size);
+			efi_mirror_found = true;
+
+			if (slot_area_index == MAX_SLOT_AREA) {
+				debug_putstr("Aborted EFI scan (slot_areas full)!\n");
+				break;
+			}
+		}
+	}

So I suggested this before: if you treat 'md' as an array of elements (which it is), then the type cast can be moved to a more natural point, where we do address calculations anyway:

	md = (efi_memory_desc_t *)(e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)));

The 'pmap' variable can be eliminated and all places in the loop that use 'md->' can use 'md[i].'.