[PATCH 2/2] arm64/efi: don't pad between EFI_MEMORY_RUNTIME regions

[Ard Biesheuvel]

The new Properties Table feature introduced in UEFIv2.5 may split
memory regions that cover PE/COFF memory images into separate code
and data regions.

Since the relative offset of PE/COFF .text and .data segments cannot
be changed on the fly, this means that we can no longer pad out those
regions to be mappable using 64 KB pages.
Unfortunately, there is no annotation in the UEFI memory map that
identifies data regions that were split off from a code region, so we
must apply this logic to all runtime code and data regions.

So instead of rounding each memory region to 64 KB alignment at both
ends, only round down regions that are not directly preceded by another
runtime region. Since the UEFI spec does not mandate that the memory map
be sorted, this means we also need to sort it first.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel at linaro.org>
---
 drivers/firmware/efi/libstub/arm-stub.c | 58 +++++++++++++++-----
 1 file changed, 43 insertions(+), 15 deletions(-)

diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index e29560e6b40b..dd9e2addc9fb 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/efi.h>
+#include <linux/sort.h>
 #include <asm/efi.h>
 
 #include "efistub.h"
@@ -305,6 +306,13 @@ fail:
  */
 #define EFI_RT_VIRTUAL_BASE	0x40000000
 
+static int cmp_mem_desc(const void *a, const void *b)
+{
+	efi_memory_desc_t const *left = a, *right = b;
+
+	return (left->phys_addr > right->phys_addr) ? 1 : -1;
+}
+
 /*
  * efi_get_virtmap() - create a virtual mapping for the EFI memory map
  *
@@ -317,33 +325,53 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
 		     int *count)
 {
 	u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
-	efi_memory_desc_t *out = runtime_map;
+	efi_memory_desc_t *in, *prev = NULL, *out = runtime_map;
 	int l;
 
-	for (l = 0; l < map_size; l += desc_size) {
-		efi_memory_desc_t *in = (void *)memory_map + l;
+	/*
+	 * To work around potential issues with the Properties Table feature
+	 * introduced in UEFI 2.5 (which may split PE/COFF memory images
+	 * into several RuntimeServicesCode and RuntimeServicesData regions
+	 * whose relative offset in memory needs to be retained), we need to
+	 * sort the memory map before traversing it, and avoid padding out those
+	 * regions to 64 KB granularity.
+	 */
+	sort(memory_map, map_size / desc_size, desc_size, cmp_mem_desc, NULL);
+
+	for (l = 0; l < map_size; l += desc_size, prev = in) {
 		u64 paddr, size;
 
+		in = (void *)memory_map + l;
 		if (!(in->attribute & EFI_MEMORY_RUNTIME))
 			continue;
 
+		paddr = in->phys_addr;
+		size = in->num_pages * EFI_PAGE_SIZE;
+
 		/*
 		 * Make the mapping compatible with 64k pages: this allows
 		 * a 4k page size kernel to kexec a 64k page size kernel and
 		 * vice versa.
 		 */
-		paddr = round_down(in->phys_addr, SZ_64K);
-		size = round_up(in->num_pages * EFI_PAGE_SIZE +
-				in->phys_addr - paddr, SZ_64K);
-
-		/*
-		 * Avoid wasting memory on PTEs by choosing a virtual base that
-		 * is compatible with section mappings if this region has the
-		 * appropriate size and physical alignment. (Sections are 2 MB
-		 * on 4k granule kernels)
-		 */
-		if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
-			efi_virt_base = round_up(efi_virt_base, SZ_2M);
+		if (!prev ||
+		    !(paddr == (prev->phys_addr +
+				prev->num_pages * EFI_PAGE_SIZE) &&
+		      (prev->attribute & EFI_MEMORY_RUNTIME))) {
+
+			paddr = round_down(in->phys_addr, SZ_64K);
+			size += in->phys_addr - paddr;
+
+			/*
+			 * Avoid wasting memory on PTEs by choosing a virtual
+			 * base that is compatible with section mappings if this
+			 * region has the appropriate size and physical
+			 * alignment. (Sections are 2 MB on 4k granule kernels)
+			 */
+			if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
+				efi_virt_base = round_up(efi_virt_base, SZ_2M);
+			else
+				efi_virt_base = round_up(efi_virt_base, SZ_64K);
+		}
 
 		in->virt_addr = efi_virt_base + in->phys_addr - paddr;
 		efi_virt_base += size;
-- 
1.9.1