efi: Handle memory error structures produced based on old versions of standard

The memory error record structure includes as its first field a
bitmask of which subsequent fields are valid. The allows new fields
to be added to the structure while keeping compatibility with older
software that parses these records. This mechanism was used between
versions 2.2 and 2.3 to add four new fields, growing the size of the
structure from 73 bytes to 80. But Linux just added all the new
fields so this test:
	if (gdata->error_data_length >= sizeof(*mem_err))
		cper_print_mem(newpfx, mem_err);
	else
		goto err_section_too_small;
now make Linux complain about old format records being too short.

Add a definition for the old format of the structure and use that
for the minimum size check. Pass the actual size to cper_print_mem()
so it can sanity check the validation_bits field to ensure that if
a BIOS using the old format sets bits as if it were new, we won't
access fields beyond the end of the structure.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

drivers/firmware/efi/cper.c

@@ -305,10 +305,17 @@ const char *cper_mem_err_unpack(struct trace_seq *p,
 	return ret;
 }
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
+	int len)
 {
 	struct cper_mem_err_compact cmem;
 
+	/* Don't trust UEFI 2.1/2.2 structure with bad validation bits */
+	if (len == sizeof(struct cper_sec_mem_err_old) &&
+	    (mem->validation_bits & ~(CPER_MEM_VALID_RANK_NUMBER - 1))) {
+		pr_err(FW_WARN "valid bits set for fields beyond structure\n");
+		return;
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
@@ -405,8 +412,10 @@ static void cper_estatus_print_section(
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
 		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
 		printk("%s""section_type: memory error\n", newpfx);
-		if (gdata->error_data_length >= sizeof(*mem_err))
-			cper_print_mem(newpfx, mem_err);
+		if (gdata->error_data_length >=
+		    sizeof(struct cper_sec_mem_err_old))
+			cper_print_mem(newpfx, mem_err,
+				       gdata->error_data_length);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {

include/linux/cper.h

@@ -340,7 +340,27 @@ struct cper_ia_proc_ctx {
 	__u64	mm_reg_addr;
 };
 
-/* Memory Error Section */
+/* Old Memory Error Section UEFI 2.1, 2.2 */
+struct cper_sec_mem_err_old {
+	__u64	validation_bits;
+	__u64	error_status;
+	__u64	physical_addr;
+	__u64	physical_addr_mask;
+	__u16	node;
+	__u16	card;
+	__u16	module;
+	__u16	bank;
+	__u16	device;
+	__u16	row;
+	__u16	column;
+	__u16	bit_pos;
+	__u64	requestor_id;
+	__u64	responder_id;
+	__u64	target_id;
+	__u8	error_type;
+};
+
+/* Memory Error Section UEFI >= 2.3 */
 struct cper_sec_mem_err {
 	__u64	validation_bits;
 	__u64	error_status;