cbfs: Add LZ4 in-place decompression support for pre-RAM stages

This patch ports the LZ4 decompression code that debuted in libpayload
last year to coreboot for use in CBFS stages (upgrading the base
algorithm to LZ4's dev branch to access the new in-place decompression
checks). This is especially useful for pre-RAM stages in constrained
SRAM-based systems, which previously could not be compressed due to
the size requirements of the LZMA scratchpad and bounce buffer. The
LZ4 algorithm offers a very lean decompressor function and in-place
decompression support to achieve roughly the same boot speed gains
(trading compression ratio for decompression time) with nearly no
memory overhead.

For now we only activate it for the stages that had previously not been
compressed at all on non-XIP (read: non-x86) boards. In the future we
may also consider replacing LZMA completely for certain boards, since
which algorithm wins out on boot speed depends on board-specific
parameters (architecture, processor speed, SPI transfer rate, etc.).

BRANCH=None
BUG=None
TEST=Built and booted Oak, Jerry, Nyan and Falco. Measured boot time on
Oak to be about ~20ms faster (cutting load times for affected stages
almost in half).

Change-Id: Iec256c0e6d585d1b69985461939884a54e3ab900
Signed-off-by: Julius Werner <jwerner@chromium.org>
Reviewed-on: https://review.coreboot.org/13638
Tested-by: build bot (Jenkins)
Reviewed-by: Aaron Durbin <adurbin@chromium.org>

1 files changed, 38 insertions, 0 deletions

diff --git a/util/cbfstool/cbfs-mkstage.c b/util/cbfstool/cbfs-mkstage.c
index 9d8865828e..53d3edbd3e 100644
--- a/util/cbfstool/cbfs-mkstage.c
+++ b/util/cbfstool/cbfs-mkstage.c
@@ -26,6 +26,8 @@
 #include "cbfs.h"
 #include "rmodule.h"
 
+#include <commonlib/compression.h>
+
 /* Checks if program segment contains the ignored section */
 static int is_phdr_ignored(Elf64_Phdr *phdr, Elf64_Shdr *shdr)
 {
@@ -267,8 +269,44 @@ int parse_elf_to_stage(const struct buffer *input, struct buffer *output,
 		     "- disabled.\n");
 		memcpy(output->data + sizeof(struct cbfs_stage),
 		       buffer, data_end - data_start);
+		outlen = data_end - data_start;
 		algo = CBFS_COMPRESS_NONE;
 	}
+
+	/* Check for enough BSS scratch space to decompress LZ4 in-place. */
+	if (algo == CBFS_COMPRESS_LZ4) {
+		size_t result;
+		size_t memlen = mem_end - data_start;
+		size_t compressed_size = outlen;
+		char *compare_buffer = malloc(memlen);
+		char *start = compare_buffer + memlen - compressed_size;
+
+		if (compare_buffer == NULL) {
+			ERROR("Can't allocate memory!\n");
+			free(buffer);
+			goto err;
+		}
+
+		memcpy(start, output->data + sizeof(struct cbfs_stage),
+		       compressed_size);
+		result = ulz4fn(start, compressed_size, compare_buffer, memlen);
+
+		if (result == 0) {
+			ERROR("Not enough scratch space to decompress LZ4 in-place -- increase BSS size or disable compression!\n");
+			free(compare_buffer);
+			free(buffer);
+			goto err;
+		}
+		if (result != data_end - data_start ||
+		    memcmp(compare_buffer, buffer, data_end - data_start)) {
+			ERROR("LZ4 compression BUG! Report to mailing list.\n");
+			free(compare_buffer);
+			free(buffer);
+			goto err;
+		}
+		free(compare_buffer);
+	}
+
 	free(buffer);
 
 	/* Set up for output marshaling. */