Introduce bootblock self-decompression

Masked ROMs are the silent killers of boot speed on devices without
memory-mapped SPI flash. They often contain awfully slow SPI drivers
(presumably bit-banged) that take hundreds of milliseconds to load our
bootblock, and every extra kilobyte of bootblock size has a hugely
disproportionate impact on boot speed. The coreboot timestamps can never
show that component, but it impacts our users all the same.

This patch tries to alleviate that issue a bit by allowing us to
compress the bootblock with LZ4, which can cut its size down to nearly
half. Of course, masked ROMs usually don't come with decompression
algorithms built in, so we need to introduce a little decompression stub
that can decompress the rest of the bootblock. This is done by creating
a new "decompressor" stage which runs before the bootblock, but includes
the compressed bootblock code in its data section. It needs to be as
small as possible to get a real benefit from this approach, which means
no device drivers, no console output, no exception handling, etc.
Besides the decompression algorithm itself we only include the timer
driver so that we can measure the boot speed impact of decompression. On
ARM and ARM64 systems, we also need to give SoC code a chance to
initialize the MMU, since running decompression without MMU is
prohibitively slow on these architectures.

This feature is implemented for ARM and ARM64 architectures for now,
although most of it is architecture-independent and it should be
relatively simple to port to other platforms where a masked ROM loads
the bootblock into SRAM. It is also supposed to be a clean starting
point from which later optimizations can hopefully cut down the
decompression stub size (currently ~4K on RK3399) a bit more.

NOTE: Bootblock compression is not for everyone. Possible side effects
include trying to run LZ4 on CPUs that come out of reset extremely
underclocked or enabling this too early in SoC bring-up and getting
frustrated trying to find issues in an undebuggable environment. Ask
your SoC vendor if bootblock compression is right for you.

Change-Id: I0dc1cad9ae7508892e477739e743cd1afb5945e8
Signed-off-by: Julius Werner <jwerner@chromium.org>
Reviewed-on: https://review.coreboot.org/26340
Tested-by: build bot (Jenkins) <no-reply@coreboot.org>
Reviewed-by: Aaron Durbin <adurbin@chromium.org>

5 files changed, 55 insertions, 1 deletions

diff --git a/src/include/bootblock_common.h b/src/include/bootblock_common.h
index fa67098111..0f6c5e467f 100644
--- a/src/include/bootblock_common.h
+++ b/src/include/bootblock_common.h
@@ -26,6 +26,7 @@
  * The 'early' variants are called prior to console initialization. Also, the
  * SoC functions are called prior to the mainboard fucntions.
  */
+void decompressor_soc_init(void);
 void bootblock_mainboard_early_init(void);
 void bootblock_mainboard_init(void);
 void bootblock_soc_early_init(void);
@@ -47,4 +48,11 @@ asmlinkage void bootblock_c_entry(uint64_t base_timestamp);
 asmlinkage void bootblock_main_with_timestamp(uint64_t base_timestamp,
 	struct timestamp_entry *timestamps, size_t num_timestamps);
 
+/* This is the argument structure passed from decompressor to bootblock. */
+struct bootblock_arg {
+	uint64_t base_timestamp;
+	uint32_t num_timestamps;
+	struct timestamp_entry timestamps[];
+};
+
 #endif	/* __BOOTBLOCK_COMMON_H */
diff --git a/src/include/memlayout.h b/src/include/memlayout.h
index c9c77cfa5c..5de2370e4b 100644
--- a/src/include/memlayout.h
+++ b/src/include/memlayout.h
@@ -102,6 +102,26 @@
 #endif
 
 /* Careful: 'INCLUDE <filename>' must always be at the end of the output line */
+#if ENV_DECOMPRESSOR
+	#define DECOMPRESSOR(addr, sz) \
+		SYMBOL(decompressor, addr) \
+		_edecompressor = _decompressor + sz; \
+		_ = ASSERT(_eprogram - _program <= sz, \
+			STR(decompressor exceeded its allotted size! (sz))); \
+		INCLUDE "decompressor/lib/program.ld"
+
+	#define OVERLAP_DECOMPRESSOR_ROMSTAGE(addr, sz) DECOMPRESSOR(addr, sz)
+	#define OVERLAP_DECOMPRESSOR_VERSTAGE_ROMSTAGE(addr, sz) \
+		DECOMPRESSOR(addr, sz)
+#else
+	#define DECOMPRESSOR(addr, sz) \
+		REGION(decompressor, addr, sz, 1)
+
+	#define OVERLAP_DECOMPRESSOR_ROMSTAGE(addr, sz) ROMSTAGE(addr, sz)
+	#define OVERLAP_DECOMPRESSOR_VERSTAGE_ROMSTAGE(addr, sz) \
+		OVERLAP_VERSTAGE_ROMSTAGE(addr, sz)
+#endif
+
 #if ENV_BOOTBLOCK
 	#define BOOTBLOCK(addr, sz) \
 		SYMBOL(bootblock, addr) \
diff --git a/src/include/program_loading.h b/src/include/program_loading.h
index 5eeef530d2..e5d26e1d42 100644
--- a/src/include/program_loading.h
+++ b/src/include/program_loading.h
@@ -28,6 +28,7 @@ enum {
 
 enum prog_type {
 	PROG_UNKNOWN,
+	PROG_BOOTBLOCK,
 	PROG_VERSTAGE,
 	PROG_ROMSTAGE,
 	PROG_RAMSTAGE,
diff --git a/src/include/rules.h b/src/include/rules.h
index 4017d37ff5..deea50b977 100644
--- a/src/include/rules.h
+++ b/src/include/rules.h
@@ -19,7 +19,20 @@
  * romstage, ramstage or SMM.
  */
 
-#if defined(__BOOTBLOCK__)
+#if defined(__DECOMPRESSOR__)
+#define ENV_DECOMPRESSOR 1
+#define ENV_BOOTBLOCK 0
+#define ENV_ROMSTAGE 0
+#define ENV_RAMSTAGE 0
+#define ENV_SMM 0
+#define ENV_VERSTAGE 0
+#define ENV_RMODULE 0
+#define ENV_POSTCAR 0
+#define ENV_LIBAGESA 0
+#define ENV_STRING "decompressor"
+
+#elif defined(__BOOTBLOCK__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 1
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -31,6 +44,7 @@
 #define ENV_STRING "bootblock"
 
 #elif defined(__ROMSTAGE__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 1
 #define ENV_RAMSTAGE 0
@@ -42,6 +56,7 @@
 #define ENV_STRING "romstage"
 
 #elif defined(__SMM__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -53,6 +68,7 @@
 #define ENV_STRING "smm"
 
 #elif defined(__VERSTAGE__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -64,6 +80,7 @@
 #define ENV_STRING "verstage"
 
 #elif defined(__RAMSTAGE__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 1
@@ -75,6 +92,7 @@
 #define ENV_STRING "ramstage"
 
 #elif defined(__RMODULE__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -86,6 +104,7 @@
 #define ENV_STRING "rmodule"
 
 #elif defined(__POSTCAR__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -97,6 +116,7 @@
 #define ENV_STRING "postcar"
 
 #elif defined(__LIBAGESA__)
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
@@ -112,6 +132,7 @@
  * Default case of nothing set for random blob generation using
  * create_class_compiler that isn't bound to a stage.
  */
+#define ENV_DECOMPRESSOR 0
 #define ENV_BOOTBLOCK 0
 #define ENV_ROMSTAGE 0
 #define ENV_RAMSTAGE 0
diff --git a/src/include/symbols.h b/src/include/symbols.h
index 5b92899cee..fc9ef21ecf 100644
--- a/src/include/symbols.h
+++ b/src/include/symbols.h
@@ -68,6 +68,10 @@ extern u8 _eprogram[];
 
 /* _<stage>_size is always the maximum amount allocated in memlayout, whereas
  * _program_size gives the actual memory footprint *used* by current stage. */
+extern u8 _decompressor[];
+extern u8 _edecompressor[];
+#define _decompressor_size (_edecompressor - _decompressor)
+
 extern u8 _bootblock[];
 extern u8 _ebootblock[];
 #define _bootblock_size (_ebootblock - _bootblock)