From 3bd2cbb95543acf44fe123eb9f038de54e655eb4 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 21 Apr 2011 21:45:08 -0400 Subject: ARM: zImage: make sure the stack is 64-bit aligned With ARMv5+ and EABI, the compiler expects a 64-bit aligned stack so instructions like STRD and LDRD can be used. Without this, mysterious boot failures were seen semi randomly with the LZMA decompressor. While at it, let's align .bss as well. Signed-off-by: Nicolas Pitre Tested-by: Shawn Guo Acked-by: Tony Lindgren CC: stable@kernel.org diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 8ebbb51..0c6852d 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -74,7 +74,7 @@ ZTEXTADDR := $(CONFIG_ZBOOT_ROM_TEXT) ZBSSADDR := $(CONFIG_ZBOOT_ROM_BSS) else ZTEXTADDR := 0 -ZBSSADDR := ALIGN(4) +ZBSSADDR := ALIGN(8) endif SEDFLAGS = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/ diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in index 5309909..ea80abe 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.in +++ b/arch/arm/boot/compressed/vmlinux.lds.in @@ -54,6 +54,7 @@ SECTIONS .bss : { *(.bss) } _end = .; + . = ALIGN(8); /* the stack must be 64-bit aligned */ .stack : { *(.stack) } .stab 0 : { *(.stab) } -- cgit v0.10.2 From 7c2527f0c4bf6bd096f58296597e1373387d69fd Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 26 Apr 2011 05:37:46 -0700 Subject: ARM: zImage: Fix bad SP address after relocating kernel Otherwise cache_clean_flush can overwrite some of the relocated area depending on where the kernel image gets loaded. This fixes booting on n900 after commit 6d7d0ae51574943bf571d269da3243257a2d15db (ARM: 6750/1: improvements to compressed/head.S). Thanks to Aaro Koskinen for debugging the address of the relocated area that gets corrupted, and to Nicolas Pitre for the other uncompress related fixes. Signed-off-by: Tony Lindgren Signed-off-by: Nicolas Pitre diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 84ac4d6..55a5bcb 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -253,6 +253,11 @@ restart: adr r0, LC0 /* Preserve offset to relocated code. */ sub r6, r9, r6 +#ifndef CONFIG_ZBOOT_ROM + /* cache_clean_flush may use the stack, so relocate it */ + add sp, sp, r6 +#endif + bl cache_clean_flush adr r0, BSYM(restart) -- cgit v0.10.2 From adcc25915b98e5752d51d66774ec4a61e50af3c5 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 27 Apr 2011 16:15:11 -0400 Subject: ARM: zImage: make sure not to relocate on top of the relocation code If the zImage load address is slightly below the relocation address, there is a risk for the copied data to overwrite the copy loop or cache flush code that the relocation process requires. Always bump the relocation address by the size of that code to avoid this issue. Noticed by Tony Lindgren . While at it, let's start the copy from the restart symbol which makes the above code size computation possible by the assembler directly (same sections), given that we don't need to preserve the code before that point anyway. And therefore we don't need to carry the _start pointer in r5 anymore. Signed-off-by: Nicolas Pitre Tested-by: Tony Lindgren diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 55a5bcb..53dd5da 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -187,15 +187,14 @@ not_angel: bl cache_on restart: adr r0, LC0 - ldmia r0, {r1, r2, r3, r5, r6, r9, r11, r12} - ldr sp, [r0, #32] + ldmia r0, {r1, r2, r3, r6, r9, r11, r12} + ldr sp, [r0, #28] /* * We might be running at a different address. We need * to fix up various pointers. */ sub r0, r0, r1 @ calculate the delta offset - add r5, r5, r0 @ _start add r6, r6, r0 @ _edata #ifndef CONFIG_ZBOOT_ROM @@ -214,31 +213,39 @@ restart: adr r0, LC0 /* * Check to see if we will overwrite ourselves. * r4 = final kernel address - * r5 = start of this image * r9 = size of decompressed image * r10 = end of this image, including bss/stack/malloc space if non XIP * We basically want: * r4 >= r10 -> OK - * r4 + image length <= r5 -> OK + * r4 + image length <= current position (pc) -> OK */ cmp r4, r10 bhs wont_overwrite add r10, r4, r9 - cmp r10, r5 + ARM( cmp r10, pc ) + THUMB( mov lr, pc ) + THUMB( cmp r10, lr ) bls wont_overwrite /* * Relocate ourselves past the end of the decompressed kernel. - * r5 = start of this image * r6 = _edata * r10 = end of the decompressed kernel * Because we always copy ahead, we need to do it from the end and go * backward in case the source and destination overlap. */ - /* Round up to next 256-byte boundary. */ - add r10, r10, #256 + /* + * Bump to the next 256-byte boundary with the size of + * the relocation code added. This avoids overwriting + * ourself when the offset is small. + */ + add r10, r10, #((reloc_code_end - restart + 256) & ~255) bic r10, r10, #255 + /* Get start of code we want to copy and align it down. */ + adr r5, restart + bic r5, r5, #31 + sub r9, r6, r5 @ size to copy add r9, r9, #31 @ rounded up to a multiple bic r9, r9, #31 @ ... of 32 bytes @@ -346,7 +353,6 @@ not_relocated: mov r0, #0 LC0: .word LC0 @ r1 .word __bss_start @ r2 .word _end @ r3 - .word _start @ r5 .word _edata @ r6 .word _image_size @ r9 .word _got_start @ r11 @@ -1075,6 +1081,7 @@ memdump: mov r12, r0 #endif .ltorg +reloc_code_end: .align .section ".stack", "aw", %nobits -- cgit v0.10.2 From ea9df3b168e641e87dbf889afae16390119e4179 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 21 Apr 2011 22:52:06 -0400 Subject: ARM: zImage: the page table memory must be considered before relocation For correctness, the initial page table located right before the decompressed kernel should be considered when determining if relocation is required. Signed-off-by: Nicolas Pitre Tested-by: Shawn Guo Acked-by: Tony Lindgren diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 53dd5da..d1fd1cf 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -216,9 +216,10 @@ restart: adr r0, LC0 * r9 = size of decompressed image * r10 = end of this image, including bss/stack/malloc space if non XIP * We basically want: - * r4 >= r10 -> OK + * r4 - 16k page directory >= r10 -> OK * r4 + image length <= current position (pc) -> OK */ + add r10, r10, #16384 cmp r4, r10 bhs wont_overwrite add r10, r4, r9 -- cgit v0.10.2