From ccc97388778f9575bcd8de72f508eb8cb295f8fe Mon Sep 17 00:00:00 2001 From: Dave Higham Date: Tue, 21 Jan 2014 20:07:57 +0000 Subject: [PATCH] core/linux-imx6-cubox fixes via memset patch --- core/linux-imx6-cubox/PKGBUILD | 17 ++- core/linux-imx6-cubox/memset.patch | 204 +++++++++++++++++++++++++++++ 2 files changed, 215 insertions(+), 6 deletions(-) create mode 100644 core/linux-imx6-cubox/memset.patch diff --git a/core/linux-imx6-cubox/PKGBUILD b/core/linux-imx6-cubox/PKGBUILD index 0bd4e13e7..b1edb179e 100644 --- a/core/linux-imx6-cubox/PKGBUILD +++ b/core/linux-imx6-cubox/PKGBUILD @@ -10,12 +10,12 @@ buildarch=4 pkgbase=linux-imx6-cubox pkgname=('linux-imx6-cubox' 'linux-headers-imx6-cubox') # pkgname=linux-custom # Build kernel with a different name -_commit=da311d2e415b318673b6042bf9b0137bcfcb73b3 +_commit=be699c6777f376b5f28e60d8d65942ac94b39908 _srcname=linux-imx6-${_commit} _kernelname=${pkgname#linux} _basekernel=3.0 pkgver=${_basekernel}.35 -pkgrel=3 +pkgrel=5 arch=('arm') url="http://www.kernel.org/" license=('GPL2') @@ -24,10 +24,12 @@ options=('!strip') source=("https://github.com/solidrun/linux-imx6/archive/${_commit}.tar.gz" 'config' - 'change-default-console-loglevel.pat') -md5sums=('17c0223a6519e8763d216865f19f0ebe' - 'e261a171d58ac7ac04aeff8f3989dd1b' - '9d3c56a4b999c8bfbd4018089a62f662') + 'change-default-console-loglevel.pat' + 'memset.patch') +md5sums=('ec483c15c977807a87a98de633b3e410' + '6697f8ff6e73e6431c7ab3cf9d7c6e18' + '9d3c56a4b999c8bfbd4018089a62f662' + '39be2896f0b968d61a19b33da75ce6e0') prepare() { cd "${srcdir}/${_srcname}" @@ -45,6 +47,9 @@ prepare() { # (relevant patch sent upstream: https://lkml.org/lkml/2011/7/26/227) patch -Np1 -i "${srcdir}/change-default-console-loglevel.pat" + msg2 "Fix memset for GCC 4.8" + patch -p1 -i "${srcdir}/memset.patch" + } build() { diff --git a/core/linux-imx6-cubox/memset.patch b/core/linux-imx6-cubox/memset.patch new file mode 100644 index 000000000..a741741ab --- /dev/null +++ b/core/linux-imx6-cubox/memset.patch @@ -0,0 +1,204 @@ +--- a/arch/arm/lib/memset.S ++++ b/arch/arm/lib/memset.S +@@ -19,9 +19,9 @@ + 1: subs r2, r2, #4 @ 1 do we have enough + blt 5f @ 1 bytes to align with? + cmp r3, #2 @ 1 +- strltb r1, [r0], #1 @ 1 +- strleb r1, [r0], #1 @ 1 +- strb r1, [r0], #1 @ 1 ++ strltb r1, [ip], #1 @ 1 ++ strleb r1, [ip], #1 @ 1 ++ strb r1, [ip], #1 @ 1 + add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) + /* + * The pointer is now aligned and the length is adjusted. Try doing the +@@ -29,10 +29,14 @@ + */ + + ENTRY(memset) +- ands r3, r0, #3 @ 1 unaligned? ++/* ++ * Preserve the contents of r0 for the return value. ++ */ ++ mov ip, r0 ++ ands r3, ip, #3 @ 1 unaligned? + bne 1b @ 1 + /* +- * we know that the pointer in r0 is aligned to a word boundary. ++ * we know that the pointer in ip is aligned to a word boundary. + */ + orr r1, r1, r1, lsl #8 + orr r1, r1, r1, lsl #16 +@@ -43,29 +47,28 @@ ENTRY(memset) + #if ! CALGN(1)+0 + + /* +- * We need an extra register for this loop - save the return address and +- * use the LR ++ * We need 2 extra registers for this loop - use r8 and the LR + */ +- str lr, [sp, #-4]! +- mov ip, r1 ++ stmfd sp!, {r8, lr} ++ mov r8, r1 + mov lr, r1 + + 2: subs r2, r2, #64 +- stmgeia r0!, {r1, r3, ip, lr} @ 64 bytes at a time. +- stmgeia r0!, {r1, r3, ip, lr} +- stmgeia r0!, {r1, r3, ip, lr} +- stmgeia r0!, {r1, r3, ip, lr} ++ stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time. ++ stmgeia ip!, {r1, r3, r8, lr} ++ stmgeia ip!, {r1, r3, r8, lr} ++ stmgeia ip!, {r1, r3, r8, lr} + bgt 2b +- ldmeqfd sp!, {pc} @ Now <64 bytes to go. ++ ldmeqfd sp!, {r8, pc} @ Now <64 bytes to go. + /* + * No need to correct the count; we're only testing bits from now on + */ + tst r2, #32 +- stmneia r0!, {r1, r3, ip, lr} +- stmneia r0!, {r1, r3, ip, lr} ++ stmneia ip!, {r1, r3, r8, lr} ++ stmneia ip!, {r1, r3, r8, lr} + tst r2, #16 +- stmneia r0!, {r1, r3, ip, lr} +- ldr lr, [sp], #4 ++ stmneia ip!, {r1, r3, r8, lr} ++ ldmfd sp!, {r8, lr} + + #else + +@@ -74,54 +77,54 @@ ENTRY(memset) + * whole cache lines at once. + */ + +- stmfd sp!, {r4-r7, lr} ++ stmfd sp!, {r4-r8, lr} + mov r4, r1 + mov r5, r1 + mov r6, r1 + mov r7, r1 +- mov ip, r1 ++ mov r8, r1 + mov lr, r1 + + cmp r2, #96 +- tstgt r0, #31 ++ tstgt ip, #31 + ble 3f + +- and ip, r0, #31 +- rsb ip, ip, #32 +- sub r2, r2, ip +- movs ip, ip, lsl #(32 - 4) +- stmcsia r0!, {r4, r5, r6, r7} +- stmmiia r0!, {r4, r5} +- tst ip, #(1 << 30) +- mov ip, r1 +- strne r1, [r0], #4 ++ and r8, ip, #31 ++ rsb r8, r8, #32 ++ sub r2, r2, r8 ++ movs r8, r8, lsl #(32 - 4) ++ stmcsia ip!, {r4, r5, r6, r7} ++ stmmiia ip!, {r4, r5} ++ tst r8, #(1 << 30) ++ mov r8, r1 ++ strne r1, [ip], #4 + + 3: subs r2, r2, #64 +- stmgeia r0!, {r1, r3-r7, ip, lr} +- stmgeia r0!, {r1, r3-r7, ip, lr} ++ stmgeia ip!, {r1, r3-r8, lr} ++ stmgeia ip!, {r1, r3-r8, lr} + bgt 3b +- ldmeqfd sp!, {r4-r7, pc} ++ ldmeqfd sp!, {r4-r8, pc} + + tst r2, #32 +- stmneia r0!, {r1, r3-r7, ip, lr} ++ stmneia ip!, {r1, r3-r8, lr} + tst r2, #16 +- stmneia r0!, {r4-r7} +- ldmfd sp!, {r4-r7, lr} ++ stmneia ip!, {r4-r7} ++ ldmfd sp!, {r4-r8, lr} + + #endif + + 4: tst r2, #8 +- stmneia r0!, {r1, r3} ++ stmneia ip!, {r1, r3} + tst r2, #4 +- strne r1, [r0], #4 ++ strne r1, [ip], #4 + /* + * When we get here, we've got less than 4 bytes to zero. We + * may have an unaligned pointer as well. + */ + 5: tst r2, #2 +- strneb r1, [r0], #1 +- strneb r1, [r0], #1 ++ strneb r1, [ip], #1 ++ strneb r1, [ip], #1 + tst r2, #1 +- strneb r1, [r0], #1 ++ strneb r1, [ip], #1 + mov pc, lr + ENDPROC(memset) +--- a/arch/arm/lib/memset.S ++++ b/arch/arm/lib/memset.S +@@ -14,31 +14,15 @@ + + .text + .align 5 +- .word 0 +- +-1: subs r2, r2, #4 @ 1 do we have enough +- blt 5f @ 1 bytes to align with? +- cmp r3, #2 @ 1 +- strltb r1, [ip], #1 @ 1 +- strleb r1, [ip], #1 @ 1 +- strb r1, [ip], #1 @ 1 +- add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) +-/* +- * The pointer is now aligned and the length is adjusted. Try doing the +- * memset again. +- */ + + ENTRY(memset) +-/* +- * Preserve the contents of r0 for the return value. +- */ +- mov ip, r0 +- ands r3, ip, #3 @ 1 unaligned? +- bne 1b @ 1 ++ ands r3, r0, #3 @ 1 unaligned? ++ mov ip, r0 @ preserve r0 as return value ++ bne 6f @ 1 + /* + * we know that the pointer in ip is aligned to a word boundary. + */ +- orr r1, r1, r1, lsl #8 ++1: orr r1, r1, r1, lsl #8 + orr r1, r1, r1, lsl #16 + mov r3, r1 + cmp r2, #16 +@@ -127,4 +111,13 @@ ENTRY(memset) + tst r2, #1 + strneb r1, [ip], #1 + mov pc, lr ++ ++6: subs r2, r2, #4 @ 1 do we have enough ++ blt 5b @ 1 bytes to align with? ++ cmp r3, #2 @ 1 ++ strltb r1, [ip], #1 @ 1 ++ strleb r1, [ip], #1 @ 1 ++ strb r1, [ip], #1 @ 1 ++ add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3)) ++ b 1b + ENDPROC(memset)