From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.lixom.net (lixom.net [66.141.50.11]) by ozlabs.org (Postfix) with ESMTP id 07404DDE21 for ; Thu, 15 Nov 2007 08:27:21 +1100 (EST) Date: Wed, 14 Nov 2007 15:28:23 -0600 From: Olof Johansson To: Benjamin Herrenschmidt Subject: [PATCH v2] [POWERPC] vdso: Fixes for cache block sizes Message-ID: <20071114212823.GA3044@lixom.net> References: <20071114192405.GA1637@lixom.net> <1195072102.28865.41.camel@pasglop> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <1195072102.28865.41.camel@pasglop> Cc: dwmw2@infradead.org, paulus@samba.org, linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , [POWERPC] vdso: Fixes for cache line sizes Current VDSO implementation is hardcoded to 128 byte cache blocks, which are only used on IBM's 64-bit processors. Convert it to get the blocks sizes out of vdso_data instead, similar to how the ppc64 in-kernel cache flush does it. Signed-off-by: Olof Johansson --- Paul, this is needed to make for example the IBM jvm run on pa6t. Please include as bugfix for 2.6.24. On Thu, Nov 15, 2007 at 07:28:22AM +1100, Benjamin Herrenschmidt wrote: > > On Wed, 2007-11-14 at 13:24 -0600, Olof Johansson wrote: > > [POWERPC] vdso: Fixes for cache line sizes > > > > Current VDSO implementation is hardcoded to 128 byte cachelines, which > > only works on IBM's 64-bit processors. > > > > Convert it to get the line sizes out of vdso_data instead, similar to > > how the ppc64 in-kernel cache flush does it. > > Please call the fields "block size" not "line size". There are subtle > differences and per architecture, it should really be block size. Alright. I've added block sizes since I'm not sure whether the old systemcfg data is actually line or block sizes, and I guess it's something we need to stay compatible with. See separate new patch. Also, ppc64_caches only has line sizes, so fill it with that for now. I'll submit a separate patch to complete ppc64_caches with block sizes, but that's a cleanup not a bug fix (i.e. target for that would be 2.6.25). > > Paul, this is needed to make for example the IBM jvm run on pa6t. Please > > include as bugfix for 2.6.24. > > Heh, they use the vdso for flushes ? I didn't know that ! Me neither, and the fact that the vdso was hardcoded for 128 had completely passed me by. -Olof diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 2c8e756..d67bcd8 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -284,6 +284,10 @@ int main(void) DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); + DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size)); + DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size)); + DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size)); + DEFINE(CFG_DCACHE_LOGBLOCKSZ, offsetof(struct vdso_data, dcache_log_block_size)); #ifdef CONFIG_PPC64 DEFINE(CFG_SYSCALL_MAP64, offsetof(struct vdso_data, syscall_map_64)); DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec)); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 2322ba5..3702df7 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -699,11 +699,22 @@ static int __init vdso_init(void) vdso_data->icache_size = ppc64_caches.isize; vdso_data->icache_line_size = ppc64_caches.iline_size; + /* XXXOJN: Blocks should be added to ppc64_caches and used instead */ + vdso_data->dcache_block_size = ppc64_caches.dline_size; + vdso_data->icache_block_size = ppc64_caches.iline_size; + vdso_data->dcache_log_block_size = ppc64_caches.log_dline_size; + vdso_data->icache_log_block_size = ppc64_caches.log_iline_size; + /* * Calculate the size of the 64 bits vDSO */ vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT; DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages); +#else + vdso_data->dcache_block_size = L1_CACHE_BYTES; + vdso_data->dcache_log_block_size = L1_CACHE_SHIFT; + vdso_data->icache_block_size = L1_CACHE_BYTES; + vdso_data->icache_log_block_size = L1_CACHE_SHIFT; #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index 9cb3199..99a76f7 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -23,29 +23,44 @@ * * Flushes the data cache & invalidate the instruction cache for the * provided range [start, end[ - * - * Note: all CPUs supported by this kernel have a 128 bytes cache - * line size so we don't have to peek that info from the datapage */ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc - li r5,127 - andc r6,r3,r5 /* round low to line bdy */ + mflr r12 + .cfi_register lr,r12 + mr r11,r3 + bl __get_datapage@local + mtlr r12 + mr r10,r3 + + lwz r7,CFG_DCACHE_BLOCKSZ(r10) + addi r5,r7,-1 + andc r6,r11,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - srwi. r8,r8,7 /* compute line count */ - crclr cr0*4+so + lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) + srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 - mr r3,r6 -1: dcbst 0,r3 - addi r3,r3,128 +1: dcbst 0,r6 + add r6,r6,r7 bdnz 1b sync + +/* Now invalidate the instruction cache */ + + lwz r7,CFG_ICACHE_BLOCKSZ(r10) + addi r5,r7,-1 + andc r6,r11,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 + lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ mtctr r8 -1: icbi 0,r6 - addi r6,r6,128 - bdnz 1b +2: icbi 0,r6 + add r6,r6,r7 + bdnz 2b isync li r3,0 blr diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 66a36d3..6ed5916 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -23,29 +23,44 @@ * * Flushes the data cache & invalidate the instruction cache for the * provided range [start, end[ - * - * Note: all CPUs supported by this kernel have a 128 bytes cache - * line size so we don't have to peek that info from the datapage */ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc - li r5,127 - andc r6,r3,r5 /* round low to line bdy */ + mflr r12 + .cfi_register lr,r12 + mr r11,r3 + bl V_LOCAL_FUNC(__get_datapage) + mtlr r12 + mr r10,r3 + + lwz r7,CFG_DCACHE_BLOCKSZ(r10) + addi r5,r7,-1 + andc r6,r11,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ - srwi. r8,r8,7 /* compute line count */ - crclr cr0*4+so + lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) + srw. r8,r8,r9 /* compute line count */ beqlr /* nothing to do? */ mtctr r8 - mr r3,r6 -1: dcbst 0,r3 - addi r3,r3,128 +1: dcbst 0,r6 + add r6,r6,r7 bdnz 1b sync + +/* Now invalidate the instruction cache */ + + lwz r7,CFG_ICACHE_BLOCKSZ(r10) + addi r5,r7,-1 + andc r6,r11,r5 /* round low to line bdy */ + subf r8,r6,r4 /* compute length */ + add r8,r8,r5 + lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) + srw. r8,r8,r9 /* compute line count */ + beqlr /* nothing to do? */ mtctr r8 -1: icbi 0,r6 - addi r6,r6,128 - bdnz 1b +2: icbi 0,r6 + add r6,r6,r7 + bdnz 2b isync li r3,0 blr diff --git a/include/asm-powerpc/vdso_datapage.h b/include/asm-powerpc/vdso_datapage.h index 8a94f0e..f013932 100644 --- a/include/asm-powerpc/vdso_datapage.h +++ b/include/asm-powerpc/vdso_datapage.h @@ -77,6 +77,10 @@ struct vdso_data { /* those additional ones don't have to be located anywhere * special as they were not part of the original systemcfg */ + __u32 dcache_block_size; /* L1 d-cache block size */ + __u32 icache_block_size; /* L1 i-cache block size */ + __u32 dcache_log_block_size; /* L1 d-cache log block size */ + __u32 icache_log_block_size; /* L1 i-cache log block size */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ @@ -99,6 +103,10 @@ struct vdso_data { __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ + __u32 dcache_block_size; /* L1 d-cache block size */ + __u32 icache_block_size; /* L1 i-cache block size */ + __u32 dcache_log_block_size; /* L1 d-cache log block size */ + __u32 icache_log_block_size; /* L1 i-cache log block size */ }; #endif /* CONFIG_PPC64 */