linux_dsm_epyc7002/arch/arm/mm/cache-v4wt.S

206 lines
4.6 KiB
ArmAsm
Raw Normal View History

/*
* linux/arch/arm/mm/cache-v4wt.S
*
* Copyright (C) 1997-2002 Russell king
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* ARMv4 write through cache operations support.
*
* We assume that the write buffer is not enabled.
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/page.h>
#include "proc-macros.S"
/*
* The size of one data cache line.
*/
#define CACHE_DLINESIZE 32
/*
* The number of data cache segments.
*/
#define CACHE_DSEGMENTS 8
/*
* The number of lines in a cache segment.
*/
#define CACHE_DENTRIES 64
/*
* This is the size at which it becomes more efficient to
* clean the whole cache, rather than using the individual
* cache line maintenance instructions.
*
* *** This needs benchmarking
*/
#define CACHE_DLIMIT 16384
ARM: 6466/1: implement flush_icache_all for the rest of the CPUs Commit 81d11955bf0 ("ARM: 6405/1: Handle __flush_icache_all for CONFIG_SMP_ON_UP") added a new function to struct cpu_cache_fns: flush_icache_all(). It also implemented this for v6 and v7 but not for v5 and backwards. Without the function pointer in place, we will be calling wrong cache functions. For example with ep93xx we get following: Unable to handle kernel paging request at virtual address ee070f38 pgd = c0004000 [ee070f38] *pgd=00000000 Internal error: Oops: 80000005 [#1] PREEMPT last sysfs file: Modules linked in: CPU: 0 Not tainted (2.6.36+ #1) PC is at 0xee070f38 LR is at __dma_alloc+0x11c/0x2d0 pc : [<ee070f38>] lr : [<c0032c8c>] psr: 60000013 sp : c581bde0 ip : 00000000 fp : c0472000 r10: c0472000 r9 : 000000d0 r8 : 00020000 r7 : 0001ffff r6 : 00000000 r5 : c0472400 r4 : c5980000 r3 : c03ab7e0 r2 : 00000000 r1 : c59a0000 r0 : c5980000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: c000717f Table: c0004000 DAC: 00000017 Process swapper (pid: 1, stack limit = 0xc581a270) [<c0032c8c>] (__dma_alloc+0x11c/0x2d0) [<c0032e5c>] (dma_alloc_writecombine+0x1c/0x24) [<c0204148>] (ep93xx_pcm_preallocate_dma_buffer+0x44/0x60) [<c02041c0>] (ep93xx_pcm_new+0x5c/0x88) [<c01ff188>] (snd_soc_instantiate_cards+0x8a8/0xbc0) [<c01ff59c>] (soc_probe+0xfc/0x134) [<c01adafc>] (platform_drv_probe+0x18/0x1c) [<c01acca4>] (driver_probe_device+0xb0/0x16c) [<c01ac284>] (bus_for_each_drv+0x48/0x84) [<c01ace90>] (device_attach+0x50/0x68) [<c01ac0f8>] (bus_probe_device+0x24/0x44) [<c01aad7c>] (device_add+0x2fc/0x44c) [<c01adfa8>] (platform_device_add+0x104/0x15c) [<c0015eb8>] (simone_init+0x60/0x94) [<c0021410>] (do_one_initcall+0xd0/0x1a4) __dma_alloc() calls (inlined) __dma_alloc_buffer() which ends up calling dmac_flush_range(). Now since the entries in the arm920_cache_fns are shifted by one, we jump into address 0xee070f38 which is actually next instruction after the arm920_cache_fns structure. So implement flush_icache_all() for the rest of the supported CPUs using a generic 'invalidate I cache' instruction. Signed-off-by: Mika Westerberg <mika.westerberg@iki.fi> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-10-28 17:27:40 +07:00
/*
* flush_icache_all()
*
* Unconditionally clean and invalidate the entire icache.
*/
ENTRY(v4wt_flush_icache_all)
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
mov pc, lr
ENDPROC(v4wt_flush_icache_all)
/*
* flush_user_cache_all()
*
* Invalidate all cache entries in a particular address
* space.
*/
ENTRY(v4wt_flush_user_cache_all)
/* FALLTHROUGH */
/*
* flush_kern_cache_all()
*
* Clean and invalidate the entire cache.
*/
ENTRY(v4wt_flush_kern_cache_all)
mov r2, #VM_EXEC
mov ip, #0
__flush_whole_cache:
tst r2, #VM_EXEC
mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache
mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache
mov pc, lr
/*
* flush_user_cache_range(start, end, flags)
*
* Clean and invalidate a range of cache entries in the specified
* address space.
*
* - start - start address (inclusive, page aligned)
* - end - end address (exclusive, page aligned)
* - flags - vma_area_struct flags describing address space
*/
ENTRY(v4wt_flush_user_cache_range)
sub r3, r1, r0 @ calculate total size
cmp r3, #CACHE_DLIMIT
bhs __flush_whole_cache
1: mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
tst r2, #VM_EXEC
mcrne p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
mov pc, lr
/*
* coherent_kern_range(start, end)
*
* Ensure coherency between the Icache and the Dcache in the
* region described by start. If you have non-snooping
* Harvard caches, you need to implement this function.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(v4wt_coherent_kern_range)
/* FALLTRHOUGH */
/*
* coherent_user_range(start, end)
*
* Ensure coherency between the Icache and the Dcache in the
* region described by start. If you have non-snooping
* Harvard caches, you need to implement this function.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(v4wt_coherent_user_range)
bic r0, r0, #CACHE_DLINESIZE - 1
1: mcr p15, 0, r0, c7, c5, 1 @ invalidate I entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
mov r0, #0
mov pc, lr
/*
* flush_kern_dcache_area(void *addr, size_t size)
*
* Ensure no D cache aliasing occurs, either with itself or
* the I cache
*
* - addr - kernel address
* - size - region size
*/
ENTRY(v4wt_flush_kern_dcache_area)
mov r2, #0
mcr p15, 0, r2, c7, c5, 0 @ invalidate I cache
add r1, r0, r1
/* fallthrough */
/*
* dma_inv_range(start, end)
*
* Invalidate (discard) the specified virtual address range.
* May not write back any entries. If 'start' or 'end'
* are not cache line aligned, those lines must be written
* back.
*
* - start - virtual start address
* - end - virtual end address
*/
v4wt_dma_inv_range:
bic r0, r0, #CACHE_DLINESIZE - 1
1: mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
mov pc, lr
/*
* dma_flush_range(start, end)
*
* Clean and invalidate the specified virtual address range.
*
* - start - virtual start address
* - end - virtual end address
*/
.globl v4wt_dma_flush_range
.equ v4wt_dma_flush_range, v4wt_dma_inv_range
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v4wt_dma_unmap_area)
add r1, r1, r0
teq r2, #DMA_TO_DEVICE
bne v4wt_dma_inv_range
/* FALLTHROUGH */
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v4wt_dma_map_area)
mov pc, lr
ENDPROC(v4wt_dma_unmap_area)
ENDPROC(v4wt_dma_map_area)
ARM: mm: implement LoUIS API for cache maintenance ops ARM v7 architecture introduced the concept of cache levels and related control registers. New processors like A7 and A15 embed an L2 unified cache controller that becomes part of the cache level hierarchy. Some operations in the kernel like cpu_suspend and __cpu_disable do not require a flush of the entire cache hierarchy to DRAM but just the cache levels belonging to the Level of Unification Inner Shareable (LoUIS), which in most of ARM v7 systems correspond to L1. The current cache flushing API used in cpu_suspend and __cpu_disable, flush_cache_all(), ends up flushing the whole cache hierarchy since for v7 it cleans and invalidates all cache levels up to Level of Coherency (LoC) which cripples system performance when used in hot paths like hotplug and cpuidle. Therefore a new kernel cache maintenance API must be added to cope with latest ARM system requirements. This patch adds flush_cache_louis() to the ARM kernel cache maintenance API. This function cleans and invalidates all data cache levels up to the Level of Unification Inner Shareable (LoUIS) and invalidates the instruction cache for processors that support it (> v7). This patch also creates an alias of the cache LoUIS function to flush_kern_all for all processor versions prior to v7, so that the current cache flushing behaviour is unchanged for those processors. v7 cache maintenance code implements a cache LoUIS function that cleans and invalidates the D-cache up to LoUIS and invalidates the I-cache, according to the new API. Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Shawn Guo <shawn.guo@linaro.org>
2012-09-06 20:05:13 +07:00
.globl v4wt_flush_kern_cache_louis
.equ v4wt_flush_kern_cache_louis, v4wt_flush_kern_cache_all
__INITDATA
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions v4wt