linux_dsm_epyc7002/arch/mips/mm/cache.c

241 lines
7.0 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1994 - 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
* Copyright (C) 2007 MIPS Technologies, Inc.
*/
#include <linux/fs.h>
#include <linux/fcntl.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/mm.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/cpu.h>
#include <asm/cpu-features.h>
/* Cache operations. */
void (*flush_cache_all)(void);
void (*__flush_cache_all)(void);
void (*flush_cache_mm)(struct mm_struct *mm);
void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page,
unsigned long pfn);
void (*flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(flush_icache_range);
void (*local_flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(local_flush_icache_range);
void (*__flush_cache_vmap)(void);
void (*__flush_cache_vunmap)(void);
void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range);
void (*__invalidate_kernel_vmap_range)(unsigned long vaddr, int size);
/* MIPS specific cache operations */
void (*flush_cache_sigtramp)(unsigned long addr);
void (*local_flush_data_cache_page)(void * addr);
void (*flush_data_cache_page)(unsigned long addr);
void (*flush_icache_all)(void);
EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
EXPORT_SYMBOL(flush_data_cache_page);
EXPORT_SYMBOL(flush_icache_all);
#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
/* DMA cache operations. */
void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
void (*_dma_cache_wback)(unsigned long start, unsigned long size);
void (*_dma_cache_inv)(unsigned long start, unsigned long size);
EXPORT_SYMBOL(_dma_cache_wback_inv);
#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
/*
* We could optimize the case where the cache argument is not BCACHE but
* that seems very atypical use ...
*/
SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
unsigned int, cache)
{
if (bytes == 0)
return 0;
if (!access_ok(VERIFY_WRITE, (void __user *) addr, bytes))
return -EFAULT;
flush_icache_range(addr, addr + bytes);
return 0;
}
void __flush_dcache_page(struct page *page)
{
struct address_space *mapping = page_mapping(page);
unsigned long addr;
[MIPS] Retire flush_icache_page from mm use. On the 34K the redundant cache operations were causing excessive stalls resulting in realtime code running on the second VPE missing its deadline. For all other platforms this patch is just a significant performance improvment as illustrated by below benchmark numbers. Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 25Kf 2.6.18-rc4 533 0.49 1.16 7.57 33.4 30.5 1.34 12.4 5497 17.K 54.K 25Kf 2.6.18-rc4-p 533 0.49 1.16 6.68 23.0 30.7 1.36 8.55 5030 16.K 48.K 4Kc 2.6.18-rc4 80 4.21 15.0 131. 289. 261. 16.5 258. 18.K 70.K 227K 4Kc 2.6.18-rc4-p 80 4.34 13.1 128. 285. 262. 18.2 258. 12.K 52.K 176K 34Kc 2.6.18-rc4 40 5.01 14.0 61.6 90.0 477. 17.9 94.7 29.K 108K 342K 34Kc 2.6.18-rc4-p 40 4.98 13.9 61.2 89.7 475. 17.6 93.7 8758 44.K 158K BCM1480 2.6.18-rc4 700 0.28 0.60 3.68 5.92 16.0 0.78 5.08 931. 3163 15.K BCM1480 2.6.18-rc4-p 700 0.28 0.61 3.65 5.85 16.0 0.79 5.20 395. 1464 8385 TX49-16K 2.6.18-rc3 197 0.73 2.41 19.0 37.8 82.9 2.94 17.5 4438 14.K 56.K TX49-16K 2.6.18-rc3-p 197 0.73 2.40 19.9 36.3 82.9 2.94 23.4 2577 9103 38.K TX49-32K 2.6.18-rc3 396 0.36 1.19 6.80 11.8 41.0 1.46 8.17 2738 8465 32.K TX49-32K 2.6.18-rc3-p 396 0.36 1.19 6.82 10.2 41.0 1.46 8.18 1330 4638 18.K Original patch by me with enhancements by Atsushi Nemoto. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
2006-08-12 22:40:08 +07:00
if (PageHighMem(page))
return;
if (mapping && !mapping_mapped(mapping)) {
SetPageDcacheDirty(page);
return;
}
/*
* We could delay the flush for the !page_mapping case too. But that
* case is for exec env/arg pages and those are %99 certainly going to
* get faulted into the tlb (and thus flushed) anyways.
*/
addr = (unsigned long) page_address(page);
flush_data_cache_page(addr);
}
EXPORT_SYMBOL(__flush_dcache_page);
void __flush_anon_page(struct page *page, unsigned long vmaddr)
{
unsigned long addr = (unsigned long) page_address(page);
if (pages_do_alias(addr, vmaddr)) {
if (page_mapped(page) && !Page_dcache_dirty(page)) {
void *kaddr;
kaddr = kmap_coherent(page, vmaddr);
flush_data_cache_page((unsigned long)kaddr);
kunmap_coherent();
} else
flush_data_cache_page(addr);
}
}
EXPORT_SYMBOL(__flush_anon_page);
MIPS: Fix race condition in lazy cache flushing. The lazy cache flushing implemented in the MIPS kernel suffers from a race condition that is exposed by do_set_pte() in mm/memory.c. A pre-condition is a file-system that writes to the page from the CPU in its readpage method and then calls flush_dcache_page(). One example is ubifs. Another pre-condition is that the dcache flush is postponed in __flush_dcache_page(). Upon a page fault for an executable mapping not existing in the page-cache, the following will happen: 1. Write to the page 2. flush_dcache_page 3. flush_icache_page 4. set_pte_at 5. update_mmu_cache (commits the flush of a dcache-dirty page) Between steps 4 and 5 another thread can hit the same page and it will encounter a valid pte. Because the data still is in the L1 dcache the CPU will fetch stale data from L2 into the icache and execute garbage. This fix moves the commit of the cache flush to step 3 to close the race window. It also reduces the amount of flushes on non-executable mappings because we never enter __flush_dcache_page() for non-aliasing CPUs. Regressions can occur in drivers that mistakenly relies on the flush_dcache_page() in get_user_pages() for DMA operations. [ralf@linux-mips.org: Folded in patch 9346 to fix highmem issue.] Signed-off-by: Lars Persson <larper@axis.com> Cc: linux-mips@linux-mips.org Cc: paul.burton@imgtec.com Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/9346/ Patchwork: https://patchwork.linux-mips.org/patch/9738/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2015-02-26 20:16:03 +07:00
void __flush_icache_page(struct vm_area_struct *vma, struct page *page)
{
unsigned long addr;
if (PageHighMem(page))
return;
addr = (unsigned long) page_address(page);
flush_data_cache_page(addr);
}
EXPORT_SYMBOL_GPL(__flush_icache_page);
void __update_cache(struct vm_area_struct *vma, unsigned long address,
pte_t pte)
{
struct page *page;
unsigned long pfn, addr;
int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;
pfn = pte_pfn(pte);
[MIPS] Retire flush_icache_page from mm use. On the 34K the redundant cache operations were causing excessive stalls resulting in realtime code running on the second VPE missing its deadline. For all other platforms this patch is just a significant performance improvment as illustrated by below benchmark numbers. Processor, Processes - times in microseconds - smaller is better ------------------------------------------------------------------------------ Host OS Mhz null null open slct sig sig fork exec sh call I/O stat clos TCP inst hndl proc proc proc --------- ------------- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- ---- 25Kf 2.6.18-rc4 533 0.49 1.16 7.57 33.4 30.5 1.34 12.4 5497 17.K 54.K 25Kf 2.6.18-rc4-p 533 0.49 1.16 6.68 23.0 30.7 1.36 8.55 5030 16.K 48.K 4Kc 2.6.18-rc4 80 4.21 15.0 131. 289. 261. 16.5 258. 18.K 70.K 227K 4Kc 2.6.18-rc4-p 80 4.34 13.1 128. 285. 262. 18.2 258. 12.K 52.K 176K 34Kc 2.6.18-rc4 40 5.01 14.0 61.6 90.0 477. 17.9 94.7 29.K 108K 342K 34Kc 2.6.18-rc4-p 40 4.98 13.9 61.2 89.7 475. 17.6 93.7 8758 44.K 158K BCM1480 2.6.18-rc4 700 0.28 0.60 3.68 5.92 16.0 0.78 5.08 931. 3163 15.K BCM1480 2.6.18-rc4-p 700 0.28 0.61 3.65 5.85 16.0 0.79 5.20 395. 1464 8385 TX49-16K 2.6.18-rc3 197 0.73 2.41 19.0 37.8 82.9 2.94 17.5 4438 14.K 56.K TX49-16K 2.6.18-rc3-p 197 0.73 2.40 19.9 36.3 82.9 2.94 23.4 2577 9103 38.K TX49-32K 2.6.18-rc3 396 0.36 1.19 6.80 11.8 41.0 1.46 8.17 2738 8465 32.K TX49-32K 2.6.18-rc3-p 396 0.36 1.19 6.82 10.2 41.0 1.46 8.18 1330 4638 18.K Original patch by me with enhancements by Atsushi Nemoto. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
2006-08-12 22:40:08 +07:00
if (unlikely(!pfn_valid(pfn)))
return;
page = pfn_to_page(pfn);
if (page_mapping(page) && Page_dcache_dirty(page)) {
addr = (unsigned long) page_address(page);
if (exec || pages_do_alias(addr, address & PAGE_MASK))
flush_data_cache_page(addr);
ClearPageDcacheDirty(page);
}
}
unsigned long _page_cachable_default;
EXPORT_SYMBOL(_page_cachable_default);
static inline void setup_protection_map(void)
{
if (cpu_has_rixi) {
protection_map[0] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[1] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[2] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[3] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[4] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[5] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[6] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[7] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[8] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
protection_map[9] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
} else {
protection_map[0] = PAGE_NONE;
protection_map[1] = PAGE_READONLY;
protection_map[2] = PAGE_COPY;
protection_map[3] = PAGE_COPY;
protection_map[4] = PAGE_READONLY;
protection_map[5] = PAGE_READONLY;
protection_map[6] = PAGE_COPY;
protection_map[7] = PAGE_COPY;
protection_map[8] = PAGE_NONE;
protection_map[9] = PAGE_READONLY;
protection_map[10] = PAGE_SHARED;
protection_map[11] = PAGE_SHARED;
protection_map[12] = PAGE_READONLY;
protection_map[13] = PAGE_READONLY;
protection_map[14] = PAGE_SHARED;
protection_map[15] = PAGE_SHARED;
}
}
MIPS: Delete __cpuinit/__CPUINIT usage from MIPS code commit 3747069b25e419f6b51395f48127e9812abc3596 upstream. The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) and are flagged as __cpuinit -- so if we remove the __cpuinit from the arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit related content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. Here, we remove all the MIPS __cpuinit from C code and __CPUINIT from asm files. MIPS is interesting in this respect, because there are also uasm users hiding behind their own renamed versions of the __cpuinit macros. [1] https://lkml.org/lkml/2013/5/20/589 [ralf@linux-mips.org: Folded in Paul's followup fix.] Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5494/ Patchwork: https://patchwork.linux-mips.org/patch/5495/ Patchwork: https://patchwork.linux-mips.org/patch/5509/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2013-06-18 20:38:59 +07:00
void cpu_cache_init(void)
{
if (cpu_has_3k_cache) {
extern void __weak r3k_cache_init(void);
r3k_cache_init();
}
if (cpu_has_6k_cache) {
extern void __weak r6k_cache_init(void);
r6k_cache_init();
}
if (cpu_has_4k_cache) {
extern void __weak r4k_cache_init(void);
r4k_cache_init();
}
if (cpu_has_8k_cache) {
extern void __weak r8k_cache_init(void);
r8k_cache_init();
}
if (cpu_has_tx39_cache) {
extern void __weak tx39_cache_init(void);
tx39_cache_init();
}
if (cpu_has_octeon_cache) {
extern void __weak octeon_cache_init(void);
octeon_cache_init();
}
setup_protection_map();
}
int __weak __uncached_access(struct file *file, unsigned long addr)
{
vfs: Implement proper O_SYNC semantics While Linux provided an O_SYNC flag basically since day 1, it took until Linux 2.4.0-test12pre2 to actually get it implemented for filesystems, since that day we had generic_osync_around with only minor changes and the great "For now, when the user asks for O_SYNC, we'll actually give O_DSYNC" comment. This patch intends to actually give us real O_SYNC semantics in addition to the O_DSYNC semantics. After Jan's O_SYNC patches which are required before this patch it's actually surprisingly simple, we just need to figure out when to set the datasync flag to vfs_fsync_range and when not. This patch renames the existing O_SYNC flag to O_DSYNC while keeping it's numerical value to keep binary compatibility, and adds a new real O_SYNC flag. To guarantee backwards compatiblity it is defined as expanding to both the O_DSYNC and the new additional binary flag (__O_SYNC) to make sure we are backwards-compatible when compiled against the new headers. This also means that all places that don't care about the differences can just check O_DSYNC and get the right behaviour for O_SYNC, too - only places that actuall care need to check __O_SYNC in addition. Drivers and network filesystems have been updated in a fail safe way to always do the full sync magic if O_DSYNC is set. The few places setting O_SYNC for lower layers are kept that way for now to stay failsafe. We enforce that O_DSYNC is set when __O_SYNC is set early in the open path to make sure we always get these sane options. Note that parisc really screwed up their headers as they already define a O_DSYNC that has always been a no-op. We try to repair it by using it for the new O_DSYNC and redefinining O_SYNC to send both the traditional O_SYNC numerical value _and_ the O_DSYNC one. Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger@sun.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jan Kara <jack@suse.cz>
2009-10-27 17:05:28 +07:00
if (file->f_flags & O_DSYNC)
return 1;
return addr >= __pa(high_memory);
}