OpenCloudOS-Kernel/arch/arm/mm/fault-armv.c

267 lines
6.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/mm/fault-armv.c
*
* Copyright (C) 1995 Linus Torvalds
* Modifications for ARM processor (c) 1995-2002 Russell King
*/
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bitops.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/pagemap.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <asm/bugs.h>
#include <asm/cacheflush.h>
#include <asm/cachetype.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include "mm.h"
static pteval_t shared_pte_mask = L_PTE_MT_BUFFERABLE;
#if __LINUX_ARM_ARCH__ < 6
/*
* We take the easy way out of this problem - we make the
* PTE uncacheable. However, we leave the write buffer on.
*
* Note that the pte lock held when calling update_mmu_cache must also
* guard the pte (somewhere else in the same mm) that we modify here.
* Therefore those configurations which might call adjust_pte (those
* without CONFIG_CPU_CACHE_VIPT) cannot support split page_table_lock.
*/
static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
unsigned long pfn, pte_t *ptep)
{
pte_t entry = *ptep;
int ret;
/*
* If this page is present, it's actually being shared.
*/
ret = pte_present(entry);
/*
* If this page isn't present, or is already setup to
* fault (ie, is old), we can safely ignore any issues.
*/
if (ret && (pte_val(entry) & L_PTE_MT_MASK) != shared_pte_mask) {
flush_cache_page(vma, address, pfn);
outer_flush_range((pfn << PAGE_SHIFT),
(pfn << PAGE_SHIFT) + PAGE_SIZE);
pte_val(entry) &= ~L_PTE_MT_MASK;
pte_val(entry) |= shared_pte_mask;
set_pte_at(vma->vm_mm, address, ptep, entry);
flush_tlb_page(vma, address);
}
return ret;
}
#if USE_SPLIT_PTE_PTLOCKS
/*
* If we are using split PTE locks, then we need to take the page
* lock here. Otherwise we are using shared mm->page_table_lock
* which is already locked, thus cannot take it.
*/
static inline void do_pte_lock(spinlock_t *ptl)
{
/*
* Use nested version here to indicate that we are already
* holding one similar spinlock.
*/
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
}
static inline void do_pte_unlock(spinlock_t *ptl)
{
spin_unlock(ptl);
}
#else /* !USE_SPLIT_PTE_PTLOCKS */
static inline void do_pte_lock(spinlock_t *ptl) {}
static inline void do_pte_unlock(spinlock_t *ptl) {}
#endif /* USE_SPLIT_PTE_PTLOCKS */
static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
unsigned long pfn)
{
spinlock_t *ptl;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
int ret;
pgd = pgd_offset(vma->vm_mm, address);
if (pgd_none_or_clear_bad(pgd))
return 0;
pud = pud_offset(pgd, address);
if (pud_none_or_clear_bad(pud))
return 0;
pmd = pmd_offset(pud, address);
if (pmd_none_or_clear_bad(pmd))
return 0;
/*
* This is called while another page table is mapped, so we
* must use the nested version. This also means we need to
* open-code the spin-locking.
*/
ptl = pte_lockptr(vma->vm_mm, pmd);
pte = pte_offset_map(pmd, address);
do_pte_lock(ptl);
ret = do_adjust_pte(vma, address, pfn, pte);
do_pte_unlock(ptl);
pte_unmap(pte);
return ret;
}
static void
make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep, unsigned long pfn)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_area_struct *mpnt;
unsigned long offset;
pgoff_t pgoff;
int aliases = 0;
pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT);
/*
* If we have any shared mappings that are in the same mm
* space, then we need to handle them specially to maintain
* cache coherency.
*/
flush_dcache_mmap_lock(mapping);
vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
/*
* If this VMA is not in our MM, we can ignore it.
* Note that we intentionally mask out the VMA
* that we are fixing up.
*/
if (mpnt->vm_mm != mm || mpnt == vma)
continue;
if (!(mpnt->vm_flags & VM_MAYSHARE))
continue;
offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn);
}
flush_dcache_mmap_unlock(mapping);
if (aliases)
do_adjust_pte(vma, addr, pfn, ptep);
}
/*
* Take care of architecture specific things when placing a new PTE into
* a page table, or changing an existing PTE. Basically, there are two
* things that we need to take care of:
*
* 1. If PG_dcache_clean is not set for the page, we need to ensure
* that any cache entries for the kernels virtual memory
* range are written back to the page.
* 2. If we have multiple shared mappings of the same space in
* an object, we need to deal with the cache aliasing issues.
*
* Note that the pte lock will be held.
*/
void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
unsigned long pfn = pte_pfn(*ptep);
struct address_space *mapping;
struct page *page;
if (!pfn_valid(pfn))
return;
/*
* The zero page is never written to, so never has any dirty
* cache lines, and therefore never needs to be flushed.
*/
page = pfn_to_page(pfn);
if (page == ZERO_PAGE(0))
return;
mm: fix races between swapoff and flush dcache Thanks to commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks"), after swapoff the address_space associated with the swap device will be freed. So page_mapping() users which may touch the address_space need some kind of mechanism to prevent the address_space from being freed during accessing. The dcache flushing functions (flush_dcache_page(), etc) in architecture specific code may access the address_space of swap device for anonymous pages in swap cache via page_mapping() function. But in some cases there are no mechanisms to prevent the swap device from being swapoff, for example, CPU1 CPU2 __get_user_pages() swapoff() flush_dcache_page() mapping = page_mapping() ... exit_swap_address_space() ... kvfree(spaces) mapping_mapped(mapping) The address space may be accessed after being freed. But from cachetlb.txt and Russell King, flush_dcache_page() only care about file cache pages, for anonymous pages, flush_anon_page() should be used. The implementation of flush_dcache_page() in all architectures follows this too. They will check whether page_mapping() is NULL and whether mapping_mapped() is true to determine whether to flush the dcache immediately. And they will use interval tree (mapping->i_mmap) to find all user space mappings. While mapping_mapped() and mapping->i_mmap isn't used by anonymous pages in swap cache at all. So, to fix the race between swapoff and flush dcache, __page_mapping() is add to return the address_space for file cache pages and NULL otherwise. All page_mapping() invoking in flush dcache functions are replaced with page_mapping_file(). [akpm@linux-foundation.org: simplify page_mapping_file(), per Mike] Link: http://lkml.kernel.org/r/20180305083634.15174-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "David S. Miller" <davem@davemloft.net> Cc: Chris Zankel <chris@zankel.net> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 07:24:39 +08:00
mapping = page_mapping_file(page);
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
__flush_dcache_page(mapping, page);
if (mapping) {
if (cache_is_vivt())
make_coherent(mapping, vma, addr, ptep, pfn);
else if (vma->vm_flags & VM_EXEC)
__flush_icache_all();
}
}
#endif /* __LINUX_ARM_ARCH__ < 6 */
/*
* Check whether the write buffer has physical address aliasing
* issues. If it has, we need to avoid them for the case where
* we have several shared mappings of the same object in user
* space.
*/
static int __init check_writebuffer(unsigned long *p1, unsigned long *p2)
{
register unsigned long zero = 0, one = 1, val;
local_irq_disable();
mb();
*p1 = one;
mb();
*p2 = zero;
mb();
val = *p1;
mb();
local_irq_enable();
return val != zero;
}
void __init check_writebuffer_bugs(void)
{
struct page *page;
const char *reason;
unsigned long v = 1;
pr_info("CPU: Testing write buffer coherency: ");
page = alloc_page(GFP_KERNEL);
if (page) {
unsigned long *p1, *p2;
pgprot_t prot = __pgprot_modify(PAGE_KERNEL,
L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE);
p1 = vmap(&page, 1, VM_IOREMAP, prot);
p2 = vmap(&page, 1, VM_IOREMAP, prot);
if (p1 && p2) {
v = check_writebuffer(p1, p2);
reason = "enabling work-around";
} else {
reason = "unable to map memory\n";
}
vunmap(p1);
vunmap(p2);
put_page(page);
} else {
reason = "unable to grab page\n";
}
if (v) {
pr_cont("failed, %s\n", reason);
shared_pte_mask = L_PTE_MT_UNCACHED;
} else {
pr_cont("ok\n");
}
}