linux/include/asm-generic/tlb.h
Dave Hansen 1de14c3c5c x86-32: Fix possible incomplete TLB invalidate with PAE pagetables
This patch attempts to fix:

	https://bugzilla.kernel.org/show_bug.cgi?id=56461

The symptom is a crash and messages like this:

	chrome: Corrupted page table at address 34a03000
	*pdpt = 0000000000000000 *pde = 0000000000000000
	Bad pagetable: 000f [#1] PREEMPT SMP

Ingo guesses this got introduced by commit 611ae8e3f5 ("x86/tlb:
enable tlb flush range support for x86") since that code started to free
unused pagetables.

On x86-32 PAE kernels, that new code has the potential to free an entire
PMD page and will clear one of the four page-directory-pointer-table
(aka pgd_t entries).

The hardware aggressively "caches" these top-level entries and invlpg
does not actually affect the CPU's copy.  If we clear one we *HAVE* to
do a full TLB flush, otherwise we might continue using a freed pmd page.
(note, we do this properly on the population side in pud_populate()).

This patch tracks whenever we clear one of these entries in the 'struct
mmu_gather', and ensures that we follow up with a full tlb flush.

BTW, I disassembled and checked that:

	if (tlb->fullmm == 0)
and
	if (!tlb->fullmm && !tlb->need_flush_all)

generate essentially the same code, so there should be zero impact there
to the !PAE case.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Artem S Tashkinov <t.artem@mailcity.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-12 16:56:47 -07:00

196 lines
5.8 KiB
C

/* include/asm-generic/tlb.h
*
* Generic TLB shootdown code
*
* Copyright 2001 Red Hat, Inc.
* Based on code from mm/memory.c Copyright Linus Torvalds and others.
*
* Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _ASM_GENERIC__TLB_H
#define _ASM_GENERIC__TLB_H
#include <linux/swap.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
*
* This is needed by some architectures to implement software pagetable walkers.
*
* gup_fast() and other software pagetable walkers do a lockless page-table
* walk and therefore needs some synchronization with the freeing of the page
* directories. The chosen means to accomplish that is by disabling IRQs over
* the walk.
*
* Architectures that use IPIs to flush TLBs will then automagically DTRT,
* since we unlink the page, flush TLBs, free the page. Since the disabling of
* IRQs delays the completion of the TLB flush we can never observe an already
* freed page.
*
* Architectures that do not have this (PPC) need to delay the freeing by some
* other means, this is that means.
*
* What we do is batch the freed directory pages (tables) and RCU free them.
* We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
* holds off grace periods.
*
* However, in order to batch these pages we need to allocate storage, this
* allocation is deep inside the MM code and can thus easily fail on memory
* pressure. To guarantee progress we fall back to single table freeing, see
* the implementation of tlb_remove_table_one().
*
*/
struct mmu_table_batch {
struct rcu_head rcu;
unsigned int nr;
void *tables[0];
};
#define MAX_TABLE_BATCH \
((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
extern void tlb_table_flush(struct mmu_gather *tlb);
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#endif
/*
* If we can't allocate a page to make a big batch of page pointers
* to work on, then just handle a few from the on-stack structure.
*/
#define MMU_GATHER_BUNDLE 8
struct mmu_gather_batch {
struct mmu_gather_batch *next;
unsigned int nr;
unsigned int max;
struct page *pages[0];
};
#define MAX_GATHER_BATCH \
((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
/*
* Limit the maximum number of mmu_gather batches to reduce a risk of soft
* lockups for non-preemptible kernels on huge machines when a lot of memory
* is zapped during unmapping.
* 10K pages freed at once should be safe even without a preemption point.
*/
#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH)
/* struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
#endif
unsigned long start;
unsigned long end;
unsigned int need_flush : 1, /* Did free PTEs */
fast_mode : 1; /* No batching */
/* we are in the middle of an operation to clear
* a full mm and can make some optimizations */
unsigned int fullmm : 1,
/* we have performed an operation which
* requires a complete flush of the tlb */
need_flush_all : 1;
struct mmu_gather_batch *active;
struct mmu_gather_batch local;
struct page *__pages[MMU_GATHER_BUNDLE];
unsigned int batch_count;
};
#define HAVE_GENERIC_MMU_GATHER
static inline int tlb_fast_mode(struct mmu_gather *tlb)
{
#ifdef CONFIG_SMP
return tlb->fast_mode;
#else
/*
* For UP we don't need to worry about TLB flush
* and page free order so much..
*/
return 1;
#endif
}
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
void tlb_flush_mmu(struct mmu_gather *tlb);
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
unsigned long end);
int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
/* tlb_remove_page
* Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
* required.
*/
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
if (!__tlb_remove_page(tlb, page))
tlb_flush_mmu(tlb);
}
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
* Record the fact that pte's were really umapped in ->need_flush, so we can
* later optimise away the tlb invalidate. This helps when userspace is
* unmapping already-unmapped pages, which happens quite a lot.
*/
#define tlb_remove_tlb_entry(tlb, ptep, address) \
do { \
tlb->need_flush = 1; \
__tlb_remove_tlb_entry(tlb, ptep, address); \
} while (0)
/**
* tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
* This is a nop so far, because only x86 needs it.
*/
#ifndef __tlb_remove_pmd_tlb_entry
#define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
#endif
#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \
do { \
tlb->need_flush = 1; \
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
#define pte_free_tlb(tlb, ptep, address) \
do { \
tlb->need_flush = 1; \
__pte_free_tlb(tlb, ptep, address); \
} while (0)
#ifndef __ARCH_HAS_4LEVEL_HACK
#define pud_free_tlb(tlb, pudp, address) \
do { \
tlb->need_flush = 1; \
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#define pmd_free_tlb(tlb, pmdp, address) \
do { \
tlb->need_flush = 1; \
__pmd_free_tlb(tlb, pmdp, address); \
} while (0)
#define tlb_migrate_finish(mm) do {} while (0)
#endif /* _ASM_GENERIC__TLB_H */