kernel-fxtec-pro1x/include/asm-generic/tlb.h
Michal Hocko 53a59fc67f mm: limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT
Since commit e303297e6c ("mm: extended batches for generic
mmu_gather") we are batching pages to be freed until either
tlb_next_batch cannot allocate a new batch or we are done.

This works just fine most of the time but we can get in troubles with
non-preemptible kernel (CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY)
on large machines where too aggressive batching might lead to soft
lockups during process exit path (exit_mmap) because there are no
scheduling points down the free_pages_and_swap_cache path and so the
freeing can take long enough to trigger the soft lockup.

The lockup is harmless except when the system is setup to panic on
softlockup which is not that unusual.

The simplest way to work around this issue is to limit the maximum
number of batches in a single mmu_gather.  10k of collected pages should
be safe to prevent from soft lockups (we would have 2ms for one) even if
they are all freed without an explicit scheduling point.

This patch doesn't add any new explicit scheduling points because it
relies on zap_pmd_range during page tables zapping which calls
cond_resched per PMD.

The following lockup has been reported for 3.0 kernel with a huge
process (in order of hundreds gigs but I do know any more details).

  BUG: soft lockup - CPU#56 stuck for 22s! [kernel:31053]
  Modules linked in: af_packet nfs lockd fscache auth_rpcgss nfs_acl sunrpc mptctl mptbase autofs4 binfmt_misc dm_round_robin dm_multipath bonding cpufreq_conservative cpufreq_userspace cpufreq_powersave pcc_cpufreq mperf microcode fuse loop osst sg sd_mod crc_t10dif st qla2xxx scsi_transport_fc scsi_tgt netxen_nic i7core_edac iTCO_wdt joydev e1000e serio_raw pcspkr edac_core iTCO_vendor_support acpi_power_meter rtc_cmos hpwdt hpilo button container usbhid hid dm_mirror dm_region_hash dm_log linear uhci_hcd ehci_hcd usbcore usb_common scsi_dh_emc scsi_dh_alua scsi_dh_hp_sw scsi_dh_rdac scsi_dh dm_snapshot pcnet32 mii edd dm_mod raid1 ext3 mbcache jbd fan thermal processor thermal_sys hwmon cciss scsi_mod
  Supported: Yes
  CPU 56
  Pid: 31053, comm: kernel Not tainted 3.0.31-0.9-default #1 HP ProLiant DL580 G7
  RIP: 0010:  _raw_spin_unlock_irqrestore+0x8/0x10
  RSP: 0018:ffff883ec1037af0  EFLAGS: 00000206
  RAX: 0000000000000e00 RBX: ffffea01a0817e28 RCX: ffff88803ffd9e80
  RDX: 0000000000000200 RSI: 0000000000000206 RDI: 0000000000000206
  RBP: 0000000000000002 R08: 0000000000000001 R09: ffff887ec724a400
  R10: 0000000000000000 R11: dead000000200200 R12: ffffffff8144c26e
  R13: 0000000000000030 R14: 0000000000000297 R15: 000000000000000e
  FS:  00007ed834282700(0000) GS:ffff88c03f200000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: 000000000068b240 CR3: 0000003ec13c5000 CR4: 00000000000006e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
  Process kernel (pid: 31053, threadinfo ffff883ec1036000, task ffff883ebd5d4100)
  Call Trace:
    release_pages+0xc5/0x260
    free_pages_and_swap_cache+0x9d/0xc0
    tlb_flush_mmu+0x5c/0x80
    tlb_finish_mmu+0xe/0x50
    exit_mmap+0xbd/0x120
    mmput+0x49/0x120
    exit_mm+0x122/0x160
    do_exit+0x17a/0x430
    do_group_exit+0x3d/0xb0
    get_signal_to_deliver+0x247/0x480
    do_signal+0x71/0x1b0
    do_notify_resume+0x98/0xb0
    int_signal+0x12/0x17
  DWARF2 unwinder stuck at int_signal+0x12/0x17

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: <stable@vger.kernel.org>	[3.0+]
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-04 16:11:46 -08:00

190 lines
5.6 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 */
unsigned int fullmm;
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 */