linux/include/asm-generic/tlb.h

244 lines
7.1 KiB
C
Raw Normal View History

/* 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
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:11:45 +08:00
*
* 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
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:11:45 +08:00
/*
* 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 *))
mm: limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT Since commit e303297e6c3a ("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>
2013-01-05 07:35:12 +08:00
/*
* 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;
2013-04-13 07:23:54 +08:00
/* we are in the middle of an operation to clear
* a full mm and can make some optimizations */
unsigned int fullmm : 1,
2013-04-13 07:23:54 +08:00
/* 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];
mm: limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT Since commit e303297e6c3a ("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>
2013-01-05 07:35:12 +08:00
unsigned int batch_count;
mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 06:24:09 +08:00
/*
* __tlb_adjust_range will track the new addr here,
* that that we can adjust the range after the flush
*/
unsigned long addr;
};
#define HAVE_GENERIC_MMU_GATHER
Fix TLB gather virtual address range invalidation corner cases Ben Tebulin reported: "Since v3.7.2 on two independent machines a very specific Git repository fails in 9/10 cases on git-fsck due to an SHA1/memory failures. This only occurs on a very specific repository and can be reproduced stably on two independent laptops. Git mailing list ran out of ideas and for me this looks like some very exotic kernel issue" and bisected the failure to the backport of commit 53a59fc67f97 ("mm: limit mmu_gather batching to fix soft lockups on !CONFIG_PREEMPT"). That commit itself is not actually buggy, but what it does is to make it much more likely to hit the partial TLB invalidation case, since it introduces a new case in tlb_next_batch() that previously only ever happened when running out of memory. The real bug is that the TLB gather virtual memory range setup is subtly buggered. It was introduced in commit 597e1c3580b7 ("mm/mmu_gather: enable tlb flush range in generic mmu_gather"), and the range handling was already fixed at least once in commit e6c495a96ce0 ("mm: fix the TLB range flushed when __tlb_remove_page() runs out of slots"), but that fix was not complete. The problem with the TLB gather virtual address range is that it isn't set up by the initial tlb_gather_mmu() initialization (which didn't get the TLB range information), but it is set up ad-hoc later by the functions that actually flush the TLB. And so any such case that forgot to update the TLB range entries would potentially miss TLB invalidates. Rather than try to figure out exactly which particular ad-hoc range setup was missing (I personally suspect it's the hugetlb case in zap_huge_pmd(), which didn't have the same logic as zap_pte_range() did), this patch just gets rid of the problem at the source: make the TLB range information available to tlb_gather_mmu(), and initialize it when initializing all the other tlb gather fields. This makes the patch larger, but conceptually much simpler. And the end result is much more understandable; even if you want to play games with partial ranges when invalidating the TLB contents in chunks, now the range information is always there, and anybody who doesn't want to bother with it won't introduce subtle bugs. Ben verified that this fixes his problem. Reported-bisected-and-tested-by: Ben Tebulin <tebulin@googlemail.com> Build-testing-by: Stephen Rothwell <sfr@canb.auug.org.au> Build-testing-by: Richard Weinberger <richard.weinberger@gmail.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-16 02:42:25 +08:00
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
unsigned long end);
mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 06:24:09 +08:00
bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
static inline void __tlb_adjust_range(struct mmu_gather *tlb,
unsigned long address)
{
tlb->start = min(tlb->start, address);
tlb->end = max(tlb->end, address + PAGE_SIZE);
mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 06:24:09 +08:00
/*
* Track the last address with which we adjusted the range. This
* will be used later to adjust again after a mmu_flush due to
* failed __tlb_remove_page
*/
tlb->addr = address;
}
static inline void __tlb_reset_range(struct mmu_gather *tlb)
{
if (tlb->fullmm) {
tlb->start = tlb->end = ~0;
} else {
tlb->start = TASK_SIZE;
tlb->end = 0;
}
}
mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 06:24:09 +08:00
/* 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_adjust_range(tlb, tlb->addr);
__tlb_remove_page(tlb, page);
}
}
static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
{
/* active->nr should be zero when we call this */
VM_BUG_ON_PAGE(tlb->active->nr, page);
__tlb_adjust_range(tlb, tlb->addr);
return __tlb_remove_page(tlb, page);
}
/*
* In the case of tlb vma handling, we can optimise these away in the
* case where we're doing a full MM flush. When we're doing a munmap,
* the vmas are adjusted to only cover the region to be torn down.
*/
#ifndef tlb_start_vma
#define tlb_start_vma(tlb, vma) do { } while (0)
#endif
#define __tlb_end_vma(tlb, vma) \
do { \
if (!tlb->fullmm && tlb->end) { \
tlb_flush(tlb); \
__tlb_reset_range(tlb); \
} \
} while (0)
#ifndef tlb_end_vma
#define tlb_end_vma __tlb_end_vma
#endif
#ifndef __tlb_remove_tlb_entry
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
#endif
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
* Record the fact that pte's were really unmapped by updating the range,
* 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_adjust_range(tlb, address); \
__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_adjust_range(tlb, address); \
__tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \
} while (0)
#define pte_free_tlb(tlb, ptep, address) \
do { \
__tlb_adjust_range(tlb, address); \
__pte_free_tlb(tlb, ptep, address); \
} while (0)
#ifndef __ARCH_HAS_4LEVEL_HACK
#define pud_free_tlb(tlb, pudp, address) \
do { \
__tlb_adjust_range(tlb, address); \
__pud_free_tlb(tlb, pudp, address); \
} while (0)
#endif
#define pmd_free_tlb(tlb, pmdp, address) \
do { \
__tlb_adjust_range(tlb, address); \
__pmd_free_tlb(tlb, pmdp, address); \
} while (0)
#define tlb_migrate_finish(mm) do {} while (0)
#endif /* _ASM_GENERIC__TLB_H */