aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/cdrom
Commit message (Collapse)AuthorAge
* cdrom: handle TOCAlexander Inyukhin2008-08-18
| | | | | | | | | | | | | | | | | | | | | | | | This patch should fix TOC handling for cdroms that can not play audio. It extends commit af744e3294d09d706c4eae26cffaaa68a8d40337 ("cdrom: don't check CDC_PLAY_AUDIO in cdrom_count_tracks()") with a safety check and non-audio ioctls support. Since CDC_PLAY_AUDIO flag was used not only to check ability to play audio but also to ensure that audio_ioctl was not NULL, all TOC-related operations had to use it. As far as I understand, now audio_ioctl is never NULL, so a sanity check during device registration should be sufficient. It was tested on Optiarc AD7203A device, that has no ability to play audio. Cc: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [bart: remove now unneeded ->audio_ioctl check (noticed by Borislav)] Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* gdrom: add dummy audio_ioctl handlerBorislav Petkov2008-08-18
| | | | | | | | | | | Make sure audio_ioctl is always defined even if being a dummy function since the cdrom_ioctl interface assumes its existence and we don't want to BUG on null ptr on some ioctls like, e.g. CDROMREADTOCENTRY, CDROMREADTOCHDR etc. when we fix CDC_PLAY_AUDIO checking in cdrom.c. Signed-off-by: Borislav Petkov <petkovbb@gmail.com> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* viocd: add dummy audio ioctl handlerBorislav Petkov2008-08-18
| | | | | | | | | | | Make sure audio_ioctl is always defined even if being a dummy function since the cdrom_ioctl interface assumes its existence and we don't want to BUG on null ptr on some ioctls like, e.g. CDROMREADTOCENTRY, CDROMREADTOCHDR etc. when we fix CDC_PLAY_AUDIO checking in cdrom.c. Signed-off-by: Borislav Petkov <petkovbb@gmail.com> Acked-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* cdrom: don't check CDC_PLAY_AUDIO in cdrom_count_tracks()Tejun Heo2008-08-05
| | | | | | | | | | | | | | | | According to MMC-3 (or any later versions) READ TOCs are mandatory commands and have nothing to do with CDC_PLAY_AUDIO. I have no idea why the check was put there in the first place but it now only breaks automatic actions on certain drives. Note that this test was only effective when ide-cdrom was being used as sr didn't mask CDC_PLAY_AUDIO according to the capabilities. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Jens Axboe <jens.axboe@oracle.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* sh: More header path fixups for mach dir refactoring.Paul Mundt2008-07-29
| | | | Signed-off-by: Paul Mundt <lethal@linux-sh.org>
* cdrom: revert commit 22a9189 (cdrom: use kmalloced buffers instead of ↵FUJITA Tomonori2008-07-04
| | | | | | | | | | | | | | | | | | | | | | | | buffers on stack) The commit 22a9189fd073db3d03a4cf8b8c098aa207602de1 (cdrom: use kmalloced buffers instead of buffers on stack) is introduced to use kmalloced buffers for packet commands to avoid stack corruption on non coherent platforms. SCSI cdrom uses blk_rq_map_kern, which properly avoids DMA on the stack by using the bounce buffers. IDE cdrom also has the mechnism to avoids DMA on the stack. So we don't need this extra complexitiy in cdrom.c, such as allocating just 8 bytes. The lower layers can handle it. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Tejun Heo <htejun@gmail.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* [POWERPC] iSeries: Remove unused mail addressStephen Rothwell2008-05-23
| | | | | | | | I don't use my IBM email address normally and people can find me in CREDITS. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
* Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-blockLinus Torvalds2008-04-29
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://git.kernel.dk/linux-2.6-block: block: Skip I/O merges when disabled block: add large command support block: replace sizeof(rq->cmd) with BLK_MAX_CDB ide: use blk_rq_init() to initialize the request block: use blk_rq_init() to initialize the request block: rename and export rq_init() block: no need to initialize rq->cmd with blk_get_request block: no need to initialize rq->cmd in prepare_flush_fn hook block/blk-barrier.c:blk_ordered_cur_seq() mustn't be inline block/elevator.c:elv_rq_merge_ok() mustn't be inline block: make queue flags non-atomic block: add dma alignment and padding support to blk_rq_map_kern unexport blk_max_pfn ps3disk: Remove superfluous cast block: make rq_init() do a full memset() relay: fix splice problem
| * block: no need to initialize rq->cmd with blk_get_requestFUJITA Tomonori2008-04-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | blk_get_request initializes rq->cmd (rq_init does) so the users don't need to do that. The purpose of this patch is to remove sizeof(rq->cmd) and &rq->cmd, as a preparation for large command support, which changes rq->cmd from the static array to a pointer. sizeof(rq->cmd) will not make sense and &rq->cmd won't work. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* | drivers: use non-racy method for proc entries creation (2)Denis V. Lunev2008-04-29
|/ | | | | | | | | | | | | | | | | | | Use proc_create()/proc_create_data() to make sure that ->proc_fops and ->data be setup before gluing PDE to main tree. Signed-off-by: Denis V. Lunev <den@openvz.org> Cc: Greg Kroah-Hartman <gregkh@suse.de> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Dmitry Torokhov <dtor@mail.ru> Cc: Neil Brown <neilb@suse.de> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Bjorn Helgaas <bjorn.helgaas@hp.com> Cc: Alessandro Zummo <a.zummo@towertech.it> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* cdrom: use kmalloced buffers instead of buffers on stackThomas Bogendoerfer2008-04-21
| | | | | | | | | | If cdrom commands are issued to a scsi drive in most cases the buffer will be filled via dma. This leads to bad stack corruption on non coherent platforms, because the buffers are neither cache line aligned nor is the size a multiple of the cache line size. Using kmalloced buffers avoids this. Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* cdrom: make unregister_cdrom() return voidAkinobu Mita2008-04-21
| | | | | | | | | | Now unregister_cdrom() always returns 0. Make it return void and update all callers that check the return value. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* cdrom: use list_head for cdrom_device_info listAkinobu Mita2008-04-21
| | | | | | | | Use list_head for cdrom_device_info list instead of opencoded singly list handling. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* cdrom: protect cdrom_device_info list by mutexAkinobu Mita2008-04-21
| | | | | | | | This patch protects the list of cdrom_device_info by cdrom_mutex when the file in /proc/sys/dev/cdrom/ is written. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* cdrom: cleanup hardcoded error-codeAkinobu Mita2008-04-21
| | | | | | | | | | | This patch eliminates hardcoded return value of register_cdrom(). It also changes the return value to -EINVAL. It is more appropriate than -2 (-ENOENT) because it is only happen invalid usage of register_cdrom() by broken cdrom driver. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* cdrom: remove ifdef CONFIG_SYSCTLAkinobu Mita2008-04-21
| | | | | | | | | This patch removes #ifdef for CONFIG_SYSCTL by defining empty cdrom_sysctl_register and cdrom_sysctl_unregister when CONFIG_SYSCTL is not defined. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* make cdrom.c:check_for_audio_disc() staticAdrian Bunk2008-03-04
| | | | | | | This patch makes the needlessly global check_for_audio_disc() static. Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* Merge branch 'for-2.6.25' of ↵Linus Torvalds2008-02-07
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc * 'for-2.6.25' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (69 commits) [POWERPC] Add SPE registers to core dumps [POWERPC] Use regset code for compat PTRACE_*REGS* calls [POWERPC] Use generic compat_sys_ptrace [POWERPC] Use generic compat_ptrace_request [POWERPC] Use generic ptrace peekdata/pokedata [POWERPC] Use regset code for PTRACE_*REGS* requests [POWERPC] Switch to generic compat_binfmt_elf code [POWERPC] Switch to using user_regset-based core dumps [POWERPC] Add user_regset compat support [POWERPC] Add user_regset_view definitions [POWERPC] Use user_regset accessors for GPRs [POWERPC] ptrace accessors for special regs MSR and TRAP [POWERPC] Use user_regset accessors for SPE regs [POWERPC] Use user_regset accessors for altivec regs [POWERPC] Use user_regset accessors for FP regs [POWERPC] mpc52xx: fix compile error introduce when rebasing patch [POWERPC] 4xx: PCIe indirect DCR spinlock fix. [POWERPC] Add missing native dcr dcr_ind_lock spinlock [POWERPC] 4xx: Fix offset value on Warp board [POWERPC] 4xx: Add 440EPx Sequoia ehci dts entry ...
| * [POWERPC] iSeries: Fix section mismatch in viocdStephen Rothwell2008-02-06
| | | | | | | | | | | | | | WARNING: drivers/cdrom/viocd.o(.text+0x504): Section mismatch in reference from the function .viocd_probe() to the function .init.text:.find_capability() Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | drivers/cdrom/cdrom.c: simplify logic in cdrom_release()Borislav Petkov2008-02-06
|/ | | | | | | | | Simplify logic in cdrom_release() without semantic change. Signed-off-by: Borislav Petkov <bbpetkov@yahoo.de> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* ide-cd: move lba_to_msf() and msf_to_lba() to <linux/cdrom.h>Bartlomiej Zolnierkiewicz2008-02-01
| | | | | | | | | | * Move lba_to_msf() and msf_to_lba() to <linux/cdrom.h> (use 'u8' type instead of 'byte' while at it). * Remove msf_to_lba() copy from drivers/cdrom/cdrom.c. Acked-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6Linus Torvalds2008-01-28
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (197 commits) sh: add spi header and r2d platform data V3 sh: update r7780rp interrupt code sh: remove consistent alloc stuff from the machine vector sh: use declared coherent memory for dreamcast pci ethernet adapter sh: declared coherent memory support V2 sh: Add support for SDK7780 board. sh: constify function pointer tables sh: Kill off -traditional for linker script. cdrom: Add support for Sega Dreamcast GD-ROM. sh: Kill off hs7751rvoip reference from arch/sh/Kconfig. sh: Drop r7780rp_defconfig, use r7780mp_defconfig as kbuild default. sh: Kill off dead HS771RVoIP board support. sh: r7785rp: Fix up DECLARE_INTC_DESC() arg mismatch. sh: r7785rp: Hook up the rest of the HL7785 FPGA IRQ vectors. sh: r2d - enable sm501 usb host function sh: remove voyagergx sh: r2d - add lcd planel timings to sm501 platform data sh: Add OHCI and UDC platform devices for SH7720. sh: intc - remove default interrupt priority tables sh: Correct pte size mismatch for X2 TLB. ...
| * cdrom: Add support for Sega Dreamcast GD-ROM.Adrian McMenamin2008-01-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds support for the GD-Rom drive, SEGA's proprietary implementation of an IDE CD Rom for the SEGA Dreamcast. This driver implements Sega's Packet Interface (SPI) - at least partially. It will also read disks in SEGA's propreitary GD format. Unlike previous drivers (which were never in mainline) this uses DMA and not PIO to read disks. It is a new driver, not a refactoring of old drivers. Signed-off by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
* | blk_end_request: changing viocd (take 4)Kiyoshi Ueda2008-01-28
|/ | | | | | | | | | | | | This patch converts viocd to use blk_end_request interfaces. Related 'uptodate' arguments are converted to 'error'. As a result, the interface of internal function, viocd_end_request(), is changed. Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* SG: audit of drivers that use blk_rq_map_sg()Jens Axboe2007-10-24
| | | | | | | They need to properly init the sg table, or blk_rq_map_sg() will complain if CONFIG_DEBUG_SG is set. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* Use helpers to obtain task pid in printksPavel Emelyanov2007-10-19
| | | | | | | | | | | | | | | | The task_struct->pid member is going to be deprecated, so start using the helpers (task_pid_nr/task_pid_vnr/task_pid_nr_ns) in the kernel. The first thing to start with is the pid, printed to dmesg - in this case we may safely use task_pid_nr(). Besides, printks produce more (much more) than a half of all the explicit pid usage. [akpm@linux-foundation.org: git-drm went and changed lots of stuff] Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Cc: Dave Airlie <airlied@linux.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* sysctl: remove broken cdrom binary sysctlsEric W. Biederman2007-10-18
| | | | | | | | | | | | | The binary interface for the cdrom sysctls can't possilby work. So remove the binary sysctls and update the test for finding out which sysctl table entry we are dealy with to use the procname and not the ctl_name (which I am removing). Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Alexey Dobriyan <adobriyan@sw.ru> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [POWERPC] iSeries: Move detection of virtual cdromsStephen Rothwell2007-10-11
| | | | | | | | | | Now we will only have entries in the device tree for the actual existing devices (including their OS/400 properties). This way viocd.c gets all the information about the devices from the device tree. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] Remove iSeries_vio_devStephen Rothwell2007-10-11
| | | | | | | | | | It was only being used to carry around dma_iommu_ops and vio_iommu_table which we can use directly instead. This also means that vio_bus_device doesn't need to refer to them either. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] iSeries: Simplify viocd initialisationStephen Rothwell2007-10-11
| | | | | | | | | We don't need to keep a lump of dma coherent memory around for the life of the module. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* cdrom_open() forgets to unlock on -EROFS failure exitsAl Viro2007-09-26
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* [BLOCK] Get rid of request_queue_t typedefJens Axboe2007-07-24
| | | | | | | | | Some of the code has been gradually transitioned to using the proper struct request_queue, but there's lots left. So do a full sweet of the kernel and get rid of this typedef and replace its uses with the proper type. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* bsg: add a request_queue argument to scsi_cmd_ioctl()FUJITA Tomonori2007-07-16
| | | | | | | | | | | | bsg uses scsi_cmd_ioctl() for some SCSI/sg ioctl commands. scsi_cmd_ioctl() gets a request queue from a gendisk arguement. This prevents bsg being bound to SCSI devices that don't have a gendisk (like OSD). This adds a request_queue argument to scsi_cmd_ioctl(). The SCSI/sg ioctl commands doesn't use a gendisk so it's safe for any SCSI devices to use scsi_cmd_ioctl(). Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* Remove legacy CDROM driversJens Axboe2007-07-10
| | | | | | | | | | | They are all broken beyond repair. Given that nobody has complained about them (most haven't worked in 2.6 AT ALL), remove them from the tree. A new mitsumi driver that actually works is in progress, it'll get added when completed. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* [PATCH] fix request->cmd == INT casesBoaz Harrosh2007-07-10
| | | | | | | | | | | | | | | | | | | | | | | | | - I have unearthed very old bugs in stale drivers that still used request->cmd as a READ|WRITE int - This patch is maybe a proof that these drivers have not been used for a long time. Should they be removed completely? Drivers that currently do not work for sure: drivers/acorn/block/fd1772.c | 2 +- drivers/acorn/block/mfmhd.c | 8 ++++---- drivers/cdrom/aztcd.c | 2 +- drivers/cdrom/cm206.c | 2 +- drivers/cdrom/gscd.c | 2 +- drivers/cdrom/mcdx.c | 2 +- drivers/cdrom/optcd.c | 2 +- drivers/cdrom/sjcd.c | 2 +- Drivers with cosmetic fixes only: b/drivers/block/amiflop.c b/drivers/block/nbd.c b/drivers/ide/legacy/hd.c Signed-off-by: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* [PATCH] cdrom_sysctl_info fixDave Young2007-07-10
| | | | | | | | Fix the cdrom_sysctl_info possible buffer overwrite bug. Also fix the locking of accessing topCdromPtr pointer. Signed-off-by: Dave Young <hidave.darkstar@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* potential parse error in ifdef part 3Yoann Padioleau2007-06-08
| | | | | | | | | | | | | Fix various bits of obviously-busted code which we're not happening to compile, due to ifdefs. Signed-off-by: Yoann Padioleau <padator@wanadoo.fr> Cc: Andi Kleen <ak@suse.de> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Paul Mundt <lethal@linux-sh.org> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* mm: remove destroy_dirty_buffers from invalidate_bdev()Peter Zijlstra2007-05-07
| | | | | | | | | | | | | | | Remove the destroy_dirty_buffers argument from invalidate_bdev(), it hasn't been used in 6 years (so akpm says). find * -name \*.[ch] | xargs grep -l invalidate_bdev | while read file; do quilt add $file; sed -ie 's/invalidate_bdev(\([^,]*\),[^)]*)/invalidate_bdev(\1)/g' $file; done Signed-off-by: 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>
* [PATCH] Fix soft lockup with iSeries viocd driverTony Breeds2007-03-05
| | | | | | | | | | | | | | | | | | | | | Fix soft lockup with iSeries viocd driver, caused by eventually calling end_that_request_first() with nr_bytes 0. Some versions of hald do an SG_IO ioctl on the viocd device which becomes a request with hard_nr_sectors and hard_cur_sectors set to zero. Passing zero as the number of sectors to end_request() (which calls end_that_request_first()) causes an infinite loop when the bio is being freed. This patch makes sure that the zero is never passed. It only requires some number larger the the request size the terminate the loop. The lockup is triggered by hald, interrogating the device. Signed-off-by: Tony Breeds <tony@bakeyournoodle.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] sysctl: remove insert_at_head from register_sysctlEric W. Biederman2007-02-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The semantic effect of insert_at_head is that it would allow new registered sysctl entries to override existing sysctl entries of the same name. Which is pain for caching and the proc interface never implemented. I have done an audit and discovered that none of the current users of register_sysctl care as (excpet for directories) they do not register duplicate sysctl entries. So this patch simply removes the support for overriding existing entries in the sys_sysctl interface since no one uses it or cares and it makes future enhancments harder. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: David Howells <dhowells@redhat.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@muc.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Corey Minyard <minyard@acm.org> Cc: Neil Brown <neilb@suse.de> Cc: "John W. Linville" <linville@tuxdriver.com> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Jan Kara <jack@ucw.cz> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Mark Fasheh <mark.fasheh@oracle.com> Cc: David Chinner <dgc@sgi.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] sysctl: cdrom: don't set de->ownerEric W. Biederman2007-02-14
| | | | | | | | | | | | | | | | | | | There is no need for open files in /proc/sys/XXX to hold a reference count on the module that provides the file to prevent module unload races. While there is code active in the module p->used in the sysctl_table_header is incremented, preventing the sysctl from being unregisted. Once the sysctl is unregistered it cannot be found. Open files are also not a problem as they revalidate the sysctl information and bump p->used before accessing module code. So setting de->owner is unnecessary, makes for a bad example and gets in my way of removing ctl_table->de. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: Jens Axboe <jens.axboe@oracle.com> Acked-by: James Bottomley <James.Bottomley@SteelEye.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] sysctl: cdrom: remove unnecessary insert_at_head flagEric W. Biederman2007-02-14
| | | | | | | | | | With unique binary sysctl numbers setting insert_at_head to override other sysctl entries is pointless. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Acked-by: James Bottomley <James.Bottomley@SteelEye.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] remove many unneeded #includes of sched.hTim Schmielau2007-02-14
| | | | | | | | | | | | | | | | | | | | | | | | After Al Viro (finally) succeeded in removing the sched.h #include in module.h recently, it makes sense again to remove other superfluous sched.h includes. There are quite a lot of files which include it but don't actually need anything defined in there. Presumably these includes were once needed for macros that used to live in sched.h, but moved to other header files in the course of cleaning it up. To ease the pain, this time I did not fiddle with any header files and only removed #includes from .c-files, which tend to cause less trouble. Compile tested against 2.6.20-rc2 and 2.6.20-rc2-mm2 (with offsets) on alpha, arm, i386, ia64, mips, powerpc, and x86_64 with allnoconfig, defconfig, allmodconfig, and allyesconfig as well as a few randconfigs on x86_64 and all configs in arch/arm/configs on arm. I also checked that no new warnings were introduced by the patch (actually, some warnings are removed that were emitted by unnecessarily included header files). Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] mark struct file_operations const 3Arjan van de Ven2007-02-12
| | | | | | | | | | | Many struct file_operations in the kernel can be "const". Marking them const moves these to the .rodata section, which avoids false sharing with potential dirty data. In addition it'll catch accidental writes at compile time to these shared resources. Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* [PATCH] cdrom: set default timeout to 7 secondsJens Axboe2007-01-03
| | | | | | | | | | | | | | | | | | | It's a known fact that Windows times out commands after 7 seconds, so drives generally try and respond if they can before that happens. We default to 5 seconds, which sometimes is a bit too short. Jeremy Higdon reported here: http://lkml.org/lkml/2007/1/1/145 that his drive takes longer than 5 seconds for a "read track information" command, later confirming that it is about 6.7 seconds. So just do the sane thing and change the default command timeout to 7 seconds to avoid other surprises. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge branch 'for-linus' of git://brick.kernel.dk/data/git/linux-2.6-blockLinus Torvalds2006-12-21
|\ | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://brick.kernel.dk/data/git/linux-2.6-block: [PATCH] block: document io scheduler allow_merge_fn hook [PATCH] cfq-iosched: don't allow sync merges across queues [PATCH] Fixup blk_rq_unmap_user() API [PATCH] __blk_rq_unmap_user() fails to return error [PATCH] __blk_rq_map_user() doesn't need to grab the queue_lock [PATCH] Remove queue merging hooks [PATCH] ->nr_sectors and ->hard_nr_sectors are not used for BLOCK_PC requests [PATCH] cciss: fix XFER_READ/XFER_WRITE in do_cciss_request [PATCH] cciss: set default raid level when reading geometry fails
| * [PATCH] Fixup blk_rq_unmap_user() APIJens Axboe2006-12-19
| | | | | | | | | | | | | | | | | | The blk_rq_unmap_user() API is not very nice. It expects the caller to know that rq->bio has to be reset to the original bio, and it will silently do nothing if that is not done. Instead make it explicit that we need to pass in the first bio, by expecting a bio argument. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* | [POWERPC] iSeries: fix viocd initStephen Rothwell2006-12-20
|/ | | | | | | Only initialise viocd on legacy iSeries. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [PATCH] getting rid of all casts of k[cmz]alloc() callsRobert P. J. Day2006-12-13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Run this: #!/bin/sh for f in $(grep -Erl "\([^\)]*\) *k[cmz]alloc" *) ; do echo "De-casting $f..." perl -pi -e "s/ ?= ?\([^\)]*\) *(k[cmz]alloc) *\(/ = \1\(/" $f done And then go through and reinstate those cases where code is casting pointers to non-pointers. And then drop a few hunks which conflicted with outstanding work. Cc: Russell King <rmk@arm.linux.org.uk>, Ian Molton <spyro@f2s.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Greg KH <greg@kroah.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Paul Fulghum <paulkf@microgate.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Karsten Keil <kkeil@suse.de> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Jeff Garzik <jeff@garzik.org> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Ian Kent <raven@themaw.net> Cc: Steven French <sfrench@us.ibm.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: Jaroslav Kysela <perex@suse.cz> Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] drivers/cdrom/*: trivial vsnprintf() conversionAlexey Dobriyan2006-12-07
| | | | | | | | | Fixing sbpcd.c baroque error printing in process. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Jens Axboe <axboe@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-15 11:57:20 -0400
href='#n2329'>2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 
/*
 *  linux/mm/memory.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

/*
 * Real VM (paging to/from disk) started 18.12.91. Much more work and
 * thought has to go into this. Oh, well..
 * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
 *		Found it. Everything seems to work now.
 * 20.12.91  -  Ok, making the swap-device changeable like the root.
 */

/*
 * 05.04.94  -  Multi-page memory management added for v1.1.
 * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
 *
 * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
 *		(Gerhard.Wichert@pdb.siemens.de)
 *
 * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
 */

#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/kallsyms.h>
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
#include <linux/dma-debug.h>
#include <linux/debugfs.h>

#include <asm/io.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>

#include "internal.h"

#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif

#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;

EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif

/*
 * A number of key systems in x86 including ioremap() rely on the assumption
 * that high_memory defines the upper bound on direct map memory, then end
 * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
 * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
 * and ZONE_HIGHMEM.
 */
void * high_memory;

EXPORT_SYMBOL(high_memory);

/*
 * Randomize the address space (stacks, mmaps, brk, etc.).
 *
 * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
 *   as ancient (libc5 based) binaries can segfault. )
 */
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
					1;
#else
					2;
#endif

static int __init disable_randmaps(char *s)
{
	randomize_va_space = 0;
	return 1;
}
__setup("norandmaps", disable_randmaps);

unsigned long zero_pfn __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;

/*
 * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
 */
static int __init init_zero_pfn(void)
{
	zero_pfn = page_to_pfn(ZERO_PAGE(0));
	return 0;
}
core_initcall(init_zero_pfn);


#if defined(SPLIT_RSS_COUNTING)

void sync_mm_rss(struct mm_struct *mm)
{
	int i;

	for (i = 0; i < NR_MM_COUNTERS; i++) {
		if (current->rss_stat.count[i]) {
			add_mm_counter(mm, i, current->rss_stat.count[i]);
			current->rss_stat.count[i] = 0;
		}
	}
	current->rss_stat.events = 0;
}

static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
{
	struct task_struct *task = current;

	if (likely(task->mm == mm))
		task->rss_stat.count[member] += val;
	else
		add_mm_counter(mm, member, val);
}
#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1)
#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1)

/* sync counter once per 64 page faults */
#define TASK_RSS_EVENTS_THRESH	(64)
static void check_sync_rss_stat(struct task_struct *task)
{
	if (unlikely(task != current))
		return;
	if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
		sync_mm_rss(task->mm);
}
#else /* SPLIT_RSS_COUNTING */

#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)

static void check_sync_rss_stat(struct task_struct *task)
{
}

#endif /* SPLIT_RSS_COUNTING */

#ifdef HAVE_GENERIC_MMU_GATHER

static int tlb_next_batch(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	batch = tlb->active;
	if (batch->next) {
		tlb->active = batch->next;
		return 1;
	}

	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
		return 0;

	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
	if (!batch)
		return 0;

	tlb->batch_count++;
	batch->next = NULL;
	batch->nr   = 0;
	batch->max  = MAX_GATHER_BATCH;

	tlb->active->next = batch;
	tlb->active = batch;

	return 1;
}

/* tlb_gather_mmu
 *	Called to initialize an (on-stack) mmu_gather structure for page-table
 *	tear-down from @mm. The @fullmm argument is used when @mm is without
 *	users and we're going to destroy the full address space (exit/execve).
 */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
	tlb->mm = mm;

	/* Is it from 0 to ~0? */
	tlb->fullmm     = !(start | (end+1));
	tlb->need_flush_all = 0;
	tlb->start	= start;
	tlb->end	= end;
	tlb->need_flush = 0;
	tlb->local.next = NULL;
	tlb->local.nr   = 0;
	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
	tlb->active     = &tlb->local;
	tlb->batch_count = 0;

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb->batch = NULL;
#endif
}

static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
	tlb->need_flush = 0;
	tlb_flush(tlb);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb_table_flush(tlb);
#endif
}

static void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	for (batch = &tlb->local; batch; batch = batch->next) {
		free_pages_and_swap_cache(batch->pages, batch->nr);
		batch->nr = 0;
	}
	tlb->active = &tlb->local;
}

void tlb_flush_mmu(struct mmu_gather *tlb)
{
	if (!tlb->need_flush)
		return;
	tlb_flush_mmu_tlbonly(tlb);
	tlb_flush_mmu_free(tlb);
}

/* tlb_finish_mmu
 *	Called at the end of the shootdown operation to free up any resources
 *	that were required.
 */
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
{
	struct mmu_gather_batch *batch, *next;

	tlb_flush_mmu(tlb);

	/* keep the page table cache within bounds */
	check_pgt_cache();

	for (batch = tlb->local.next; batch; batch = next) {
		next = batch->next;
		free_pages((unsigned long)batch, 0);
	}
	tlb->local.next = NULL;
}

/* __tlb_remove_page
 *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
 *	handling the additional races in SMP caused by other CPUs caching valid
 *	mappings in their TLBs. Returns the number of free page slots left.
 *	When out of page slots we must call tlb_flush_mmu().
 */
int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
	struct mmu_gather_batch *batch;

	VM_BUG_ON(!tlb->need_flush);

	batch = tlb->active;
	batch->pages[batch->nr++] = page;
	if (batch->nr == batch->max) {
		if (!tlb_next_batch(tlb))
			return 0;
		batch = tlb->active;
	}
	VM_BUG_ON_PAGE(batch->nr > batch->max, page);

	return batch->max - batch->nr;
}

#endif /* HAVE_GENERIC_MMU_GATHER */

#ifdef CONFIG_HAVE_RCU_TABLE_FREE

/*
 * See the comment near struct mmu_table_batch.
 */

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

static void tlb_remove_table_one(void *table)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely on
	 * IRQ disabling. See the comment near struct mmu_table_batch.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
	__tlb_remove_table(table);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	struct mmu_table_batch *batch;
	int i;

	batch = container_of(head, struct mmu_table_batch, rcu);

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	tlb->need_flush = 1;

	/*
	 * When there's less then two users of this mm there cannot be a
	 * concurrent page-table walk.
	 */
	if (atomic_read(&tlb->mm->mm_users) < 2) {
		__tlb_remove_table(table);
		return;
	}

	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}
	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_table_flush(tlb);
}

#endif /* CONFIG_HAVE_RCU_TABLE_FREE */

/*
 * Note: this doesn't free the actual pages themselves. That
 * has been handled earlier when unmapping all the memory regions.
 */
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
			   unsigned long addr)
{
	pgtable_t token = pmd_pgtable(*pmd);
	pmd_clear(pmd);
	pte_free_tlb(tlb, token, addr);
	atomic_long_dec(&tlb->mm->nr_ptes);
}

static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
{
	pmd_t *pmd;
	unsigned long next;
	unsigned long start;

	start = addr;
	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		free_pte_range(tlb, pmd, addr);
	} while (pmd++, addr = next, addr != end);

	start &= PUD_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PUD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pmd = pmd_offset(pud, start);
	pud_clear(pud);
	pmd_free_tlb(tlb, pmd, start);
}

static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
{
	pud_t *pud;
	unsigned long next;
	unsigned long start;

	start = addr;
	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
	} while (pud++, addr = next, addr != end);

	start &= PGDIR_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PGDIR_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pud = pud_offset(pgd, start);
	pgd_clear(pgd);
	pud_free_tlb(tlb, pud, start);
}

/*
 * This function frees user-level page tables of a process.
 */
void free_pgd_range(struct mmu_gather *tlb,
			unsigned long addr, unsigned long end,
			unsigned long floor, unsigned long ceiling)
{
	pgd_t *pgd;
	unsigned long next;

	/*
	 * The next few lines have given us lots of grief...
	 *
	 * Why are we testing PMD* at this top level?  Because often
	 * there will be no work to do at all, and we'd prefer not to
	 * go all the way down to the bottom just to discover that.
	 *
	 * Why all these "- 1"s?  Because 0 represents both the bottom
	 * of the address space and the top of it (using -1 for the
	 * top wouldn't help much: the masks would do the wrong thing).
	 * The rule is that addr 0 and floor 0 refer to the bottom of
	 * the address space, but end 0 and ceiling 0 refer to the top
	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
	 * that end 0 case should be mythical).
	 *
	 * Wherever addr is brought up or ceiling brought down, we must
	 * be careful to reject "the opposite 0" before it confuses the
	 * subsequent tests.  But what about where end is brought down
	 * by PMD_SIZE below? no, end can't go down to 0 there.
	 *
	 * Whereas we round start (addr) and ceiling down, by different
	 * masks at different levels, in order to test whether a table
	 * now has no other vmas using it, so can be freed, we don't
	 * bother to round floor or end up - the tests don't need that.
	 */

	addr &= PMD_MASK;
	if (addr < floor) {
		addr += PMD_SIZE;
		if (!addr)
			return;
	}
	if (ceiling) {
		ceiling &= PMD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		end -= PMD_SIZE;
	if (addr > end - 1)
		return;

	pgd = pgd_offset(tlb->mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		free_pud_range(tlb, pgd, addr, next, floor, ceiling);
	} while (pgd++, addr = next, addr != end);
}

void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
		unsigned long floor, unsigned long ceiling)
{
	while (vma) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long addr = vma->vm_start;

		/*
		 * Hide vma from rmap and truncate_pagecache before freeing
		 * pgtables
		 */
		unlink_anon_vmas(vma);
		unlink_file_vma(vma);

		if (is_vm_hugetlb_page(vma)) {
			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		} else {
			/*
			 * Optimization: gather nearby vmas into one call down
			 */
			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
			       && !is_vm_hugetlb_page(next)) {
				vma = next;
				next = vma->vm_next;
				unlink_anon_vmas(vma);
				unlink_file_vma(vma);
			}
			free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		}
		vma = next;
	}
}

int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
		pmd_t *pmd, unsigned long address)
{
	spinlock_t *ptl;
	pgtable_t new = pte_alloc_one(mm, address);
	int wait_split_huge_page;
	if (!new)
		return -ENOMEM;

	/*
	 * Ensure all pte setup (eg. pte page lock and page clearing) are
	 * visible before the pte is made visible to other CPUs by being
	 * put into page tables.
	 *
	 * The other side of the story is the pointer chasing in the page
	 * table walking code (when walking the page table without locking;
	 * ie. most of the time). Fortunately, these data accesses consist
	 * of a chain of data-dependent loads, meaning most CPUs (alpha
	 * being the notable exception) will already guarantee loads are
	 * seen in-order. See the alpha page table accessors for the
	 * smp_read_barrier_depends() barriers in page table walking code.
	 */
	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */

	ptl = pmd_lock(mm, pmd);
	wait_split_huge_page = 0;
	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
		atomic_long_inc(&mm->nr_ptes);
		pmd_populate(mm, pmd, new);
		new = NULL;
	} else if (unlikely(pmd_trans_splitting(*pmd)))
		wait_split_huge_page = 1;
	spin_unlock(ptl);
	if (new)
		pte_free(mm, new);
	if (wait_split_huge_page)
		wait_split_huge_page(vma->anon_vma, pmd);
	return 0;
}

int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
{
	pte_t *new = pte_alloc_one_kernel(&init_mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&init_mm.page_table_lock);
	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
		pmd_populate_kernel(&init_mm, pmd, new);
		new = NULL;
	} else
		VM_BUG_ON(pmd_trans_splitting(*pmd));
	spin_unlock(&init_mm.page_table_lock);
	if (new)
		pte_free_kernel(&init_mm, new);
	return 0;
}

static inline void init_rss_vec(int *rss)
{
	memset(rss, 0, sizeof(int) * NR_MM_COUNTERS);
}

static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
{
	int i;

	if (current->mm == mm)
		sync_mm_rss(mm);
	for (i = 0; i < NR_MM_COUNTERS; i++)
		if (rss[i])
			add_mm_counter(mm, i, rss[i]);
}

/*
 * This function is called to print an error when a bad pte
 * is found. For example, we might have a PFN-mapped pte in
 * a region that doesn't allow it.
 *
 * The calling function must still handle the error.
 */
static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
			  pte_t pte, struct page *page)
{
	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
	pud_t *pud = pud_offset(pgd, addr);
	pmd_t *pmd = pmd_offset(pud, addr);
	struct address_space *mapping;
	pgoff_t index;
	static unsigned long resume;
	static unsigned long nr_shown;
	static unsigned long nr_unshown;

	/*
	 * Allow a burst of 60 reports, then keep quiet for that minute;
	 * or allow a steady drip of one report per second.
	 */
	if (nr_shown == 60) {
		if (time_before(jiffies, resume)) {
			nr_unshown++;
			return;
		}
		if (nr_unshown) {
			printk(KERN_ALERT
				"BUG: Bad page map: %lu messages suppressed\n",
				nr_unshown);
			nr_unshown = 0;
		}
		nr_shown = 0;
	}
	if (nr_shown++ == 0)
		resume = jiffies + 60 * HZ;

	mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
	index = linear_page_index(vma, addr);

	printk(KERN_ALERT
		"BUG: Bad page map in process %s  pte:%08llx pmd:%08llx\n",
		current->comm,
		(long long)pte_val(pte), (long long)pmd_val(*pmd));
	if (page)
		dump_page(page, "bad pte");
	printk(KERN_ALERT
		"addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n",
		(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
	/*
	 * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y
	 */
	if (vma->vm_ops)
		printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n",
		       vma->vm_ops->fault);
	if (vma->vm_file)
		printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n",
		       vma->vm_file->f_op->mmap);
	dump_stack();
	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}

/*
 * vm_normal_page -- This function gets the "struct page" associated with a pte.
 *
 * "Special" mappings do not wish to be associated with a "struct page" (either
 * it doesn't exist, or it exists but they don't want to touch it). In this
 * case, NULL is returned here. "Normal" mappings do have a struct page.
 *
 * There are 2 broad cases. Firstly, an architecture may define a pte_special()
 * pte bit, in which case this function is trivial. Secondly, an architecture
 * may not have a spare pte bit, which requires a more complicated scheme,
 * described below.
 *
 * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
 * special mapping (even if there are underlying and valid "struct pages").
 * COWed pages of a VM_PFNMAP are always normal.
 *
 * The way we recognize COWed pages within VM_PFNMAP mappings is through the
 * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
 * set, and the vm_pgoff will point to the first PFN mapped: thus every special
 * mapping will always honor the rule
 *
 *	pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
 *
 * And for normal mappings this is false.
 *
 * This restricts such mappings to be a linear translation from virtual address
 * to pfn. To get around this restriction, we allow arbitrary mappings so long
 * as the vma is not a COW mapping; in that case, we know that all ptes are
 * special (because none can have been COWed).
 *
 *
 * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
 *
 * VM_MIXEDMAP mappings can likewise contain memory with or without "struct
 * page" backing, however the difference is that _all_ pages with a struct
 * page (that is, those where pfn_valid is true) are refcounted and considered
 * normal pages by the VM. The disadvantage is that pages are refcounted
 * (which can be slower and simply not an option for some PFNMAP users). The
 * advantage is that we don't have to follow the strict linearity rule of
 * PFNMAP mappings in order to support COWable mappings.
 *
 */
#ifdef __HAVE_ARCH_PTE_SPECIAL
# define HAVE_PTE_SPECIAL 1
#else
# define HAVE_PTE_SPECIAL 0
#endif
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
				pte_t pte)
{
	unsigned long pfn = pte_pfn(pte);

	if (HAVE_PTE_SPECIAL) {
		if (likely(!pte_special(pte)))
			goto check_pfn;
		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
			return NULL;
		if (!is_zero_pfn(pfn))
			print_bad_pte(vma, addr, pte, NULL);
		return NULL;
	}

	/* !HAVE_PTE_SPECIAL case follows: */

	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
		if (vma->vm_flags & VM_MIXEDMAP) {
			if (!pfn_valid(pfn))
				return NULL;
			goto out;
		} else {
			unsigned long off;
			off = (addr - vma->vm_start) >> PAGE_SHIFT;
			if (pfn == vma->vm_pgoff + off)
				return NULL;
			if (!is_cow_mapping(vma->vm_flags))
				return NULL;
		}
	}

	if (is_zero_pfn(pfn))
		return NULL;
check_pfn:
	if (unlikely(pfn > highest_memmap_pfn)) {
		print_bad_pte(vma, addr, pte, NULL);
		return NULL;
	}

	/*
	 * NOTE! We still have PageReserved() pages in the page tables.
	 * eg. VDSO mappings can cause them to exist.
	 */
out:
	return pfn_to_page(pfn);
}

/*
 * copy one vm_area from one task to the other. Assumes the page tables
 * already present in the new task to be cleared in the whole range
 * covered by this vma.
 */

static inline unsigned long
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
		unsigned long addr, int *rss)
{
	unsigned long vm_flags = vma->vm_flags;
	pte_t pte = *src_pte;
	struct page *page;

	/* pte contains position in swap or file, so copy. */
	if (unlikely(!pte_present(pte))) {
		if (!pte_file(pte)) {
			swp_entry_t entry = pte_to_swp_entry(pte);

			if (swap_duplicate(entry) < 0)
				return entry.val;

			/* make sure dst_mm is on swapoff's mmlist. */
			if (unlikely(list_empty(&dst_mm->mmlist))) {
				spin_lock(&mmlist_lock);
				if (list_empty(&dst_mm->mmlist))
					list_add(&dst_mm->mmlist,
						 &src_mm->mmlist);
				spin_unlock(&mmlist_lock);
			}
			if (likely(!non_swap_entry(entry)))
				rss[MM_SWAPENTS]++;
			else if (is_migration_entry(entry)) {
				page = migration_entry_to_page(entry);

				if (PageAnon(page))
					rss[MM_ANONPAGES]++;
				else
					rss[MM_FILEPAGES]++;

				if (is_write_migration_entry(entry) &&
				    is_cow_mapping(vm_flags)) {
					/*
					 * COW mappings require pages in both
					 * parent and child to be set to read.
					 */
					make_migration_entry_read(&entry);
					pte = swp_entry_to_pte(entry);
					if (pte_swp_soft_dirty(*src_pte))
						pte = pte_swp_mksoft_dirty(pte);
					set_pte_at(src_mm, addr, src_pte, pte);
				}
			}
		}
		goto out_set_pte;
	}

	/*
	 * If it's a COW mapping, write protect it both
	 * in the parent and the child
	 */
	if (is_cow_mapping(vm_flags)) {
		ptep_set_wrprotect(src_mm, addr, src_pte);
		pte = pte_wrprotect(pte);
	}

	/*
	 * If it's a shared mapping, mark it clean in
	 * the child
	 */
	if (vm_flags & VM_SHARED)
		pte = pte_mkclean(pte);
	pte = pte_mkold(pte);

	page = vm_normal_page(vma, addr, pte);
	if (page) {
		get_page(page);
		page_dup_rmap(page);
		if (PageAnon(page))
			rss[MM_ANONPAGES]++;
		else
			rss[MM_FILEPAGES]++;
	}

out_set_pte:
	set_pte_at(dst_mm, addr, dst_pte, pte);
	return 0;
}

static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
		   unsigned long addr, unsigned long end)
{
	pte_t *orig_src_pte, *orig_dst_pte;
	pte_t *src_pte, *dst_pte;
	spinlock_t *src_ptl, *dst_ptl;
	int progress = 0;
	int rss[NR_MM_COUNTERS];
	swp_entry_t entry = (swp_entry_t){0};

again:
	init_rss_vec(rss);

	dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
	if (!dst_pte)
		return -ENOMEM;
	src_pte = pte_offset_map(src_pmd, addr);
	src_ptl = pte_lockptr(src_mm, src_pmd);
	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
	orig_src_pte = src_pte;
	orig_dst_pte = dst_pte;
	arch_enter_lazy_mmu_mode();

	do {
		/*
		 * We are holding two locks at this point - either of them
		 * could generate latencies in another task on another CPU.
		 */
		if (progress >= 32) {
			progress = 0;
			if (need_resched() ||
			    spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
				break;
		}
		if (pte_none(*src_pte)) {
			progress++;
			continue;
		}
		entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
							vma, addr, rss);
		if (entry.val)
			break;
		progress += 8;
	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);

	arch_leave_lazy_mmu_mode();
	spin_unlock(src_ptl);
	pte_unmap(orig_src_pte);
	add_mm_rss_vec(dst_mm, rss);
	pte_unmap_unlock(orig_dst_pte, dst_ptl);
	cond_resched();

	if (entry.val) {
		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
			return -ENOMEM;
		progress = 0;
	}
	if (addr != end)
		goto again;
	return 0;
}

static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pmd_t *src_pmd, *dst_pmd;
	unsigned long next;

	dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
	if (!dst_pmd)
		return -ENOMEM;
	src_pmd = pmd_offset(src_pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_trans_huge(*src_pmd)) {
			int err;
			VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
			err = copy_huge_pmd(dst_mm, src_mm,
					    dst_pmd, src_pmd, addr, vma);
			if (err == -ENOMEM)
				return -ENOMEM;
			if (!err)
				continue;
			/* fall through */
		}
		if (pmd_none_or_clear_bad(src_pmd))
			continue;
		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
	return 0;
}

static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pud_t *src_pud, *dst_pud;
	unsigned long next;

	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
	if (!dst_pud)
		return -ENOMEM;
	src_pud = pud_offset(src_pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(src_pud))
			continue;
		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pud++, src_pud++, addr = next, addr != end);
	return 0;
}

int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		struct vm_area_struct *vma)
{
	pgd_t *src_pgd, *dst_pgd;
	unsigned long next;
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */
	bool is_cow;
	int ret;

	/*
	 * Don't copy ptes where a page fault will fill them correctly.
	 * Fork becomes much lighter when there are big shared or private
	 * readonly mappings. The tradeoff is that copy_page_range is more
	 * efficient than faulting.
	 */
	if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR |
			       VM_PFNMAP | VM_MIXEDMAP))) {
		if (!vma->anon_vma)
			return 0;
	}

	if (is_vm_hugetlb_page(vma))
		return copy_hugetlb_page_range(dst_mm, src_mm, vma);

	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
		/*
		 * We do not free on error cases below as remove_vma
		 * gets called on error from higher level routine
		 */
		ret = track_pfn_copy(vma);
		if (ret)
			return ret;
	}

	/*
	 * We need to invalidate the secondary MMU mappings only when
	 * there could be a permission downgrade on the ptes of the
	 * parent mm. And a permission downgrade will only happen if
	 * is_cow_mapping() returns true.
	 */
	is_cow = is_cow_mapping(vma->vm_flags);
	mmun_start = addr;
	mmun_end   = end;
	if (is_cow)
		mmu_notifier_invalidate_range_start(src_mm, mmun_start,
						    mmun_end);

	ret = 0;
	dst_pgd = pgd_offset(dst_mm, addr);
	src_pgd = pgd_offset(src_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(src_pgd))
			continue;
		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
					    vma, addr, next))) {
			ret = -ENOMEM;
			break;
		}
	} while (dst_pgd++, src_pgd++, addr = next, addr != end);

	if (is_cow)
		mmu_notifier_invalidate_range_end(src_mm, mmun_start, mmun_end);
	return ret;
}

static unsigned long zap_pte_range(struct mmu_gather *tlb,
				struct vm_area_struct *vma, pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	struct mm_struct *mm = tlb->mm;
	int force_flush = 0;
	int rss[NR_MM_COUNTERS];
	spinlock_t *ptl;
	pte_t *start_pte;
	pte_t *pte;

again:
	init_rss_vec(rss);
	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
	pte = start_pte;
	arch_enter_lazy_mmu_mode();
	do {
		pte_t ptent = *pte;
		if (pte_none(ptent)) {
			continue;
		}

		if (pte_present(ptent)) {
			struct page *page;

			page = vm_normal_page(vma, addr, ptent);
			if (unlikely(details) && page) {
				/*
				 * unmap_shared_mapping_pages() wants to
				 * invalidate cache without truncating:
				 * unmap shared but keep private pages.
				 */
				if (details->check_mapping &&
				    details->check_mapping != page->mapping)
					continue;
				/*
				 * Each page->index must be checked when
				 * invalidating or truncating nonlinear.
				 */
				if (details->nonlinear_vma &&
				    (page->index < details->first_index ||
				     page->index > details->last_index))
					continue;
			}
			ptent = ptep_get_and_clear_full(mm, addr, pte,
							tlb->fullmm);
			tlb_remove_tlb_entry(tlb, pte, addr);
			if (unlikely(!page))
				continue;
			if (unlikely(details) && details->nonlinear_vma
			    && linear_page_index(details->nonlinear_vma,
						addr) != page->index) {
				pte_t ptfile = pgoff_to_pte(page->index);
				if (pte_soft_dirty(ptent))
					pte_file_mksoft_dirty(ptfile);
				set_pte_at(mm, addr, pte, ptfile);
			}
			if (PageAnon(page))
				rss[MM_ANONPAGES]--;
			else {
				if (pte_dirty(ptent)) {
					force_flush = 1;
					set_page_dirty(page);
				}
				if (pte_young(ptent) &&
				    likely(!(vma->vm_flags & VM_SEQ_READ)))
					mark_page_accessed(page);
				rss[MM_FILEPAGES]--;
			}
			page_remove_rmap(page);
			if (unlikely(page_mapcount(page) < 0))
				print_bad_pte(vma, addr, ptent, page);
			if (unlikely(!__tlb_remove_page(tlb, page))) {
				force_flush = 1;
				break;
			}
			continue;
		}
		/*
		 * If details->check_mapping, we leave swap entries;
		 * if details->nonlinear_vma, we leave file entries.
		 */
		if (unlikely(details))
			continue;
		if (pte_file(ptent)) {
			if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
				print_bad_pte(vma, addr, ptent, NULL);
		} else {
			swp_entry_t entry = pte_to_swp_entry(ptent);

			if (!non_swap_entry(entry))
				rss[MM_SWAPENTS]--;
			else if (is_migration_entry(entry)) {
				struct page *page;

				page = migration_entry_to_page(entry);

				if (PageAnon(page))
					rss[MM_ANONPAGES]--;
				else
					rss[MM_FILEPAGES]--;
			}
			if (unlikely(!free_swap_and_cache(entry)))
				print_bad_pte(vma, addr, ptent, NULL);
		}
		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
	} while (pte++, addr += PAGE_SIZE, addr != end);

	add_mm_rss_vec(mm, rss);
	arch_leave_lazy_mmu_mode();

	/* Do the actual TLB flush before dropping ptl */
	if (force_flush) {
		unsigned long old_end;

		/*
		 * Flush the TLB just for the previous segment,
		 * then update the range to be the remaining
		 * TLB range.
		 */
		old_end = tlb->end;
		tlb->end = addr;
		tlb_flush_mmu_tlbonly(tlb);
		tlb->start = addr;
		tlb->end = old_end;
	}
	pte_unmap_unlock(start_pte, ptl);

	/*
	 * If we forced a TLB flush (either due to running out of
	 * batch buffers or because we needed to flush dirty TLB
	 * entries before releasing the ptl), free the batched
	 * memory too. Restart if we didn't do everything.
	 */
	if (force_flush) {
		force_flush = 0;
		tlb_flush_mmu_free(tlb);

		if (addr != end)
			goto again;
	}

	return addr;
}

static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
				struct vm_area_struct *vma, pud_t *pud,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_trans_huge(*pmd)) {
			if (next - addr != HPAGE_PMD_SIZE) {
#ifdef CONFIG_DEBUG_VM
				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
						__func__, addr, end,
						vma->vm_start,
						vma->vm_end);
					BUG();
				}
#endif
				split_huge_page_pmd(vma, addr, pmd);
			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
				goto next;
			/* fall through */
		}
		/*
		 * Here there can be other concurrent MADV_DONTNEED or
		 * trans huge page faults running, and if the pmd is
		 * none or trans huge it can change under us. This is
		 * because MADV_DONTNEED holds the mmap_sem in read
		 * mode.
		 */
		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
			goto next;
		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
next:
		cond_resched();
	} while (pmd++, addr = next, addr != end);

	return addr;
}

static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
				struct vm_area_struct *vma, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
	} while (pud++, addr = next, addr != end);

	return addr;
}

static void unmap_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end,
			     struct zap_details *details)
{
	pgd_t *pgd;
	unsigned long next;

	if (details && !details->check_mapping && !details->nonlinear_vma)
		details = NULL;

	BUG_ON(addr >= end);
	tlb_start_vma(tlb, vma);
	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
	} while (pgd++, addr = next, addr != end);
	tlb_end_vma(tlb, vma);
}


static void unmap_single_vma(struct mmu_gather *tlb,
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr,
		struct zap_details *details)
{
	unsigned long start = max(vma->vm_start, start_addr);
	unsigned long end;

	if (start >= vma->vm_end)
		return;
	end = min(vma->vm_end, end_addr);
	if (end <= vma->vm_start)
		return;

	if (vma->vm_file)
		uprobe_munmap(vma, start, end);

	if (unlikely(vma->vm_flags & VM_PFNMAP))
		untrack_pfn(vma, 0, 0);

	if (start != end) {
		if (unlikely(is_vm_hugetlb_page(vma))) {
			/*
			 * It is undesirable to test vma->vm_file as it
			 * should be non-null for valid hugetlb area.
			 * However, vm_file will be NULL in the error
			 * cleanup path of mmap_region. When
			 * hugetlbfs ->mmap method fails,
			 * mmap_region() nullifies vma->vm_file
			 * before calling this function to clean up.
			 * Since no pte has actually been setup, it is
			 * safe to do nothing in this case.
			 */
			if (vma->vm_file) {
				mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
				__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
				mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
			}
		} else
			unmap_page_range(tlb, vma, start, end, details);
	}
}

/**
 * unmap_vmas - unmap a range of memory covered by a list of vma's
 * @tlb: address of the caller's struct mmu_gather
 * @vma: the starting vma
 * @start_addr: virtual address at which to start unmapping
 * @end_addr: virtual address at which to end unmapping
 *
 * Unmap all pages in the vma list.
 *
 * Only addresses between `start' and `end' will be unmapped.
 *
 * The VMA list must be sorted in ascending virtual address order.
 *
 * unmap_vmas() assumes that the caller will flush the whole unmapped address
 * range after unmap_vmas() returns.  So the only responsibility here is to
 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
 * drops the lock and schedules.
 */
void unmap_vmas(struct mmu_gather *tlb,
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr)
{
	struct mm_struct *mm = vma->vm_mm;

	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
		unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
}

/**
 * zap_page_range - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @start: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 *
 * Caller must protect the VMA list
 */
void zap_page_range(struct vm_area_struct *vma, unsigned long start,
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather tlb;
	unsigned long end = start + size;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, start, end);
	update_hiwater_rss(mm);
	mmu_notifier_invalidate_range_start(mm, start, end);
	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
		unmap_single_vma(&tlb, vma, start, end, details);
	mmu_notifier_invalidate_range_end(mm, start, end);
	tlb_finish_mmu(&tlb, start, end);
}

/**
 * zap_page_range_single - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 *
 * The range must fit into one VMA.
 */
static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather tlb;
	unsigned long end = address + size;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, address, end);
	update_hiwater_rss(mm);
	mmu_notifier_invalidate_range_start(mm, address, end);
	unmap_single_vma(&tlb, vma, address, end, details);
	mmu_notifier_invalidate_range_end(mm, address, end);
	tlb_finish_mmu(&tlb, address, end);
}

/**
 * zap_vma_ptes - remove ptes mapping the vma
 * @vma: vm_area_struct holding ptes to be zapped
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 *
 * This function only unmaps ptes assigned to VM_PFNMAP vmas.
 *
 * The entire address range must be fully contained within the vma.
 *
 * Returns 0 if successful.
 */
int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
		unsigned long size)
{
	if (address < vma->vm_start || address + size > vma->vm_end ||
	    		!(vma->vm_flags & VM_PFNMAP))
		return -1;
	zap_page_range_single(vma, address, size, NULL);
	return 0;
}
EXPORT_SYMBOL_GPL(zap_vma_ptes);

pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
			spinlock_t **ptl)
{
	pgd_t * pgd = pgd_offset(mm, addr);
	pud_t * pud = pud_alloc(mm, pgd, addr);
	if (pud) {
		pmd_t * pmd = pmd_alloc(mm, pud, addr);
		if (pmd) {
			VM_BUG_ON(pmd_trans_huge(*pmd));
			return pte_alloc_map_lock(mm, pmd, addr, ptl);
		}
	}
	return NULL;
}

/*
 * This is the old fallback for page remapping.
 *
 * For historical reasons, it only allows reserved pages. Only
 * old drivers should use this, and they needed to mark their
 * pages reserved for the old functions anyway.
 */
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
			struct page *page, pgprot_t prot)
{
	struct mm_struct *mm = vma->vm_mm;
	int retval;
	pte_t *pte;
	spinlock_t *ptl;

	retval = -EINVAL;
	if (PageAnon(page))
		goto out;
	retval = -ENOMEM;
	flush_dcache_page(page);
	pte = get_locked_pte(mm, addr, &ptl);
	if (!pte)
		goto out;
	retval = -EBUSY;
	if (!pte_none(*pte))
		goto out_unlock;

	/* Ok, finally just insert the thing.. */
	get_page(page);
	inc_mm_counter_fast(mm, MM_FILEPAGES);
	page_add_file_rmap(page);
	set_pte_at(mm, addr, pte, mk_pte(page, prot));

	retval = 0;
	pte_unmap_unlock(pte, ptl);
	return retval;
out_unlock:
	pte_unmap_unlock(pte, ptl);
out:
	return retval;
}

/**
 * vm_insert_page - insert single page into user vma
 * @vma: user vma to map to
 * @addr: target user address of this page
 * @page: source kernel page
 *
 * This allows drivers to insert individual pages they've allocated
 * into a user vma.
 *
 * The page has to be a nice clean _individual_ kernel allocation.
 * If you allocate a compound page, you need to have marked it as
 * such (__GFP_COMP), or manually just split the page up yourself
 * (see split_page()).
 *
 * NOTE! Traditionally this was done with "remap_pfn_range()" which
 * took an arbitrary page protection parameter. This doesn't allow
 * that. Your vma protection will have to be set up correctly, which
 * means that if you want a shared writable mapping, you'd better
 * ask for a shared writable mapping!
 *
 * The page does not need to be reserved.
 *
 * Usually this function is called from f_op->mmap() handler
 * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
 * Caller must set VM_MIXEDMAP on vma if it wants to call this
 * function from other places, for example from page-fault handler.
 */
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
			struct page *page)
{
	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;
	if (!page_count(page))
		return -EINVAL;
	if (!(vma->vm_flags & VM_MIXEDMAP)) {
		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
		BUG_ON(vma->vm_flags & VM_PFNMAP);
		vma->vm_flags |= VM_MIXEDMAP;
	}
	return insert_page(vma, addr, page, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_page);

static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn, pgprot_t prot)
{
	struct mm_struct *mm = vma->vm_mm;
	int retval;
	pte_t *pte, entry;
	spinlock_t *ptl;

	retval = -ENOMEM;
	pte = get_locked_pte(mm, addr, &ptl);
	if (!pte)
		goto out;
	retval = -EBUSY;
	if (!pte_none(*pte))
		goto out_unlock;

	/* Ok, finally just insert the thing.. */
	entry = pte_mkspecial(pfn_pte(pfn, prot));
	set_pte_at(mm, addr, pte, entry);
	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */

	retval = 0;
out_unlock:
	pte_unmap_unlock(pte, ptl);
out:
	return retval;
}

/**
 * vm_insert_pfn - insert single pfn into user vma
 * @vma: user vma to map to
 * @addr: target user address of this page
 * @pfn: source kernel pfn
 *
 * Similar to vm_insert_page, this allows drivers to insert individual pages
 * they've allocated into a user vma. Same comments apply.
 *
 * This function should only be called from a vm_ops->fault handler, and
 * in that case the handler should return NULL.
 *
 * vma cannot be a COW mapping.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 */
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn)
{
	int ret;
	pgprot_t pgprot = vma->vm_page_prot;
	/*
	 * Technically, architectures with pte_special can avoid all these
	 * restrictions (same for remap_pfn_range).  However we would like
	 * consistency in testing and feature parity among all, so we should
	 * try to keep these invariants in place for everybody.
	 */
	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
						(VM_PFNMAP|VM_MIXEDMAP));
	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;
	if (track_pfn_insert(vma, &pgprot, pfn))
		return -EINVAL;

	ret = insert_pfn(vma, addr, pfn, pgprot);

	return ret;
}
EXPORT_SYMBOL(vm_insert_pfn);

int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn)
{
	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;

	/*
	 * If we don't have pte special, then we have to use the pfn_valid()
	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
	 * refcount the page if pfn_valid is true (hence insert_page rather
	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
	 * without pte special, it would there be refcounted as a normal page.
	 */
	if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
		struct page *page;

		page = pfn_to_page(pfn);
		return insert_page(vma, addr, page, vma->vm_page_prot);
	}
	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_mixed);

/*
 * maps a range of physical memory into the requested pages. the old
 * mappings are removed. any references to nonexistent pages results
 * in null mappings (currently treated as "copy-on-access")
 */
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pte_t *pte;
	spinlock_t *ptl;

	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
	if (!pte)
		return -ENOMEM;
	arch_enter_lazy_mmu_mode();
	do {
		BUG_ON(!pte_none(*pte));
		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(pte - 1, ptl);
	return 0;
}

static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	do {
		next = pmd_addr_end(addr, end);
		if (remap_pte_range(mm, pmd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (remap_pmd_range(mm, pud, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

/**
 * remap_pfn_range - remap kernel memory to userspace
 * @vma: user vma to map to
 * @addr: target user address to start at
 * @pfn: physical address of kernel memory
 * @size: size of map area
 * @prot: page protection flags for this mapping
 *
 *  Note: this is only safe if the mm semaphore is held when called.
 */
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
		    unsigned long pfn, unsigned long size, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + PAGE_ALIGN(size);
	struct mm_struct *mm = vma->vm_mm;
	int err;

	/*
	 * Physically remapped pages are special. Tell the
	 * rest of the world about it:
	 *   VM_IO tells people not to look at these pages
	 *	(accesses can have side effects).
	 *   VM_PFNMAP tells the core MM that the base pages are just
	 *	raw PFN mappings, and do not have a "struct page" associated
	 *	with them.
	 *   VM_DONTEXPAND
	 *      Disable vma merging and expanding with mremap().
	 *   VM_DONTDUMP
	 *      Omit vma from core dump, even when VM_IO turned off.
	 *
	 * There's a horrible special case to handle copy-on-write
	 * behaviour that some programs depend on. We mark the "original"
	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
	 * See vm_normal_page() for details.
	 */
	if (is_cow_mapping(vma->vm_flags)) {
		if (addr != vma->vm_start || end != vma->vm_end)
			return -EINVAL;
		vma->vm_pgoff = pfn;
	}

	err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
	if (err)
		return -EINVAL;

	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;

	BUG_ON(addr >= end);
	pfn -= addr >> PAGE_SHIFT;
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	do {
		next = pgd_addr_end(addr, end);
		err = remap_pud_range(mm, pgd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	if (err)
		untrack_pfn(vma, pfn, PAGE_ALIGN(size));

	return err;
}
EXPORT_SYMBOL(remap_pfn_range);

/**
 * vm_iomap_memory - remap memory to userspace
 * @vma: user vma to map to
 * @start: start of area
 * @len: size of area
 *
 * This is a simplified io_remap_pfn_range() for common driver use. The
 * driver just needs to give us the physical memory range to be mapped,
 * we'll figure out the rest from the vma information.
 *
 * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
 * whatever write-combining details or similar.
 */
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
	unsigned long vm_len, pfn, pages;

	/* Check that the physical memory area passed in looks valid */
	if (start + len < start)
		return -EINVAL;
	/*
	 * You *really* shouldn't map things that aren't page-aligned,
	 * but we've historically allowed it because IO memory might
	 * just have smaller alignment.
	 */
	len += start & ~PAGE_MASK;
	pfn = start >> PAGE_SHIFT;
	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
	if (pfn + pages < pfn)
		return -EINVAL;

	/* We start the mapping 'vm_pgoff' pages into the area */
	if (vma->vm_pgoff > pages)
		return -EINVAL;
	pfn += vma->vm_pgoff;
	pages -= vma->vm_pgoff;

	/* Can we fit all of the mapping? */
	vm_len = vma->vm_end - vma->vm_start;
	if (vm_len >> PAGE_SHIFT > pages)
		return -EINVAL;

	/* Ok, let it rip */
	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_iomap_memory);

static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pte_t *pte;
	int err;
	pgtable_t token;
	spinlock_t *uninitialized_var(ptl);

	pte = (mm == &init_mm) ?
		pte_alloc_kernel(pmd, addr) :
		pte_alloc_map_lock(mm, pmd, addr, &ptl);
	if (!pte)
		return -ENOMEM;

	BUG_ON(pmd_huge(*pmd));

	arch_enter_lazy_mmu_mode();

	token = pmd_pgtable(*pmd);

	do {
		err = fn(pte++, token, addr, data);
		if (err)
			break;
	} while (addr += PAGE_SIZE, addr != end);

	arch_leave_lazy_mmu_mode();

	if (mm != &init_mm)
		pte_unmap_unlock(pte-1, ptl);
	return err;
}

static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pmd_t *pmd;
	unsigned long next;
	int err;

	BUG_ON(pud_huge(*pud));

	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
		if (err)
			break;
	} while (pmd++, addr = next, addr != end);
	return err;
}

static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pud_t *pud;
	unsigned long next;
	int err;

	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
		if (err)
			break;
	} while (pud++, addr = next, addr != end);
	return err;
}

/*
 * Scan a region of virtual memory, filling in page tables as necessary
 * and calling a provided function on each leaf page table.
 */
int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
			unsigned long size, pte_fn_t fn, void *data)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + size;
	int err;

	BUG_ON(addr >= end);
	pgd = pgd_offset(mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	return err;
}
EXPORT_SYMBOL_GPL(apply_to_page_range);

/*
 * handle_pte_fault chooses page fault handler according to an entry
 * which was read non-atomically.  Before making any commitment, on
 * those architectures or configurations (e.g. i386 with PAE) which
 * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
 * must check under lock before unmapping the pte and proceeding
 * (but do_wp_page is only called after already making such a check;
 * and do_anonymous_page can safely check later on).
 */
static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
				pte_t *page_table, pte_t orig_pte)
{
	int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
	if (sizeof(pte_t) > sizeof(unsigned long)) {
		spinlock_t *ptl = pte_lockptr(mm, pmd);
		spin_lock(ptl);
		same = pte_same(*page_table, orig_pte);
		spin_unlock(ptl);
	}
#endif
	pte_unmap(page_table);
	return same;
}

static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
{
	debug_dma_assert_idle(src);

	/*
	 * If the source page was a PFN mapping, we don't have
	 * a "struct page" for it. We do a best-effort copy by
	 * just copying from the original user address. If that
	 * fails, we just zero-fill it. Live with it.
	 */
	if (unlikely(!src)) {
		void *kaddr = kmap_atomic(dst);
		void __user *uaddr = (void __user *)(va & PAGE_MASK);

		/*
		 * This really shouldn't fail, because the page is there
		 * in the page tables. But it might just be unreadable,
		 * in which case we just give up and fill the result with
		 * zeroes.
		 */
		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
			clear_page(kaddr);
		kunmap_atomic(kaddr);
		flush_dcache_page(dst);
	} else
		copy_user_highpage(dst, src, va, vma);
}

/*
 * Notify the address space that the page is about to become writable so that
 * it can prohibit this or wait for the page to get into an appropriate state.
 *
 * We do this without the lock held, so that it can sleep if it needs to.
 */
static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
	       unsigned long address)
{
	struct vm_fault vmf;
	int ret;

	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
	vmf.pgoff = page->index;
	vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
	vmf.page = page;

	ret = vma->vm_ops->page_mkwrite(vma, &vmf);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
		return ret;
	if (unlikely(!(ret & VM_FAULT_LOCKED))) {
		lock_page(page);
		if (!page->mapping) {
			unlock_page(page);
			return 0; /* retry */
		}
		ret |= VM_FAULT_LOCKED;
	} else
		VM_BUG_ON_PAGE(!PageLocked(page), page);
	return ret;
}

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * Note that this routine assumes that the protection checks have been
 * done by the caller (the low-level page fault routine in most cases).
 * Thus we can safely just mark it writable once we've done any necessary
 * COW.
 *
 * We also mark the page dirty at this point even though the page will
 * change only once the write actually happens. This avoids a few races,
 * and potentially makes it more efficient.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), with pte both mapped and locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		spinlock_t *ptl, pte_t orig_pte)
	__releases(ptl)
{
	struct page *old_page, *new_page = NULL;
	pte_t entry;
	int ret = 0;
	int page_mkwrite = 0;
	struct page *dirty_page = NULL;
	unsigned long mmun_start = 0;	/* For mmu_notifiers */
	unsigned long mmun_end = 0;	/* For mmu_notifiers */
	struct mem_cgroup *memcg;

	old_page = vm_normal_page(vma, address, orig_pte);
	if (!old_page) {
		/*
		 * VM_MIXEDMAP !pfn_valid() case
		 *
		 * We should not cow pages in a shared writeable mapping.
		 * Just mark the pages writable as we can't do any dirty
		 * accounting on raw pfn maps.
		 */
		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
				     (VM_WRITE|VM_SHARED))
			goto reuse;
		goto gotten;
	}

	/*
	 * Take out anonymous pages first, anonymous shared vmas are
	 * not dirty accountable.
	 */
	if (PageAnon(old_page) && !PageKsm(old_page)) {
		if (!trylock_page(old_page)) {
			page_cache_get(old_page);
			pte_unmap_unlock(page_table, ptl);
			lock_page(old_page);
			page_table = pte_offset_map_lock(mm, pmd, address,
							 &ptl);
			if (!pte_same(*page_table, orig_pte)) {
				unlock_page(old_page);
				goto unlock;
			}
			page_cache_release(old_page);
		}
		if (reuse_swap_page(old_page)) {
			/*
			 * The page is all ours.  Move it to our anon_vma so
			 * the rmap code will not search our parent or siblings.
			 * Protected against the rmap code by the page lock.
			 */
			page_move_anon_rmap(old_page, vma, address);
			unlock_page(old_page);
			goto reuse;
		}
		unlock_page(old_page);
	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
					(VM_WRITE|VM_SHARED))) {
		/*
		 * Only catch write-faults on shared writable pages,
		 * read-only shared pages can get COWed by
		 * get_user_pages(.write=1, .force=1).
		 */
		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
			int tmp;
			page_cache_get(old_page);
			pte_unmap_unlock(page_table, ptl);
			tmp = do_page_mkwrite(vma, old_page, address);
			if (unlikely(!tmp || (tmp &
					(VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
				page_cache_release(old_page);
				return tmp;
			}
			/*
			 * Since we dropped the lock we need to revalidate
			 * the PTE as someone else may have changed it.  If
			 * they did, we just return, as we can count on the
			 * MMU to tell us if they didn't also make it writable.
			 */
			page_table = pte_offset_map_lock(mm, pmd, address,
							 &ptl);
			if (!pte_same(*page_table, orig_pte)) {
				unlock_page(old_page);
				goto unlock;
			}

			page_mkwrite = 1;
		}
		dirty_page = old_page;
		get_page(dirty_page);

reuse:
		/*
		 * Clear the pages cpupid information as the existing
		 * information potentially belongs to a now completely
		 * unrelated process.
		 */
		if (old_page)
			page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1);

		flush_cache_page(vma, address, pte_pfn(orig_pte));
		entry = pte_mkyoung(orig_pte);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		if (ptep_set_access_flags(vma, address, page_table, entry,1))
			update_mmu_cache(vma, address, page_table);
		pte_unmap_unlock(page_table, ptl);
		ret |= VM_FAULT_WRITE;

		if (!dirty_page)
			return ret;

		/*
		 * Yes, Virginia, this is actually required to prevent a race
		 * with clear_page_dirty_for_io() from clearing the page dirty
		 * bit after it clear all dirty ptes, but before a racing
		 * do_wp_page installs a dirty pte.
		 *
		 * do_shared_fault is protected similarly.
		 */
		if (!page_mkwrite) {
			wait_on_page_locked(dirty_page);
			set_page_dirty_balance(dirty_page);
			/* file_update_time outside page_lock */
			if (vma->vm_file)
				file_update_time(vma->vm_file);
		}
		put_page(dirty_page);
		if (page_mkwrite) {
			struct address_space *mapping = dirty_page->mapping;

			set_page_dirty(dirty_page);
			unlock_page(dirty_page);
			page_cache_release(dirty_page);
			if (mapping)	{
				/*
				 * Some device drivers do not set page.mapping
				 * but still dirty their pages
				 */
				balance_dirty_pages_ratelimited(mapping);
			}
		}

		return ret;
	}

	/*
	 * Ok, we need to copy. Oh, well..
	 */
	page_cache_get(old_page);
gotten:
	pte_unmap_unlock(page_table, ptl);

	if (unlikely(anon_vma_prepare(vma)))
		goto oom;

	if (is_zero_pfn(pte_pfn(orig_pte))) {
		new_page = alloc_zeroed_user_highpage_movable(vma, address);
		if (!new_page)
			goto oom;
	} else {
		new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
		if (!new_page)
			goto oom;
		cow_user_page(new_page, old_page, address, vma);
	}
	__SetPageUptodate(new_page);

	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg))
		goto oom_free_new;

	mmun_start  = address & PAGE_MASK;
	mmun_end    = mmun_start + PAGE_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	/*
	 * Re-check the pte - we dropped the lock
	 */
	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (likely(pte_same(*page_table, orig_pte))) {
		if (old_page) {
			if (!PageAnon(old_page)) {
				dec_mm_counter_fast(mm, MM_FILEPAGES);
				inc_mm_counter_fast(mm, MM_ANONPAGES);
			}
		} else
			inc_mm_counter_fast(mm, MM_ANONPAGES);
		flush_cache_page(vma, address, pte_pfn(orig_pte));
		entry = mk_pte(new_page, vma->vm_page_prot);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		/*
		 * Clear the pte entry and flush it first, before updating the
		 * pte with the new entry. This will avoid a race condition
		 * seen in the presence of one thread doing SMC and another
		 * thread doing COW.
		 */
		ptep_clear_flush(vma, address, page_table);
		page_add_new_anon_rmap(new_page, vma, address);
		mem_cgroup_commit_charge(new_page, memcg, false);
		lru_cache_add_active_or_unevictable(new_page, vma);
		/*
		 * We call the notify macro here because, when using secondary
		 * mmu page tables (such as kvm shadow page tables), we want the
		 * new page to be mapped directly into the secondary page table.
		 */
		set_pte_at_notify(mm, address, page_table, entry);
		update_mmu_cache(vma, address, page_table);
		if (old_page) {
			/*
			 * Only after switching the pte to the new page may
			 * we remove the mapcount here. Otherwise another
			 * process may come and find the rmap count decremented
			 * before the pte is switched to the new page, and
			 * "reuse" the old page writing into it while our pte
			 * here still points into it and can be read by other
			 * threads.
			 *
			 * The critical issue is to order this
			 * page_remove_rmap with the ptp_clear_flush above.
			 * Those stores are ordered by (if nothing else,)
			 * the barrier present in the atomic_add_negative
			 * in page_remove_rmap.
			 *
			 * Then the TLB flush in ptep_clear_flush ensures that
			 * no process can access the old page before the
			 * decremented mapcount is visible. And the old page
			 * cannot be reused until after the decremented
			 * mapcount is visible. So transitively, TLBs to
			 * old page will be flushed before it can be reused.
			 */
			page_remove_rmap(old_page);
		}

		/* Free the old page.. */
		new_page = old_page;
		ret |= VM_FAULT_WRITE;
	} else
		mem_cgroup_cancel_charge(new_page, memcg);

	if (new_page)
		page_cache_release(new_page);
unlock:
	pte_unmap_unlock(page_table, ptl);
	if (mmun_end > mmun_start)
		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	if (old_page) {
		/*
		 * Don't let another task, with possibly unlocked vma,
		 * keep the mlocked page.
		 */
		if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) {
			lock_page(old_page);	/* LRU manipulation */
			munlock_vma_page(old_page);
			unlock_page(old_page);
		}
		page_cache_release(old_page);
	}
	return ret;
oom_free_new:
	page_cache_release(new_page);
oom:
	if (old_page)
		page_cache_release(old_page);
	return VM_FAULT_OOM;
}

static void unmap_mapping_range_vma(struct vm_area_struct *vma,
		unsigned long start_addr, unsigned long end_addr,
		struct zap_details *details)
{
	zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}

static inline void unmap_mapping_range_tree(struct rb_root *root,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;
	pgoff_t vba, vea, zba, zea;

	vma_interval_tree_foreach(vma, root,
			details->first_index, details->last_index) {

		vba = vma->vm_pgoff;
		vea = vba + vma_pages(vma) - 1;
		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
		zba = details->first_index;
		if (zba < vba)
			zba = vba;
		zea = details->last_index;
		if (zea > vea)
			zea = vea;

		unmap_mapping_range_vma(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
				details);
	}
}

static inline void unmap_mapping_range_list(struct list_head *head,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;

	/*
	 * In nonlinear VMAs there is no correspondence between virtual address
	 * offset and file offset.  So we must perform an exhaustive search
	 * across *all* the pages in each nonlinear VMA, not just the pages
	 * whose virtual address lies outside the file truncation point.
	 */
	list_for_each_entry(vma, head, shared.nonlinear) {
		details->nonlinear_vma = vma;
		unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
	}
}

/**
 * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file.
 * @mapping: the address space containing mmaps to be unmapped.
 * @holebegin: byte in first page to unmap, relative to the start of
 * the underlying file.  This will be rounded down to a PAGE_SIZE
 * boundary.  Note that this is different from truncate_pagecache(), which
 * must keep the partial page.  In contrast, we must get rid of
 * partial pages.
 * @holelen: size of prospective hole in bytes.  This will be rounded
 * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
 * end of the file.
 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
 * but 0 when invalidating pagecache, don't throw away private data.
 */
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows)
{
	struct zap_details details;
	pgoff_t hba = holebegin >> PAGE_SHIFT;
	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Check for overflow. */
	if (sizeof(holelen) > sizeof(hlen)) {
		long long holeend =
			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (holeend & ~(long long)ULONG_MAX)
			hlen = ULONG_MAX - hba + 1;
	}

	details.check_mapping = even_cows? NULL: mapping;
	details.nonlinear_vma = NULL;
	details.first_index = hba;
	details.last_index = hba + hlen - 1;
	if (details.last_index < details.first_index)
		details.last_index = ULONG_MAX;


	mutex_lock(&mapping->i_mmap_mutex);
	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
		unmap_mapping_range_tree(&mapping->i_mmap, &details);
	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
	mutex_unlock(&mapping->i_mmap_mutex);
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with pte unmapped and unlocked.
 *
 * We return with the mmap_sem locked or unlocked in the same cases
 * as does filemap_fault().
 */
static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	spinlock_t *ptl;
	struct page *page, *swapcache;
	struct mem_cgroup *memcg;
	swp_entry_t entry;
	pte_t pte;
	int locked;
	int exclusive = 0;
	int ret = 0;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		goto out;

	entry = pte_to_swp_entry(orig_pte);
	if (unlikely(non_swap_entry(entry))) {
		if (is_migration_entry(entry)) {
			migration_entry_wait(mm, pmd, address);
		} else if (is_hwpoison_entry(entry)) {
			ret = VM_FAULT_HWPOISON;
		} else {
			print_bad_pte(vma, address, orig_pte, NULL);
			ret = VM_FAULT_SIGBUS;
		}
		goto out;
	}
	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
	page = lookup_swap_cache(entry);
	if (!page) {
		page = swapin_readahead(entry,
					GFP_HIGHUSER_MOVABLE, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte
			 * while we released the pte lock.
			 */
			page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
			goto unlock;
		}

		/* Had to read the page from swap area: Major fault */
		ret = VM_FAULT_MAJOR;
		count_vm_event(PGMAJFAULT);
		mem_cgroup_count_vm_event(mm, PGMAJFAULT);
	} else if (PageHWPoison(page)) {
		/*
		 * hwpoisoned dirty swapcache pages are kept for killing
		 * owner processes (which may be unknown at hwpoison time)
		 */
		ret = VM_FAULT_HWPOISON;
		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
		swapcache = page;
		goto out_release;
	}

	swapcache = page;
	locked = lock_page_or_retry(page, mm, flags);

	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
	if (!locked) {
		ret |= VM_FAULT_RETRY;
		goto out_release;
	}

	/*
	 * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
	 * release the swapcache from under us.  The page pin, and pte_same
	 * test below, are not enough to exclude that.  Even if it is still
	 * swapcache, we need to check that the page's swap has not changed.
	 */
	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
		goto out_page;

	page = ksm_might_need_to_copy(page, vma, address);
	if (unlikely(!page)) {
		ret = VM_FAULT_OOM;
		page = swapcache;
		goto out_page;
	}

	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) {
		ret = VM_FAULT_OOM;
		goto out_page;
	}

	/*
	 * Back out if somebody else already faulted in this pte.
	 */
	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*page_table, orig_pte)))
		goto out_nomap;

	if (unlikely(!PageUptodate(page))) {
		ret = VM_FAULT_SIGBUS;
		goto out_nomap;
	}

	/*
	 * The page isn't present yet, go ahead with the fault.
	 *
	 * Be careful about the sequence of operations here.
	 * To get its accounting right, reuse_swap_page() must be called
	 * while the page is counted on swap but not yet in mapcount i.e.
	 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
	 * must be called after the swap_free(), or it will never succeed.
	 */

	inc_mm_counter_fast(mm, MM_ANONPAGES);
	dec_mm_counter_fast(mm, MM_SWAPENTS);
	pte = mk_pte(page, vma->vm_page_prot);
	if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
		flags &= ~FAULT_FLAG_WRITE;
		ret |= VM_FAULT_WRITE;
		exclusive = 1;
	}
	flush_icache_page(vma, page);
	if (pte_swp_soft_dirty(orig_pte))
		pte = pte_mksoft_dirty(pte);
	set_pte_at(mm, address, page_table, pte);
	if (page == swapcache) {
		do_page_add_anon_rmap(page, vma, address, exclusive);
		mem_cgroup_commit_charge(page, memcg, true);
	} else { /* ksm created a completely new copy */
		page_add_new_anon_rmap(page, vma, address);
		mem_cgroup_commit_charge(page, memcg, false);
		lru_cache_add_active_or_unevictable(page, vma);
	}

	swap_free(entry);
	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
		try_to_free_swap(page);
	unlock_page(page);
	if (page != swapcache) {
		/*
		 * Hold the lock to avoid the swap entry to be reused
		 * until we take the PT lock for the pte_same() check
		 * (to avoid false positives from pte_same). For
		 * further safety release the lock after the swap_free
		 * so that the swap count won't change under a
		 * parallel locked swapcache.
		 */
		unlock_page(swapcache);
		page_cache_release(swapcache);
	}

	if (flags & FAULT_FLAG_WRITE) {
		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
		if (ret & VM_FAULT_ERROR)
			ret &= VM_FAULT_ERROR;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, page_table);
unlock:
	pte_unmap_unlock(page_table, ptl);
out:
	return ret;
out_nomap:
	mem_cgroup_cancel_charge(page, memcg);
	pte_unmap_unlock(page_table, ptl);
out_page:
	unlock_page(page);
out_release:
	page_cache_release(page);
	if (page != swapcache) {
		unlock_page(swapcache);
		page_cache_release(swapcache);
	}
	return ret;
}

/*
 * This is like a special single-page "expand_{down|up}wards()",
 * except we must first make sure that 'address{-|+}PAGE_SIZE'
 * doesn't hit another vma.
 */
static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
{
	address &= PAGE_MASK;
	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
		struct vm_area_struct *prev = vma->vm_prev;

		/*
		 * Is there a mapping abutting this one below?
		 *
		 * That's only ok if it's the same stack mapping
		 * that has gotten split..
		 */
		if (prev && prev->vm_end == address)
			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;

		expand_downwards(vma, address - PAGE_SIZE);
	}
	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
		struct vm_area_struct *next = vma->vm_next;

		/* As VM_GROWSDOWN but s/below/above/ */
		if (next && next->vm_start == address + PAGE_SIZE)
			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;

		expand_upwards(vma, address + PAGE_SIZE);
	}
	return 0;
}

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags)
{
	struct mem_cgroup *memcg;
	struct page *page;
	spinlock_t *ptl;
	pte_t entry;

	pte_unmap(page_table);

	/* Check if we need to add a guard page to the stack */
	if (check_stack_guard_page(vma, address) < 0)
		return VM_FAULT_SIGBUS;

	/* Use the zero-page for reads */
	if (!(flags & FAULT_FLAG_WRITE)) {
		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
						vma->vm_page_prot));
		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
		if (!pte_none(*page_table))
			goto unlock;
		goto setpte;
	}

	/* Allocate our own private page. */
	if (unlikely(anon_vma_prepare(vma)))
		goto oom;
	page = alloc_zeroed_user_highpage_movable(vma, address);
	if (!page)
		goto oom;
	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * preceeding stores to the page contents become visible before
	 * the set_pte_at() write.
	 */
	__SetPageUptodate(page);

	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
		goto oom_free_page;

	entry = mk_pte(page, vma->vm_page_prot);
	if (vma->vm_flags & VM_WRITE)
		entry = pte_mkwrite(pte_mkdirty(entry));

	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (!pte_none(*page_table))
		goto release;

	inc_mm_counter_fast(mm, MM_ANONPAGES);
	page_add_new_anon_rmap(page, vma, address);
	mem_cgroup_commit_charge(page, memcg, false);
	lru_cache_add_active_or_unevictable(page, vma);
setpte:
	set_pte_at(mm, address, page_table, entry);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, page_table);
unlock:
	pte_unmap_unlock(page_table, ptl);
	return 0;
release:
	mem_cgroup_cancel_charge(page, memcg);
	page_cache_release(page);
	goto unlock;
oom_free_page:
	page_cache_release(page);
oom:
	return VM_FAULT_OOM;
}

/*
 * The mmap_sem must have been held on entry, and may have been
 * released depending on flags and vma->vm_ops->fault() return value.
 * See filemap_fault() and __lock_page_retry().
 */
static int __do_fault(struct vm_area_struct *vma, unsigned long address,
		pgoff_t pgoff, unsigned int flags, struct page **page)
{
	struct vm_fault vmf;
	int ret;

	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
	vmf.pgoff = pgoff;
	vmf.flags = flags;
	vmf.page = NULL;

	ret = vma->vm_ops->fault(vma, &vmf);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
		return ret;

	if (unlikely(PageHWPoison(vmf.page))) {
		if (ret & VM_FAULT_LOCKED)
			unlock_page(vmf.page);
		page_cache_release(vmf.page);
		return VM_FAULT_HWPOISON;
	}

	if (unlikely(!(ret & VM_FAULT_LOCKED)))
		lock_page(vmf.page);
	else
		VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);

	*page = vmf.page;
	return ret;
}

/**
 * do_set_pte - setup new PTE entry for given page and add reverse page mapping.
 *
 * @vma: virtual memory area
 * @address: user virtual address
 * @page: page to map
 * @pte: pointer to target page table entry
 * @write: true, if new entry is writable
 * @anon: true, if it's anonymous page
 *
 * Caller must hold page table lock relevant for @pte.
 *
 * Target users are page handler itself and implementations of
 * vm_ops->map_pages.
 */
void do_set_pte(struct vm_area_struct *vma, unsigned long address,
		struct page *page, pte_t *pte, bool write, bool anon)
{
	pte_t entry;

	flush_icache_page(vma, page);
	entry = mk_pte(page, vma->vm_page_prot);
	if (write)
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
	else if (pte_file(*pte) && pte_file_soft_dirty(*pte))
		entry = pte_mksoft_dirty(entry);
	if (anon) {
		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
		page_add_new_anon_rmap(page, vma, address);
	} else {
		inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
		page_add_file_rmap(page);
	}
	set_pte_at(vma->vm_mm, address, pte, entry);

	/* no need to invalidate: a not-present page won't be cached */
	update_mmu_cache(vma, address, pte);
}

static unsigned long fault_around_bytes __read_mostly =
	rounddown_pow_of_two(65536);

#ifdef CONFIG_DEBUG_FS
static int fault_around_bytes_get(void *data, u64 *val)
{
	*val = fault_around_bytes;
	return 0;
}

/*
 * fault_around_pages() and fault_around_mask() expects fault_around_bytes
 * rounded down to nearest page order. It's what do_fault_around() expects to
 * see.
 */
static int fault_around_bytes_set(void *data, u64 val)
{
	if (val / PAGE_SIZE > PTRS_PER_PTE)
		return -EINVAL;
	if (val > PAGE_SIZE)
		fault_around_bytes = rounddown_pow_of_two(val);
	else
		fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */
	return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops,
		fault_around_bytes_get, fault_around_bytes_set, "%llu\n");

static int __init fault_around_debugfs(void)
{
	void *ret;

	ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL,
			&fault_around_bytes_fops);
	if (!ret)
		pr_warn("Failed to create fault_around_bytes in debugfs");
	return 0;
}
late_initcall(fault_around_debugfs);
#endif

/*
 * do_fault_around() tries to map few pages around the fault address. The hope
 * is that the pages will be needed soon and this will lower the number of
 * faults to handle.
 *
 * It uses vm_ops->map_pages() to map the pages, which skips the page if it's
 * not ready to be mapped: not up-to-date, locked, etc.
 *
 * This function is called with the page table lock taken. In the split ptlock
 * case the page table lock only protects only those entries which belong to
 * the page table corresponding to the fault address.
 *
 * This function doesn't cross the VMA boundaries, in order to call map_pages()
 * only once.
 *
 * fault_around_pages() defines how many pages we'll try to map.
 * do_fault_around() expects it to return a power of two less than or equal to
 * PTRS_PER_PTE.
 *
 * The virtual address of the area that we map is naturally aligned to the
 * fault_around_pages() value (and therefore to page order).  This way it's
 * easier to guarantee that we don't cross page table boundaries.
 */
static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
		pte_t *pte, pgoff_t pgoff, unsigned int flags)
{
	unsigned long start_addr, nr_pages, mask;
	pgoff_t max_pgoff;
	struct vm_fault vmf;
	int off;

	nr_pages = ACCESS_ONCE(fault_around_bytes) >> PAGE_SHIFT;
	mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;

	start_addr = max(address & mask, vma->vm_start);
	off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
	pte -= off;
	pgoff -= off;

	/*
	 *  max_pgoff is either end of page table or end of vma
	 *  or fault_around_pages() from pgoff, depending what is nearest.
	 */
	max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
		PTRS_PER_PTE - 1;
	max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
			pgoff + nr_pages - 1);

	/* Check if it makes any sense to call ->map_pages */
	while (!pte_none(*pte)) {
		if (++pgoff > max_pgoff)
			return;
		start_addr += PAGE_SIZE;
		if (start_addr >= vma->vm_end)
			return;
		pte++;
	}

	vmf.virtual_address = (void __user *) start_addr;
	vmf.pte = pte;
	vmf.pgoff = pgoff;
	vmf.max_pgoff = max_pgoff;
	vmf.flags = flags;
	vma->vm_ops->map_pages(vma, &vmf);
}

static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd,
		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
	struct page *fault_page;
	spinlock_t *ptl;
	pte_t *pte;
	int ret = 0;

	/*
	 * Let's call ->map_pages() first and use ->fault() as fallback
	 * if page by the offset is not ready to be mapped (cold cache or
	 * something).
	 */
	if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) &&
	    fault_around_bytes >> PAGE_SHIFT > 1) {
		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
		do_fault_around(vma, address, pte, pgoff, flags);
		if (!pte_same(*pte, orig_pte))
			goto unlock_out;
		pte_unmap_unlock(pte, ptl);
	}

	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
		return ret;

	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*pte, orig_pte))) {
		pte_unmap_unlock(pte, ptl);
		unlock_page(fault_page);
		page_cache_release(fault_page);
		return ret;
	}
	do_set_pte(vma, address, fault_page, pte, false, false);
	unlock_page(fault_page);
unlock_out:
	pte_unmap_unlock(pte, ptl);
	return ret;
}

static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd,
		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
	struct page *fault_page, *new_page;
	struct mem_cgroup *memcg;
	spinlock_t *ptl;
	pte_t *pte;
	int ret;

	if (unlikely(anon_vma_prepare(vma)))
		return VM_FAULT_OOM;

	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
	if (!new_page)
		return VM_FAULT_OOM;

	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) {
		page_cache_release(new_page);
		return VM_FAULT_OOM;
	}

	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
		goto uncharge_out;

	copy_user_highpage(new_page, fault_page, address, vma);
	__SetPageUptodate(new_page);

	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*pte, orig_pte))) {
		pte_unmap_unlock(pte, ptl);
		unlock_page(fault_page);
		page_cache_release(fault_page);
		goto uncharge_out;
	}
	do_set_pte(vma, address, new_page, pte, true, true);
	mem_cgroup_commit_charge(new_page, memcg, false);
	lru_cache_add_active_or_unevictable(new_page, vma);
	pte_unmap_unlock(pte, ptl);
	unlock_page(fault_page);
	page_cache_release(fault_page);
	return ret;
uncharge_out:
	mem_cgroup_cancel_charge(new_page, memcg);
	page_cache_release(new_page);
	return ret;
}

static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd,
		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
	struct page *fault_page;
	struct address_space *mapping;
	spinlock_t *ptl;
	pte_t *pte;
	int dirtied = 0;
	int ret, tmp;

	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
		return ret;

	/*
	 * Check if the backing address space wants to know that the page is
	 * about to become writable
	 */
	if (vma->vm_ops->page_mkwrite) {
		unlock_page(fault_page);
		tmp = do_page_mkwrite(vma, fault_page, address);
		if (unlikely(!tmp ||
				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
			page_cache_release(fault_page);
			return tmp;
		}
	}

	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*pte, orig_pte))) {
		pte_unmap_unlock(pte, ptl);
		unlock_page(fault_page);
		page_cache_release(fault_page);
		return ret;
	}
	do_set_pte(vma, address, fault_page, pte, true, false);
	pte_unmap_unlock(pte, ptl);

	if (set_page_dirty(fault_page))
		dirtied = 1;
	mapping = fault_page->mapping;
	unlock_page(fault_page);
	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
		/*
		 * Some device drivers do not set page.mapping but still
		 * dirty their pages
		 */
		balance_dirty_pages_ratelimited(mapping);
	}

	/* file_update_time outside page_lock */
	if (vma->vm_file && !vma->vm_ops->page_mkwrite)
		file_update_time(vma->vm_file);

	return ret;
}

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults).
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	pgoff_t pgoff = (((address & PAGE_MASK)
			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;

	pte_unmap(page_table);
	if (!(flags & FAULT_FLAG_WRITE))
		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	if (!(vma->vm_flags & VM_SHARED))
		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with pte unmapped and unlocked.
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	pgoff_t pgoff;

	flags |= FAULT_FLAG_NONLINEAR;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		return 0;

	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
		/*
		 * Page table corrupted: show pte and kill process.
		 */
		print_bad_pte(vma, address, orig_pte, NULL);
		return VM_FAULT_SIGBUS;
	}

	pgoff = pte_to_pgoff(orig_pte);
	if (!(flags & FAULT_FLAG_WRITE))
		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	if (!(vma->vm_flags & VM_SHARED))
		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
				orig_pte);
	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
				unsigned long addr, int page_nid,
				int *flags)
{
	get_page(page);

	count_vm_numa_event(NUMA_HINT_FAULTS);
	if (page_nid == numa_node_id()) {
		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
		*flags |= TNF_FAULT_LOCAL;
	}

	return mpol_misplaced(page, vma, addr);
}

static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
		   unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
{
	struct page *page = NULL;
	spinlock_t *ptl;
	int page_nid = -1;
	int last_cpupid;
	int target_nid;
	bool migrated = false;
	int flags = 0;

	/*
	* The "pte" at this point cannot be used safely without
	* validation through pte_unmap_same(). It's of NUMA type but
	* the pfn may be screwed if the read is non atomic.
	*
	* ptep_modify_prot_start is not called as this is clearing
	* the _PAGE_NUMA bit and it is not really expected that there
	* would be concurrent hardware modifications to the PTE.
	*/
	ptl = pte_lockptr(mm, pmd);
	spin_lock(ptl);
	if (unlikely(!pte_same(*ptep, pte))) {
		pte_unmap_unlock(ptep, ptl);
		goto out;
	}

	pte = pte_mknonnuma(pte);
	set_pte_at(mm, addr, ptep, pte);
	update_mmu_cache(vma, addr, ptep);

	page = vm_normal_page(vma, addr, pte);
	if (!page) {
		pte_unmap_unlock(ptep, ptl);
		return 0;
	}
	BUG_ON(is_zero_pfn(page_to_pfn(page)));

	/*
	 * Avoid grouping on DSO/COW pages in specific and RO pages
	 * in general, RO pages shouldn't hurt as much anyway since
	 * they can be in shared cache state.
	 */
	if (!pte_write(pte))
		flags |= TNF_NO_GROUP;

	/*
	 * Flag if the page is shared between multiple address spaces. This
	 * is later used when determining whether to group tasks together
	 */
	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
		flags |= TNF_SHARED;

	last_cpupid = page_cpupid_last(page);
	page_nid = page_to_nid(page);
	target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
	pte_unmap_unlock(ptep, ptl);
	if (target_nid == -1) {
		put_page(page);
		goto out;
	}

	/* Migrate to the requested node */
	migrated = migrate_misplaced_page(page, vma, target_nid);
	if (migrated) {
		page_nid = target_nid;
		flags |= TNF_MIGRATED;
	}

out:
	if (page_nid != -1)
		task_numa_fault(last_cpupid, page_nid, 1, flags);
	return 0;
}

/*
 * These routines also need to handle stuff like marking pages dirty
 * and/or accessed for architectures that don't do it in hardware (most
 * RISC architectures).  The early dirtying is also good on the i386.
 *
 * There is also a hook called "update_mmu_cache()" that architectures
 * with external mmu caches can use to update those (ie the Sparc or
 * PowerPC hashed page tables that act as extended TLBs).
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with pte unmapped and unlocked.
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int handle_pte_fault(struct mm_struct *mm,
		     struct vm_area_struct *vma, unsigned long address,
		     pte_t *pte, pmd_t *pmd, unsigned int flags)
{
	pte_t entry;
	spinlock_t *ptl;

	entry = ACCESS_ONCE(*pte);
	if (!pte_present(entry)) {
		if (pte_none(entry)) {
			if (vma->vm_ops) {
				if (likely(vma->vm_ops->fault))
					return do_linear_fault(mm, vma, address,
						pte, pmd, flags, entry);
			}
			return do_anonymous_page(mm, vma, address,
						 pte, pmd, flags);
		}
		if (pte_file(entry))
			return do_nonlinear_fault(mm, vma, address,
					pte, pmd, flags, entry);
		return do_swap_page(mm, vma, address,
					pte, pmd, flags, entry);
	}

	if (pte_numa(entry))
		return do_numa_page(mm, vma, address, entry, pte, pmd);

	ptl = pte_lockptr(mm, pmd);
	spin_lock(ptl);
	if (unlikely(!pte_same(*pte, entry)))
		goto unlock;
	if (flags & FAULT_FLAG_WRITE) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address,
					pte, pmd, ptl, entry);
		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
		update_mmu_cache(vma, address, pte);
	} else {
		/*
		 * This is needed only for protection faults but the arch code
		 * is not yet telling us if this is a protection fault or not.
		 * This still avoids useless tlb flushes for .text page faults
		 * with threads.
		 */
		if (flags & FAULT_FLAG_WRITE)
			flush_tlb_fix_spurious_fault(vma, address);
	}
unlock:
	pte_unmap_unlock(pte, ptl);
	return 0;
}

/*
 * By the time we get here, we already hold the mm semaphore
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			     unsigned long address, unsigned int flags)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (unlikely(is_vm_hugetlb_page(vma)))
		return hugetlb_fault(mm, vma, address, flags);

	pgd = pgd_offset(mm, address);
	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		return VM_FAULT_OOM;
	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		return VM_FAULT_OOM;
	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
		int ret = VM_FAULT_FALLBACK;
		if (!vma->vm_ops)
			ret = do_huge_pmd_anonymous_page(mm, vma, address,
					pmd, flags);
		if (!(ret & VM_FAULT_FALLBACK))
			return ret;
	} else {
		pmd_t orig_pmd = *pmd;
		int ret;

		barrier();
		if (pmd_trans_huge(orig_pmd)) {
			unsigned int dirty = flags & FAULT_FLAG_WRITE;

			/*
			 * If the pmd is splitting, return and retry the
			 * the fault.  Alternative: wait until the split
			 * is done, and goto retry.
			 */
			if (pmd_trans_splitting(orig_pmd))
				return 0;

			if (pmd_numa(orig_pmd))
				return do_huge_pmd_numa_page(mm, vma, address,
							     orig_pmd, pmd);

			if (dirty && !pmd_write(orig_pmd)) {
				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
							  orig_pmd);
				if (!(ret & VM_FAULT_FALLBACK))
					return ret;
			} else {
				huge_pmd_set_accessed(mm, vma, address, pmd,
						      orig_pmd, dirty);
				return 0;
			}
		}
	}

	/*
	 * Use __pte_alloc instead of pte_alloc_map, because we can't
	 * run pte_offset_map on the pmd, if an huge pmd could
	 * materialize from under us from a different thread.
	 */
	if (unlikely(pmd_none(*pmd)) &&
	    unlikely(__pte_alloc(mm, vma, pmd, address)))
		return VM_FAULT_OOM;
	/* if an huge pmd materialized from under us just retry later */
	if (unlikely(pmd_trans_huge(*pmd)))
		return 0;
	/*
	 * A regular pmd is established and it can't morph into a huge pmd
	 * from under us anymore at this point because we hold the mmap_sem
	 * read mode and khugepaged takes it in write mode. So now it's
	 * safe to run pte_offset_map().
	 */
	pte = pte_offset_map(pmd, address);

	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}

/*
 * By the time we get here, we already hold the mm semaphore
 *
 * The mmap_sem may have been released depending on flags and our
 * return value.  See filemap_fault() and __lock_page_or_retry().
 */
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		    unsigned long address, unsigned int flags)
{
	int ret;

	__set_current_state(TASK_RUNNING);

	count_vm_event(PGFAULT);
	mem_cgroup_count_vm_event(mm, PGFAULT);

	/* do counter updates before entering really critical section. */
	check_sync_rss_stat(current);

	/*
	 * Enable the memcg OOM handling for faults triggered in user
	 * space.  Kernel faults are handled more gracefully.
	 */
	if (flags & FAULT_FLAG_USER)
		mem_cgroup_oom_enable();

	ret = __handle_mm_fault(mm, vma, address, flags);

	if (flags & FAULT_FLAG_USER) {
		mem_cgroup_oom_disable();
                /*
                 * The task may have entered a memcg OOM situation but
                 * if the allocation error was handled gracefully (no
                 * VM_FAULT_OOM), there is no need to kill anything.
                 * Just clean up the OOM state peacefully.
                 */
                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
                        mem_cgroup_oom_synchronize(false);
	}

	return ret;
}

#ifndef __PAGETABLE_PUD_FOLDED
/*
 * Allocate page upper directory.
 * We've already handled the fast-path in-line.
 */
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pud_t *new = pud_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
	if (pgd_present(*pgd))		/* Another has populated it */
		pud_free(mm, new);
	else
		pgd_populate(mm, pgd, new);
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */

#ifndef __PAGETABLE_PMD_FOLDED
/*
 * Allocate page middle directory.
 * We've already handled the fast-path in-line.
 */
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	pmd_t *new = pmd_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
#ifndef __ARCH_HAS_4LEVEL_HACK
	if (pud_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pud_populate(mm, pud, new);
#else
	if (pgd_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pgd_populate(mm, pud, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */

static int __follow_pte(struct mm_struct *mm, unsigned long address,
		pte_t **ptepp, spinlock_t **ptlp)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep;

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto out;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		goto out;

	pmd = pmd_offset(pud, address);
	VM_BUG_ON(pmd_trans_huge(*pmd));
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		goto out;

	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
	if (pmd_huge(*pmd))
		goto out;

	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
	if (!ptep)
		goto out;
	if (!pte_present(*ptep))
		goto unlock;
	*ptepp = ptep;
	return 0;
unlock:
	pte_unmap_unlock(ptep, *ptlp);
out:
	return -EINVAL;
}

static inline int follow_pte(struct mm_struct *mm, unsigned long address,
			     pte_t **ptepp, spinlock_t **ptlp)
{
	int res;

	/* (void) is needed to make gcc happy */
	(void) __cond_lock(*ptlp,
			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
	return res;
}

/**
 * follow_pfn - look up PFN at a user virtual address
 * @vma: memory mapping
 * @address: user virtual address
 * @pfn: location to store found PFN
 *
 * Only IO mappings and raw PFN mappings are allowed.
 *
 * Returns zero and the pfn at @pfn on success, -ve otherwise.
 */
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
	unsigned long *pfn)
{
	int ret = -EINVAL;
	spinlock_t *ptl;
	pte_t *ptep;

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		return ret;

	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
	if (ret)
		return ret;
	*pfn = pte_pfn(*ptep);
	pte_unmap_unlock(ptep, ptl);
	return 0;
}
EXPORT_SYMBOL(follow_pfn);

#ifdef CONFIG_HAVE_IOREMAP_PROT
int follow_phys(struct vm_area_struct *vma,
		unsigned long address, unsigned int flags,
		unsigned long *prot, resource_size_t *phys)
{
	int ret = -EINVAL;
	pte_t *ptep, pte;
	spinlock_t *ptl;

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		goto out;

	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
		goto out;
	pte = *ptep;

	if ((flags & FOLL_WRITE) && !pte_write(pte))
		goto unlock;

	*prot = pgprot_val(pte_pgprot(pte));
	*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;

	ret = 0;
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return ret;
}

int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write)
{
	resource_size_t phys_addr;
	unsigned long prot = 0;
	void __iomem *maddr;
	int offset = addr & (PAGE_SIZE-1);

	if (follow_phys(vma, addr, write, &prot, &phys_addr))
		return -EINVAL;

	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
	if (write)
		memcpy_toio(maddr + offset, buf, len);
	else
		memcpy_fromio(buf, maddr + offset, len);
	iounmap(maddr);

	return len;
}
EXPORT_SYMBOL_GPL(generic_access_phys);
#endif

/*
 * Access another process' address space as given in mm.  If non-NULL, use the
 * given task for page fault accounting.
 */
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long addr, void *buf, int len, int write)
{
	struct vm_area_struct *vma;
	void *old_buf = buf;

	down_read(&mm->mmap_sem);
	/* ignore errors, just check how much was successfully transferred */
	while (len) {
		int bytes, ret, offset;
		void *maddr;
		struct page *page = NULL;

		ret = get_user_pages(tsk, mm, addr, 1,
				write, 1, &page, &vma);
		if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
			break;
#else
			/*
			 * Check if this is a VM_IO | VM_PFNMAP VMA, which
			 * we can access using slightly different code.
			 */
			vma = find_vma(mm, addr);
			if (!vma || vma->vm_start > addr)
				break;
			if (vma->vm_ops && vma->vm_ops->access)
				ret = vma->vm_ops->access(vma, addr, buf,
							  len, write);
			if (ret <= 0)
				break;
			bytes = ret;
#endif
		} else {
			bytes = len;
			offset = addr & (PAGE_SIZE-1);
			if (bytes > PAGE_SIZE-offset)
				bytes = PAGE_SIZE-offset;

			maddr = kmap(page);
			if (write) {
				copy_to_user_page(vma, page, addr,
						  maddr + offset, buf, bytes);
				set_page_dirty_lock(page);
			} else {
				copy_from_user_page(vma, page, addr,
						    buf, maddr + offset, bytes);
			}
			kunmap(page);
			page_cache_release(page);
		}
		len -= bytes;
		buf += bytes;
		addr += bytes;
	}
	up_read(&mm->mmap_sem);

	return buf - old_buf;
}

/**
 * access_remote_vm - access another process' address space
 * @mm:		the mm_struct of the target address space
 * @addr:	start address to access
 * @buf:	source or destination buffer
 * @len:	number of bytes to transfer
 * @write:	whether the access is a write
 *
 * The caller must hold a reference on @mm.
 */
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
		void *buf, int len, int write)
{
	return __access_remote_vm(NULL, mm, addr, buf, len, write);
}

/*
 * Access another process' address space.
 * Source/target buffer must be kernel space,
 * Do not walk the page table directly, use get_user_pages
 */
int access_process_vm(struct task_struct *tsk, unsigned long addr,
		void *buf, int len, int write)
{
	struct mm_struct *mm;
	int ret;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
	mmput(mm);

	return ret;
}

/*
 * Print the name of a VMA.
 */
void print_vma_addr(char *prefix, unsigned long ip)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	/*
	 * Do not print if we are in atomic
	 * contexts (in exception stacks, etc.):
	 */
	if (preempt_count())
		return;

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, ip);
	if (vma && vma->vm_file) {
		struct file *f = vma->vm_file;
		char *buf = (char *)__get_free_page(GFP_KERNEL);
		if (buf) {
			char *p;

			p = d_path(&f->f_path, buf, PAGE_SIZE);
			if (IS_ERR(p))
				p = "?";
			printk("%s%s[%lx+%lx]", prefix, kbasename(p),
					vma->vm_start,
					vma->vm_end - vma->vm_start);
			free_page((unsigned long)buf);
		}
	}
	up_read(&mm->mmap_sem);
}

#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
void might_fault(void)
{
	/*
	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
	 * holding the mmap_sem, this is safe because kernel memory doesn't
	 * get paged out, therefore we'll never actually fault, and the
	 * below annotations will generate false positives.
	 */
	if (segment_eq(get_fs(), KERNEL_DS))
		return;

	/*
	 * it would be nicer only to annotate paths which are not under
	 * pagefault_disable, however that requires a larger audit and
	 * providing helpers like get_user_atomic.
	 */
	if (in_atomic())
		return;

	__might_sleep(__FILE__, __LINE__, 0);

	if (current->mm)
		might_lock_read(&current->mm->mmap_sem);
}
EXPORT_SYMBOL(might_fault);
#endif

#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
static void clear_gigantic_page(struct page *page,
				unsigned long addr,
				unsigned int pages_per_huge_page)
{
	int i;
	struct page *p = page;

	might_sleep();
	for (i = 0; i < pages_per_huge_page;
	     i++, p = mem_map_next(p, page, i)) {
		cond_resched();
		clear_user_highpage(p, addr + i * PAGE_SIZE);
	}
}
void clear_huge_page(struct page *page,
		     unsigned long addr, unsigned int pages_per_huge_page)
{
	int i;

	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
		clear_gigantic_page(page, addr, pages_per_huge_page);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page; i++) {
		cond_resched();
		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
	}
}

static void copy_user_gigantic_page(struct page *dst, struct page *src,
				    unsigned long addr,
				    struct vm_area_struct *vma,
				    unsigned int pages_per_huge_page)
{
	int i;
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < pages_per_huge_page; ) {
		cond_resched();
		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

void copy_user_huge_page(struct page *dst, struct page *src,
			 unsigned long addr, struct vm_area_struct *vma,
			 unsigned int pages_per_huge_page)
{
	int i;

	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
		copy_user_gigantic_page(dst, src, addr, vma,
					pages_per_huge_page);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page; i++) {
		cond_resched();
		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
	}
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */

#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS

static struct kmem_cache *page_ptl_cachep;

void __init ptlock_cache_init(void)
{
	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
			SLAB_PANIC, NULL);
}

bool ptlock_alloc(struct page *page)
{
	spinlock_t *ptl;

	ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
	if (!ptl)
		return false;
	page->ptl = ptl;
	return true;
}

void ptlock_free(struct page *page)
{
	kmem_cache_free(page_ptl_cachep, page->ptl);
}
#endif
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-15 11:57:17 -0400