Pull rdma fixes from Jason Gunthorpe:
"A small set of late-rc patches, mostly fixes for various crashers,
some syzkaller fixes and a mlx5 HW limitation:
- Several MAINTAINERS updates
- Memory leak regression in ODP
- Several fixes for syzkaller related crashes. Google recently taught
syzkaller to create the software RDMA devices
- Crash fixes for HFI1
- Several fixes for mlx5 crashes
- Prevent unprivileged access to an unsafe mlx5 HW resource"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
RDMA/mlx5: Block delay drop to unprivileged users
RDMA/mlx5: Fix access to wrong pointer while performing flush due to error
RDMA/core: Ensure security pkey modify is not lost
MAINTAINERS: Clean RXE section and add Zhu as RXE maintainer
IB/hfi1: Ensure pq is not left on waitlist
IB/rdmavt: Free kernel completion queue when done
RDMA/mad: Do not crash if the rdma device does not have a umad interface
RDMA/core: Fix missing error check on dev_set_name()
RDMA/nl: Do not permit empty devices names during RDMA_NLDEV_CMD_NEWLINK/SET
RDMA/mlx5: Fix the number of hwcounters of a dynamic counter
MAINTAINERS: Update maintainers for HISILICON ROCE DRIVER
RDMA/odp: Fix leaking the tgid for implicit ODP
hmm_range_fault() will succeed for any kind of device private memory, even
if it doesn't belong to the calling entity. While nouveau has some crude
checks for that, they are broken because they assume nouveau is the only
user of device private memory. Fix this by passing in an expected pgmap
owner in the hmm_range_fault structure.
If a device_private page is found and doesn't match the owner then it is
treated as an non-present and non-faultable page.
This prevents a bug in amdgpu, where it doesn't know how to handle
device_private pages, but hmm_range_fault would return them anyhow.
Fixes: 4ef589dc9b ("mm/hmm/devmem: device memory hotplug using ZONE_DEVICE")
Link: https://lore.kernel.org/r/20200316193216.920734-5-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Remove the HMM_PFN_DEVICE_PRIVATE flag, no driver has ever set this flag
on input, and the only place that uses it on output can be trivially
changed to use is_device_private_page().
This removes the ability to request that device_private pages are faulted
back into system memory.
Link: https://lore.kernel.org/r/20200316193216.920734-4-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Add a new src_owner field to struct migrate_vma. If the field is set,
only device private pages with page->pgmap->owner equal to that field are
migrated. If the field is not set only "normal" pages are migrated.
Fixes: df6ad69838 ("mm/device-public-memory: device memory cache coherent with CPU")
Link: https://lore.kernel.org/r/20200316193216.920734-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Tested-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Setting a pfns entry to NONE before returning -EBUSY is a bug that will
cause corruption of the input flags on the next loop.
There is just a single caller using hmm_vma_walk_hole_() for the non-fault
case. Use hmm_pfns_fill() to fill the whole pfn array with zeroes in the
only caller for the non-fault case and remove the non-fault path from
hmm_vma_walk_hole_(). This avoids setting NONE before returning -EBUSY.
Also rename the function to hmm_vma_fault() to better describe what it
does.
Fixes: 2aee09d8c1 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Link: https://lore.kernel.org/r/20200316135310.899364-5-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
pmd_to_hmm_pfn_flags() already checks it and makes the cpu flags 0. If no
fault is requested then the pfns should be returned with the not valid
flags.
It should not unconditionally fault if faulting is not requested.
Fixes: 2aee09d8c1 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently if a special PTE is encountered hmm_range_fault() immediately
returns EFAULT and sets the HMM_PFN_SPECIAL error output (which nothing
uses).
EFAULT should only be returned after testing with hmm_pte_need_fault().
Also pte_devmap() and pte_special() are exclusive, and there is no need to
check IS_ENABLED, pte_special() is stubbed out to return false on
unsupported architectures.
Fixes: 992de9a8b7 ("mm/hmm: allow to mirror vma of a file on a DAX backed filesystem")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
hmm_range_fault() should never return 0 if the caller requested a valid
page, but the pfns output for that page would be HMM_PFN_ERROR.
hmm_pte_need_fault() must always be called before setting HMM_PFN_ERROR to
detect if the page is in faulting mode or not.
Fix two cases in hmm_vma_walk_pmd() and reorganize some of the duplicated
code.
Fixes: d08faca018 ("mm/hmm: properly handle migration pmd")
Fixes: da4c3c735e ("mm/hmm/mirror: helper to snapshot CPU page table")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The intention with this code is to determine if the caller required the
pages to be valid, and if so, then take some action to make them valid.
The action varies depending on the page type.
In all cases, if the caller doesn't ask for the page, then
hmm_range_fault() should not return an error.
Revise the implementation to be clearer, and fix some bugs:
- hmm_pte_need_fault() must always be called before testing fault or
write_fault otherwise the defaults of false apply and the if()'s don't
work. This was missed on the is_migration_entry() branch
- -EFAULT should not be returned unless hmm_pte_need_fault() indicates
fault is required - ie snapshotting should not fail.
- For !pte_present() the cpu_flags are always 0, except in the special
case of is_device_private_entry(), calling pte_to_hmm_pfn_flags() is
confusing.
Reorganize the flow so that it always follows the pattern of calling
hmm_pte_need_fault() and then checking fault || write_fault.
Fixes: 2aee09d8c1 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All return paths that do EFAULT must call hmm_range_need_fault() to
determine if the user requires this page to be valid.
If the page cannot be made valid if the user later requires it, due to vma
flags in this case, then the return should be HMM_PFN_ERROR.
Fixes: a3e0d41c2b ("mm/hmm: improve driver API to work and wait over a range")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All success exit paths from the walker functions must set the pfns array.
A migration entry with no required fault is a HMM_PFN_NONE return, just
like the pte case.
Fixes: d08faca018 ("mm/hmm: properly handle migration pmd")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This eventually calls into handle_mm_fault() which is a sleeping function.
Release the lock first.
hmm_vma_walk_hole() does not touch the contents of the PUD, so it does not
need the lock.
Fixes: 3afc423632 ("mm: pagewalk: add p4d_entry() and pgd_entry()")
Cc: Steven Price <steven.price@arm.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Many of the direct returns of error skipped doing the pte_unmap(). All non
zero exit paths must unmap the pte.
The pte_unmap() is split unnaturally like this because some of the error
exit paths trigger a sleep and must release the lock before sleeping.
Fixes: 992de9a8b7 ("mm/hmm: allow to mirror vma of a file on a DAX backed filesystem")
Fixes: 53f5c3f489 ("mm/hmm: factor out pte and pmd handling to simplify hmm_vma_walk_pmd()")
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The KERN_VIRT_START defines the start virtual address of kernel space.
Use this macro instead of magic number.
Signed-off-by: Zong Li <zong.li@sifive.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
In a similar manner to arm64, x86, powerpc, etc., it can traverse all
page tables, and dump the page table layout with the memory types and
permissions.
Add a debugfs file at /sys/kernel/debug/kernel_page_tables to export
the page table layout to userspace.
Signed-off-by: Zong Li <zong.li@sifive.com>
Tested-by: Alexandre Ghiti <alex@ghiti.fr>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
* move ata_eh_analyze_ncq_error() and ata_eh_read_log_10h() to
libata-sata.c
* add static inline for ata_eh_analyze_ncq_error() for
CONFIG_SATA_HOST=n case (link->sactive is non-zero only if
NCQ commands are actually queued so empty function body is
sufficient)
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
16164 18 0 16182 3f36 drivers/ata/libata-eh.o
after:
15446 18 0 15464 3c68 drivers/ata/libata-eh.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Start separating SATA specific code from libata-scsi.c:
* un-static ata_scsi_find_dev()
* move following code to libata-sata.c:
- SATA only sysfs device attributes handling
- __ata_change_queue_depth()
- ata_scsi_change_queue_depth()
* cover with CONFIG_SATA_HOST ifdef SATA only sysfs device
attributes handling code and ATA_SHT_NCQ() macro in
<linux/libata.h>
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
20702 105 576 21383 5387 drivers/ata/libata-scsi.o
after:
19137 23 576 19736 4d18 drivers/ata/libata-scsi.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Start separating SATA specific code from libata-core.c:
* move following functions to libata-sata.c:
- ata_tf_to_fis()
- ata_tf_from_fis()
- sata_link_scr_lpm()
- ata_slave_link_init()
- sata_lpm_ignore_phy_events()
* group above functions together in <linux/libata.h>
* include libata-sata.c in the build when CONFIG_SATA_HOST=y
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
37582 572 40 38194 9532 drivers/ata/libata-core.o
after:
36762 572 40 37374 91fe drivers/ata/libata-core.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add !IS_ENABLED(CONFIG_SATA_HOST) to ata_eh_set_lpm() to allow
compiler to optimize out the function for non-SATA configs (for
PATA hosts "ap && !ap->ops->set_lpm" condition is always true so
it's sufficient for the function to return zero).
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
17353 18 0 17371 43db drivers/ata/libata-eh.o
after:
16607 18 0 16625 40f1 drivers/ata/libata-eh.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add !IS_ENABLED(CONFIG_SATA_HOST) to ata_dev_config_ncq() to allow
compiler to optimize out the function for non-SATA configs.
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
37582 572 40 38194 9532 drivers/ata/libata-core.o
after:
36462 572 40 37074 90d2 drivers/ata/libata-core.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Separate PATA timings code from libata-core.c:
* add PATA_TIMINGS config option and make corresponding PATA
host drivers (and ATA ACPI code) select it
* move following PATA timings code to libata-pata-timings.c:
- ata_timing_quantize()
- ata_timing_merge()
- ata_timing_find_mode()
- ata_timing_compute()
* group above functions together in <linux/libata.h>
* include libata-pata-timings.c in the build when PATA_TIMINGS
config option is enabled
* cover ata_timing_cycle2mode() with CONFIG_ATA_ACPI ifdef (it
depends on code from libata-core.c and libata-pata-timings.c
while its only user is ATA ACPI)
Code size savings on m68k arch using (modified) atari_defconfig:
text data bss dec hex filename
before:
39688 573 40 40301 9d6d drivers/ata/libata-core.o
after:
37820 572 40 38432 9620 drivers/ata/libata-core.o
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
* fix the overly long line in ata_timing_quantize()
* use standard kernel CodingStyle in ata_timing_merge()
* do not use assignment in if condition in ata_timing_compute()
* fix non-standard comment style in ata_timing_compute()
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
