Nicholas Piggin [Tue, 9 May 2017 03:16:52 +0000 (13:16 +1000)]
powerpc/64s: Support new device tree binding for discovering CPU features
The ibm,powerpc-cpu-features device tree binding describes CPU features with
ASCII names and extensible compatibility, privilege, and enablement metadata
that allows improved flexibility and compatibility with new hardware.
The interface is described in detail in ibm,powerpc-cpu-features.txt in this
patch.
Currently this code is not enabled by default, and there are no released
firmwares that provide the binding.
Nicholas Piggin [Tue, 9 May 2017 03:17:08 +0000 (13:17 +1000)]
powerpc: Don't print cpu_spec->cpu_name if it's NULL
Currently we assume that if the cpu_spec has a pvr_mask then it must also have a
cpu_name. But that will change in a subsequent commit when we do CPU feature
discovery via the device tree, so check explicitly if cpu_name is NULL.
Nicholas Piggin [Tue, 18 Apr 2017 19:12:18 +0000 (05:12 +1000)]
of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle
Introduce primitives for FDT parsing. These will be used for powerpc
cpufeatures node scanning, which has quite complex structure but should
be processed early.
Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux into next
Freescale updates from Scott:
"Includes a fix for a powerpc/next mm regression on 64e, a fix for a
kernel hang on 64e when using a debugger inside a relocated kernel, a
qman fix, and misc qe improvements."
Paolo Bonzini [Tue, 9 May 2017 10:51:49 +0000 (12:51 +0200)]
Merge tag 'kvm-arm-for-v4.12-round2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
Second round of KVM/ARM Changes for v4.12.
Changes include:
- A fix related to the 32-bit idmap stub
- A fix to the bitmask used to deode the operands of an AArch32 CP
instruction
- We have moved the files shared between arch/arm/kvm and
arch/arm64/kvm to virt/kvm/arm
- We add support for saving/restoring the virtual ITS state to
userspace
KVM: arm/arm64: Don't call map_resources when restoring ITS tables
The only reason we called kvm_vgic_map_resources() when restoring the
ITS tables was because we wanted to have the KVM iodevs registered in
the KVM IO bus framework at the time when the ITS was restored such that
a restored and active device can inject MSIs prior to otherwise calling
kvm_vgic_map_resources() from the first run of a VCPU.
Since we now register the KVM iodevs for the redestributors and ITS as
soon as possible (when setting the base addresses), we no longer need
this call and kvm_vgic_map_resources() is again called only when first
running a VCPU.
KVM: arm/arm64: Register ITS iodev when setting base address
We have to register the ITS iodevice before running the VM, because in
migration scenarios, we may be restoring a live device that wishes to
inject MSIs before the VCPUs have started.
All we need to register the ITS io device is the base address of the
ITS, so we can simply register that when the base address of the ITS is
set.
[ Code to fix concurrency issues when setting the ITS base address and
to fix the undef base address check written by Marc Zyngier ]
Marc Zyngier [Mon, 8 May 2017 17:15:40 +0000 (18:15 +0100)]
KVM: arm/arm64: Get rid of its->initialized field
The its->initialized doesn't bring much to the table, and creates
unnecessary ordering between setting the address and initializing it
(which amounts to exactly nothing).
Let's kill it altogether, making KVM_DEV_ARM_VGIC_CTRL_INIT the no-op
it deserves to be.
KVM: arm/arm64: Register iodevs when setting redist base and creating VCPUs
Instead of waiting with registering KVM iodevs until the first VCPU is
run, we can actually create the iodevs when the redist base address is
set. The only downside is that we must now also check if we need to do
this for VCPUs which are created after creating the VGIC, because there
is no enforced ordering between creating the VGIC (and setting its base
addresses) and creating the VCPUs.
As we are about to handle setting the address for the redistributor base
region separately from some of the other base addresses, let's rework
this function to leave a little more room for being flexible in what
each type of base address does.
KVM: arm/arm64: Make vgic_v3_check_base more broadly usable
As we are about to fiddle with the IO device registration mechanism,
let's be a little more careful when setting base addresses as early as
possible. When setting a base address, we can check that there's
address space enough for its scope and when the last of the two
base addresses (dist and redist) get set, we can also check if the
regions overlap at that time.
This allows us to provide error messages to the user at time when trying
to set the base address, as opposed to later when trying to run the VM.
To do this, we make vgic_v3_check_base available in the core vgic-v3
code as well as in the other parts of the GICv3 code, namely the MMIO
config code.
We also return true for undefined base addresses so that the function
can be used before all base addresses are set; all callers already check
for uninitialized addresses before calling this function.
Split out the function to register all the redistributor iodevs into a
function that handles a single redistributor at a time in preparation
for being able to call this per VCPU as these get created.
KVM: Add kvm_vcpu_get_idx to get vcpu index in kvm->vcpus
There are occasional needs to use the index of vcpu in the kvm->vcpus
array to map something related to a VCPU. For example, unlike the
vcpu->vcpu_id, the vcpu index is guaranteed to not be sparse across all
vcpus which is useful when allocating a memory area for each vcpu.
Bandan Das [Fri, 5 May 2017 19:25:15 +0000 (15:25 -0400)]
nVMX: Advertise PML to L1 hypervisor
Advertise the PML bit in vmcs12 but don't try to enable
it in hardware when running L2 since L0 is emulating it. Also,
preserve L0's settings for PML since it may still
want to log writes.
With EPT A/D enabled, processor access to L2 guest
paging structures will result in a write violation.
When this happens, write the GUEST_PHYSICAL_ADDRESS
to the pml buffer provided by L1 if the access is
write and the dirty bit is being set.
This patch also adds necessary checks during VMEntry if L1
has enabled PML. If the PML index overflows, we change the
exit reason and run L1 to simulate a PML full event.
Jim Mattson [Fri, 5 May 2017 18:28:09 +0000 (11:28 -0700)]
kvm: nVMX: Validate CR3 target count on nested VM-entry
According to the SDM, the CR3-target count must not be greater than
4. Future processors may support a different number of CR3-target
values. Software should read the VMX capability MSR IA32_VMX_MISC to
determine the number of values supported.
Paolo Bonzini [Tue, 9 May 2017 09:50:01 +0000 (11:50 +0200)]
Merge branch 'kvm-ppc-next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD
The main thing here is a new implementation of the in-kernel
XICS interrupt controller emulation for POWER9 machines, from Ben
Herrenschmidt.
POWER9 has a new interrupt controller called XIVE (eXternal Interrupt
Virtualization Engine) which is able to deliver interrupts directly
to guest virtual CPUs in hardware without hypervisor intervention.
With this new code, the guest still sees the old XICS interface but
performance is better because the XICS emulation in the host uses the
XIVE directly rather than going through a XICS emulation in firmware.
Geliang Tang [Sat, 6 May 2017 15:37:19 +0000 (23:37 +0800)]
KVM: set no_llseek in stat_fops_per_vm
In vm_stat_get_per_vm_fops and vcpu_stat_get_per_vm_fops, since we
use nonseekable_open() to open, we should use no_llseek() to seek,
not generic_file_llseek().
Similarly to commit 2563a70c3b ("powerpc/64s: Remove unnecessary relocation
branch from idle handler"), the machine check handler has a BRANCH_TO from
relocated to relocated code, which is unnecessary.
It has also caused build errors with some toolchains:
arch/powerpc/kernel/exceptions-64s.S: Assembler messages:
arch/powerpc/kernel/exceptions-64s.S:395: Error: operand out of range
(0xffffffffffff8280 is not between 0x0000000000000000 and
0x000000000000ffff)
Fixes: 1945bc4549e5 ("powerpc/64s: Fix POWER9 machine check handler from stop state") Signed-off-by: Nicholas Piggin <[email protected]>
Reported-and-tested-by : Abdul Haleem <[email protected]> Signed-off-by: Michael Ellerman <[email protected]>
powerpc/mm/book3s/64: Rework page table geometry for lower memory usage
Recently in commit f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB")
we increased the virtual address space for user processes to 128TB by default,
and up to 512TB if user space opts in.
This obviously required expanding the range of the Linux page tables. For Book3s
64-bit using hash and with PAGE_SIZE=64K, we increased the PGD to 2^15 entries.
This meant we could cover the full address range, while still being able to
insert a 16G hugepage at the PGD level and a 16M hugepage in the PMD.
The downside of that geometry is that it uses a lot of memory for the PGD, and
in particular makes the PGD a 4-page allocation, which means it's much more
likely to fail under memory pressure.
Instead we can make the PMD larger, so that a single PUD entry maps 16G,
allowing the 16G hugepages to sit at that level in the tree. We're then able to
split the remaining bits between the PUG and PGD. We make the PGD slightly
larger as that results in lower memory usage for typical programs.
When THP is enabled the PMD actually doubles in size, to 2^11 entries, or 2^14
bytes, which is large but still < PAGE_SIZE.
Horia Geantă [Mon, 8 May 2017 08:50:16 +0000 (11:50 +0300)]
powerpc: Fix distclean with Makefile.postlink
Makefile.postlink always includes include/config/auto.conf, however
this file is not present in a clean kernel tree, causing make to fail:
$ git clone linuxppc.git
$ cd linuxppc.git
$ make distclean
arch/powerpc/Makefile.postlink:10: include/config/auto.conf: No such file or directory
make[1]: *** No rule to make target `include/config/auto.conf'. Stop.
make: *** [vmlinuxclean] Error 2
Equally running 'make distclean; make distclean' will trip the error case.
Change the inclusion such that file not being found does not trigger an error.
Fixes: f188d0524d7e ("powerpc: Use the new post-link pass to check relocations") Reported-by: Mircea Pop <[email protected]> Signed-off-by: Horia Geantă <[email protected]> Tested-by: Justin M. Forbes <[email protected]> Signed-off-by: Michael Ellerman <[email protected]>
KVM: arm/arm64: vgic: Rename kvm_vgic_vcpu_init to kvm_vgic_vcpu_enable
This function really doesn't init anything, it enables the CPU
interface, so name it as such, which gives us the name to use for actual
init work later on.
arch_timer_mem_find_best_frame() looks through ARCH_TIMER_MEM_MAX_FRAMES
frames even after finding matches to ensure the best frame is chosen,
which means the variable frame will point to the last valid frame but
not necessarily the best frame.
On Juno, we get the following error as the wrong frame is returned as the
best frame from arch_timer_mem_find_best_frame():
arch_timer: Unable to map frame @ 0x0000000000000000
arch_timer: Frame missing phys irq.
Failed to initialize '/timer@2a810000': -22
Fix the issue by correctly returning the best frame from
arch_timer_mem_find_best_frame().
Andy Lutomirski [Tue, 9 May 2017 00:09:10 +0000 (17:09 -0700)]
x86/boot/32: Fix UP boot on Quark and possibly other platforms
This partially reverts commit:
23b2a4ddebdd17f ("x86/boot/32: Defer resyncing initial_page_table until per-cpu is set up")
That commit had one definite bug and one potential bug. The
definite bug is that setup_per_cpu_areas() uses a differnet generic
implementation on UP kernels, so initial_page_table never got
resynced. This was fine for access to percpu data (it's in the
identity map on UP), but it breaks other users of
initial_page_table. The potential bug is that helpers like
efi_init() would be called before the tables were synced.
Avoid both problems by just syncing the page tables in setup_arch()
*and* setup_per_cpu_areas().
Laura Abbott [Mon, 8 May 2017 21:23:16 +0000 (14:23 -0700)]
x86/mm/32: Set the '__vmalloc_start_set' flag in initmem_init()
'__vmalloc_start_set' currently only gets set in initmem_init() when
!CONFIG_NEED_MULTIPLE_NODES. This breaks detection of vmalloc address
with virt_addr_valid() with CONFIG_NEED_MULTIPLE_NODES=y, causing
a kernel crash:
[mm/usercopy] 517e1fbeb6: kernel BUG at arch/x86/mm/physaddr.c:78!
Set '__vmalloc_start_set' appropriately for that case as well.
Linus Torvalds [Tue, 9 May 2017 03:43:30 +0000 (20:43 -0700)]
Merge tag 'linux-kselftest-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest
Pull kselftest updates from Shuah Khan:
"This update consists of:
- important fixes for build failures and clean target related
warnings to address regressions introduced in commit 88baa78d1f31
("selftests: remove duplicated all and clean target")
- several minor spelling fixes in and log messages and comment
blocks.
- Enabling configs for better test coverage in ftrace, vm, and
cpufreq tests.
- .gitignore changes"
* tag 'linux-kselftest-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest: (26 commits)
selftests: x86: add missing executables to .gitignore
selftests: watchdog: accept multiple params on command line
selftests: create cpufreq kconfig fragments
selftests: x86: override clean in lib.mk to fix warnings
selftests: sync: override clean in lib.mk to fix warnings
selftests: splice: override clean in lib.mk to fix warnings
selftests: gpio: fix clean target to remove all generated files and dirs
selftests: add gpio generated files to .gitignore
selftests: powerpc: override clean in lib.mk to fix warnings
selftests: gpio: override clean in lib.mk to fix warnings
selftests: futex: override clean in lib.mk to fix warnings
selftests: lib.mk: define CLEAN macro to allow Makefiles to override clean
selftests: splice: fix clean target to not remove default_file_splice_read.sh
selftests: gpio: add config fragment for gpio-mockup
selftests: breakpoints: allow to cross-compile for aarch64/arm64
selftests/Makefile: Add missed PHONY targets
selftests/vm/run_vmtests: Fix wrong comment
selftests/Makefile: Add missed closing `"` in comment
selftests/vm/run_vmtests: Polish output text
selftests/timers: fix spelling mistake: "Asynchronous"
...
Linus Torvalds [Tue, 9 May 2017 03:36:38 +0000 (20:36 -0700)]
Merge tag 'trace-v4.12-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull more tracing updates from Steven Rostedt:
"These are three simple changes.
The first one is just a switch from using strcpy() to strlcpy().
Someone thought that it may cause an overflow bug, but since it only
copies comms into a pre-allocated array of TASK_COMM_LEN, and no comm
should ever be bigger than that, nor not end with a nul character,
this change is more of a safety precaution than fixing anything that
is actually broken.
The other two changes are simply cleaning and optimizing some code"
* tag 'trace-v4.12-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
ftrace: Simplify ftrace_match_record() even more
ftrace: Remove an unneeded condition
tracing: Use strlcpy() instead of strcpy() in __trace_find_cmdline()
Linus Torvalds [Tue, 9 May 2017 03:07:29 +0000 (20:07 -0700)]
Merge tags 'for-linus' and 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull more rdma updates from Doug Ledford:
"As mentioned in my first pull request, this is the subsequent pull
requests I had. This is all I have, and in fact this cleans out the
RDMA subsystem's entire patchworks queue of kernel changes that are
ready to go (well, it did for the weekend anyway, a few new patches
are in, but they'll be coming during the -rc cycle).
The first tag contains a single patch that would have conflicted if
taken from my tree or DaveM's tree as it needed our trees merged to
come cleanly.
The second tag contains the patch series from Intel plus three other
stragllers that came in late last week. I took them because it allowed
me to legitimately claim that the RDMA patchworks queue was, for a
short time, 100% cleared of all waiting kernel patches, woohoo! :-).
I have it under my for-next tag, so it did get 0day and linux- next
over the end of last week, and linux-next did show one minor conflict.
Summary:
'for-linus' tag:
- mlx5/IPoIB fixup patch
'for-next' tag:
- the hfi1 15 patch set that landed late
- IPoIB get_link_ksettings which landed late because I asked for a
respin
- one late rxe change
- one -rc worthy fix that's in early"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
IB/mlx5: Enable IPoIB acceleration
* tag 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
rxe: expose num_possible_cpus() cnum_comp_vectors
IB/rxe: Update caller's CRC for RXE_MEM_TYPE_DMA memory type
IB/hfi1: Clean up on context initialization failure
IB/hfi1: Fix an assign/ordering issue with shared context IDs
IB/hfi1: Clean up context initialization
IB/hfi1: Correctly clear the pkey
IB/hfi1: Search shared contexts on the opened device, not all devices
IB/hfi1: Remove atomic operations for SDMA_REQ_HAVE_AHG bit
IB/hfi1: Use filedata rather than filepointer
IB/hfi1: Name function prototype parameters
IB/hfi1: Fix a subcontext memory leak
IB/hfi1: Return an error on memory allocation failure
IB/hfi1: Adjust default eager_buffer_size to 8MB
IB/hfi1: Get rid of divide when setting the tx request header
IB/hfi1: Fix yield logic in send engine
IB/hfi1, IB/rdmavt: Move r_adefered to r_lock cache line
IB/hfi1: Fix checks for Offline transient state
IB/ipoib: add get_link_ksettings in ethtool
- add ITE 8893 bridge DMA alias quirk (Jarod Wilson)
- restrict Cavium ACS quirk only to CN81xx/CN83xx/CN88xx devices
(Manish Jaggi)
* tag 'pci-v4.12-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (146 commits)
PCI: Don't allow unbinding host controllers that aren't prepared
ARM: DRA7: clockdomain: Change the CLKTRCTRL of CM_PCIE_CLKSTCTRL to SW_WKUP
MAINTAINERS: Add PCI Endpoint maintainer
Documentation: PCI: Add userguide for PCI endpoint test function
tools: PCI: Add sample test script to invoke pcitest
tools: PCI: Add a userspace tool to test PCI endpoint
Documentation: misc-devices: Add Documentation for pci-endpoint-test driver
misc: Add host side PCI driver for PCI test function device
PCI: Add device IDs for DRA74x and DRA72x
dt-bindings: PCI: dra7xx: Add DT bindings to enable unaligned access
PCI: dwc: dra7xx: Workaround for errata id i870
dt-bindings: PCI: dra7xx: Add DT bindings for PCI dra7xx EP mode
PCI: dwc: dra7xx: Add EP mode support
PCI: dwc: dra7xx: Facilitate wrapper and MSI interrupts to be enabled independently
dt-bindings: PCI: Add DT bindings for PCI designware EP mode
PCI: dwc: designware: Add EP mode support
Documentation: PCI: Add binding documentation for pci-test endpoint function
ixgbe: Use pcie_flr() instead of duplicating it
IB/hfi1: Use pcie_flr() instead of duplicating it
PCI: imx6: Fix spelling mistake: "contol" -> "control"
...
Linus Torvalds [Tue, 9 May 2017 01:49:23 +0000 (18:49 -0700)]
Merge tag 'tty-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty
Pull tty/serial updates from Greg KH:
"Here is the "big" TTY/Serial patch updates for 4.12-rc1
Not a lot of new things here, the normal number of serial driver
updates and additions, tiny bugs fixed, and some core files split up
to make future changes a bit easier for Nicolas's "tiny-tty" work.
All of these have been in linux-next for a while"
* tag 'tty-4.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty: (62 commits)
serial: small Makefile reordering
tty: split job control support into a file of its own
tty: move baudrate handling code to a file of its own
console: move console_init() out of tty_io.c
serial: 8250_early: Add earlycon support for Palmchip UART
tty: pl011: use "qdf2400_e44" as the earlycon name for QDF2400 E44
vt: make mouse selection of non-ASCII consistent
vt: set mouse selection word-chars to gpm's default
imx-serial: Reduce RX DMA startup latency when opening for reading
serial: omap: suspend device on probe errors
serial: omap: fix runtime-pm handling on unbind
tty: serial: omap: add UPF_BOOT_AUTOCONF flag for DT init
serial: samsung: Remove useless spinlock
serial: samsung: Add missing checks for dma_map_single failure
serial: samsung: Use right device for DMA-mapping calls
serial: imx: setup DCEDTE early and ensure DCD and RI irqs to be off
tty: fix comment typo s/repsonsible/responsible/
tty: amba-pl011: Fix spurious TX interrupts
serial: xuartps: Enable clocks in the pm disable case also
serial: core: Re-use struct uart_port {name} field
...
Linus Torvalds [Tue, 9 May 2017 01:17:56 +0000 (18:17 -0700)]
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
- the rest of MM
- various misc things
- procfs updates
- lib/ updates
- checkpatch updates
- kdump/kexec updates
- add kvmalloc helpers, use them
- time helper updates for Y2038 issues. We're almost ready to remove
current_fs_time() but that awaits a btrfs merge.
- add tracepoints to DAX
* emailed patches from Andrew Morton <[email protected]>: (114 commits)
drivers/staging/ccree/ssi_hash.c: fix build with gcc-4.4.4
selftests/vm: add a test for virtual address range mapping
dax: add tracepoint to dax_insert_mapping()
dax: add tracepoint to dax_writeback_one()
dax: add tracepoints to dax_writeback_mapping_range()
dax: add tracepoints to dax_load_hole()
dax: add tracepoints to dax_pfn_mkwrite()
dax: add tracepoints to dax_iomap_pte_fault()
mtd: nand: nandsim: convert to memalloc_noreclaim_*()
treewide: convert PF_MEMALLOC manipulations to new helpers
mm: introduce memalloc_noreclaim_{save,restore}
mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC
mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required
mm/huge_memory.c: use zap_deposited_table() more
time: delete CURRENT_TIME_SEC and CURRENT_TIME
gfs2: replace CURRENT_TIME with current_time
apparmorfs: replace CURRENT_TIME with current_time()
lustre: replace CURRENT_TIME macro
fs: ubifs: replace CURRENT_TIME_SEC with current_time
fs: ufs: use ktime_get_real_ts64() for birthtime
...
Andrew Morton [Mon, 8 May 2017 23:00:22 +0000 (16:00 -0700)]
drivers/staging/ccree/ssi_hash.c: fix build with gcc-4.4.4
drivers/staging/ccree/ssi_hash.c:1990: error: unknown field 'template_ahash' specified in initializer
drivers/staging/ccree/ssi_hash.c:1991: error: unknown field 'init' specified in initializer
drivers/staging/ccree/ssi_hash.c:1991: warning: missing braces around initializer
drivers/staging/ccree/ssi_hash.c:1991: warning: (near initialization for 'driver_hash[0].<anonymous>.template_ahash')
drivers/staging/ccree/ssi_hash.c:1992: error: unknown field 'update' specified in initializer
drivers/staging/ccree/ssi_hash.c:1992: warning: excess elements in union initializer
drivers/staging/ccree/ssi_hash.c:1992: warning: (near initialization for 'driver_hash[0].<anonymous>')
drivers/staging/ccree/ssi_hash.c:1993: error: unknown field 'final' specified in initializer
drivers/staging/ccree/ssi_hash.c:1993: warning: excess elements in union initializer
drivers/staging/ccree/ssi_hash.c:1993: warning: (near initialization for 'driver_hash[0].<anonymous>')
...
gcc-4.4.4 has issues with anon union initializers. Work around this.
selftests/vm: add a test for virtual address range mapping
This verifies virtual address mapping below and above the 128TB range
and makes sure that address returned are within the expected range
depending upon the hint passed from the user space.
Ross Zwisler [Mon, 8 May 2017 23:00:16 +0000 (16:00 -0700)]
dax: add tracepoint to dax_insert_mapping()
Add a tracepoint to dax_insert_mapping(), following the same logging
conventions as the rest of DAX. This tracepoint, along with the one in
dax_load_hole(), lets us know how a DAX PTE fault was serviced.
Here is an example DAX fault that inserts a PTE mapping:
Ross Zwisler [Mon, 8 May 2017 23:00:00 +0000 (16:00 -0700)]
dax: add tracepoints to dax_iomap_pte_fault()
Patch series "second round of tracepoints for DAX".
This second round of DAX tracepoint patches adds tracing to the PTE
fault path (dax_iomap_pte_fault(), dax_pfn_mkwrite(), dax_load_hole(),
dax_insert_mapping()) and to the writeback path
(dax_writeback_mapping_range(), dax_writeback_one()).
The purpose of this tracing is to give us a high level view of what DAX
is doing, whether faults are being serviced by PMDs or PTEs, and by real
storage or by zero pages covering holes.
I do have some patches nearly ready which also add tracing to
grab_mapping_entry() and dax_insert_mapping_entry(). These are more
targeted at logging how we are interacting with the radix tree, how we
use empty entries for locking, whether we "downgrade" huge zero pages to
4k PTE sized allocations, etc. In the end it seemed to me that this
might be too detailed to have as constantly present tracepoints, but if
anyone sees value in having tracepoints like this in the DAX code
permanently (Jan?), please let me know and I'll add those last two
patches.
All these tracepoints were done to be consistent with the style of the
XFS tracepoints and with the existing DAX PMD tracepoints.
This patch (of 6):
Add tracepoints to dax_iomap_pte_fault(), following the same logging
conventions as the rest of DAX.
Here is an example fault that initially tries to be serviced by the PMD
fault handler but which falls back to PTEs because the VMA isn't large
enough to hold a PMD:
small-1086 [005] ....
71.140014: xfs_filemap_huge_fault: dev 259:0 ino 0x1003
Vlastimil Babka [Mon, 8 May 2017 22:59:57 +0000 (15:59 -0700)]
mtd: nand: nandsim: convert to memalloc_noreclaim_*()
Nandsim has own functions set_memalloc() and clear_memalloc() for robust
setting and clearing of PF_MEMALLOC. Replace them by the new generic
helpers. No functional change.
Vlastimil Babka [Mon, 8 May 2017 22:59:53 +0000 (15:59 -0700)]
treewide: convert PF_MEMALLOC manipulations to new helpers
We now have memalloc_noreclaim_{save,restore} helpers for robust setting
and clearing of PF_MEMALLOC. Let's convert the code which was using the
generic tsk_restore_flags(). No functional change.
Vlastimil Babka [Mon, 8 May 2017 22:59:50 +0000 (15:59 -0700)]
mm: introduce memalloc_noreclaim_{save,restore}
The previous patch ("mm: prevent potential recursive reclaim due to
clearing PF_MEMALLOC") has shown that simply setting and clearing
PF_MEMALLOC in current->flags can result in wrongly clearing a
pre-existing PF_MEMALLOC flag and potentially lead to recursive reclaim.
Let's introduce helpers that support proper nesting by saving the
previous stat of the flag, similar to the existing memalloc_noio_* and
memalloc_nofs_* helpers. Convert existing setting/clearing of
PF_MEMALLOC within mm to the new helpers.
There are no known issues with the converted code, but the change makes
it more robust.
Vlastimil Babka [Mon, 8 May 2017 22:59:46 +0000 (15:59 -0700)]
mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC
Patch series "more robust PF_MEMALLOC handling"
This series aims to unify the setting and clearing of PF_MEMALLOC, which
prevents recursive reclaim. There are some places that clear the flag
unconditionally from current->flags, which may result in clearing a
pre-existing flag. This already resulted in a bug report that Patch 1
fixes (without the new helpers, to make backporting easier). Patch 2
introduces the new helpers, modelled after existing memalloc_noio_* and
memalloc_nofs_* helpers, and converts mm core to use them. Patches 3
and 4 convert non-mm code.
This patch (of 4):
__alloc_pages_direct_compact() sets PF_MEMALLOC to prevent deadlock
during page migration by lock_page() (see the comment in
__unmap_and_move()). Then it unconditionally clears the flag, which can
clear a pre-existing PF_MEMALLOC flag and result in recursive reclaim.
This was not a problem until commit a8161d1ed609 ("mm, page_alloc:
restructure direct compaction handling in slowpath"), because direct
compation was called only after direct reclaim, which was skipped when
PF_MEMALLOC flag was set.
Even now it's only a theoretical issue, as the new callsite of
__alloc_pages_direct_compact() is reached only for costly orders and
when gfp_pfmemalloc_allowed() is true, which means either
__GFP_NOMEMALLOC is in gfp_flags or in_interrupt() is true. There is no
such known context, but let's play it safe and make
__alloc_pages_direct_compact() robust for cases where PF_MEMALLOC is
already set.
mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required
Although all architectures use a deposited page table for THP on
anonymous VMAs, some architectures (s390 and powerpc) require the
deposited storage even for file backed VMAs due to quirks of their MMUs.
This patch adds support for depositing a table in DAX PMD fault handling
path for archs that require it. Other architectures should see no
functional changes.
Depending on the flags of the PMD being zapped there may or may not be a
deposited pgtable to be freed. In two of the three cases this is open
coded while the third uses the zap_deposited_table() helper. This patch
converts the others to use the helper to clean things up a bit.
Deepa Dinamani [Mon, 8 May 2017 22:59:37 +0000 (15:59 -0700)]
time: delete CURRENT_TIME_SEC and CURRENT_TIME
All uses of CURRENT_TIME_SEC and CURRENT_TIME macros have been replaced
by other time functions. These macros are also not y2038 safe. And,
all their use cases can be fulfilled by y2038 safe ktime_get_* variants.
Deepa Dinamani [Mon, 8 May 2017 22:59:31 +0000 (15:59 -0700)]
apparmorfs: replace CURRENT_TIME with current_time()
CURRENT_TIME macro is not y2038 safe on 32 bit systems.
The patch replaces all the uses of CURRENT_TIME by current_time().
This is also in preparation for the patch that transitions vfs
timestamps to use 64 bit time and hence make them y2038 safe.
current_time() is also planned to be transitioned to y2038 safe behavior
along with this change.
CURRENT_TIME macro will be deleted before merging the aforementioned
change.
Deepa Dinamani [Mon, 8 May 2017 22:59:28 +0000 (15:59 -0700)]
lustre: replace CURRENT_TIME macro
CURRENT_TIME macro is not y2038 safe on 32 bit systems.
The patch replaces all the uses of CURRENT_TIME by current_time() for
filesystem times, and ktime_get_* functions for others.
struct timespec is also not y2038 safe. Retain timespec for timestamp
representation here as lustre uses it internally everywhere. These
references will be changed to use struct timespec64 in a separate patch.
This is also in preparation for the patch that transitions vfs
timestamps to use 64 bit time and hence make them y2038 safe.
current_time() is also planned to be transitioned to y2038 safe behavior
along with this change.
CURRENT_TIME macro will be deleted before merging the aforementioned
change.
Deepa Dinamani [Mon, 8 May 2017 22:59:25 +0000 (15:59 -0700)]
fs: ubifs: replace CURRENT_TIME_SEC with current_time
CURRENT_TIME_SEC is not y2038 safe. current_time() will be transitioned
to use 64 bit time along with vfs in a separate patch. There is no plan
to transition CURRENT_TIME_SEC to use y2038 safe time interfaces.
current_time() returns timestamps according to the granularities set in
the inode's super_block. The granularity check to call
current_fs_time() or CURRENT_TIME_SEC is not required.
Use current_time() directly to update inode timestamp. Use
timespec_trunc during file system creation, before the first inode is
created.
Deepa Dinamani [Mon, 8 May 2017 22:59:19 +0000 (15:59 -0700)]
fs: ceph: CURRENT_TIME with ktime_get_real_ts()
CURRENT_TIME is not y2038 safe. The macro will be deleted and all the
references to it will be replaced by ktime_get_* apis.
struct timespec is also not y2038 safe. Retain timespec for timestamp
representation here as ceph uses it internally everywhere. These
references will be changed to use struct timespec64 in a separate patch.
The current_fs_time() api is being changed to use vfs struct inode* as
an argument instead of struct super_block*.
Set the new mds client request r_stamp field using ktime_get_real_ts()
instead of using current_fs_time().
Also, since r_stamp is used as mtime on the server, use timespec_trunc()
to truncate the timestamp, using the right granularity from the
superblock.
This api will be transitioned to be y2038 safe along with vfs.
Deepa Dinamani [Mon, 8 May 2017 22:59:16 +0000 (15:59 -0700)]
fs: cifs: replace CURRENT_TIME by other appropriate apis
CURRENT_TIME macro is not y2038 safe on 32 bit systems.
The patch replaces all the uses of CURRENT_TIME by current_time() for
filesystem times, and ktime_get_* functions for authentication
timestamps and timezone calculations.
This is also in preparation for the patch that transitions vfs
timestamps to use 64 bit time and hence make them y2038 safe.
CURRENT_TIME macro will be deleted before merging the aforementioned
change.
The inode timestamps read from the server are assumed to have correct
granularity and range.
The patch also assumes that the difference between server and client
times lie in the range INT_MIN..INT_MAX. This is valid because this is
the difference between current times between server and client, and the
largest timezone difference is in the range of one day.
All cifs timestamps currently use timespec representation internally.
Authentication and timezone timestamps can also be transitioned into
using timespec64 when all other timestamps for cifs is transitioned to
use timespec64.
Deepa Dinamani [Mon, 8 May 2017 22:59:13 +0000 (15:59 -0700)]
trace: make trace_hwlat timestamp y2038 safe
struct timespec is not y2038 safe on 32 bit machines and needs to be
replaced by struct timespec64 in order to represent times beyond year
2038 on such machines.
Fix all the timestamp representation in struct trace_hwlat and all the
corresponding implementations.
Kees Cook [Mon, 8 May 2017 22:59:05 +0000 (15:59 -0700)]
format-security: move static strings to const
While examining output from trial builds with -Wformat-security enabled,
many strings were found that should be defined as "const", or as a char
array instead of char pointer. This makes some static analysis easier,
by producing fewer false positives.
As these are all trivial changes, it seemed best to put them all in a
single patch rather than chopping them up per maintainer.
Tetsuo Handa [Mon, 8 May 2017 22:58:59 +0000 (15:58 -0700)]
fs: semove set but not checked AOP_FLAG_UNINTERRUPTIBLE flag
Commit afddba49d18f ("fs: introduce write_begin, write_end, and
perform_write aops") introduced AOP_FLAG_UNINTERRUPTIBLE flag which was
checked in pagecache_write_begin(), but that check was removed by 4e02ed4b4a2f ("fs: remove prepare_write/commit_write").
Between these two commits, commit d9414774dc0c ("cifs: Convert cifs to
new aops.") added a check in cifs_write_begin(), but that check was soon
removed by commit a98ee8c1c707 ("[CIFS] fix regression in
cifs_write_begin/cifs_write_end").
Therefore, AOP_FLAG_UNINTERRUPTIBLE flag is checked nowhere. Let's
remove this flag. This patch has no functionality changes.
Andi Kleen [Mon, 8 May 2017 22:58:56 +0000 (15:58 -0700)]
include/linux/uaccess.h: remove expensive WARN_ON in pagefault_disabled_dec
pagefault_disabled_dec is frequently used inline, and it has a WARN_ON
for underflow that expands to about 6.5k of extra code. The warning
doesn't seem to be that useful and worth so much code so remove it.
If it was needed could make it depending on some debug kernel option.
Andi Kleen [Mon, 8 May 2017 22:58:50 +0000 (15:58 -0700)]
kref: remove WARN_ON for NULL release functions
The kref functions check for NULL release functions. This WARN_ON seems
rather pointless. We will eventually release and then just crash
nicely. It is also somewhat expensive because these functions are
inlined in a lot of places. Removing the WARN_ONs saves around 2.3k in
this kernel (likely more in others with more drivers)
Laura Abbott [Mon, 8 May 2017 22:57:59 +0000 (15:57 -0700)]
treewide: move set_memory_* functions away from cacheflush.h
Patch series "set_memory_* functions header refactor", v3.
The set_memory_* APIs came out of a desire to have a better way to
change memory attributes. Many of these attributes were linked to cache
functionality so the prototypes were put in cacheflush.h. These days,
the APIs have grown and have a much wider use than just cache APIs. To
support this growth, split off set_memory_* and friends into a separate
header file to avoid growing cacheflush.h for APIs that have nothing to
do with caches.
The only problem is that many people are not aware that they really want
to give __GFP_HIGHMEM along with other flags because there is really no
reason to consume precious lowmemory on CONFIG_HIGHMEM systems for pages
which are mapped to the kernel vmalloc space. About half of users don't
use this flag, though. This signals that we make the API unnecessarily
too complex.
This patch simply uses __GFP_HIGHMEM implicitly when allocating pages to
be mapped to the vmalloc space. Current users which add __GFP_HIGHMEM
are simplified and drop the flag.
Huang Ying [Mon, 8 May 2017 22:57:40 +0000 (15:57 -0700)]
mm, swap: use kvzalloc to allocate some swap data structures
Now vzalloc() is used in swap code to allocate various data structures,
such as swap cache, swap slots cache, cluster info, etc. Because the
size may be too large on some system, so that normal kzalloc() may fail.
But using kzalloc() has some advantages, for example, less memory
fragmentation, less TLB pressure, etc. So change the data structure
allocation in swap code to use kvzalloc() which will try kzalloc()
firstly, and fallback to vzalloc() if kzalloc() failed.
In general, although kmalloc() will reduce the number of high-order
pages in short term, vmalloc() will cause more pain for memory
fragmentation in the long term. And the swap data structure allocation
that is changed in this patch is expected to be long term allocation.
From Dave Hansen:
"for example, we have a two-page data structure. vmalloc() takes two
effectively random order-0 pages, probably from two different 2M pages
and pins them. That "kills" two 2M pages. kmalloc(), allocating two
*contiguous* pages, will not cross a 2M boundary. That means it will
only "kill" the possibility of a single 2M page. More 2M pages == less
fragmentation.
The allocation in this patch occurs during swap on time, which is
usually done during system boot, so usually we have high opportunity to
allocate the contiguous pages successfully.
The allocation for swap_map[] in struct swap_info_struct is not changed,
because that is usually quite large and vmalloc_to_page() is used for
it. That makes it a little harder to change.
Michal Hocko [Mon, 8 May 2017 22:57:37 +0000 (15:57 -0700)]
drivers/md/bcache/super.c: use kvmalloc
bcache_device_init uses kmalloc for small requests and vmalloc for those
which are larger than 64 pages. This alone is a strange criterion.
Moreover kmalloc can fallback to vmalloc on the failure. Let's simply
use kvmalloc instead as it knows how to handle the fallback properly
Michal Hocko [Mon, 8 May 2017 22:57:34 +0000 (15:57 -0700)]
drivers/md/dm-ioctl.c: use kvmalloc rather than opencoded variant
copy_params uses kmalloc with vmalloc fallback. We already have a
helper for that - kvmalloc. This caller requires GFP_NOIO semantic so
it hasn't been converted with many others by previous patches. All we
need to achieve this semantic is to use the scope
memalloc_noio_{save,restore} around kvmalloc.
Michal Hocko [Mon, 8 May 2017 22:57:31 +0000 (15:57 -0700)]
net: use kvmalloc with __GFP_REPEAT rather than open coded variant
fq_alloc_node, alloc_netdev_mqs and netif_alloc* open code kmalloc with
vmalloc fallback. Use the kvmalloc variant instead. Keep the
__GFP_REPEAT flag based on explanation from Eric:
"At the time, tests on the hardware I had in my labs showed that
vmalloc() could deliver pages spread all over the memory and that was
a small penalty (once memory is fragmented enough, not at boot time)"
The way how the code is constructed means, however, that we prefer to go
and hit the OOM killer before we fall back to the vmalloc for requests
<=32kB (with 4kB pages) in the current code. This is rather disruptive
for something that can be achived with the fallback. On the other hand
__GFP_REPEAT doesn't have any useful semantic for these requests. So
the effect of this patch is that requests which fit into 32kB will fall
back to vmalloc easier now.
projects / linux.git / log