IPQ8074 comes in 2 silicon versions:
* v1 with 2x Gen2 PCIe ports and QMP PHY-s
* v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s
v2 is the final and production version that is actually supported by the
kernel, however it looks like PCIe related nodes were added for the v1 SoC.
Finish the PCIe fixup by using the correct compatible, adding missing ATU
register space, declaring max-link-speed, use correct ranges, add missing
clocks and resets.
Fixes: 33057e1672 ("ARM: dts: ipq8074: Add pcie nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-8-robimarko@gmail.com
Add the generic 'max-link-speed' property to describe the Gen2 PCIe link
generation limit.
This allows the generic DWC code to configure the link speed correctly.
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-4-robimarko@gmail.com
Current ranges property set in Gen2 PCIe node is incorrect, replace it
with the downstream 5.4 QCA kernel value.
Fixes: 33057e1672 ("ARM: dts: ipq8074: Add pcie nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-3-robimarko@gmail.com
IPQ8074 comes in 2 silicon versions:
* v1 with 2x Gen2 PCIe ports and QMP PHY-s
* v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s
v2 is the final and production version that is actually supported by the
kernel, however it looks like PCIe related nodes were added for the v1 SoC.
Now that we have Gen3 QMP PHY support, we can start fixing the PCIe support
by fixing the Gen3 QMP PHY node first.
Change the compatible to the Gen3 QMP PHY, correct the register space start
and size, add the missing misc PCS register space.
Fixes: 33057e1672 ("ARM: dts: ipq8074: Add pcie nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-2-robimarko@gmail.com
Serdes register space sizes are incorrect, update them to match the
actual sizes from downstream QCA 5.4 kernel.
Fixes: 942bcd33ed ("arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-1-robimarko@gmail.com
When the firmware (FW) supports multiple requests per VM, multiple requests
from the same/different VM can reach the firmware at the same time. Since
the firmware currently being used has limited resources, it guards them
with a resource lock and puts requests on a wait-queue internally and
signals to HLOS that it is doing so. It does this by returning a new return
value in addition to success or error: SCM_WAITQ_SLEEP. A sleeping SCM call
can be woken up by an interrupt that the FW raises.
1) SCM_WAITQ_SLEEP:
When an SCM call receives this return value instead of success
or error, FW has placed this call on a wait-queue and has signalled
HLOS to put it to non-interruptible sleep.
Along with this return value, FW also passes to HLOS `wq_ctx` -
a unique number (UID) identifying the wait-queue that it has put
the call on, internally. This is to help HLOS with its own
bookkeeping to wake this sleeping call later.
Additionally, FW also passes to HLOS `smc_call_ctx` - a UID
identifying the SCM call thus being put to sleep. This is also
for HLOS' bookkeeping to wake this call up later.
These two additional values are passed via the a1 and a2
registers.
N.B.: The "ctx" in the above UID names = "context".
The handshake mechanism that HLOS uses to talk to FW about wait-queue
operations involves two new SMC calls.
1) get_wq_ctx():
Arguments: None
Returns: wq_ctx, flags, more_pending
Get the wait-queue context, and wake up either one or all of the
sleeping SCM calls associated with that wait-queue.
Additionally, repeat this if there are more wait-queues that are
ready to have their requests woken up (`more_pending`).
2) wq_resume(smc_call_ctx):
Arguments: smc_call_ctx
HLOS needs to issue this in response to receiving an
IRQ, passing to FW the same smc_call_ctx that FW
receives from HLOS via the get_wq_ctx() call.
(The mechanism to wake a SMC call back up is described in detail below)
VM_1 VM_2 Firmware
│ │ │
│ │ │
│ │ │
│ │ │
│ REQUEST_1 │ │
├────────────────────────┼─────────────────────────────────┤
│ │ │
│ │ ┌──┼──┐
│ │ │ │ │
│ │ REQUEST_2 │ │ │
│ ├──────────────────────────────┼──┤ │
│ │ │ │ │Resource
│ │ │ │ │is busy
│ │ {WQ_SLEEP} │ │ │
│ │◄─────────────────────────────┼──┤ │
│ │ wq_ctx, smc_call_ctx │ │ │
│ │ └──┼──┘
│ REQUEST_1 COMPLETE │ │
│◄───────────────────────┼─────────────────────────────────┤
│ │ │
│ │ IRQ │
│ │◄─-------------------------------│
│ │ │
│ │ get_wq_ctx() │
│ ├────────────────────────────────►│
│ │ │
│ │ │
│ │◄────────────────────────────────┤
│ │ wq_ctx, flags, and │
│ │ more_pending │
│ │ │
│ │ │
│ │ wq_resume(smc_call_ctx) │
│ ├────────────────────────────────►│
│ │ │
│ │ │
│ │ REQUEST_2 COMPLETE │
│ │◄────────────────────────────────┤
│ │ │
│ │ │
With the exception of get_wq_ctx(), the other SMC call wq_resume() can
return WQ_SLEEP (these nested rounds of WQ_SLEEP are not shown in the
above diagram for the sake of simplicity). Therefore, introduce a new
do-while loop to handle multiple WQ_SLEEP return values for the same
parent SCM call.
Request Completion in the above diagram refers to either a success
return value (zero) or error (and not SMC_WAITQ_SLEEP)
Also add the interrupt handler that wakes up a sleeping SCM call.
Signed-off-by: Guru Das Srinagesh <quic_gurus@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Guru Das Srinagesh <quic_gurus@quicinc.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113161114.22607-3-quic_sibis@quicinc.com
Add an interrupt specification to the bindings to support the wait-queue
feature on SM8450 SoCs.
Signed-off-by: Guru Das Srinagesh <quic_gurus@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113161114.22607-2-quic_sibis@quicinc.com
SM4250 and SM6115 use a shared device tree and the RPMPDs are
identical. There's no need for a separate entry, so remove it.
This reverts commit 45ac44ed10.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113152232.2624545-2-konrad.dybcio@linaro.org
SM4250 and SM6115 use a shared device tree and the RPMPDs are
identical. There's no need for a separate entry, so remove it.
This reverts commit 5b617b1b10.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113152232.2624545-1-konrad.dybcio@linaro.org
Geni I2C Controller node does not allow a "label" property and Linux
driver does not parse it:
sdm845-db845c.dtb: i2c@a8c000: Unevaluated properties are not allowed ('label' was unexpected)
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113145231.79280-1-krzysztof.kozlowski@linaro.org
In some cases the driver might need using GPLL0 to drive CPU clocks.
Bring it in through the sys_apcs_aux clock.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-15-dmitry.baryshkov@linaro.org
Check whether L2 registers contain correct values and skip programming
if they are valid. This follows the code present downstream.
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-7-dmitry.baryshkov@linaro.org
In some cases the driver might need using GPLL0 to drive CPU clocks.
Bring it in through the sys_apcs_aux clock.
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-6-dmitry.baryshkov@linaro.org
Current multiplier (60) results in CPU getting the rate which is
unlisted in the CPU frequency tables (60 * 19.2 = 1152 MHz). This
results in warnings from the cpufreq during startup.
Change PLL programming (l = 54) to init CPU clocks to start with the
frequency of 54 * 19.2 = 1036.8 MHz which is supported by both power and
performance clusters from all speed bins.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-5-dmitry.baryshkov@linaro.org
Program PLL_TEST and PLL_TEST_U registers if required by the pll
configuration.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-3-dmitry.baryshkov@linaro.org
The MSM8996 CPU clock controller can make use of the sys_apcs_aux clock.
Add it to the bindings.
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113120544.59320-2-dmitry.baryshkov@linaro.org
Add Global Clock Controller (GCC) support for QDU1000 and QRU1000 SoCs.
Signed-off-by: Taniya Das <quic_tdas@quicinc.com>
Signed-off-by: Melody Olvera <quic_molvera@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
[bjorn: Made gcc_pcie_0_pipe_clk_src use clk_regmap_phy_mux_ops]
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230112204446.30236-3-quic_molvera@quicinc.com
Add device tree bindings for global clock controller on QDU1000 and
QRU1000 SoCs.
Signed-off-by: Melody Olvera <quic_molvera@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230112204446.30236-2-quic_molvera@quicinc.com
In current bpf_send_signal() and bpf_send_signal_thread() helper
implementation, irq_work is used to handle nmi context. Hao Sun
reported in [1] that the current task at the entry of the helper
might be gone during irq_work callback processing. To fix the issue,
a reference is acquired for the current task before enqueuing into
the irq_work so that the queued task is still available during
irq_work callback processing.
[1] https://lore.kernel.org/bpf/20230109074425.12556-1-sunhao.th@gmail.com/
Fixes: 8b401f9ed2 ("bpf: implement bpf_send_signal() helper")
Tested-by: Hao Sun <sunhao.th@gmail.com>
Reported-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230118204815.3331855-1-yhs@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
According to the definition of sizes[NUM_CACHES], when the size passed
to bpf_mem_cache_size() is 256, it should return 6 instead 7.
Fixes: 7c8199e24f ("bpf: Introduce any context BPF specific memory allocator.")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230118084630.3750680-1-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The devicetree should specify both MSI implementations and the OS/driver
should choose the one based on the platform requirements. Currently, Linux
DWC driver will choose GIC-ITS over the internal MSI controller.
Fixes: a11bbf6adef4 ("arm64: dts: qcom: sm8450: Use GIC-ITS for PCIe0 and PCIe1")
Suggested-by: Rob Herring <robh@kernel.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230111123004.21048-2-manivannan.sadhasivam@linaro.org
Commit 0d0e7d1eea ("drm/i915/mtl: Define engine context layouts")
added the engine context for Meteor Lake. In a second revision of the
patch it was believed the xcs offsets were wrong due to a tagging
issue in the spec. The first version was actually correct, as shown
by the intel_lrc_live_selftests/live_lrc_layout test:
i915: Running gt_lrc
i915: Running intel_lrc_live_selftests/live_lrc_layout
bcs0: LRI command mismatch at dword 1, expected 1108101d found 11081019
[drm:drm_helper_probe_single_connector_modes [drm_kms_helper]] [CONNECTOR:236:DP-1] disconnected
bcs0: HW register image:
[0000] 00000000 1108101d 00022244 ffff0008 00022034 00000088 00022030 00000088
...
bcs0: SW register image:
[0000] 00000000 11081019 00022244 00090009 00022034 00000000 00022030 00000000
The difference in the 2 additional dwords (0x1d vs 0x19) are the offsets
0x120 / 0x124 that are indeed part of the context image.
Bspec: 45585
Fixes: 0d0e7d1eea ("drm/i915/mtl: Define engine context layouts")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230111235531.3353815-2-radhakrishna.sripada@intel.com
__USE_GNU should be an internal macro only used inside glibc. Either
memfd_create() or fallocate() requires _GNU_SOURCE per man page, where
__USE_GNU will further be defined by glibc headers include/features.h:
#ifdef _GNU_SOURCE
# define __USE_GNU 1
#endif
This fixes:
>> hugetlb-madvise.c:20: warning: "__USE_GNU" redefined
20 | #define __USE_GNU
|
In file included from /usr/include/x86_64-linux-gnu/bits/libc-header-start.h:33,
from /usr/include/stdlib.h:26,
from hugetlb-madvise.c:16:
/usr/include/features.h:407: note: this is the location of the previous definition
407 | # define __USE_GNU 1
|
Link: https://lkml.kernel.org/r/Y8V9z+z6Tk7NetI3@x1n
Signed-off-by: Peter Xu <peterx@redhat.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Selftests vm builds break when doing cross-compilation. The Makefile
MACHINE variable incorrectly picks upp the host machine architecture.
If the CROSS_COMPILE variable is set, dig out the target host architecture
from CROSS_COMPILE, instead of calling uname.
Link: https://lkml.kernel.org/r/20230109114251.3349638-1-bjorn@kernel.org
Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Remove redundant import of the sys module.
Also use the sort function instead of sorted. It sorts the direct array
without create the new one in memory.
Link: https://lkml.kernel.org/r/20230108105023.4289-1-apantykhin@gmail.com
Signed-off-by: Alexander Pantyukhin <apantykhin@gmail.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The implementation of strscpy() is more robust and safer.
That's now the recommended way to copy NUL-terminated strings.
Link: https://lkml.kernel.org/r/202301091946553770006@zte.com.cn
Signed-off-by: Xu Panda <xu.panda@zte.com.cn>
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Convert mext_page_double_lock() to use folios. This change saves 146
bytes of kernel text. It also removes 6 calls to compound_head() and 2
calls to folio_file_page().
Link: https://lkml.kernel.org/r/20221207181009.4016-1-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
If MADV_PAGEOUT is not defined (e.g., on AlmaLinux 8), compilation will
fail. Let's fix that like khugepaged.c does by conditionally defining
MADV_PAGEOUT.
Link: https://lkml.kernel.org/r/20230109171255.488749-1-david@redhat.com
Fixes: 69c66add56 ("selftests/vm: anon_cow: test COW handling of anonymous memory")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The page table debug tests need a physical address to validate low-level
page table manipulation with. The memory at this address is not actually
touched, it just encoded in the page table entries at various levels
during the tests only.
Since the memory is not used, the code just picks the physical address of
the start_kernel symbol. This value is then truncated to get a properly
aligned address that is to be used for various tests. Because of the
truncation, the address might not actually exist, or might not describe a
complete huge page. That's not a problem for most tests, but the
arch-specific code may check for attribute validity and consistency. The
x86 version of {pud,pmd}_set_huge actually validates the MTRRs for the
PMD/PUD range. This may fail with an address derived from start_kernel,
depending on where the kernel was loaded and what the physical memory
layout of the system is. This then leads to false negatives for the
{pud,pmd}_set_huge tests.
Avoid this by finding a properly aligned memory range that exists and is
usable. If such a range is not found, skip the tests that needed it.
[fvdl@google.com: v3]
Link: https://lkml.kernel.org/r/20230110181208.1633879-1-fvdl@google.com
Link: https://lkml.kernel.org/r/20230109174332.329366-1-fvdl@google.com
Fixes: 399145f9eb ("mm/debug: add tests validating architecture page table helpers")
Signed-off-by: Frank van der Linden <fvdl@google.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
'damon_pa_access_chk_result' struct contains only one field. Use a
variable instead.
Link: https://lkml.kernel.org/r/20230109213335.62525-7-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
DAMON physical address space monitoring operations set gets and saves size
of the folio for a given physical address inside rmap walks, but it can be
directly caluclated outside of the walks. Remove the 'folio_sz' field
from 'damon_pa_access_chk_result struct' and calculate the size directly
from outside of the walks.
Link: https://lkml.kernel.org/r/20230109213335.62525-6-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
DAMON's physical address space monitoring operations set is using folio
now. Rename 'damon_pa_access_chk_result->page_sz' to reflect the fact.
Link: https://lkml.kernel.org/r/20230109213335.62525-5-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
DAMON virtual address spaces monitoring operations set doesn't set folio
size of the access checked address if access is not found. It could
result in unnecessary and inefficient repeated check. Appropriately set
the size regardless of access check result.
Link: https://lkml.kernel.org/r/20230109213335.62525-4-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
DAMON virtual address space monitoring operations set treats folios having
non-HPAGE_PMD_SIZE size as having PAGE_SIZE size. Use the exact size of
the folio.
Link: https://lkml.kernel.org/r/20230109213335.62525-3-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "mm/damon/{v,p}addr: misc fixups for folio usage".
DAMON's monitoring operations set for the virtual and the physical address
spaces use folio now, but some code is not reflecting the fact. Further
cleanup the code for folio usage.
This patch (of 6):
DAMON's virtual address space monitoring operations set is using folio
now. Rename 'damon_pa_access_chk_result->page_sz' to reflect the fact.
Link: https://lkml.kernel.org/r/20230109213335.62525-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20230109213335.62525-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The only in-kernel users that need PageMovable() to be exported are z3fold
and zsmalloc and they are only using it for dubious debugging
functionality. So remove those usages and the export so that no driver
code accidentally thinks that they are allowed to use this symbol.
Link: https://lkml.kernel.org/r/20230106135900.3763622-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Add a folio equivalent for page_is_pfmemalloc. This removes two instances
of page_is_pfmemalloc(folio_page(folio, 0)) so the folio can be used
directly.
Link: https://lkml.kernel.org/r/20230106215251.599222-1-sidhartha.kumar@oracle.com
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This patch adds POSIX_FADV_NOREUSE to vma_has_recency() so that the LRU
algorithm can ignore access to mapped files marked by this flag.
The advantages of POSIX_FADV_NOREUSE are:
1. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not alter the
default readahead behavior.
2. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not split VMAs and
therefore does not take mmap_lock.
3. Unlike MADV_COLD, setting it has a negligible cost, regardless of
how many pages it affects.
Its limitations are:
1. Like POSIX_FADV_RANDOM and POSIX_FADV_SEQUENTIAL, it currently does
not support range. IOW, its scope is the entire file.
2. It currently does not ignore access through file descriptors.
Specifically, for the active/inactive LRU, given a file page shared
by two users and one of them having set POSIX_FADV_NOREUSE on the
file, this page will be activated upon the second user accessing
it. This corner case can be covered by checking POSIX_FADV_NOREUSE
before calling folio_mark_accessed() on the read path. But it is
considered not worth the effort.
There have been a few attempts to support POSIX_FADV_NOREUSE, e.g., [1].
This time the goal is to fill a niche: a few desktop applications, e.g.,
large file transferring and video encoding/decoding, want fast file
streaming with mmap() rather than direct IO. Among those applications, an
SVT-AV1 regression was reported when running with MGLRU [2]. The
following test can reproduce that regression.
kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo)
kb=$((kb - 8*1024*1024))
modprobe brd rd_nr=1 rd_size=$kb
dd if=/dev/zero of=/dev/ram0 bs=1M
mkfs.ext4 /dev/ram0
mount /dev/ram0 /mnt/
swapoff -a
fallocate -l 8G /mnt/swapfile
mkswap /mnt/swapfile
swapon /mnt/swapfile
wget http://ultravideo.cs.tut.fi/video/Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
7z e -o/mnt/ Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
SvtAv1EncApp --preset 12 -w 3840 -h 2160 \
-i /mnt/Bosphorus_3840x2160.y4m
For MGLRU, the following change showed a [9-11]% increase in FPS,
which makes it on par with the active/inactive LRU.
patch Source/App/EncApp/EbAppMain.c <<EOF
31a32
> #include <fcntl.h>
35d35
< #include <fcntl.h> /* _O_BINARY */
117a118
> posix_fadvise(config->mmap.fd, 0, 0, POSIX_FADV_NOREUSE);
EOF
[1] https://lore.kernel.org/r/1308923350-7932-1-git-send-email-andrea@betterlinux.com/
[2] https://openbenchmarking.org/result/2209259-PTS-MGLRU8GB57
Link: https://lkml.kernel.org/r/20221230215252.2628425-2-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Righi <andrea.righi@canonical.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Add vma_has_recency() to indicate whether a VMA may exhibit temporal
locality that the LRU algorithm relies on.
This function returns false for VMAs marked by VM_SEQ_READ or
VM_RAND_READ. While the former flag indicates linear access, i.e., a
special case of spatial locality, both flags indicate a lack of temporal
locality, i.e., the reuse of an area within a relatively small duration.
"Recency" is chosen over "locality" to avoid confusion between temporal
and spatial localities.
Before this patch, the active/inactive LRU only ignored the accessed bit
from VMAs marked by VM_SEQ_READ. After this patch, the active/inactive
LRU and MGLRU share the same logic: they both ignore the accessed bit if
vma_has_recency() returns false.
For the active/inactive LRU, the following fio test showed a [6, 8]%
increase in IOPS when randomly accessing mapped files under memory
pressure.
kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo)
kb=$((kb - 8*1024*1024))
modprobe brd rd_nr=1 rd_size=$kb
dd if=/dev/zero of=/dev/ram0 bs=1M
mkfs.ext4 /dev/ram0
mount /dev/ram0 /mnt/
swapoff -a
fio --name=test --directory=/mnt/ --ioengine=mmap --numjobs=8 \
--size=8G --rw=randrw --time_based --runtime=10m \
--group_reporting
The discussion that led to this patch is here [1]. Additional test
results are available in that thread.
[1] https://lore.kernel.org/r/Y31s%2FK8T85jh05wH@google.com/
Link: https://lkml.kernel.org/r/20221230215252.2628425-1-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Righi <andrea.righi@canonical.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
A MAP_SHARED mapping always has VM_MAYSHARE set, and writable
(VM_MAYWRITE) MAP_SHARED mappings have VM_SHARED set as well. To identify
a MAP_SHARED mapping, it's sufficient to look at VM_MAYSHARE.
We cannot have VM_MAYSHARE|VM_WRITE mappings without having VM_SHARED set.
Consequently, current code will never actually end up clearing
VM_MAYSHARE and that code is confusing, because nobody is supposed to mess
with VM_MAYWRITE.
Let's clean it up and restructure the code. No functional change intended.
Link: https://lkml.kernel.org/r/20230102160856.500584-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Let's stop using VM_MAYSHARE for MAP_PRIVATE mappings and use
VM_MAYOVERLAY instead. Rewrite determine_vm_flags() to make the whole
logic easier to digest, and to cleanly separate MAP_PRIVATE vs.
MAP_SHARED.
No functional change intended.
Link: https://lkml.kernel.org/r/20230102160856.500584-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "mm/nommu: don't use VM_MAYSHARE for MAP_PRIVATE mappings".
Trying to reduce the confusion around VM_SHARED and VM_MAYSHARE first
requires !CONFIG_MMU to stop using VM_MAYSHARE for MAP_PRIVATE mappings.
CONFIG_MMU only sets VM_MAYSHARE for MAP_SHARED mappings.
This paves the way for further VM_MAYSHARE and VM_SHARED cleanups: for
example, renaming VM_MAYSHARED to VM_MAP_SHARED to make it cleaner what is
actually means.
Let's first get the weird case out of the way and not use VM_MAYSHARE in
MAP_PRIVATE mappings, using a new VM_MAYOVERLAY flag instead.
This patch (of 3):
We want to stop using VM_MAYSHARE in private mappings to pave the way for
clarifying the semantics of VM_MAYSHARE vs. VM_SHARED and reduce the
confusion. While CONFIG_MMU uses VM_MAYSHARE to represent MAP_SHARED,
!CONFIG_MMU also sets VM_MAYSHARE for selected R/O private file mappings
that are an effective overlay of a file mapping.
Let's factor out all relevant VM_MAYSHARE checks in !CONFIG_MMU code into
is_nommu_shared_mapping() first.
Note that whenever VM_SHARED is set, VM_MAYSHARE must be set as well
(unless there is a serious BUG). So there is not need to test for
VM_SHARED manually.
No functional change intended.
Link: https://lkml.kernel.org/r/20230102160856.500584-1-david@redhat.com
Link: https://lkml.kernel.org/r/20230102160856.500584-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Nicolas Pitre <nico@fluxnic.net>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Add a test to assert that we can mremap() and expand a mapping starting
from an offset within an existing mapping. We unmap the last page in a 3
page mapping to ensure that the remap should always succeed, before
remapping from the 2nd page.
This is additionally a regression test for the issue solved in "mm,
mremap: fix mremap() expanding vma with addr inside vma" and confirmed to
fail prior to the change and pass after it.
Finally, this patch updates the existing mremap expand merge test to check
error conditions and reduce code duplication between the two tests.
[lstoakes@gmail.com: increment num_expand_tests so test doesn't complain about unexpected tests being run]
Link: https://lkml.kernel.org/r/8ff3ba3cadc0b6c1b2688ae5c851bf73aa062d57.1673701836.git.lstoakes@gmail.com
Link: https://lkml.kernel.org/r/02b117a8ffd52acc01dc66c2fb39754f08d92c0e.1672675824.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jakub Matěna <matenajakub@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When supplied buffer does not have assignment sign next_arg() sets `val`
pointer to NULL, so we cannot dereference it. Add a NULL pointer test to
handle `param` case, in addition to `*val` test, which handles cases when
param has no value assigned to it: `param=`.
Link: https://lkml.kernel.org/r/20230103030119.1496358-1-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When __mpage_writepage() is called for a page beyond EOF, it will go and
allocate all blocks underlying the page. This is not only unnecessary but
this way blocks can get leaked (e.g. if a page beyond EOF is marked dirty
but in the end write fails and i_size is not extended).
Link: https://lkml.kernel.org/r/20230103104430.27749-1-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
