summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/cgroup-v1/memory.rst7
-rw-r--r--Documentation/devicetree/bindings/ata/pata-common.yaml1
-rw-r--r--Documentation/devicetree/bindings/clock/renesas,5p35023.yaml11
-rw-r--r--Documentation/devicetree/bindings/i2c/i2c-mxs.yaml5
-rw-r--r--Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml43
-rw-r--r--Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml7
-rw-r--r--Documentation/filesystems/porting.rst96
-rw-r--r--MAINTAINERS11
-rw-r--r--arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi5
-rw-r--r--arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi3
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi5
-rw-r--r--arch/arm/boot/dts/ti/omap/omap443x.dtsi1
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4460.dtsi1
-rw-r--r--arch/arm/include/asm/hardware/locomo.h2
-rw-r--r--arch/arm/mach-omap2/pm44xx.c4
-rw-r--r--arch/arm/mach-sa1100/include/mach/collie.h2
-rw-r--r--arch/arm/mm/cache-uniphier.c4
-rw-r--r--arch/arm64/boot/dts/freescale/Makefile1
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi32
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts5
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi2
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8195.dtsi10
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/include/asm/hugetlb.h2
-rw-r--r--arch/arm64/mm/hugetlbpage.c23
-rw-r--r--arch/loongarch/include/asm/elf.h9
-rw-r--r--arch/loongarch/kernel/module.c22
-rw-r--r--arch/loongarch/kernel/numa.c2
-rw-r--r--arch/mips/alchemy/devboards/db1000.c4
-rw-r--r--arch/mips/alchemy/devboards/db1200.c6
-rw-r--r--arch/mips/alchemy/devboards/db1300.c4
-rw-r--r--arch/parisc/include/asm/hugetlb.h2
-rw-r--r--arch/parisc/mm/hugetlbpage.c2
-rw-r--r--arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h3
-rw-r--r--arch/powerpc/kernel/stacktrace.c27
-rw-r--r--arch/powerpc/mm/book3s64/hugetlbpage.c5
-rw-r--r--arch/powerpc/mm/book3s64/radix_hugetlbpage.c3
-rw-r--r--arch/powerpc/mm/nohash/8xx.c3
-rw-r--r--arch/powerpc/mm/pgtable.c3
-rw-r--r--arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi51
-rw-r--r--arch/riscv/include/asm/hugetlb.h3
-rw-r--r--arch/riscv/mm/hugetlbpage.c3
-rw-r--r--arch/s390/include/asm/hugetlb.h6
-rw-r--r--arch/s390/mm/hugetlbpage.c8
-rw-r--r--arch/sparc/include/asm/hugetlb.h6
-rw-r--r--arch/sparc/mm/hugetlbpage.c8
-rw-r--r--arch/x86/events/amd/core.c24
-rw-r--r--arch/x86/include/asm/pgtable.h8
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c30
-rw-r--r--arch/x86/kernel/kgdb.c1
-rw-r--r--arch/xtensa/boot/Makefile3
-rw-r--r--arch/xtensa/boot/lib/zmem.c5
-rw-r--r--arch/xtensa/include/asm/core.h4
-rw-r--r--arch/xtensa/include/asm/hw_breakpoint.h1
-rw-r--r--arch/xtensa/include/asm/processor.h5
-rw-r--r--arch/xtensa/include/asm/ptrace.h3
-rw-r--r--arch/xtensa/include/asm/smp.h1
-rw-r--r--arch/xtensa/include/asm/tlb.h2
-rw-r--r--arch/xtensa/kernel/hw_breakpoint.c1
-rw-r--r--arch/xtensa/kernel/irq.c1
-rw-r--r--arch/xtensa/kernel/ptrace.c1
-rw-r--r--arch/xtensa/kernel/signal.c2
-rw-r--r--arch/xtensa/kernel/smp.c1
-rw-r--r--arch/xtensa/kernel/stacktrace.c1
-rw-r--r--arch/xtensa/kernel/traps.c1
-rw-r--r--arch/xtensa/lib/umulsidi3.S4
-rw-r--r--arch/xtensa/mm/fault.c1
-rw-r--r--arch/xtensa/mm/tlb.c1
-rw-r--r--arch/xtensa/platforms/iss/network.c4
-rw-r--r--block/blk-rq-qos.c2
-rw-r--r--block/disk-events.c1
-rw-r--r--drivers/accel/ivpu/ivpu_drv.c3
-rw-r--r--drivers/accel/ivpu/ivpu_drv.h2
-rw-r--r--drivers/accel/ivpu/ivpu_fw.c8
-rw-r--r--drivers/accel/ivpu/ivpu_gem.h5
-rw-r--r--drivers/accel/ivpu/ivpu_hw_40xx.c28
-rw-r--r--drivers/accel/ivpu/ivpu_hw_40xx_reg.h2
-rw-r--r--drivers/accel/ivpu/ivpu_ipc.c11
-rw-r--r--drivers/acpi/acpi_video.c7
-rw-r--r--drivers/ata/libata-core.c149
-rw-r--r--drivers/ata/libata-eh.c48
-rw-r--r--drivers/ata/libata-scsi.c100
-rw-r--r--drivers/ata/libata-transport.c9
-rw-r--r--drivers/ata/libata.h4
-rw-r--r--drivers/block/rbd.c412
-rw-r--r--drivers/bus/ti-sysc.c31
-rw-r--r--drivers/clk/clk-si521xx.c9
-rw-r--r--drivers/clk/clk-versaclock3.c81
-rw-r--r--drivers/clk/sprd/ums512-clk.c2
-rw-r--r--drivers/clk/tegra/clk-bpmp.c2
-rw-r--r--drivers/firewire/sbp2.c9
-rw-r--r--drivers/firmware/arm_ffa/driver.c16
-rw-r--r--drivers/firmware/arm_scmi/perf.c4
-rw-r--r--drivers/firmware/imx/imx-dsp.c1
-rw-r--r--drivers/gpio/gpio-pmic-eic-sprd.c1
-rw-r--r--drivers/gpio/gpio-timberdale.c5
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_shmem.c11
-rw-r--r--drivers/gpu/drm/i915/gt/intel_ggtt.c23
-rw-r--r--drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c38
-rw-r--r--drivers/i2c/busses/i2c-npcm7xx.c17
-rw-r--r--drivers/i2c/i2c-mux.c2
-rw-r--r--drivers/irqchip/irq-xtensa-mx.c1
-rw-r--r--drivers/misc/cardreader/rts5227.c55
-rw-r--r--drivers/misc/cardreader/rts5228.c57
-rw-r--r--drivers/misc/cardreader/rts5249.c56
-rw-r--r--drivers/misc/cardreader/rts5260.c43
-rw-r--r--drivers/misc/cardreader/rts5261.c52
-rw-r--r--drivers/misc/cardreader/rtsx_pcr.c51
-rw-r--r--drivers/power/reset/Kconfig2
-rw-r--r--drivers/power/reset/pwr-mlxbf.c2
-rw-r--r--drivers/power/reset/vexpress-poweroff.c2
-rw-r--r--drivers/power/supply/Kconfig1
-rw-r--r--drivers/power/supply/ab8500_btemp.c9
-rw-r--r--drivers/power/supply/ab8500_chargalg.c2
-rw-r--r--drivers/power/supply/mt6370-charger.c2
-rw-r--r--drivers/power/supply/power_supply_sysfs.c7
-rw-r--r--drivers/power/supply/rk817_charger.c16
-rw-r--r--drivers/power/supply/rt9467-charger.c4
-rw-r--r--drivers/power/supply/ucs1002_power.c3
-rw-r--r--drivers/scsi/scsi.c11
-rw-r--r--drivers/scsi/scsi_scan.c20
-rw-r--r--drivers/scsi/sd.c101
-rw-r--r--drivers/scsi/sd.h1
-rw-r--r--drivers/soc/imx/soc-imx8m.c10
-rw-r--r--drivers/soc/loongson/Kconfig1
-rw-r--r--drivers/soc/loongson/loongson2_guts.c6
-rw-r--r--drivers/soc/loongson/loongson2_pm.c7
-rw-r--r--drivers/spi/spi-cs42l43.c1
-rw-r--r--drivers/spi/spi-gxp.c2
-rw-r--r--drivers/tee/optee/optee_private.h2
-rw-r--r--drivers/tee/tee_private.h2
-rw-r--r--drivers/tty/n_gsm.c4
-rw-r--r--drivers/tty/serial/8250/8250_port.c5
-rw-r--r--drivers/vfio/mdev/mdev_sysfs.c3
-rw-r--r--drivers/vfio/pci/pds/Kconfig2
-rw-r--r--drivers/vfio/pci/pds/vfio_dev.c2
-rw-r--r--fs/aio.c2
-rw-r--r--fs/binfmt_elf_fdpic.c5
-rw-r--r--fs/btrfs/delayed-ref.c46
-rw-r--r--fs/btrfs/delayed-ref.h1
-rw-r--r--fs/btrfs/extent-tree.c18
-rw-r--r--fs/btrfs/extent_io.c8
-rw-r--r--fs/btrfs/super.c2
-rw-r--r--fs/btrfs/transaction.c6
-rw-r--r--fs/btrfs/tree-log.c2
-rw-r--r--fs/btrfs/volumes.c13
-rw-r--r--fs/buffer.c11
-rw-r--r--fs/ceph/crypto.c6
-rw-r--r--fs/fs-writeback.c11
-rw-r--r--fs/iomap/buffered-io.c2
-rw-r--r--fs/libfs.c1
-rw-r--r--fs/nfsd/nfs4xdr.c4
-rw-r--r--fs/nilfs2/gcinode.c6
-rw-r--r--fs/ntfs3/super.c1
-rw-r--r--fs/overlayfs/copy_up.c2
-rw-r--r--fs/overlayfs/file.c6
-rw-r--r--fs/pipe.c1
-rw-r--r--fs/reiserfs/reiserfs.h6
-rw-r--r--fs/smb/client/fs_context.c1
-rw-r--r--fs/smb/server/connection.c3
-rw-r--r--fs/smb/server/server.c4
-rw-r--r--fs/smb/server/smb2misc.c4
-rw-r--r--fs/tracefs/event_inode.c2
-rw-r--r--fs/xfs/xfs_export.c16
-rw-r--r--fs/xfs/xfs_inode.c48
-rw-r--r--fs/xfs/xfs_itable.c2
-rw-r--r--fs/xfs/xfs_qm.c15
-rw-r--r--include/asm-generic/hugetlb.h2
-rw-r--r--include/linux/ceph/ceph_fs.h24
-rw-r--r--include/linux/hugetlb.h6
-rw-r--r--include/linux/interrupt.h6
-rw-r--r--include/linux/libata.h10
-rw-r--r--include/linux/maple_tree.h11
-rw-r--r--include/linux/pgtable.h10
-rw-r--r--include/linux/swiotlb.h23
-rw-r--r--include/scsi/scsi.h3
-rw-r--r--include/scsi/scsi_device.h5
-rw-r--r--include/scsi/scsi_host.h2
-rw-r--r--io_uring/fs.c2
-rw-r--r--kernel/crash_core.c17
-rw-r--r--kernel/dma/swiotlb.c31
-rw-r--r--kernel/sched/cpupri.c1
-rw-r--r--kernel/trace/ring_buffer.c3
-rw-r--r--kernel/trace/trace_events.c1
-rw-r--r--kernel/trace/trace_events_user.c58
-rw-r--r--kernel/workqueue.c9
-rw-r--r--lib/maple_tree.c221
-rw-r--r--lib/test_maple_tree.c87
-rw-r--r--mm/damon/vaddr-test.h2
-rw-r--r--mm/damon/vaddr.c3
-rw-r--r--mm/filemap.c4
-rw-r--r--mm/hugetlb.c43
-rw-r--r--mm/memcontrol.c13
-rw-r--r--mm/mempolicy.c39
-rw-r--r--mm/migrate.c7
-rw-r--r--mm/rmap.c23
-rw-r--r--mm/slab_common.c36
-rw-r--r--mm/vmalloc.c2
-rw-r--r--mm/zswap.c20
-rw-r--r--tools/arch/x86/include/asm/msr-index.h12
-rw-r--r--tools/include/uapi/asm-generic/unistd.h5
-rw-r--r--tools/include/uapi/drm/drm.h84
-rw-r--r--tools/include/uapi/linux/seccomp.h157
-rw-r--r--tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl1
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl1
-rw-r--r--tools/perf/arch/s390/entry/syscalls/syscall.tbl1
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl2
-rw-r--r--tools/perf/bench/sched-seccomp-notify.c2
-rwxr-xr-xtools/perf/check-headers.sh1
-rwxr-xr-xtools/perf/pmu-events/jevents.py2
-rw-r--r--tools/perf/pmu-events/metric.py4
-rw-r--r--tools/perf/util/bpf-prologue.c508
-rw-r--r--tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c2
-rw-r--r--tools/perf/util/hashmap.h10
-rw-r--r--tools/perf/util/pmu.c2
-rwxr-xr-xtools/testing/selftests/mm/charge_reserved_hugetlb.sh4
-rwxr-xr-xtools/testing/selftests/mm/hugetlb_reparenting_test.sh4
-rw-r--r--tools/testing/selftests/powerpc/Makefile7
-rw-r--r--tools/testing/selftests/powerpc/pmu/Makefile11
-rw-r--r--tools/testing/selftests/user_events/abi_test.c4
-rw-r--r--tools/testing/selftests/user_events/dyn_test.c5
-rw-r--r--tools/testing/selftests/user_events/ftrace_test.c5
-rw-r--r--tools/testing/selftests/user_events/perf_test.c5
-rw-r--r--tools/testing/selftests/user_events/user_events_selftests.h24
226 files changed, 2404 insertions, 1604 deletions
diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst
index 5f502bf68fbc..ff456871bf4b 100644
--- a/Documentation/admin-guide/cgroup-v1/memory.rst
+++ b/Documentation/admin-guide/cgroup-v1/memory.rst
@@ -92,6 +92,13 @@ Brief summary of control files.
memory.oom_control set/show oom controls.
memory.numa_stat show the number of memory usage per numa
node
+ memory.kmem.limit_in_bytes Deprecated knob to set and read the kernel
+ memory hard limit. Kernel hard limit is not
+ supported since 5.16. Writing any value to
+ do file will not have any effect same as if
+ nokmem kernel parameter was specified.
+ Kernel memory is still charged and reported
+ by memory.kmem.usage_in_bytes.
memory.kmem.usage_in_bytes show current kernel memory allocation
memory.kmem.failcnt show the number of kernel memory usage
hits limits
diff --git a/Documentation/devicetree/bindings/ata/pata-common.yaml b/Documentation/devicetree/bindings/ata/pata-common.yaml
index 337ddf1113c4..4e867dd4d402 100644
--- a/Documentation/devicetree/bindings/ata/pata-common.yaml
+++ b/Documentation/devicetree/bindings/ata/pata-common.yaml
@@ -38,6 +38,7 @@ patternProperties:
ID number 0 and the slave drive will have ID number 1. The PATA port
nodes will be named "ide-port".
type: object
+ additionalProperties: false
properties:
reg:
diff --git a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml
index 839648e753d4..42b6f80613f3 100644
--- a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml
+++ b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml
@@ -37,6 +37,9 @@ properties:
maxItems: 1
'#clock-cells':
+ description:
+ The index in the assigned-clocks is mapped to the output clock as below
+ 0 - REF, 1 - SE1, 2 - SE2, 3 - SE3, 4 - DIFF1, 5 - DIFF2.
const: 1
clocks:
@@ -68,7 +71,7 @@ examples:
reg = <0x68>;
#clock-cells = <1>;
- clocks = <&x1_x2>;
+ clocks = <&x1>;
renesas,settings = [
80 00 11 19 4c 02 23 7f 83 19 08 a9 5f 25 24 bf
@@ -79,8 +82,8 @@ examples:
assigned-clocks = <&versa3 0>, <&versa3 1>,
<&versa3 2>, <&versa3 3>,
<&versa3 4>, <&versa3 5>;
- assigned-clock-rates = <12288000>, <25000000>,
- <12000000>, <11289600>,
- <11289600>, <24000000>;
+ assigned-clock-rates = <24000000>, <11289600>,
+ <11289600>, <12000000>,
+ <25000000>, <12288000>;
};
};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
index 21ae7bce038e..171a41407241 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml
@@ -9,6 +9,9 @@ title: Freescale MXS Inter IC (I2C) Controller
maintainers:
- Shawn Guo <shawnguo@kernel.org>
+allOf:
+ - $ref: /schemas/i2c/i2c-controller.yaml#
+
properties:
compatible:
enum:
@@ -37,7 +40,7 @@ required:
- dmas
- dma-names
-additionalProperties: false
+unevaluatedProperties: false
examples:
- |
diff --git a/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml b/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml
index da2dcfeebf12..510f6cb0f084 100644
--- a/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml
+++ b/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml
@@ -11,11 +11,16 @@ maintainers:
properties:
compatible:
- items:
- - enum:
- - loongson,ls2k0500-pmc
- - loongson,ls2k1000-pmc
- - const: syscon
+ oneOf:
+ - items:
+ - const: loongson,ls2k0500-pmc
+ - const: syscon
+ - items:
+ - enum:
+ - loongson,ls2k1000-pmc
+ - loongson,ls2k2000-pmc
+ - const: loongson,ls2k0500-pmc
+ - const: syscon
reg:
maxItems: 1
@@ -32,6 +37,18 @@ properties:
addition, the PM need according to it to indicate that current
SoC whether support Suspend To RAM.
+ syscon-poweroff:
+ $ref: /schemas/power/reset/syscon-poweroff.yaml#
+ type: object
+ description:
+ Node for power off method
+
+ syscon-reboot:
+ $ref: /schemas/power/reset/syscon-reboot.yaml#
+ type: object
+ description:
+ Node for reboot method
+
required:
- compatible
- reg
@@ -44,9 +61,23 @@ examples:
#include <dt-bindings/interrupt-controller/irq.h>
power-management@1fe27000 {
- compatible = "loongson,ls2k1000-pmc", "syscon";
+ compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon";
reg = <0x1fe27000 0x58>;
interrupt-parent = <&liointc1>;
interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
loongson,suspend-address = <0x0 0x1c000500>;
+
+ syscon-reboot {
+ compatible = "syscon-reboot";
+ offset = <0x30>;
+ mask = <0x1>;
+ };
+
+ syscon-poweroff {
+ compatible = "syscon-poweroff";
+ regmap = <&pmc>;
+ offset = <0x14>;
+ mask = <0x3c00>;
+ value = <0x3c00>;
+ };
};
diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
index 2f593c7225e5..14cac0e6e0a1 100644
--- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
+++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml
@@ -23,6 +23,13 @@ properties:
- const: fsl,imx51-ecspi
- const: fsl,imx53-ecspi
- items:
+ - enum:
+ - fsl,imx25-cspi
+ - fsl,imx50-cspi
+ - fsl,imx51-cspi
+ - fsl,imx53-cspi
+ - const: fsl,imx35-cspi
+ - items:
- const: fsl,imx8mp-ecspi
- const: fsl,imx6ul-ecspi
- items:
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index deac4e973ddc..4d05b9862451 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -949,3 +949,99 @@ mmap_lock held. All in-tree users have been audited and do not seem to
depend on the mmap_lock being held, but out of tree users should verify
for themselves. If they do need it, they can return VM_FAULT_RETRY to
be called with the mmap_lock held.
+
+---
+
+**mandatory**
+
+The order of opening block devices and matching or creating superblocks has
+changed.
+
+The old logic opened block devices first and then tried to find a
+suitable superblock to reuse based on the block device pointer.
+
+The new logic tries to find a suitable superblock first based on the device
+number, and opening the block device afterwards.
+
+Since opening block devices cannot happen under s_umount because of lock
+ordering requirements s_umount is now dropped while opening block devices and
+reacquired before calling fill_super().
+
+In the old logic concurrent mounters would find the superblock on the list of
+superblocks for the filesystem type. Since the first opener of the block device
+would hold s_umount they would wait until the superblock became either born or
+was discarded due to initialization failure.
+
+Since the new logic drops s_umount concurrent mounters could grab s_umount and
+would spin. Instead they are now made to wait using an explicit wait-wake
+mechanism without having to hold s_umount.
+
+---
+
+**mandatory**
+
+The holder of a block device is now the superblock.
+
+The holder of a block device used to be the file_system_type which wasn't
+particularly useful. It wasn't possible to go from block device to owning
+superblock without matching on the device pointer stored in the superblock.
+This mechanism would only work for a single device so the block layer couldn't
+find the owning superblock of any additional devices.
+
+In the old mechanism reusing or creating a superblock for a racing mount(2) and
+umount(2) relied on the file_system_type as the holder. This was severly
+underdocumented however:
+
+(1) Any concurrent mounter that managed to grab an active reference on an
+ existing superblock was made to wait until the superblock either became
+ ready or until the superblock was removed from the list of superblocks of
+ the filesystem type. If the superblock is ready the caller would simple
+ reuse it.
+
+(2) If the mounter came after deactivate_locked_super() but before
+ the superblock had been removed from the list of superblocks of the
+ filesystem type the mounter would wait until the superblock was shutdown,
+ reuse the block device and allocate a new superblock.
+
+(3) If the mounter came after deactivate_locked_super() and after
+ the superblock had been removed from the list of superblocks of the
+ filesystem type the mounter would reuse the block device and allocate a new
+ superblock (the bd_holder point may still be set to the filesystem type).
+
+Because the holder of the block device was the file_system_type any concurrent
+mounter could open the block devices of any superblock of the same
+file_system_type without risking seeing EBUSY because the block device was
+still in use by another superblock.
+
+Making the superblock the owner of the block device changes this as the holder
+is now a unique superblock and thus block devices associated with it cannot be
+reused by concurrent mounters. So a concurrent mounter in (2) could suddenly
+see EBUSY when trying to open a block device whose holder was a different
+superblock.
+
+The new logic thus waits until the superblock and the devices are shutdown in
+->kill_sb(). Removal of the superblock from the list of superblocks of the
+filesystem type is now moved to a later point when the devices are closed:
+
+(1) Any concurrent mounter managing to grab an active reference on an existing
+ superblock is made to wait until the superblock is either ready or until
+ the superblock and all devices are shutdown in ->kill_sb(). If the
+ superblock is ready the caller will simply reuse it.
+
+(2) If the mounter comes after deactivate_locked_super() but before
+ the superblock has been removed from the list of superblocks of the
+ filesystem type the mounter is made to wait until the superblock and the
+ devices are shut down in ->kill_sb() and the superblock is removed from the
+ list of superblocks of the filesystem type. The mounter will allocate a new
+ superblock and grab ownership of the block device (the bd_holder pointer of
+ the block device will be set to the newly allocated superblock).
+
+(3) This case is now collapsed into (2) as the superblock is left on the list
+ of superblocks of the filesystem type until all devices are shutdown in
+ ->kill_sb(). In other words, if the superblock isn't on the list of
+ superblock of the filesystem type anymore then it has given up ownership of
+ all associated block devices (the bd_holder pointer is NULL).
+
+As this is a VFS level change it has no practical consequences for filesystems
+other than that all of them must use one of the provided kill_litter_super(),
+kill_anon_super(), or kill_block_super() helpers.
diff --git a/MAINTAINERS b/MAINTAINERS
index b19995690904..35977b269d5e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1963,12 +1963,12 @@ F: drivers/irqchip/irq-aspeed-i2c-ic.c
ARM/ASPEED MACHINE SUPPORT
M: Joel Stanley <joel@jms.id.au>
-R: Andrew Jeffery <andrew@aj.id.au>
+R: Andrew Jeffery <andrew@codeconstruct.com.au>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
S: Supported
Q: https://patchwork.ozlabs.org/project/linux-aspeed/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/joel/aspeed.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/joel/bmc.git
F: Documentation/devicetree/bindings/arm/aspeed/
F: arch/arm/boot/dts/aspeed/
F: arch/arm/mach-aspeed/
@@ -3058,7 +3058,7 @@ F: Documentation/devicetree/bindings/peci/peci-aspeed.yaml
F: drivers/peci/controller/peci-aspeed.c
ASPEED PINCTRL DRIVERS
-M: Andrew Jeffery <andrew@aj.id.au>
+M: Andrew Jeffery <andrew@codeconstruct.com.au>
L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
L: openbmc@lists.ozlabs.org (moderated for non-subscribers)
L: linux-gpio@vger.kernel.org
@@ -3075,7 +3075,7 @@ F: drivers/irqchip/irq-aspeed-scu-ic.c
F: include/dt-bindings/interrupt-controller/aspeed-scu-ic.h
ASPEED SD/MMC DRIVER
-M: Andrew Jeffery <andrew@aj.id.au>
+M: Andrew Jeffery <andrew@codeconstruct.com.au>
L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
L: openbmc@lists.ozlabs.org (moderated for non-subscribers)
L: linux-mmc@vger.kernel.org
@@ -4082,7 +4082,7 @@ F: drivers/net/wireless/broadcom/brcm80211/
BROADCOM BRCMSTB GPIO DRIVER
M: Doug Berger <opendmb@gmail.com>
-M: Florian Fainelli <florian.fainelli@broadcom>
+M: Florian Fainelli <florian.fainelli@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
S: Supported
F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml
@@ -6647,6 +6647,7 @@ F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c
DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS
M: Karol Herbst <kherbst@redhat.com>
M: Lyude Paul <lyude@redhat.com>
+M: Danilo Krummrich <dakr@redhat.com>
L: dri-devel@lists.freedesktop.org
L: nouveau@lists.freedesktop.org
S: Supported
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
index 091ba310053e..d2d516d113ba 100644
--- a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
@@ -614,12 +614,12 @@
/* Configure pwm clock source for timers 8 & 9 */
&timer8 {
assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>;
- assigned-clock-parents = <&sys_clkin_ck>;
+ assigned-clock-parents = <&sys_32k_ck>;
};
&timer9 {
assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>;
- assigned-clock-parents = <&sys_clkin_ck>;
+ assigned-clock-parents = <&sys_32k_ck>;
};
/*
@@ -640,6 +640,7 @@
&uart3 {
interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH
&omap4_pmx_core 0x17c>;
+ overrun-throttle-ms = <500>;
};
&uart4 {
diff --git a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
index 0da759f8e2c2..7dd2340bc5e4 100644
--- a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
@@ -12,8 +12,7 @@ cpu_thermal: cpu-thermal {
polling-delay = <1000>; /* milliseconds */
coefficients = <0 20000>;
- /* sensor ID */
- thermal-sensors = <&bandgap 0>;
+ thermal-sensors = <&bandgap>;
cpu_trips: trips {
cpu_alert0: cpu_alert {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
index 801b4f10350c..d484ec1e4fd8 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
@@ -12,7 +12,10 @@ cpu_thermal: cpu_thermal {
polling-delay-passive = <250>; /* milliseconds */
polling-delay = <1000>; /* milliseconds */
- /* sensor ID */
+ /*
+ * See 44xx files for single sensor addressing, omap5 and dra7 need
+ * also sensor ID for addressing.
+ */
thermal-sensors = <&bandgap 0>;
cpu_trips: trips {
diff --git a/arch/arm/boot/dts/ti/omap/omap443x.dtsi b/arch/arm/boot/dts/ti/omap/omap443x.dtsi
index 238aceb799f8..2104170fe2cd 100644
--- a/arch/arm/boot/dts/ti/omap/omap443x.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap443x.dtsi
@@ -69,6 +69,7 @@
};
&cpu_thermal {
+ thermal-sensors = <&bandgap>;
coefficients = <0 20000>;
};
diff --git a/arch/arm/boot/dts/ti/omap/omap4460.dtsi b/arch/arm/boot/dts/ti/omap/omap4460.dtsi
index 1b27a862ae81..a6764750d447 100644
--- a/arch/arm/boot/dts/ti/omap/omap4460.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4460.dtsi
@@ -79,6 +79,7 @@
};
&cpu_thermal {
+ thermal-sensors = <&bandgap>;
coefficients = <348 (-9301)>;
};
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index 246a3de25931..aaaedafef7cc 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -195,7 +195,7 @@ struct locomo_driver {
#define LOCOMO_DRIVER_NAME(_ldev) ((_ldev)->dev.driver->name)
-void locomo_lcd_power(struct locomo_dev *, int, unsigned int);
+extern void locomolcd_power(int on);
int locomo_driver_register(struct locomo_driver *);
void locomo_driver_unregister(struct locomo_driver *);
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index f57802f3ee3a..37b168119fe4 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -99,7 +99,7 @@ static int omap4_pm_suspend(void)
* possible causes.
* http://www.spinics.net/lists/arm-kernel/msg218641.html
*/
- pr_warn("A possible cause could be an old bootloader - try u-boot >= v2012.07\n");
+ pr_debug("A possible cause could be an old bootloader - try u-boot >= v2012.07\n");
} else {
pr_info("Successfully put all powerdomains to target state\n");
}
@@ -257,7 +257,7 @@ int __init omap4_pm_init(void)
* http://www.spinics.net/lists/arm-kernel/msg218641.html
*/
if (cpu_is_omap44xx())
- pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+ pr_debug("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
ret = pwrdm_for_each(pwrdms_setup, NULL);
if (ret) {
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index b7bc23ffd3c6..c95273c9567b 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -16,8 +16,6 @@
#include "hardware.h" /* Gives GPIO_MAX */
-extern void locomolcd_power(int on);
-
#define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1)
#define COLLIE_GPIO_CHARGE_ON (COLLIE_SCOOP_GPIO_BASE + 0)
#define COLLIE_SCP_DIAG_BOOT1 SCOOP_GPCR_PA12
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index ff2881458504..84a2f17ff32d 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -58,11 +58,13 @@
((op & UNIPHIER_SSCOQM_S_MASK) == UNIPHIER_SSCOQM_S_RANGE)
/**
- * uniphier_cache_data - UniPhier outer cache specific data
+ * struct uniphier_cache_data - UniPhier outer cache specific data
*
* @ctrl_base: virtual base address of control registers
* @rev_base: virtual base address of revision registers
* @op_base: virtual base address of operation registers
+ * @way_ctrl_base: virtual address of the way control registers for this
+ * SoC revision
* @way_mask: each bit specifies if the way is present
* @nsets: number of associativity sets
* @line_size: line size in bytes
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index c6872b7e9471..89aee6c92576 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -66,6 +66,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-mx8menlo.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-nitrogen-r2.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-phg.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-rdk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-prt8mm.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-var-som-symphony.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw71xx-0x.dtb
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index e31ab8b4f54f..a882c86ec313 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -26,7 +26,7 @@
port {
hdmi_connector_in: endpoint {
- remote-endpoint = <&adv7533_out>;
+ remote-endpoint = <&adv7535_out>;
};
};
};
@@ -72,6 +72,13 @@
enable-active-high;
};
+ reg_vddext_3v3: regulator-vddext-3v3 {
+ compatible = "regulator-fixed";
+ regulator-name = "VDDEXT_3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
backlight: backlight {
compatible = "pwm-backlight";
pwms = <&pwm1 0 5000000 0>;
@@ -317,15 +324,16 @@
hdmi@3d {
compatible = "adi,adv7535";
- reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>;
- reg-names = "main", "cec", "edid", "packet";
+ reg = <0x3d>;
+ interrupt-parent = <&gpio1>;
+ interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
adi,dsi-lanes = <4>;
-
- adi,input-depth = <8>;
- adi,input-colorspace = "rgb";
- adi,input-clock = "1x";
- adi,input-style = <1>;
- adi,input-justification = "evenly";
+ avdd-supply = <&buck5_reg>;
+ dvdd-supply = <&buck5_reg>;
+ pvdd-supply = <&buck5_reg>;
+ a2vdd-supply = <&buck5_reg>;
+ v3p3-supply = <&reg_vddext_3v3>;
+ v1p2-supply = <&buck5_reg>;
ports {
#address-cells = <1>;
@@ -334,7 +342,7 @@
port@0 {
reg = <0>;
- adv7533_in: endpoint {
+ adv7535_in: endpoint {
remote-endpoint = <&dsi_out>;
};
};
@@ -342,7 +350,7 @@
port@1 {
reg = <1>;
- adv7533_out: endpoint {
+ adv7535_out: endpoint {
remote-endpoint = <&hdmi_connector_in>;
};
};
@@ -448,7 +456,7 @@
reg = <1>;
dsi_out: endpoint {
- remote-endpoint = <&adv7533_in>;
+ remote-endpoint = <&adv7535_in>;
data-lanes = <1 2 3 4>;
};
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index 06e91297fb16..acd265d8b58e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -381,9 +381,10 @@
&sai3 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sai3>;
- assigned-clocks = <&clk IMX8MP_CLK_SAI3>;
+ assigned-clocks = <&clk IMX8MP_CLK_SAI3>,
+ <&clk IMX8MP_AUDIO_PLL2> ;
assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
- assigned-clock-rates = <12288000>;
+ assigned-clock-rates = <12288000>, <361267200>;
fsl,sai-mclk-direction-output;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 6f2f50e1639c..83d907294fbc 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -790,6 +790,12 @@
reg = <IMX8MP_POWER_DOMAIN_AUDIOMIX>;
clocks = <&clk IMX8MP_CLK_AUDIO_ROOT>,
<&clk IMX8MP_CLK_AUDIO_AXI>;
+ assigned-clocks = <&clk IMX8MP_CLK_AUDIO_AHB>,
+ <&clk IMX8MP_CLK_AUDIO_AXI_SRC>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <400000000>,
+ <600000000>;
};
pgc_gpu2d: power-domain@6 {
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
index 1c71c08becde..f6e422dc2663 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
@@ -81,7 +81,7 @@
&gpio1 {
pmic-irq-hog {
gpio-hog;
- gpios = <2 GPIO_ACTIVE_LOW>;
+ gpios = <3 GPIO_ACTIVE_LOW>;
input;
line-name = "PMIC_IRQ#";
};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index 4dbbf8fdab75..a9e52b50c8c4 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -2957,7 +2957,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xc000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE0_DL_ASYNC>;
};
@@ -2970,7 +2970,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xd000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE1_DL_ASYNC>;
};
@@ -2983,7 +2983,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xe000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE2_DL_ASYNC>;
};
@@ -2996,7 +2996,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xf000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE3_DL_ASYNC>;
};
@@ -3009,7 +3009,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c11XXXX 0x0000 0x1000>;
- mediatek,merge-fifo-en = <1>;
+ mediatek,merge-fifo-en;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE4_DL_ASYNC>;
};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 5315789f4868..a789119e6483 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -636,6 +636,7 @@ CONFIG_POWER_RESET_MSM=y
CONFIG_POWER_RESET_QCOM_PON=m
CONFIG_POWER_RESET_XGENE=y
CONFIG_POWER_RESET_SYSCON=y
+CONFIG_POWER_RESET_SYSCON_POWEROFF=y
CONFIG_SYSCON_REBOOT_MODE=y
CONFIG_NVMEM_REBOOT_MODE=m
CONFIG_BATTERY_SBS=m
@@ -1175,7 +1176,6 @@ CONFIG_COMMON_CLK_S2MPS11=y
CONFIG_COMMON_CLK_PWM=y
CONFIG_COMMON_CLK_RS9_PCIE=y
CONFIG_COMMON_CLK_VC5=y
-CONFIG_COMMON_CLK_NPCM8XX=y
CONFIG_COMMON_CLK_BD718XX=m
CONFIG_CLK_RASPBERRYPI=m
CONFIG_CLK_IMX8MM=y
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index f43a38ac1779..2ddc33d93b13 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -28,7 +28,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte);
+ pte_t *ptep, pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 9c52718ea750..13fd592228b1 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -241,15 +241,8 @@ static void clear_flush(struct mm_struct *mm,
flush_tlb_range(&vma, saddr, addr);
}
-static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
-{
- VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
-
- return page_folio(pfn_to_page(swp_offset_pfn(entry)));
-}
-
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+ pte_t *ptep, pte_t pte, unsigned long sz)
{
size_t pgsize;
int i;
@@ -257,13 +250,10 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
unsigned long pfn, dpfn;
pgprot_t hugeprot;
- if (!pte_present(pte)) {
- struct folio *folio;
-
- folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte));
- ncontig = num_contig_ptes(folio_size(folio), &pgsize);
+ ncontig = num_contig_ptes(sz, &pgsize);
- for (i = 0; i < ncontig; i++, ptep++)
+ if (!pte_present(pte)) {
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
set_pte_at(mm, addr, ptep, pte);
return;
}
@@ -273,7 +263,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
return;
}
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
pfn = pte_pfn(pte);
dpfn = pgsize >> PAGE_SHIFT;
hugeprot = pte_pgprot(pte);
@@ -571,5 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ unsigned long psize = huge_page_size(hstate_vma(vma));
+
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index 7af0cebf28d7..b9a4ab54285c 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -111,6 +111,15 @@
#define R_LARCH_TLS_GD_HI20 98
#define R_LARCH_32_PCREL 99
#define R_LARCH_RELAX 100
+#define R_LARCH_DELETE 101
+#define R_LARCH_ALIGN 102
+#define R_LARCH_PCREL20_S2 103
+#define R_LARCH_CFA 104
+#define R_LARCH_ADD6 105
+#define R_LARCH_SUB6 106
+#define R_LARCH_ADD_ULEB128 107
+#define R_LARCH_SUB_ULEB128 108
+#define R_LARCH_64_PCREL 109
#ifndef ELF_ARCH
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index b8b86088b2dd..b13b2858fe39 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -367,6 +367,24 @@ static int apply_r_larch_got_pc(struct module *mod,
return apply_r_larch_pcala(mod, location, got, rela_stack, rela_stack_top, type);
}
+static int apply_r_larch_32_pcrel(struct module *mod, u32 *location, Elf_Addr v,
+ s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+ ptrdiff_t offset = (void *)v - (void *)location;
+
+ *(u32 *)location = offset;
+ return 0;
+}
+
+static int apply_r_larch_64_pcrel(struct module *mod, u32 *location, Elf_Addr v,
+ s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+ ptrdiff_t offset = (void *)v - (void *)location;
+
+ *(u64 *)location = offset;
+ return 0;
+}
+
/*
* reloc_handlers_rela() - Apply a particular relocation to a module
* @mod: the module to apply the reloc to
@@ -382,7 +400,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v,
/* The handlers for known reloc types */
static reloc_rela_handler reloc_rela_handlers[] = {
- [R_LARCH_NONE ... R_LARCH_RELAX] = apply_r_larch_error,
+ [R_LARCH_NONE ... R_LARCH_64_PCREL] = apply_r_larch_error,
[R_LARCH_NONE] = apply_r_larch_none,
[R_LARCH_32] = apply_r_larch_32,
@@ -396,6 +414,8 @@ static reloc_rela_handler reloc_rela_handlers[] = {
[R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field,
[R_LARCH_ADD32 ... R_LARCH_SUB64] = apply_r_larch_add_sub,
[R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12] = apply_r_larch_pcala,
+ [R_LARCH_32_PCREL] = apply_r_larch_32_pcrel,
+ [R_LARCH_64_PCREL] = apply_r_larch_64_pcrel,
};
int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index c7d33c489e04..6e65ff12d5c7 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -436,7 +436,7 @@ void __init paging_init(void)
void __init mem_init(void)
{
- high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
+ high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
memblock_free_all();
}
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 012da042d0a4..7b9f91db227f 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -164,6 +164,7 @@ static struct platform_device db1x00_audio_dev = {
/******************************************************************************/
+#ifdef CONFIG_MMC_AU1X
static irqreturn_t db1100_mmc_cd(int irq, void *ptr)
{
mmc_detect_change(ptr, msecs_to_jiffies(500));
@@ -369,6 +370,7 @@ static struct platform_device db1100_mmc1_dev = {
.num_resources = ARRAY_SIZE(au1100_mmc1_res),
.resource = au1100_mmc1_res,
};
+#endif /* CONFIG_MMC_AU1X */
/******************************************************************************/
@@ -440,8 +442,10 @@ static struct platform_device *db1x00_devs[] = {
static struct platform_device *db1100_devs[] = {
&au1100_lcd_device,
+#ifdef CONFIG_MMC_AU1X
&db1100_mmc0_dev,
&db1100_mmc1_dev,
+#endif
};
int __init db1000_dev_setup(void)
diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c
index 76080c71a2a7..f521874ebb07 100644
--- a/arch/mips/alchemy/devboards/db1200.c
+++ b/arch/mips/alchemy/devboards/db1200.c
@@ -326,6 +326,7 @@ static struct platform_device db1200_ide_dev = {
/**********************************************************************/
+#ifdef CONFIG_MMC_AU1X
/* SD carddetects: they're supposed to be edge-triggered, but ack
* doesn't seem to work (CPLD Rev 2). Instead, the screaming one
* is disabled and its counterpart enabled. The 200ms timeout is
@@ -584,6 +585,7 @@ static struct platform_device pb1200_mmc1_dev = {
.num_resources = ARRAY_SIZE(au1200_mmc1_res),
.resource = au1200_mmc1_res,
};
+#endif /* CONFIG_MMC_AU1X */
/**********************************************************************/
@@ -751,7 +753,9 @@ static struct platform_device db1200_audiodma_dev = {
static struct platform_device *db1200_devs[] __initdata = {
NULL, /* PSC0, selected by S6.8 */
&db1200_ide_dev,
+#ifdef CONFIG_MMC_AU1X
&db1200_mmc0_dev,
+#endif
&au1200_lcd_dev,
&db1200_eth_dev,
&db1200_nand_dev,
@@ -762,7 +766,9 @@ static struct platform_device *db1200_devs[] __initdata = {
};
static struct platform_device *pb1200_devs[] __initdata = {
+#ifdef CONFIG_MMC_AU1X
&pb1200_mmc1_dev,
+#endif
};
/* Some peripheral base addresses differ on the PB1200 */
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index ff61901329c6..d377e043b49f 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -450,6 +450,7 @@ static struct platform_device db1300_ide_dev = {
/**********************************************************************/
+#ifdef CONFIG_MMC_AU1X
static irqreturn_t db1300_mmc_cd(int irq, void *ptr)
{
disable_irq_nosync(irq);
@@ -632,6 +633,7 @@ static struct platform_device db1300_sd0_dev = {
.resource = au1300_sd0_res,
.num_resources = ARRAY_SIZE(au1300_sd0_res),
};
+#endif /* CONFIG_MMC_AU1X */
/**********************************************************************/
@@ -767,8 +769,10 @@ static struct platform_device *db1300_dev[] __initdata = {
&db1300_5waysw_dev,
&db1300_nand_dev,
&db1300_ide_dev,
+#ifdef CONFIG_MMC_AU1X
&db1300_sd0_dev,
&db1300_sd1_dev,
+#endif
&db1300_lcd_dev,
&db1300_ac97_dev,
&db1300_i2s_dev,
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index f7f078c2872c..72daacc472a0 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -6,7 +6,7 @@
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte);
+ pte_t *ptep, pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index a8a1a7c1e16e..a9f7e21f6656 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -140,7 +140,7 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t entry)
+ pte_t *ptep, pte_t entry, unsigned long sz)
{
__set_huge_pte_at(mm, addr, ptep, entry);
}
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index de092b04ee1a..92df40c6cc6b 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift)
}
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTE_CLEAR
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index b15f15dcacb5..e6a958a5da27 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -73,29 +73,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
bool firstframe;
stack_end = stack_page + THREAD_SIZE;
- if (!is_idle_task(task)) {
- /*
- * For user tasks, this is the SP value loaded on
- * kernel entry, see "PACAKSAVE(r13)" in _switch() and
- * system_call_common().
- *
- * Likewise for non-swapper kernel threads,
- * this also happens to be the top of the stack
- * as setup by copy_thread().
- *
- * Note that stack backlinks are not properly setup by
- * copy_thread() and thus, a forked task() will have
- * an unreliable stack trace until it's been
- * _switch()'ed to for the first time.
- */
- stack_end -= STACK_USER_INT_FRAME_SIZE;
- } else {
- /*
- * idle tasks have a custom stack layout,
- * c.f. cpu_idle_thread_init().
- */
+
+ // See copy_thread() for details.
+ if (task->flags & PF_KTHREAD)
stack_end -= STACK_FRAME_MIN_SIZE;
- }
+ else
+ stack_end -= STACK_USER_INT_FRAME_SIZE;
if (task == current)
sp = current_stack_frame();
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 3bc0eb21b2a0..5a2e512e96db 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
+ unsigned long psize;
if (radix_enabled())
return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
old_pte, pte);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+ psize = huge_page_size(hstate_vma(vma));
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
void __init hugetlbpage_init_defaultsize(void)
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 17075c78d4bc..35fd2a95be24 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
pte_t old_pte, pte_t pte)
{
struct mm_struct *mm = vma->vm_mm;
+ unsigned long psize = huge_page_size(hstate_vma(vma));
/*
* POWER9 NMMU must flush the TLB after clearing the PTE before
@@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
atomic_read(&mm->context.copros) > 0)
radix__flush_hugetlb_page(vma, addr);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index dbbfe897455d..a642a7929892 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
return -EINVAL;
- set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+ set_huge_pte_at(&init_mm, va, ptep,
+ pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
return 0;
}
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 3f86fd217690..3ba9fe411604 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -288,7 +288,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
}
#if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz)
{
pmd_t *pmd = pmd_off(mm, addr);
pte_basic_t val;
diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
index d79f94432b27..12ebe9792356 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
@@ -262,7 +262,7 @@
reg = <0x100000 0x400000>;
};
reserved-data@600000 {
- reg = <0x600000 0x1000000>;
+ reg = <0x600000 0xa00000>;
};
};
};
@@ -440,30 +440,6 @@
};
};
- uart0_pins: uart0-0 {
- tx-pins {
- pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX,
- GPOEN_ENABLE,
- GPI_NONE)>;
- bias-disable;
- drive-strength = <12>;
- input-disable;
- input-schmitt-disable;
- slew-rate = <0>;
- };
-
- rx-pins {
- pinmux = <GPIOMUX(6, GPOUT_LOW,
- GPOEN_DISABLE,
- GPI_SYS_UART0_RX)>;
- bias-disable; /* external pull-up */
- drive-strength = <2>;
- input-enable;
- input-schmitt-enable;
- slew-rate = <0>;
- };
- };
-
tdm_pins: tdm-0 {
tx-pins {
pinmux = <GPIOMUX(44, GPOUT_SYS_TDM_TXD,
@@ -497,6 +473,30 @@
input-enable;
};
};
+
+ uart0_pins: uart0-0 {
+ tx-pins {
+ pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX,
+ GPOEN_ENABLE,
+ GPI_NONE)>;
+ bias-disable;
+ drive-strength = <12>;
+ input-disable;
+ input-schmitt-disable;
+ slew-rate = <0>;
+ };
+
+ rx-pins {
+ pinmux = <GPIOMUX(6, GPOUT_LOW,
+ GPOEN_DISABLE,
+ GPI_SYS_UART0_RX)>;
+ bias-disable; /* external pull-up */
+ drive-strength = <2>;
+ input-enable;
+ input-schmitt-enable;
+ slew-rate = <0>;
+ };
+ };
};
&tdm {
@@ -513,6 +513,7 @@
&usb0 {
dr_mode = "peripheral";
+ status = "okay";
};
&U74_1 {
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 34e24f078cc1..4c5b0e929890 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -18,7 +18,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pte);
+ unsigned long addr, pte_t *ptep, pte_t pte,
+ unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 96225a8533ad..e4a2ace92dbe 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -180,7 +180,8 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
void set_huge_pte_at(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
- pte_t pte)
+ pte_t pte,
+ unsigned long sz)
{
int i, pte_num;
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index f07267875a19..deb198a61039 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -16,6 +16,8 @@
#define hugepages_supported() (MACHINE_HAS_EDAT1)
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
pte_t huge_ptep_get(pte_t *ptep);
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
@@ -65,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
int changed = !pte_same(huge_ptep_get(ptep), pte);
if (changed) {
huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ __set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}
return changed;
}
@@ -74,7 +76,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
- set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
+ __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
}
static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index c718f2a0de94..297a6d897d5a 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -142,7 +142,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
__storage_key_init_range(paddr, paddr + size - 1);
}
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
unsigned long rste;
@@ -163,6 +163,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
set_pte(ptep, __pte(rste));
}
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ __set_huge_pte_at(mm, addr, ptep, pte);
+}
+
pte_t huge_ptep_get(pte_t *ptep)
{
return __rste_to_pte(pte_val(*ptep));
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 0a26cca24232..c714ca6a05aa 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -14,6 +14,8 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
@@ -32,7 +34,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t old_pte = *ptep;
- set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+ __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
}
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -42,7 +44,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
{
int changed = !pte_same(*ptep, pte);
if (changed) {
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ __set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
flush_tlb_page(vma, addr);
}
return changed;
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d7018823206c..b432500c13a5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -328,7 +328,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return pte_offset_huge(pmd, addr);
}
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
unsigned int nptes, orig_shift, shift;
@@ -364,6 +364,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
orig_shift);
}
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t entry, unsigned long sz)
+{
+ __set_huge_pte_at(mm, addr, ptep, entry);
+}
+
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index abadd5f23425..e24976593a29 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu)
/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
- /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+ /*
+ * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
+ * and PerfCntrGLobalStatus.PerfCntrOvfl
+ */
+ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+ GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
}
static int amd_pmu_cpu_prepare(int cpu)
@@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu)
int i, nb_id;
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
+ amd_pmu_cpu_reset(cpu);
if (!x86_pmu.amd_nb_constraints)
return;
@@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->amd_nb->nb_id = nb_id;
cpuc->amd_nb->refcnt++;
-
- amd_pmu_cpu_reset(cpu);
}
static void amd_pmu_cpu_dead(int cpu)
@@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu)
kfree(cpuhw->lbr_sel);
cpuhw->lbr_sel = NULL;
+ amd_pmu_cpu_reset(cpu);
if (!x86_pmu.amd_nb_constraints)
return;
@@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu)
cpuhw->amd_nb = NULL;
}
-
- amd_pmu_cpu_reset(cpu);
}
static inline void amd_pmu_set_global_ctl(u64 ctl)
@@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
struct hw_perf_event *hwc;
struct perf_event *event;
int handled = 0, idx;
- u64 status, mask;
+ u64 reserved, status, mask;
bool pmu_enabled;
/*
@@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
status &= ~GLOBAL_STATUS_LBRS_FROZEN;
}
+ reserved = status & ~amd_pmu_global_cntr_mask;
+ if (reserved)
+ pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n",
+ reserved);
+
+ /* Clear any reserved bits set by buggy microcode */
+ status &= amd_pmu_global_cntr_mask;
+
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
if (!test_bit(idx, cpuc->active_mask))
continue;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index d6ad98ca1288..e02b179ec659 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b)
return a.pte == b.pte;
}
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+ if (__pte_needs_invert(pte_val(pte)))
+ return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+ return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn pte_next_pfn
+
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 382d4e6b848d..4e5ffc8b0e46 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1303,7 +1303,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
- VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
VULNBL_AMD(0x19, SRSO),
{}
};
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 91fa70e51004..279148e72459 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
return epc_page;
}
+/*
+ * Ensure the SECS page is not swapped out. Must be called with encl->lock
+ * to protect the enclave states including SECS and ensure the SECS page is
+ * not swapped out again while being used.
+ */
+static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl)
+{
+ struct sgx_epc_page *epc_page = encl->secs.epc_page;
+
+ if (!epc_page)
+ epc_page = sgx_encl_eldu(&encl->secs, NULL);
+
+ return epc_page;
+}
+
static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
struct sgx_encl_page *entry)
{
@@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
return entry;
}
- if (!(encl->secs.epc_page)) {
- epc_page = sgx_encl_eldu(&encl->secs, NULL);
- if (IS_ERR(epc_page))
- return ERR_CAST(epc_page);
- }
+ epc_page = sgx_encl_load_secs(encl);
+ if (IS_ERR(epc_page))
+ return ERR_CAST(epc_page);
epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
if (IS_ERR(epc_page))
@@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
mutex_lock(&encl->lock);
+ epc_page = sgx_encl_load_secs(encl);
+ if (IS_ERR(epc_page)) {
+ if (PTR_ERR(epc_page) == -EBUSY)
+ vmret = VM_FAULT_NOPAGE;
+ goto err_out_unlock;
+ }
+
epc_page = sgx_alloc_epc_page(encl_page, false);
if (IS_ERR(epc_page)) {
if (PTR_ERR(epc_page) == -EBUSY)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 3a43a2dee658..9c9faa1634fb 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -695,7 +695,6 @@ void kgdb_arch_exit(void)
}
/**
- *
* kgdb_skipexception - Bail out of KGDB when we've been triggered.
* @exception: Exception vector number
* @regs: Current &struct pt_regs.
diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index a65b7a9ebff2..d8b0fadf429a 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -9,8 +9,7 @@
# KBUILD_CFLAGS used when building rest of boot (takes effect recursively)
-KBUILD_CFLAGS += -fno-builtin -Iarch/$(ARCH)/boot/include
-HOSTFLAGS += -Iarch/$(ARCH)/boot/include
+KBUILD_CFLAGS += -fno-builtin
subdir-y := lib
targets += vmlinux.bin vmlinux.bin.gz
diff --git a/arch/xtensa/boot/lib/zmem.c b/arch/xtensa/boot/lib/zmem.c
index e3ecd743c515..b89189355122 100644
--- a/arch/xtensa/boot/lib/zmem.c
+++ b/arch/xtensa/boot/lib/zmem.c
@@ -4,13 +4,14 @@
/* bits taken from ppc */
extern void *avail_ram, *end_avail;
+void gunzip(void *dst, int dstlen, unsigned char *src, int *lenp);
-void exit (void)
+static void exit(void)
{
for (;;);
}
-void *zalloc(unsigned size)
+static void *zalloc(unsigned int size)
{
void *p = avail_ram;
diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h
index 3f5ffae89b58..6f02f6f21890 100644
--- a/arch/xtensa/include/asm/core.h
+++ b/arch/xtensa/include/asm/core.h
@@ -6,6 +6,10 @@
#include <variant/core.h>
+#ifndef XCHAL_HAVE_DIV32
+#define XCHAL_HAVE_DIV32 0
+#endif
+
#ifndef XCHAL_HAVE_EXCLUSIVE
#define XCHAL_HAVE_EXCLUSIVE 0
#endif
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index 9f119c1ca0b5..9ec86f440a48 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -48,6 +48,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp);
void hw_breakpoint_pmu_read(struct perf_event *bp);
int check_hw_breakpoint(struct pt_regs *regs);
void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+void restore_dbreak(void);
#else
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index a6d09fe04831..d008a153a2b9 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -14,6 +14,8 @@
#include <linux/compiler.h>
#include <linux/stringify.h>
+
+#include <asm/bootparam.h>
#include <asm/ptrace.h>
#include <asm/types.h>
#include <asm/regs.h>
@@ -217,6 +219,9 @@ struct mm_struct;
extern unsigned long __get_wchan(struct task_struct *p);
+void init_arch(bp_tag_t *bp_start);
+void do_notify_resume(struct pt_regs *regs);
+
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1])
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 308f209a4740..a270467556dc 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -106,6 +106,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
return regs->areg[2];
}
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
#else /* __ASSEMBLY__ */
# include <asm/asm-offsets.h>
diff --git a/arch/xtensa/include/asm/smp.h b/arch/xtensa/include/asm/smp.h
index 5dc5bf8cdd77..e446e6fc4557 100644
--- a/arch/xtensa/include/asm/smp.h
+++ b/arch/xtensa/include/asm/smp.h
@@ -23,6 +23,7 @@ struct cpumask;
void arch_send_call_function_ipi_mask(const struct cpumask *mask);
void arch_send_call_function_single_ipi(int cpu);
+void secondary_start_kernel(void);
void smp_init_cpus(void);
void secondary_init_irq(void);
void ipi_init(void);
diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h
index 50889935138a..8c3ceb427018 100644
--- a/arch/xtensa/include/asm/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
@@ -18,4 +18,6 @@
#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte)
+void check_tlb_sanity(void);
+
#endif /* _XTENSA_TLB_H */
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index 285fb2942b06..1eeecd58eb0c 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/perf_event.h>
#include <asm/core.h>
+#include <asm/hw_breakpoint.h>
/* Breakpoint currently in use for each IBREAKA. */
static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[XCHAL_NUM_IBREAK]);
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 42f106004400..b1e410f6b5ab 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -28,6 +28,7 @@
#include <asm/mxregs.h>
#include <linux/uaccess.h>
#include <asm/platform.h>
+#include <asm/traps.h>
DECLARE_PER_CPU(unsigned long, nmi_count);
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index f29477162ede..9056cd1a8302 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -541,7 +541,6 @@ long arch_ptrace(struct task_struct *child, long request,
return ret;
}
-void do_syscall_trace_leave(struct pt_regs *regs);
int do_syscall_trace_enter(struct pt_regs *regs)
{
if (regs->syscall == NO_SYSCALL)
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 5c01d7e70d90..81f0b106cfc1 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -26,6 +26,8 @@
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/coprocessor.h>
+#include <asm/processor.h>
+#include <asm/syscall.h>
#include <asm/unistd.h>
extern struct task_struct *coproc_owners[];
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 07dd6baf18cf..94a23f100726 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
+#include <linux/profile.h>
#include <linux/sched/mm.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index f643ea5e36da..831ffb648bda 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -12,6 +12,7 @@
#include <linux/sched.h>
#include <linux/stacktrace.h>
+#include <asm/ftrace.h>
#include <asm/stacktrace.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 427c125a137a..38092d21acf8 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -23,6 +23,7 @@
* for more details.
*/
+#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
diff --git a/arch/xtensa/lib/umulsidi3.S b/arch/xtensa/lib/umulsidi3.S
index 8c7a94a0c5d0..5da501b57813 100644
--- a/arch/xtensa/lib/umulsidi3.S
+++ b/arch/xtensa/lib/umulsidi3.S
@@ -3,7 +3,9 @@
#include <asm/asmmacro.h>
#include <asm/core.h>
-#if !XCHAL_HAVE_MUL16 && !XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MAC16
+#if XCHAL_HAVE_MUL16 || XCHAL_HAVE_MUL32 || XCHAL_HAVE_MAC16
+#define XCHAL_NO_MUL 0
+#else
#define XCHAL_NO_MUL 1
#endif
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index d1eb8d6c5b82..16e11b6f6f78 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -20,6 +20,7 @@
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/hardirq.h>
+#include <asm/traps.h>
void bad_page_fault(struct pt_regs*, unsigned long, int);
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 0a11fc5f185b..4f974b74883c 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -17,6 +17,7 @@
#include <linux/mm.h>
#include <asm/processor.h>
#include <asm/mmu_context.h>
+#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 85c82cd42188..e89f27f2bb18 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -201,7 +201,7 @@ static int tuntap_write(struct iss_net_private *lp, struct sk_buff **skb)
return simc_write(lp->tp.info.tuntap.fd, (*skb)->data, (*skb)->len);
}
-unsigned short tuntap_protocol(struct sk_buff *skb)
+static unsigned short tuntap_protocol(struct sk_buff *skb)
{
return eth_type_trans(skb, skb->dev);
}
@@ -441,7 +441,7 @@ static int iss_net_change_mtu(struct net_device *dev, int new_mtu)
return -EINVAL;
}
-void iss_net_user_timer_expire(struct timer_list *unused)
+static void iss_net_user_timer_expire(struct timer_list *unused)
{
}
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 167be74df4ee..dd7310c94713 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -270,7 +270,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
finish_wait(&rqw->wait, &data.wq);
/*
- * We raced with wbt_wake_function() getting a token,
+ * We raced with rq_qos_wake_function() getting a token,
* which means we now have two. Put our local token
* and wake anyone else potentially waiting for one.
*/
diff --git a/block/disk-events.c b/block/disk-events.c
index 422db8292d09..13c3372c465a 100644
--- a/block/disk-events.c
+++ b/block/disk-events.c
@@ -290,7 +290,6 @@ EXPORT_SYMBOL(disk_check_media_change);
/**
* disk_force_media_change - force a media change event
* @disk: the disk which will raise the event
- * @events: the events to raise
*
* Should be called when the media changes for @disk. Generates a uevent
* and attempts to free all dentries and inodes and invalidates all block
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index ba79f397c9e8..467a60235370 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -327,7 +327,7 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
}
if (!ret)
- ivpu_info(vdev, "VPU ready message received successfully\n");
+ ivpu_dbg(vdev, PM, "VPU ready message received successfully\n");
else
ivpu_hw_diagnose_failure(vdev);
@@ -634,6 +634,7 @@ static void ivpu_dev_fini(struct ivpu_device *vdev)
static struct pci_device_id ivpu_pci_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_ARL) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) },
{ }
};
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 9e8c075fe9ef..03b3d6532fb6 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -23,6 +23,7 @@
#define DRIVER_DATE "20230117"
#define PCI_DEVICE_ID_MTL 0x7d1d
+#define PCI_DEVICE_ID_ARL 0xad1d
#define PCI_DEVICE_ID_LNL 0x643e
#define IVPU_HW_37XX 37
@@ -165,6 +166,7 @@ static inline int ivpu_hw_gen(struct ivpu_device *vdev)
{
switch (ivpu_device_id(vdev)) {
case PCI_DEVICE_ID_MTL:
+ case PCI_DEVICE_ID_ARL:
return IVPU_HW_37XX;
case PCI_DEVICE_ID_LNL:
return IVPU_HW_40XX;
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 9827ea4d7b83..0191cf8e5964 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -220,7 +220,8 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
if (ret)
return ret;
- fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, DRM_IVPU_BO_WC);
+ fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size,
+ DRM_IVPU_BO_CACHED | DRM_IVPU_BO_NOSNOOP);
if (!fw->mem) {
ivpu_err(vdev, "Failed to allocate firmware runtime memory\n");
return -ENOMEM;
@@ -330,7 +331,7 @@ int ivpu_fw_load(struct ivpu_device *vdev)
memset(start, 0, size);
}
- wmb(); /* Flush WC buffers after writing fw->mem */
+ clflush_cache_range(fw->mem->kvaddr, fw->mem->base.size);
return 0;
}
@@ -432,6 +433,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
if (!ivpu_fw_is_cold_boot(vdev)) {
boot_params->save_restore_ret_address = 0;
vdev->pm->is_warmboot = true;
+ clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K);
return;
}
@@ -493,7 +495,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
- wmb(); /* Flush WC buffers after writing bootparams */
+ clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K);
ivpu_fw_boot_params_print(vdev, boot_params);
}
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index 6b0ceda5f253..f4130586ff1b 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -8,6 +8,8 @@
#include <drm/drm_gem.h>
#include <drm/drm_mm.h>
+#define DRM_IVPU_BO_NOSNOOP 0x10000000
+
struct dma_buf;
struct ivpu_bo_ops;
struct ivpu_file_priv;
@@ -83,6 +85,9 @@ static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo)
static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
{
+ if (bo->flags & DRM_IVPU_BO_NOSNOOP)
+ return false;
+
return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
}
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 00c5dbbe6847..8bdb59a45da6 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -57,8 +57,7 @@
#define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \
- (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
+#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
(REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI0_ERR)) | \
(REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI1_ERR)) | \
(REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR0_ERR)) | \
@@ -196,6 +195,14 @@ static int ivpu_pll_wait_for_status_ready(struct ivpu_device *vdev)
return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, READY, 1, PLL_TIMEOUT_US);
}
+static int ivpu_wait_for_clock_own_resource_ack(struct ivpu_device *vdev)
+{
+ if (ivpu_is_simics(vdev))
+ return 0;
+
+ return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US);
+}
+
static void ivpu_pll_init_frequency_ratios(struct ivpu_device *vdev)
{
struct ivpu_hw_info *hw = vdev->hw;
@@ -556,6 +563,12 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
{
int ret;
+ ret = ivpu_wait_for_clock_own_resource_ack(vdev);
+ if (ret) {
+ ivpu_err(vdev, "Timed out waiting for clock own resource ACK\n");
+ return ret;
+ }
+
ivpu_boot_pwr_island_trickle_drive(vdev, true);
ivpu_boot_pwr_island_drive(vdev, true);
@@ -1046,9 +1059,6 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
if (status == 0)
return IRQ_NONE;
- /* Disable global interrupt before handling local buttress interrupts */
- REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
-
if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
ivpu_dbg(vdev, IRQ, "FREQ_CHANGE");
@@ -1096,9 +1106,6 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
/* This must be done after interrupts are cleared at the source. */
REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status);
- /* Re-enable global interrupt */
- REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
-
if (schedule_recovery)
ivpu_pm_schedule_recovery(vdev);
@@ -1110,9 +1117,14 @@ static irqreturn_t ivpu_hw_40xx_irq_handler(int irq, void *ptr)
struct ivpu_device *vdev = ptr;
irqreturn_t ret = IRQ_NONE;
+ REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
+
ret |= ivpu_hw_40xx_irqv_handler(vdev, irq);
ret |= ivpu_hw_40xx_irqb_handler(vdev, irq);
+ /* Re-enable global interrupts to re-trigger MSI for pending interrupts */
+ REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
+
if (ret & IRQ_WAKE_THREAD)
return IRQ_WAKE_THREAD;
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
index 5139cfe88532..ff4a5d4f5821 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h
@@ -70,6 +70,8 @@
#define VPU_40XX_BUTTRESS_VPU_STATUS_READY_MASK BIT_MASK(0)
#define VPU_40XX_BUTTRESS_VPU_STATUS_IDLE_MASK BIT_MASK(1)
#define VPU_40XX_BUTTRESS_VPU_STATUS_DUP_IDLE_MASK BIT_MASK(2)
+#define VPU_40XX_BUTTRESS_VPU_STATUS_CLOCK_RESOURCE_OWN_ACK_MASK BIT_MASK(6)
+#define VPU_40XX_BUTTRESS_VPU_STATUS_POWER_RESOURCE_OWN_ACK_MASK BIT_MASK(7)
#define VPU_40XX_BUTTRESS_VPU_STATUS_PERF_CLK_MASK BIT_MASK(11)
#define VPU_40XX_BUTTRESS_VPU_STATUS_DISABLE_CLK_RELINQUISH_MASK BIT_MASK(12)
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index fa0af59e39ab..295c0d7b5039 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -209,10 +209,10 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
struct ivpu_ipc_rx_msg *rx_msg;
int wait_ret, ret = 0;
- wait_ret = wait_event_interruptible_timeout(cons->rx_msg_wq,
- (IS_KTHREAD() && kthread_should_stop()) ||
- !list_empty(&cons->rx_msg_list),
- msecs_to_jiffies(timeout_ms));
+ wait_ret = wait_event_timeout(cons->rx_msg_wq,
+ (IS_KTHREAD() && kthread_should_stop()) ||
+ !list_empty(&cons->rx_msg_list),
+ msecs_to_jiffies(timeout_ms));
if (IS_KTHREAD() && kthread_should_stop())
return -EINTR;
@@ -220,9 +220,6 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
if (wait_ret == 0)
return -ETIMEDOUT;
- if (wait_ret < 0)
- return -ERESTARTSYS;
-
spin_lock_irq(&cons->rx_msg_lock);
rx_msg = list_first_entry_or_null(&cons->rx_msg_list, struct ivpu_ipc_rx_msg, link);
if (!rx_msg) {
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 948e31f7ce6e..b411948594ff 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -2057,7 +2057,9 @@ static int acpi_video_bus_add(struct acpi_device *device)
!auto_detect)
acpi_video_bus_register_backlight(video);
- acpi_video_bus_add_notify_handler(video);
+ error = acpi_video_bus_add_notify_handler(video);
+ if (error)
+ goto err_del;
error = acpi_dev_install_notify_handler(device, ACPI_DEVICE_NOTIFY,
acpi_video_bus_notify);
@@ -2067,10 +2069,11 @@ static int acpi_video_bus_add(struct acpi_device *device)
return 0;
err_remove:
+ acpi_video_bus_remove_notify_handler(video);
+err_del:
mutex_lock(&video_list_lock);
list_del(&video->entry);
mutex_unlock(&video_list_lock);
- acpi_video_bus_remove_notify_handler(video);
acpi_video_bus_unregister_backlight(video);
err_put_video:
acpi_video_bus_put_devices(video);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 0072e0f9ad39..d8cc1e27a125 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1973,6 +1973,96 @@ retry:
}
/**
+ * ata_dev_power_set_standby - Set a device power mode to standby
+ * @dev: target device
+ *
+ * Issue a STANDBY IMMEDIATE command to set a device power mode to standby.
+ * For an HDD device, this spins down the disks.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep).
+ */
+void ata_dev_power_set_standby(struct ata_device *dev)
+{
+ unsigned long ap_flags = dev->link->ap->flags;
+ struct ata_taskfile tf;
+ unsigned int err_mask;
+
+ /* Issue STANDBY IMMEDIATE command only if supported by the device */
+ if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC)
+ return;
+
+ /*
+ * Some odd clown BIOSes issue spindown on power off (ACPI S4 or S5)
+ * causing some drives to spin up and down again. For these, do nothing
+ * if we are being called on shutdown.
+ */
+ if ((ap_flags & ATA_FLAG_NO_POWEROFF_SPINDOWN) &&
+ system_state == SYSTEM_POWER_OFF)
+ return;
+
+ if ((ap_flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) &&
+ system_entering_hibernation())
+ return;
+
+ ata_tf_init(dev, &tf);
+ tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+ tf.protocol = ATA_PROT_NODATA;
+ tf.command = ATA_CMD_STANDBYNOW1;
+
+ ata_dev_notice(dev, "Entering standby power mode\n");
+
+ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+ if (err_mask)
+ ata_dev_err(dev, "STANDBY IMMEDIATE failed (err_mask=0x%x)\n",
+ err_mask);
+}
+
+/**
+ * ata_dev_power_set_active - Set a device power mode to active
+ * @dev: target device
+ *
+ * Issue a VERIFY command to enter to ensure that the device is in the
+ * active power mode. For a spun-down HDD (standby or idle power mode),
+ * the VERIFY command will complete after the disk spins up.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep).
+ */
+void ata_dev_power_set_active(struct ata_device *dev)
+{
+ struct ata_taskfile tf;
+ unsigned int err_mask;
+
+ /*
+ * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only
+ * if supported by the device.
+ */
+ if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC)
+ return;
+
+ ata_tf_init(dev, &tf);
+ tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+ tf.protocol = ATA_PROT_NODATA;
+ tf.command = ATA_CMD_VERIFY;
+ tf.nsect = 1;
+ if (dev->flags & ATA_DFLAG_LBA) {
+ tf.flags |= ATA_TFLAG_LBA;
+ tf.device |= ATA_LBA;
+ } else {
+ /* CHS */
+ tf.lbal = 0x1; /* sect */
+ }
+
+ ata_dev_notice(dev, "Entering active power mode\n");
+
+ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+ if (err_mask)
+ ata_dev_err(dev, "VERIFY failed (err_mask=0x%x)\n",
+ err_mask);
+}
+
+/**
* ata_read_log_page - read a specific log page
* @dev: target device
* @log: log to read
@@ -2529,7 +2619,7 @@ static int ata_dev_config_lba(struct ata_device *dev)
{
const u16 *id = dev->id;
const char *lba_desc;
- char ncq_desc[24];
+ char ncq_desc[32];
int ret;
dev->flags |= ATA_DFLAG_LBA;
@@ -5037,17 +5127,19 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg,
struct ata_link *link;
unsigned long flags;
- /* Previous resume operation might still be in
- * progress. Wait for PM_PENDING to clear.
+ spin_lock_irqsave(ap->lock, flags);
+
+ /*
+ * A previous PM operation might still be in progress. Wait for
+ * ATA_PFLAG_PM_PENDING to clear.
*/
if (ap->pflags & ATA_PFLAG_PM_PENDING) {
+ spin_unlock_irqrestore(ap->lock, flags);
ata_port_wait_eh(ap);
- WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING);
+ spin_lock_irqsave(ap->lock, flags);
}
- /* request PM ops to EH */
- spin_lock_irqsave(ap->lock, flags);
-
+ /* Request PM operation to EH */
ap->pm_mesg = mesg;
ap->pflags |= ATA_PFLAG_PM_PENDING;
ata_for_each_link(link, ap, HOST_FIRST) {
@@ -5059,10 +5151,8 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg,
spin_unlock_irqrestore(ap->lock, flags);
- if (!async) {
+ if (!async)
ata_port_wait_eh(ap);
- WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING);
- }
}
/*
@@ -5078,11 +5168,27 @@ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET
static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg)
{
+ /*
+ * We are about to suspend the port, so we do not care about
+ * scsi_rescan_device() calls scheduled by previous resume operations.
+ * The next resume will schedule the rescan again. So cancel any rescan
+ * that is not done yet.
+ */
+ cancel_delayed_work_sync(&ap->scsi_rescan_task);
+
ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false);
}
static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg)
{
+ /*
+ * We are about to suspend the port, so we do not care about
+ * scsi_rescan_device() calls scheduled by previous resume operations.
+ * The next resume will schedule the rescan again. So cancel any rescan
+ * that is not done yet.
+ */
+ cancel_delayed_work_sync(&ap->scsi_rescan_task);
+
ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true);
}
@@ -5229,7 +5335,7 @@ EXPORT_SYMBOL_GPL(ata_host_resume);
#endif
const struct device_type ata_port_type = {
- .name = "ata_port",
+ .name = ATA_PORT_TYPE_NAME,
#ifdef CONFIG_PM
.pm = &ata_port_pm_ops,
#endif
@@ -5948,11 +6054,30 @@ static void ata_port_detach(struct ata_port *ap)
struct ata_link *link;
struct ata_device *dev;
- /* tell EH we're leaving & flush EH */
+ /* Wait for any ongoing EH */
+ ata_port_wait_eh(ap);
+
+ mutex_lock(&ap->scsi_scan_mutex);
spin_lock_irqsave(ap->lock, flags);
+
+ /* Remove scsi devices */
+ ata_for_each_link(link, ap, HOST_FIRST) {
+ ata_for_each_dev(dev, link, ALL) {
+ if (dev->sdev) {
+ spin_unlock_irqrestore(ap->lock, flags);
+ scsi_remove_device(dev->sdev);
+ spin_lock_irqsave(ap->lock, flags);
+ dev->sdev = NULL;
+ }
+ }
+ }
+
+ /* Tell EH to disable all devices */
ap->pflags |= ATA_PFLAG_UNLOADING;
ata_port_schedule_eh(ap);
+
spin_unlock_irqrestore(ap->lock, flags);
+ mutex_unlock(&ap->scsi_scan_mutex);
/* wait till EH commits suicide */
ata_port_wait_eh(ap);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 4cf4f57e57b8..5686353e442c 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -147,6 +147,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = {
.timeouts = ata_eh_other_timeouts, },
{ .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT),
.timeouts = ata_eh_flush_timeouts },
+ { .commands = CMDS(ATA_CMD_VERIFY),
+ .timeouts = ata_eh_reset_timeouts },
};
#undef CMDS
@@ -498,7 +500,19 @@ static void ata_eh_unload(struct ata_port *ap)
struct ata_device *dev;
unsigned long flags;
- /* Restore SControl IPM and SPD for the next driver and
+ /*
+ * Unless we are restarting, transition all enabled devices to
+ * standby power mode.
+ */
+ if (system_state != SYSTEM_RESTART) {
+ ata_for_each_link(link, ap, PMP_FIRST) {
+ ata_for_each_dev(dev, link, ENABLED)
+ ata_dev_power_set_standby(dev);
+ }
+ }
+
+ /*
+ * Restore SControl IPM and SPD for the next driver and
* disable attached devices.
*/
ata_for_each_link(link, ap, PMP_FIRST) {
@@ -684,6 +698,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
ehc->saved_xfer_mode[devno] = dev->xfer_mode;
if (ata_ncq_enabled(dev))
ehc->saved_ncq_enabled |= 1 << devno;
+
+ /* If we are resuming, wake up the device */
+ if (ap->pflags & ATA_PFLAG_RESUMING)
+ ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE;
}
}
@@ -743,6 +761,8 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
/* clean up */
spin_lock_irqsave(ap->lock, flags);
+ ap->pflags &= ~ATA_PFLAG_RESUMING;
+
if (ap->pflags & ATA_PFLAG_LOADING)
ap->pflags &= ~ATA_PFLAG_LOADING;
else if ((ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) &&
@@ -1218,6 +1238,13 @@ void ata_eh_detach_dev(struct ata_device *dev)
struct ata_eh_context *ehc = &link->eh_context;
unsigned long flags;
+ /*
+ * If the device is still enabled, transition it to standby power mode
+ * (i.e. spin down HDDs).
+ */
+ if (ata_dev_enabled(dev))
+ ata_dev_power_set_standby(dev);
+
ata_dev_disable(dev);
spin_lock_irqsave(ap->lock, flags);
@@ -2305,7 +2332,7 @@ static void ata_eh_link_report(struct ata_link *link)
struct ata_eh_context *ehc = &link->eh_context;
struct ata_queued_cmd *qc;
const char *frozen, *desc;
- char tries_buf[6] = "";
+ char tries_buf[16] = "";
int tag, nr_failed = 0;
if (ehc->i.flags & ATA_EHI_QUIET)
@@ -3016,6 +3043,15 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
if (ehc->i.flags & ATA_EHI_DID_RESET)
readid_flags |= ATA_READID_POSTRESET;
+ /*
+ * When resuming, before executing any command, make sure to
+ * transition the device to the active power mode.
+ */
+ if ((action & ATA_EH_SET_ACTIVE) && ata_dev_enabled(dev)) {
+ ata_dev_power_set_active(dev);
+ ata_eh_done(link, dev, ATA_EH_SET_ACTIVE);
+ }
+
if ((action & ATA_EH_REVALIDATE) && ata_dev_enabled(dev)) {
WARN_ON(dev->class == ATA_DEV_PMP);
@@ -3989,6 +4025,7 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap)
unsigned long flags;
int rc = 0;
struct ata_device *dev;
+ struct ata_link *link;
/* are we suspending? */
spin_lock_irqsave(ap->lock, flags);
@@ -4001,6 +4038,12 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap)
WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED);
+ /* Set all devices attached to the port in standby mode */
+ ata_for_each_link(link, ap, HOST_FIRST) {
+ ata_for_each_dev(dev, link, ENABLED)
+ ata_dev_power_set_standby(dev);
+ }
+
/*
* If we have a ZPODD attached, check its zero
* power ready status before the port is frozen.
@@ -4083,6 +4126,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap)
/* update the flags */
spin_lock_irqsave(ap->lock, flags);
ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED);
+ ap->pflags |= ATA_PFLAG_RESUMING;
spin_unlock_irqrestore(ap->lock, flags);
}
#endif /* CONFIG_PM */
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d3f28b82c97b..a371b497035e 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1050,14 +1050,13 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
}
} else {
sdev->sector_size = ata_id_logical_sector_size(dev->id);
+
/*
- * Stop the drive on suspend but do not issue START STOP UNIT
- * on resume as this is not necessary and may fail: the device
- * will be woken up by ata_port_pm_resume() with a port reset
- * and device revalidation.
+ * Ask the sd driver to issue START STOP UNIT on runtime suspend
+ * and resume only. For system level suspend/resume, devices
+ * power state is handled directly by libata EH.
*/
- sdev->manage_start_stop = 1;
- sdev->no_start_on_resume = 1;
+ sdev->manage_runtime_start_stop = true;
}
/*
@@ -1090,6 +1089,42 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
}
/**
+ * ata_scsi_slave_alloc - Early setup of SCSI device
+ * @sdev: SCSI device to examine
+ *
+ * This is called from scsi_alloc_sdev() when the scsi device
+ * associated with an ATA device is scanned on a port.
+ *
+ * LOCKING:
+ * Defined by SCSI layer. We don't really care.
+ */
+
+int ata_scsi_slave_alloc(struct scsi_device *sdev)
+{
+ struct ata_port *ap = ata_shost_to_port(sdev->host);
+ struct device_link *link;
+
+ ata_scsi_sdev_config(sdev);
+
+ /*
+ * Create a link from the ata_port device to the scsi device to ensure
+ * that PM does suspend/resume in the correct order: the scsi device is
+ * consumer (child) and the ata port the supplier (parent).
+ */
+ link = device_link_add(&sdev->sdev_gendev, &ap->tdev,
+ DL_FLAG_STATELESS |
+ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE);
+ if (!link) {
+ ata_port_err(ap, "Failed to create link to scsi device %s\n",
+ dev_name(&sdev->sdev_gendev));
+ return -ENODEV;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc);
+
+/**
* ata_scsi_slave_config - Set SCSI device attributes
* @sdev: SCSI device to examine
*
@@ -1105,14 +1140,11 @@ int ata_scsi_slave_config(struct scsi_device *sdev)
{
struct ata_port *ap = ata_shost_to_port(sdev->host);
struct ata_device *dev = __ata_scsi_find_dev(ap, sdev);
- int rc = 0;
-
- ata_scsi_sdev_config(sdev);
if (dev)
- rc = ata_scsi_dev_config(sdev, dev);
+ return ata_scsi_dev_config(sdev, dev);
- return rc;
+ return 0;
}
EXPORT_SYMBOL_GPL(ata_scsi_slave_config);
@@ -1136,6 +1168,8 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev)
unsigned long flags;
struct ata_device *dev;
+ device_link_remove(&sdev->sdev_gendev, &ap->tdev);
+
spin_lock_irqsave(ap->lock, flags);
dev = __ata_scsi_find_dev(ap, sdev);
if (dev && dev->sdev) {
@@ -1195,7 +1229,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc)
}
if (cdb[4] & 0x1) {
- tf->nsect = 1; /* 1 sector, lba=0 */
+ tf->nsect = 1; /* 1 sector, lba=0 */
if (qc->dev->flags & ATA_DFLAG_LBA) {
tf->flags |= ATA_TFLAG_LBA;
@@ -1211,7 +1245,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc)
tf->lbah = 0x0; /* cyl high */
}
- tf->command = ATA_CMD_VERIFY; /* READ VERIFY */
+ tf->command = ATA_CMD_VERIFY; /* READ VERIFY */
} else {
/* Some odd clown BIOSen issue spindown on power off (ACPI S4
* or S5) causing some drives to spin up and down again.
@@ -1221,7 +1255,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc)
goto skip;
if ((qc->ap->flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) &&
- system_entering_hibernation())
+ system_entering_hibernation())
goto skip;
/* Issue ATA STANDBY IMMEDIATE command */
@@ -1835,6 +1869,9 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
hdr[2] = 0x7; /* claim SPC-5 version compatibility */
}
+ if (args->dev->flags & ATA_DFLAG_CDL)
+ hdr[2] = 0xd; /* claim SPC-6 version compatibility */
+
memcpy(rbuf, hdr, sizeof(hdr));
memcpy(&rbuf[8], "ATA ", 8);
ata_id_string(args->id, &rbuf[16], ATA_ID_PROD, 16);
@@ -4312,7 +4349,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
break;
case MAINTENANCE_IN:
- if (scsicmd[1] == MI_REPORT_SUPPORTED_OPERATION_CODES)
+ if ((scsicmd[1] & 0x1f) == MI_REPORT_SUPPORTED_OPERATION_CODES)
ata_scsi_rbuf_fill(&args, ata_scsiop_maint_in);
else
ata_scsi_set_invalid_field(dev, cmd, 1, 0xff);
@@ -4722,7 +4759,7 @@ void ata_scsi_dev_rescan(struct work_struct *work)
struct ata_link *link;
struct ata_device *dev;
unsigned long flags;
- bool delay_rescan = false;
+ int ret = 0;
mutex_lock(&ap->scsi_scan_mutex);
spin_lock_irqsave(ap->lock, flags);
@@ -4731,37 +4768,34 @@ void ata_scsi_dev_rescan(struct work_struct *work)
ata_for_each_dev(dev, link, ENABLED) {
struct scsi_device *sdev = dev->sdev;
+ /*
+ * If the port was suspended before this was scheduled,
+ * bail out.
+ */
+ if (ap->pflags & ATA_PFLAG_SUSPENDED)
+ goto unlock;
+
if (!sdev)
continue;
if (scsi_device_get(sdev))
continue;
- /*
- * If the rescan work was scheduled because of a resume
- * event, the port is already fully resumed, but the
- * SCSI device may not yet be fully resumed. In such
- * case, executing scsi_rescan_device() may cause a
- * deadlock with the PM code on device_lock(). Prevent
- * this by giving up and retrying rescan after a short
- * delay.
- */
- delay_rescan = sdev->sdev_gendev.power.is_suspended;
- if (delay_rescan) {
- scsi_device_put(sdev);
- break;
- }
-
spin_unlock_irqrestore(ap->lock, flags);
- scsi_rescan_device(sdev);
+ ret = scsi_rescan_device(sdev);
scsi_device_put(sdev);
spin_lock_irqsave(ap->lock, flags);
+
+ if (ret)
+ goto unlock;
}
}
+unlock:
spin_unlock_irqrestore(ap->lock, flags);
mutex_unlock(&ap->scsi_scan_mutex);
- if (delay_rescan)
+ /* Reschedule with a delay if scsi_rescan_device() returned an error */
+ if (ret)
schedule_delayed_work(&ap->scsi_rescan_task,
msecs_to_jiffies(5));
}
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index e4fb9d1b9b39..3e49a877500e 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -266,6 +266,10 @@ void ata_tport_delete(struct ata_port *ap)
put_device(dev);
}
+static const struct device_type ata_port_sas_type = {
+ .name = ATA_PORT_TYPE_NAME,
+};
+
/** ata_tport_add - initialize a transport ATA port structure
*
* @parent: parent device
@@ -283,7 +287,10 @@ int ata_tport_add(struct device *parent,
struct device *dev = &ap->tdev;
device_initialize(dev);
- dev->type = &ata_port_type;
+ if (ap->flags & ATA_FLAG_SAS_HOST)
+ dev->type = &ata_port_sas_type;
+ else
+ dev->type = &ata_port_type;
dev->parent = parent;
ata_host_get(ap->host);
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 6e7d352803bd..05ac80da8ebc 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -30,6 +30,8 @@ enum {
ATA_DNXFER_QUIET = (1 << 31),
};
+#define ATA_PORT_TYPE_NAME "ata_port"
+
extern atomic_t ata_print_id;
extern int atapi_passthru16;
extern int libata_fua;
@@ -60,6 +62,8 @@ extern int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags);
extern int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class,
unsigned int readid_flags);
extern int ata_dev_configure(struct ata_device *dev);
+extern void ata_dev_power_set_standby(struct ata_device *dev);
+extern void ata_dev_power_set_active(struct ata_device *dev);
extern int sata_down_spd_limit(struct ata_link *link, u32 spd_limit);
extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel);
extern unsigned int ata_dev_set_feature(struct ata_device *dev,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 3de11f077144..a999b698b131 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -632,9 +632,8 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...)
static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
static int rbd_dev_refresh(struct rbd_device *rbd_dev);
-static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev);
-static int rbd_dev_header_info(struct rbd_device *rbd_dev);
-static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev);
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header);
static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev,
u64 snap_id);
static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
@@ -995,15 +994,24 @@ static void rbd_init_layout(struct rbd_device *rbd_dev)
RCU_INIT_POINTER(rbd_dev->layout.pool_ns, NULL);
}
+static void rbd_image_header_cleanup(struct rbd_image_header *header)
+{
+ kfree(header->object_prefix);
+ ceph_put_snap_context(header->snapc);
+ kfree(header->snap_sizes);
+ kfree(header->snap_names);
+
+ memset(header, 0, sizeof(*header));
+}
+
/*
* Fill an rbd image header with information from the given format 1
* on-disk header.
*/
-static int rbd_header_from_disk(struct rbd_device *rbd_dev,
- struct rbd_image_header_ondisk *ondisk)
+static int rbd_header_from_disk(struct rbd_image_header *header,
+ struct rbd_image_header_ondisk *ondisk,
+ bool first_time)
{
- struct rbd_image_header *header = &rbd_dev->header;
- bool first_time = header->object_prefix == NULL;
struct ceph_snap_context *snapc;
char *object_prefix = NULL;
char *snap_names = NULL;
@@ -1070,11 +1078,6 @@ static int rbd_header_from_disk(struct rbd_device *rbd_dev,
if (first_time) {
header->object_prefix = object_prefix;
header->obj_order = ondisk->options.order;
- rbd_init_layout(rbd_dev);
- } else {
- ceph_put_snap_context(header->snapc);
- kfree(header->snap_names);
- kfree(header->snap_sizes);
}
/* The remaining fields always get updated (when we refresh) */
@@ -4859,7 +4862,9 @@ out_req:
* return, the rbd_dev->header field will contain up-to-date
* information about the image.
*/
-static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev)
+static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header,
+ bool first_time)
{
struct rbd_image_header_ondisk *ondisk = NULL;
u32 snap_count = 0;
@@ -4907,7 +4912,7 @@ static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev)
snap_count = le32_to_cpu(ondisk->snap_count);
} while (snap_count != want_count);
- ret = rbd_header_from_disk(rbd_dev, ondisk);
+ ret = rbd_header_from_disk(header, ondisk, first_time);
out:
kfree(ondisk);
@@ -4931,39 +4936,6 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev)
}
}
-static int rbd_dev_refresh(struct rbd_device *rbd_dev)
-{
- u64 mapping_size;
- int ret;
-
- down_write(&rbd_dev->header_rwsem);
- mapping_size = rbd_dev->mapping.size;
-
- ret = rbd_dev_header_info(rbd_dev);
- if (ret)
- goto out;
-
- /*
- * If there is a parent, see if it has disappeared due to the
- * mapped image getting flattened.
- */
- if (rbd_dev->parent) {
- ret = rbd_dev_v2_parent_info(rbd_dev);
- if (ret)
- goto out;
- }
-
- rbd_assert(!rbd_is_snap(rbd_dev));
- rbd_dev->mapping.size = rbd_dev->header.image_size;
-
-out:
- up_write(&rbd_dev->header_rwsem);
- if (!ret && mapping_size != rbd_dev->mapping.size)
- rbd_dev_update_size(rbd_dev);
-
- return ret;
-}
-
static const struct blk_mq_ops rbd_mq_ops = {
.queue_rq = rbd_queue_rq,
};
@@ -5503,17 +5475,12 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
return 0;
}
-static int rbd_dev_v2_image_size(struct rbd_device *rbd_dev)
-{
- return _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP,
- &rbd_dev->header.obj_order,
- &rbd_dev->header.image_size);
-}
-
-static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev,
+ char **pobject_prefix)
{
size_t size;
void *reply_buf;
+ char *object_prefix;
int ret;
void *p;
@@ -5531,16 +5498,16 @@ static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev)
goto out;
p = reply_buf;
- rbd_dev->header.object_prefix = ceph_extract_encoded_string(&p,
- p + ret, NULL, GFP_NOIO);
+ object_prefix = ceph_extract_encoded_string(&p, p + ret, NULL,
+ GFP_NOIO);
+ if (IS_ERR(object_prefix)) {
+ ret = PTR_ERR(object_prefix);
+ goto out;
+ }
ret = 0;
- if (IS_ERR(rbd_dev->header.object_prefix)) {
- ret = PTR_ERR(rbd_dev->header.object_prefix);
- rbd_dev->header.object_prefix = NULL;
- } else {
- dout(" object_prefix = %s\n", rbd_dev->header.object_prefix);
- }
+ *pobject_prefix = object_prefix;
+ dout(" object_prefix = %s\n", object_prefix);
out:
kfree(reply_buf);
@@ -5591,13 +5558,6 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
return 0;
}
-static int rbd_dev_v2_features(struct rbd_device *rbd_dev)
-{
- return _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP,
- rbd_is_ro(rbd_dev),
- &rbd_dev->header.features);
-}
-
/*
* These are generic image flags, but since they are used only for
* object map, store them in rbd_dev->object_map_flags.
@@ -5634,6 +5594,14 @@ struct parent_image_info {
u64 overlap;
};
+static void rbd_parent_info_cleanup(struct parent_image_info *pii)
+{
+ kfree(pii->pool_ns);
+ kfree(pii->image_id);
+
+ memset(pii, 0, sizeof(*pii));
+}
+
/*
* The caller is responsible for @pii.
*/
@@ -5703,6 +5671,9 @@ static int __get_parent_info(struct rbd_device *rbd_dev,
if (pii->has_overlap)
ceph_decode_64_safe(&p, end, pii->overlap, e_inval);
+ dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n",
+ __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id,
+ pii->has_overlap, pii->overlap);
return 0;
e_inval:
@@ -5741,14 +5712,17 @@ static int __get_parent_info_legacy(struct rbd_device *rbd_dev,
pii->has_overlap = true;
ceph_decode_64_safe(&p, end, pii->overlap, e_inval);
+ dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n",
+ __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id,
+ pii->has_overlap, pii->overlap);
return 0;
e_inval:
return -EINVAL;
}
-static int get_parent_info(struct rbd_device *rbd_dev,
- struct parent_image_info *pii)
+static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev,
+ struct parent_image_info *pii)
{
struct page *req_page, *reply_page;
void *p;
@@ -5776,7 +5750,7 @@ static int get_parent_info(struct rbd_device *rbd_dev,
return ret;
}
-static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
+static int rbd_dev_setup_parent(struct rbd_device *rbd_dev)
{
struct rbd_spec *parent_spec;
struct parent_image_info pii = { 0 };
@@ -5786,37 +5760,12 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
if (!parent_spec)
return -ENOMEM;
- ret = get_parent_info(rbd_dev, &pii);
+ ret = rbd_dev_v2_parent_info(rbd_dev, &pii);
if (ret)
goto out_err;
- dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n",
- __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id,
- pii.has_overlap, pii.overlap);
-
- if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) {
- /*
- * Either the parent never existed, or we have
- * record of it but the image got flattened so it no
- * longer has a parent. When the parent of a
- * layered image disappears we immediately set the
- * overlap to 0. The effect of this is that all new
- * requests will be treated as if the image had no
- * parent.
- *
- * If !pii.has_overlap, the parent image spec is not
- * applicable. It's there to avoid duplication in each
- * snapshot record.
- */
- if (rbd_dev->parent_overlap) {
- rbd_dev->parent_overlap = 0;
- rbd_dev_parent_put(rbd_dev);
- pr_info("%s: clone image has been flattened\n",
- rbd_dev->disk->disk_name);
- }
-
+ if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap)
goto out; /* No parent? No problem. */
- }
/* The ceph file layout needs to fit pool id in 32 bits */
@@ -5828,58 +5777,46 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
}
/*
- * The parent won't change (except when the clone is
- * flattened, already handled that). So we only need to
- * record the parent spec we have not already done so.
+ * The parent won't change except when the clone is flattened,
+ * so we only need to record the parent image spec once.
*/
- if (!rbd_dev->parent_spec) {
- parent_spec->pool_id = pii.pool_id;
- if (pii.pool_ns && *pii.pool_ns) {
- parent_spec->pool_ns = pii.pool_ns;
- pii.pool_ns = NULL;
- }
- parent_spec->image_id = pii.image_id;
- pii.image_id = NULL;
- parent_spec->snap_id = pii.snap_id;
-
- rbd_dev->parent_spec = parent_spec;
- parent_spec = NULL; /* rbd_dev now owns this */
+ parent_spec->pool_id = pii.pool_id;
+ if (pii.pool_ns && *pii.pool_ns) {
+ parent_spec->pool_ns = pii.pool_ns;
+ pii.pool_ns = NULL;
}
+ parent_spec->image_id = pii.image_id;
+ pii.image_id = NULL;
+ parent_spec->snap_id = pii.snap_id;
+
+ rbd_assert(!rbd_dev->parent_spec);
+ rbd_dev->parent_spec = parent_spec;
+ parent_spec = NULL; /* rbd_dev now owns this */
/*
- * We always update the parent overlap. If it's zero we issue
- * a warning, as we will proceed as if there was no parent.
+ * Record the parent overlap. If it's zero, issue a warning as
+ * we will proceed as if there is no parent.
*/
- if (!pii.overlap) {
- if (parent_spec) {
- /* refresh, careful to warn just once */
- if (rbd_dev->parent_overlap)
- rbd_warn(rbd_dev,
- "clone now standalone (overlap became 0)");
- } else {
- /* initial probe */
- rbd_warn(rbd_dev, "clone is standalone (overlap 0)");
- }
- }
+ if (!pii.overlap)
+ rbd_warn(rbd_dev, "clone is standalone (overlap 0)");
rbd_dev->parent_overlap = pii.overlap;
out:
ret = 0;
out_err:
- kfree(pii.pool_ns);
- kfree(pii.image_id);
+ rbd_parent_info_cleanup(&pii);
rbd_spec_put(parent_spec);
return ret;
}
-static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev,
+ u64 *stripe_unit, u64 *stripe_count)
{
struct {
__le64 stripe_unit;
__le64 stripe_count;
} __attribute__ ((packed)) striping_info_buf = { 0 };
size_t size = sizeof (striping_info_buf);
- void *p;
int ret;
ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid,
@@ -5891,27 +5828,33 @@ static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev)
if (ret < size)
return -ERANGE;
- p = &striping_info_buf;
- rbd_dev->header.stripe_unit = ceph_decode_64(&p);
- rbd_dev->header.stripe_count = ceph_decode_64(&p);
+ *stripe_unit = le64_to_cpu(striping_info_buf.stripe_unit);
+ *stripe_count = le64_to_cpu(striping_info_buf.stripe_count);
+ dout(" stripe_unit = %llu stripe_count = %llu\n", *stripe_unit,
+ *stripe_count);
+
return 0;
}
-static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev, s64 *data_pool_id)
{
- __le64 data_pool_id;
+ __le64 data_pool_buf;
int ret;
ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid,
&rbd_dev->header_oloc, "get_data_pool",
- NULL, 0, &data_pool_id, sizeof(data_pool_id));
+ NULL, 0, &data_pool_buf,
+ sizeof(data_pool_buf));
+ dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret);
if (ret < 0)
return ret;
- if (ret < sizeof(data_pool_id))
+ if (ret < sizeof(data_pool_buf))
return -EBADMSG;
- rbd_dev->header.data_pool_id = le64_to_cpu(data_pool_id);
- WARN_ON(rbd_dev->header.data_pool_id == CEPH_NOPOOL);
+ *data_pool_id = le64_to_cpu(data_pool_buf);
+ dout(" data_pool_id = %lld\n", *data_pool_id);
+ WARN_ON(*data_pool_id == CEPH_NOPOOL);
+
return 0;
}
@@ -6103,7 +6046,8 @@ out_err:
return ret;
}
-static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev,
+ struct ceph_snap_context **psnapc)
{
size_t size;
int ret;
@@ -6164,9 +6108,7 @@ static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev)
for (i = 0; i < snap_count; i++)
snapc->snaps[i] = ceph_decode_64(&p);
- ceph_put_snap_context(rbd_dev->header.snapc);
- rbd_dev->header.snapc = snapc;
-
+ *psnapc = snapc;
dout(" snap context seq = %llu, snap_count = %u\n",
(unsigned long long)seq, (unsigned int)snap_count);
out:
@@ -6215,38 +6157,42 @@ out:
return snap_name;
}
-static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header,
+ bool first_time)
{
- bool first_time = rbd_dev->header.object_prefix == NULL;
int ret;
- ret = rbd_dev_v2_image_size(rbd_dev);
+ ret = _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP,
+ first_time ? &header->obj_order : NULL,
+ &header->image_size);
if (ret)
return ret;
if (first_time) {
- ret = rbd_dev_v2_header_onetime(rbd_dev);
+ ret = rbd_dev_v2_header_onetime(rbd_dev, header);
if (ret)
return ret;
}
- ret = rbd_dev_v2_snap_context(rbd_dev);
- if (ret && first_time) {
- kfree(rbd_dev->header.object_prefix);
- rbd_dev->header.object_prefix = NULL;
- }
+ ret = rbd_dev_v2_snap_context(rbd_dev, &header->snapc);
+ if (ret)
+ return ret;
- return ret;
+ return 0;
}
-static int rbd_dev_header_info(struct rbd_device *rbd_dev)
+static int rbd_dev_header_info(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header,
+ bool first_time)
{
rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
+ rbd_assert(!header->object_prefix && !header->snapc);
if (rbd_dev->image_format == 1)
- return rbd_dev_v1_header_info(rbd_dev);
+ return rbd_dev_v1_header_info(rbd_dev, header, first_time);
- return rbd_dev_v2_header_info(rbd_dev);
+ return rbd_dev_v2_header_info(rbd_dev, header, first_time);
}
/*
@@ -6734,60 +6680,49 @@ out:
*/
static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
{
- struct rbd_image_header *header;
-
rbd_dev_parent_put(rbd_dev);
rbd_object_map_free(rbd_dev);
rbd_dev_mapping_clear(rbd_dev);
/* Free dynamic fields from the header, then zero it out */
- header = &rbd_dev->header;
- ceph_put_snap_context(header->snapc);
- kfree(header->snap_sizes);
- kfree(header->snap_names);
- kfree(header->object_prefix);
- memset(header, 0, sizeof (*header));
+ rbd_image_header_cleanup(&rbd_dev->header);
}
-static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header)
{
int ret;
- ret = rbd_dev_v2_object_prefix(rbd_dev);
+ ret = rbd_dev_v2_object_prefix(rbd_dev, &header->object_prefix);
if (ret)
- goto out_err;
+ return ret;
/*
* Get the and check features for the image. Currently the
* features are assumed to never change.
*/
- ret = rbd_dev_v2_features(rbd_dev);
+ ret = _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP,
+ rbd_is_ro(rbd_dev), &header->features);
if (ret)
- goto out_err;
+ return ret;
/* If the image supports fancy striping, get its parameters */
- if (rbd_dev->header.features & RBD_FEATURE_STRIPINGV2) {
- ret = rbd_dev_v2_striping_info(rbd_dev);
- if (ret < 0)
- goto out_err;
+ if (header->features & RBD_FEATURE_STRIPINGV2) {
+ ret = rbd_dev_v2_striping_info(rbd_dev, &header->stripe_unit,
+ &header->stripe_count);
+ if (ret)
+ return ret;
}
- if (rbd_dev->header.features & RBD_FEATURE_DATA_POOL) {
- ret = rbd_dev_v2_data_pool(rbd_dev);
+ if (header->features & RBD_FEATURE_DATA_POOL) {
+ ret = rbd_dev_v2_data_pool(rbd_dev, &header->data_pool_id);
if (ret)
- goto out_err;
+ return ret;
}
- rbd_init_layout(rbd_dev);
return 0;
-
-out_err:
- rbd_dev->header.features = 0;
- kfree(rbd_dev->header.object_prefix);
- rbd_dev->header.object_prefix = NULL;
- return ret;
}
/*
@@ -6982,13 +6917,15 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
if (!depth)
down_write(&rbd_dev->header_rwsem);
- ret = rbd_dev_header_info(rbd_dev);
+ ret = rbd_dev_header_info(rbd_dev, &rbd_dev->header, true);
if (ret) {
if (ret == -ENOENT && !need_watch)
rbd_print_dne(rbd_dev, false);
goto err_out_probe;
}
+ rbd_init_layout(rbd_dev);
+
/*
* If this image is the one being mapped, we have pool name and
* id, image name and id, and snap name - need to fill snap id.
@@ -7017,7 +6954,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
}
if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
- ret = rbd_dev_v2_parent_info(rbd_dev);
+ ret = rbd_dev_setup_parent(rbd_dev);
if (ret)
goto err_out_probe;
}
@@ -7043,6 +6980,107 @@ err_out_format:
return ret;
}
+static void rbd_dev_update_header(struct rbd_device *rbd_dev,
+ struct rbd_image_header *header)
+{
+ rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
+ rbd_assert(rbd_dev->header.object_prefix); /* !first_time */
+
+ if (rbd_dev->header.image_size != header->image_size) {
+ rbd_dev->header.image_size = header->image_size;
+
+ if (!rbd_is_snap(rbd_dev)) {
+ rbd_dev->mapping.size = header->image_size;
+ rbd_dev_update_size(rbd_dev);
+ }
+ }
+
+ ceph_put_snap_context(rbd_dev->header.snapc);
+ rbd_dev->header.snapc = header->snapc;
+ header->snapc = NULL;
+
+ if (rbd_dev->image_format == 1) {
+ kfree(rbd_dev->header.snap_names);
+ rbd_dev->header.snap_names = header->snap_names;
+ header->snap_names = NULL;
+
+ kfree(rbd_dev->header.snap_sizes);
+ rbd_dev->header.snap_sizes = header->snap_sizes;
+ header->snap_sizes = NULL;
+ }
+}
+
+static void rbd_dev_update_parent(struct rbd_device *rbd_dev,
+ struct parent_image_info *pii)
+{
+ if (pii->pool_id == CEPH_NOPOOL || !pii->has_overlap) {
+ /*
+ * Either the parent never existed, or we have
+ * record of it but the image got flattened so it no
+ * longer has a parent. When the parent of a
+ * layered image disappears we immediately set the
+ * overlap to 0. The effect of this is that all new
+ * requests will be treated as if the image had no
+ * parent.
+ *
+ * If !pii.has_overlap, the parent image spec is not
+ * applicable. It's there to avoid duplication in each
+ * snapshot record.
+ */
+ if (rbd_dev->parent_overlap) {
+ rbd_dev->parent_overlap = 0;
+ rbd_dev_parent_put(rbd_dev);
+ pr_info("%s: clone has been flattened\n",
+ rbd_dev->disk->disk_name);
+ }
+ } else {
+ rbd_assert(rbd_dev->parent_spec);
+
+ /*
+ * Update the parent overlap. If it became zero, issue
+ * a warning as we will proceed as if there is no parent.
+ */
+ if (!pii->overlap && rbd_dev->parent_overlap)
+ rbd_warn(rbd_dev,
+ "clone has become standalone (overlap 0)");
+ rbd_dev->parent_overlap = pii->overlap;
+ }
+}
+
+static int rbd_dev_refresh(struct rbd_device *rbd_dev)
+{
+ struct rbd_image_header header = { 0 };
+ struct parent_image_info pii = { 0 };
+ int ret;
+
+ dout("%s rbd_dev %p\n", __func__, rbd_dev);
+
+ ret = rbd_dev_header_info(rbd_dev, &header, false);
+ if (ret)
+ goto out;
+
+ /*
+ * If there is a parent, see if it has disappeared due to the
+ * mapped image getting flattened.
+ */
+ if (rbd_dev->parent) {
+ ret = rbd_dev_v2_parent_info(rbd_dev, &pii);
+ if (ret)
+ goto out;
+ }
+
+ down_write(&rbd_dev->header_rwsem);
+ rbd_dev_update_header(rbd_dev, &header);
+ if (rbd_dev->parent)
+ rbd_dev_update_parent(rbd_dev, &pii);
+ up_write(&rbd_dev->header_rwsem);
+
+out:
+ rbd_parent_info_cleanup(&pii);
+ rbd_image_header_cleanup(&header);
+ return ret;
+}
+
static ssize_t do_rbd_add(const char *buf, size_t count)
{
struct rbd_device *rbd_dev = NULL;
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index eb4e7bee1e20..d57bc066dce6 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -38,6 +38,7 @@ enum sysc_soc {
SOC_2420,
SOC_2430,
SOC_3430,
+ SOC_AM35,
SOC_3630,
SOC_4430,
SOC_4460,
@@ -1097,6 +1098,11 @@ static int sysc_enable_module(struct device *dev)
if (ddata->cfg.quirks & (SYSC_QUIRK_SWSUP_SIDLE |
SYSC_QUIRK_SWSUP_SIDLE_ACT)) {
best_mode = SYSC_IDLE_NO;
+
+ /* Clear WAKEUP */
+ if (regbits->enwkup_shift >= 0 &&
+ ddata->cfg.sysc_val & BIT(regbits->enwkup_shift))
+ reg &= ~BIT(regbits->enwkup_shift);
} else {
best_mode = fls(ddata->cfg.sidlemodes) - 1;
if (best_mode > SYSC_IDLE_MASK) {
@@ -1224,6 +1230,13 @@ set_sidle:
}
}
+ if (ddata->cfg.quirks & SYSC_QUIRK_SWSUP_SIDLE_ACT) {
+ /* Set WAKEUP */
+ if (regbits->enwkup_shift >= 0 &&
+ ddata->cfg.sysc_val & BIT(regbits->enwkup_shift))
+ reg |= BIT(regbits->enwkup_shift);
+ }
+
reg &= ~(SYSC_IDLE_MASK << regbits->sidle_shift);
reg |= best_mode << regbits->sidle_shift;
if (regbits->autoidle_shift >= 0 &&
@@ -1518,16 +1531,16 @@ struct sysc_revision_quirk {
static const struct sysc_revision_quirk sysc_revision_quirks[] = {
/* These drivers need to be fixed to not use pm_runtime_irq_safe() */
SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000046, 0xffffffff,
- SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
+ SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff,
- SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
+ SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
/* Uarts on omap4 and later */
SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff,
- SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
+ SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff,
- SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
+ SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47424e03, 0xffffffff,
- SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE),
+ SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE),
/* Quirks that need to be set based on the module address */
SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff,
@@ -1862,7 +1875,7 @@ static void sysc_pre_reset_quirk_dss(struct sysc *ddata)
dev_warn(ddata->dev, "%s: timed out %08x !+ %08x\n",
__func__, val, irq_mask);
- if (sysc_soc->soc == SOC_3430) {
+ if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) {
/* Clear DSS_SDI_CONTROL */
sysc_write(ddata, 0x44, 0);
@@ -2150,8 +2163,7 @@ static int sysc_reset(struct sysc *ddata)
}
if (ddata->cfg.srst_udelay)
- usleep_range(ddata->cfg.srst_udelay,
- ddata->cfg.srst_udelay * 2);
+ fsleep(ddata->cfg.srst_udelay);
if (ddata->post_reset_quirk)
ddata->post_reset_quirk(ddata);
@@ -3025,6 +3037,7 @@ static void ti_sysc_idle(struct work_struct *work)
static const struct soc_device_attribute sysc_soc_match[] = {
SOC_FLAG("OMAP242*", SOC_2420),
SOC_FLAG("OMAP243*", SOC_2430),
+ SOC_FLAG("AM35*", SOC_AM35),
SOC_FLAG("OMAP3[45]*", SOC_3430),
SOC_FLAG("OMAP3[67]*", SOC_3630),
SOC_FLAG("OMAP443*", SOC_4430),
@@ -3229,7 +3242,7 @@ static int sysc_check_active_timer(struct sysc *ddata)
* can be dropped if we stop supporting old beagleboard revisions
* A to B4 at some point.
*/
- if (sysc_soc->soc == SOC_3430)
+ if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35)
error = -ENXIO;
else
error = -EBUSY;
diff --git a/drivers/clk/clk-si521xx.c b/drivers/clk/clk-si521xx.c
index 4eaf1b53f06b..ef4ba467e747 100644
--- a/drivers/clk/clk-si521xx.c
+++ b/drivers/clk/clk-si521xx.c
@@ -96,7 +96,7 @@ static int si521xx_regmap_i2c_write(void *context, unsigned int reg,
unsigned int val)
{
struct i2c_client *i2c = context;
- const u8 data[3] = { reg, 1, val };
+ const u8 data[2] = { reg, val };
const int count = ARRAY_SIZE(data);
int ret;
@@ -146,7 +146,7 @@ static int si521xx_regmap_i2c_read(void *context, unsigned int reg,
static const struct regmap_config si521xx_regmap_config = {
.reg_bits = 8,
.val_bits = 8,
- .cache_type = REGCACHE_NONE,
+ .cache_type = REGCACHE_FLAT,
.max_register = SI521XX_REG_DA,
.rd_table = &si521xx_readable_table,
.wr_table = &si521xx_writeable_table,
@@ -281,9 +281,10 @@ static int si521xx_probe(struct i2c_client *client)
{
const u16 chip_info = (u16)(uintptr_t)device_get_match_data(&client->dev);
const struct clk_parent_data clk_parent_data = { .index = 0 };
- struct si521xx *si;
+ const u8 data[3] = { SI521XX_REG_BC, 1, 1 };
unsigned char name[6] = "DIFF0";
struct clk_init_data init = {};
+ struct si521xx *si;
int i, ret;
if (!chip_info)
@@ -308,7 +309,7 @@ static int si521xx_probe(struct i2c_client *client)
"Failed to allocate register map\n");
/* Always read back 1 Byte via I2C */
- ret = regmap_write(si->regmap, SI521XX_REG_BC, 1);
+ ret = i2c_master_send(client, data, ARRAY_SIZE(data));
if (ret < 0)
return ret;
diff --git a/drivers/clk/clk-versaclock3.c b/drivers/clk/clk-versaclock3.c
index 7ab2447bd203..3d7de355f8f6 100644
--- a/drivers/clk/clk-versaclock3.c
+++ b/drivers/clk/clk-versaclock3.c
@@ -118,21 +118,21 @@ enum vc3_div {
VC3_DIV5,
};
-enum vc3_clk_mux {
- VC3_DIFF2_MUX,
- VC3_DIFF1_MUX,
- VC3_SE3_MUX,
- VC3_SE2_MUX,
- VC3_SE1_MUX,
-};
-
enum vc3_clk {
- VC3_DIFF2,
- VC3_DIFF1,
- VC3_SE3,
- VC3_SE2,
- VC3_SE1,
VC3_REF,
+ VC3_SE1,
+ VC3_SE2,
+ VC3_SE3,
+ VC3_DIFF1,
+ VC3_DIFF2,
+};
+
+enum vc3_clk_mux {
+ VC3_SE1_MUX = VC3_SE1 - 1,
+ VC3_SE2_MUX = VC3_SE2 - 1,
+ VC3_SE3_MUX = VC3_SE3 - 1,
+ VC3_DIFF1_MUX = VC3_DIFF1 - 1,
+ VC3_DIFF2_MUX = VC3_DIFF2 - 1,
};
struct vc3_clk_data {
@@ -401,11 +401,10 @@ static long vc3_pll_round_rate(struct clk_hw *hw, unsigned long rate,
/* Determine best fractional part, which is 16 bit wide */
div_frc = rate % *parent_rate;
div_frc *= BIT(16) - 1;
- do_div(div_frc, *parent_rate);
- vc3->div_frc = (u32)div_frc;
+ vc3->div_frc = min_t(u64, div64_ul(div_frc, *parent_rate), U16_MAX);
rate = (*parent_rate *
- (vc3->div_int * VC3_2_POW_16 + div_frc) / VC3_2_POW_16);
+ (vc3->div_int * VC3_2_POW_16 + vc3->div_frc) / VC3_2_POW_16);
} else {
rate = *parent_rate * vc3->div_int;
}
@@ -897,33 +896,33 @@ static struct vc3_hw_data clk_div[] = {
};
static struct vc3_hw_data clk_mux[] = {
- [VC3_DIFF2_MUX] = {
+ [VC3_SE1_MUX] = {
.data = &(struct vc3_clk_data) {
- .offs = VC3_DIFF2_CTRL_REG,
- .bitmsk = VC3_DIFF2_CTRL_REG_DIFF2_CLK_SEL
+ .offs = VC3_SE1_DIV4_CTRL,
+ .bitmsk = VC3_SE1_DIV4_CTRL_SE1_CLK_SEL
},
.hw.init = &(struct clk_init_data){
- .name = "diff2_mux",
+ .name = "se1_mux",
.ops = &vc3_clk_mux_ops,
.parent_hws = (const struct clk_hw *[]) {
- &clk_div[VC3_DIV1].hw,
- &clk_div[VC3_DIV3].hw
+ &clk_div[VC3_DIV5].hw,
+ &clk_div[VC3_DIV4].hw
},
.num_parents = 2,
.flags = CLK_SET_RATE_PARENT
}
},
- [VC3_DIFF1_MUX] = {
+ [VC3_SE2_MUX] = {
.data = &(struct vc3_clk_data) {
- .offs = VC3_DIFF1_CTRL_REG,
- .bitmsk = VC3_DIFF1_CTRL_REG_DIFF1_CLK_SEL
+ .offs = VC3_SE2_CTRL_REG0,
+ .bitmsk = VC3_SE2_CTRL_REG0_SE2_CLK_SEL
},
.hw.init = &(struct clk_init_data){
- .name = "diff1_mux",
+ .name = "se2_mux",
.ops = &vc3_clk_mux_ops,
.parent_hws = (const struct clk_hw *[]) {
- &clk_div[VC3_DIV1].hw,
- &clk_div[VC3_DIV3].hw
+ &clk_div[VC3_DIV5].hw,
+ &clk_div[VC3_DIV4].hw
},
.num_parents = 2,
.flags = CLK_SET_RATE_PARENT
@@ -945,33 +944,33 @@ static struct vc3_hw_data clk_mux[] = {
.flags = CLK_SET_RATE_PARENT
}
},
- [VC3_SE2_MUX] = {
+ [VC3_DIFF1_MUX] = {
.data = &(struct vc3_clk_data) {
- .offs = VC3_SE2_CTRL_REG0,
- .bitmsk = VC3_SE2_CTRL_REG0_SE2_CLK_SEL
+ .offs = VC3_DIFF1_CTRL_REG,
+ .bitmsk = VC3_DIFF1_CTRL_REG_DIFF1_CLK_SEL
},
.hw.init = &(struct clk_init_data){
- .name = "se2_mux",
+ .name = "diff1_mux",
.ops = &vc3_clk_mux_ops,
.parent_hws = (const struct clk_hw *[]) {
- &clk_div[VC3_DIV5].hw,
- &clk_div[VC3_DIV4].hw
+ &clk_div[VC3_DIV1].hw,
+ &clk_div[VC3_DIV3].hw
},
.num_parents = 2,
.flags = CLK_SET_RATE_PARENT
}
},
- [VC3_SE1_MUX] = {
+ [VC3_DIFF2_MUX] = {
.data = &(struct vc3_clk_data) {
- .offs = VC3_SE1_DIV4_CTRL,
- .bitmsk = VC3_SE1_DIV4_CTRL_SE1_CLK_SEL
+ .offs = VC3_DIFF2_CTRL_REG,
+ .bitmsk = VC3_DIFF2_CTRL_REG_DIFF2_CLK_SEL
},
.hw.init = &(struct clk_init_data){
- .name = "se1_mux",
+ .name = "diff2_mux",
.ops = &vc3_clk_mux_ops,
.parent_hws = (const struct clk_hw *[]) {
- &clk_div[VC3_DIV5].hw,
- &clk_div[VC3_DIV4].hw
+ &clk_div[VC3_DIV1].hw,
+ &clk_div[VC3_DIV3].hw
},
.num_parents = 2,
.flags = CLK_SET_RATE_PARENT
@@ -1110,7 +1109,7 @@ static int vc3_probe(struct i2c_client *client)
name, 0, CLK_SET_RATE_PARENT, 1, 1);
else
clk_out[i] = devm_clk_hw_register_fixed_factor_parent_hw(dev,
- name, &clk_mux[i].hw, CLK_SET_RATE_PARENT, 1, 1);
+ name, &clk_mux[i - 1].hw, CLK_SET_RATE_PARENT, 1, 1);
if (IS_ERR(clk_out[i]))
return PTR_ERR(clk_out[i]);
diff --git a/drivers/clk/sprd/ums512-clk.c b/drivers/clk/sprd/ums512-clk.c
index 8f4441dd572b..9384ecc6c741 100644
--- a/drivers/clk/sprd/ums512-clk.c
+++ b/drivers/clk/sprd/ums512-clk.c
@@ -800,7 +800,7 @@ static SPRD_MUX_CLK_DATA(uart1_clk, "uart1-clk", uart_parents,
0x250, 0, 3, UMS512_MUX_FLAG);
static const struct clk_parent_data thm_parents[] = {
- { .fw_name = "ext-32m" },
+ { .fw_name = "ext-32k" },
{ .hw = &clk_250k.hw },
};
static SPRD_MUX_CLK_DATA(thm0_clk, "thm0-clk", thm_parents,
diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c
index a9f3fb448de6..7bfba0afd778 100644
--- a/drivers/clk/tegra/clk-bpmp.c
+++ b/drivers/clk/tegra/clk-bpmp.c
@@ -159,7 +159,7 @@ static unsigned long tegra_bpmp_clk_recalc_rate(struct clk_hw *hw,
err = tegra_bpmp_clk_transfer(clk->bpmp, &msg);
if (err < 0)
- return err;
+ return 0;
return response.rate;
}
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 26db5b8dfc1e..749868b9e80d 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -81,7 +81,8 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device "
*
* - power condition
* Set the power condition field in the START STOP UNIT commands sent by
- * sd_mod on suspend, resume, and shutdown (if manage_start_stop is on).
+ * sd_mod on suspend, resume, and shutdown (if manage_system_start_stop or
+ * manage_runtime_start_stop is on).
* Some disks need this to spin down or to resume properly.
*
* - override internal blacklist
@@ -1517,8 +1518,10 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
sdev->use_10_for_rw = 1;
- if (sbp2_param_exclusive_login)
- sdev->manage_start_stop = 1;
+ if (sbp2_param_exclusive_login) {
+ sdev->manage_system_start_stop = true;
+ sdev->manage_runtime_start_stop = true;
+ }
if (sdev->type == TYPE_ROM)
sdev->use_10_for_ms = 1;
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 2109cd178ff7..121f4fc903cd 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -397,6 +397,19 @@ static u32 ffa_get_num_pages_sg(struct scatterlist *sg)
return num_pages;
}
+static u8 ffa_memory_attributes_get(u32 func_id)
+{
+ /*
+ * For the memory lend or donate operation, if the receiver is a PE or
+ * a proxy endpoint, the owner/sender must not specify the attributes
+ */
+ if (func_id == FFA_FN_NATIVE(MEM_LEND) ||
+ func_id == FFA_MEM_LEND)
+ return 0;
+
+ return FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | FFA_MEM_INNER_SHAREABLE;
+}
+
static int
ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize,
struct ffa_mem_ops_args *args)
@@ -413,8 +426,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize,
mem_region->tag = args->tag;
mem_region->flags = args->flags;
mem_region->sender_id = drv_info->vm_id;
- mem_region->attributes = FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK |
- FFA_MEM_INNER_SHAREABLE;
+ mem_region->attributes = ffa_memory_attributes_get(func_id);
ep_mem_access = &mem_region->ep_mem_access[0];
for (idx = 0; idx < args->nattrs; idx++, ep_mem_access++) {
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index c0cd556fbaae..30dedd6ebfde 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -1080,6 +1080,8 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph)
if (!pinfo)
return -ENOMEM;
+ pinfo->version = version;
+
ret = scmi_perf_attributes_get(ph, pinfo);
if (ret)
return ret;
@@ -1104,8 +1106,6 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph)
if (ret)
return ret;
- pinfo->version = version;
-
return ph->set_priv(ph, pinfo);
}
diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c
index 3dba590a2a95..508eab346fc6 100644
--- a/drivers/firmware/imx/imx-dsp.c
+++ b/drivers/firmware/imx/imx-dsp.c
@@ -114,6 +114,7 @@ static int imx_dsp_setup_channels(struct imx_dsp_ipc *dsp_ipc)
dsp_chan->idx = i % 2;
dsp_chan->ch = mbox_request_channel_byname(cl, chan_name);
if (IS_ERR(dsp_chan->ch)) {
+ kfree(dsp_chan->name);
ret = PTR_ERR(dsp_chan->ch);
if (ret != -EPROBE_DEFER)
dev_err(dev, "Failed to request mbox chan %s ret %d\n",
diff --git a/drivers/gpio/gpio-pmic-eic-sprd.c b/drivers/gpio/gpio-pmic-eic-sprd.c
index 2b9b7be9b8fd..01c0fd0a9d8c 100644
--- a/drivers/gpio/gpio-pmic-eic-sprd.c
+++ b/drivers/gpio/gpio-pmic-eic-sprd.c
@@ -352,6 +352,7 @@ static int sprd_pmic_eic_probe(struct platform_device *pdev)
pmic_eic->chip.set_config = sprd_pmic_eic_set_config;
pmic_eic->chip.set = sprd_pmic_eic_set;
pmic_eic->chip.get = sprd_pmic_eic_get;
+ pmic_eic->chip.can_sleep = true;
irq = &pmic_eic->chip.irq;
gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip);
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index bbd9e9191199..fad979797486 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -43,9 +43,10 @@ static int timbgpio_update_bit(struct gpio_chip *gpio, unsigned index,
unsigned offset, bool enabled)
{
struct timbgpio *tgpio = gpiochip_get_data(gpio);
+ unsigned long flags;
u32 reg;
- spin_lock(&tgpio->lock);
+ spin_lock_irqsave(&tgpio->lock, flags);
reg = ioread32(tgpio->membase + offset);
if (enabled)
@@ -54,7 +55,7 @@ static int timbgpio_update_bit(struct gpio_chip *gpio, unsigned index,
reg &= ~(1 << index);
iowrite32(reg, tgpio->membase + offset);
- spin_unlock(&tgpio->lock);
+ spin_unlock_irqrestore(&tgpio->lock, flags);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 8f1633c3fb93..73a4a4eb29e0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -100,6 +100,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
st->nents = 0;
for (i = 0; i < page_count; i++) {
struct folio *folio;
+ unsigned long nr_pages;
const unsigned int shrink[] = {
I915_SHRINK_BOUND | I915_SHRINK_UNBOUND,
0,
@@ -150,6 +151,8 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
}
} while (1);
+ nr_pages = min_t(unsigned long,
+ folio_nr_pages(folio), page_count - i);
if (!i ||
sg->length >= max_segment ||
folio_pfn(folio) != next_pfn) {
@@ -157,13 +160,13 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
sg = sg_next(sg);
st->nents++;
- sg_set_folio(sg, folio, folio_size(folio), 0);
+ sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0);
} else {
/* XXX: could overflow? */
- sg->length += folio_size(folio);
+ sg->length += nr_pages * PAGE_SIZE;
}
- next_pfn = folio_pfn(folio) + folio_nr_pages(folio);
- i += folio_nr_pages(folio) - 1;
+ next_pfn = folio_pfn(folio) + nr_pages;
+ i += nr_pages - 1;
/* Check that the i965g/gm workaround works. */
GEM_BUG_ON(gfp & __GFP_DMA32 && next_pfn >= 0x00100000UL);
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index dd0ed941441a..da21f2786b5d 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -511,20 +511,31 @@ void intel_ggtt_unbind_vma(struct i915_address_space *vm,
vm->clear_range(vm, vma_res->start, vma_res->vma_size);
}
+/*
+ * Reserve the top of the GuC address space for firmware images. Addresses
+ * beyond GUC_GGTT_TOP in the GuC address space are inaccessible by GuC,
+ * which makes for a suitable range to hold GuC/HuC firmware images if the
+ * size of the GGTT is 4G. However, on a 32-bit platform the size of the GGTT
+ * is limited to 2G, which is less than GUC_GGTT_TOP, but we reserve a chunk
+ * of the same size anyway, which is far more than needed, to keep the logic
+ * in uc_fw_ggtt_offset() simple.
+ */
+#define GUC_TOP_RESERVE_SIZE (SZ_4G - GUC_GGTT_TOP)
+
static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
{
- u64 size;
+ u64 offset;
int ret;
if (!intel_uc_uses_guc(&ggtt->vm.gt->uc))
return 0;
- GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
- size = ggtt->vm.total - GUC_GGTT_TOP;
+ GEM_BUG_ON(ggtt->vm.total <= GUC_TOP_RESERVE_SIZE);
+ offset = ggtt->vm.total - GUC_TOP_RESERVE_SIZE;
- ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, size,
- GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
- PIN_NOEVICT);
+ ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw,
+ GUC_TOP_RESERVE_SIZE, offset,
+ I915_COLOR_UNEVICTABLE, PIN_NOEVICT);
if (ret)
drm_dbg(&ggtt->vm.i915->drm,
"Failed to reserve top of GGTT for GuC\n");
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index b5b7f2fe8c78..dc7b40e06e38 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1433,6 +1433,36 @@ static void guc_timestamp_ping(struct work_struct *wrk)
int srcu, ret;
/*
+ * Ideally the busyness worker should take a gt pm wakeref because the
+ * worker only needs to be active while gt is awake. However, the
+ * gt_park path cancels the worker synchronously and this complicates
+ * the flow if the worker is also running at the same time. The cancel
+ * waits for the worker and when the worker releases the wakeref, that
+ * would call gt_park and would lead to a deadlock.
+ *
+ * The resolution is to take the global pm wakeref if runtime pm is
+ * already active. If not, we don't need to update the busyness stats as
+ * the stats would already be updated when the gt was parked.
+ *
+ * Note:
+ * - We do not requeue the worker if we cannot take a reference to runtime
+ * pm since intel_guc_busyness_unpark would requeue the worker in the
+ * resume path.
+ *
+ * - If the gt was parked longer than time taken for GT timestamp to roll
+ * over, we ignore those rollovers since we don't care about tracking
+ * the exact GT time. We only care about roll overs when the gt is
+ * active and running workloads.
+ *
+ * - There is a window of time between gt_park and runtime suspend,
+ * where the worker may run. This is acceptable since the worker will
+ * not find any new data to update busyness.
+ */
+ wakeref = intel_runtime_pm_get_if_active(&gt->i915->runtime_pm);
+ if (!wakeref)
+ return;
+
+ /*
* Synchronize with gt reset to make sure the worker does not
* corrupt the engine/guc stats. NB: can't actually block waiting
* for a reset to complete as the reset requires flushing out
@@ -1440,10 +1470,9 @@ static void guc_timestamp_ping(struct work_struct *wrk)
*/
ret = intel_gt_reset_trylock(gt, &srcu);
if (ret)
- return;
+ goto err_trylock;
- with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
- __update_guc_busyness_stats(guc);
+ __update_guc_busyness_stats(guc);
/* adjust context stats for overflow */
xa_for_each(&guc->context_lookup, index, ce)
@@ -1452,6 +1481,9 @@ static void guc_timestamp_ping(struct work_struct *wrk)
intel_gt_reset_unlock(gt, srcu);
guc_enable_busyness_worker(guc);
+
+err_trylock:
+ intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
}
static int guc_action_enable_usage_stats(struct intel_guc *guc)
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 495a8b5f6a2b..ae4bae63ad4f 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -694,6 +694,7 @@ static void npcm_i2c_callback(struct npcm_i2c *bus,
{
struct i2c_msg *msgs;
int msgs_num;
+ bool do_complete = false;
msgs = bus->msgs;
msgs_num = bus->msgs_num;
@@ -722,23 +723,17 @@ static void npcm_i2c_callback(struct npcm_i2c *bus,
msgs[1].flags & I2C_M_RD)
msgs[1].len = info;
}
- if (completion_done(&bus->cmd_complete) == false)
- complete(&bus->cmd_complete);
- break;
-
+ do_complete = true;
+ break;
case I2C_NACK_IND:
/* MASTER transmit got a NACK before tx all bytes */
bus->cmd_err = -ENXIO;
- if (bus->master_or_slave == I2C_MASTER)
- complete(&bus->cmd_complete);
-
+ do_complete = true;
break;
case I2C_BUS_ERR_IND:
/* Bus error */
bus->cmd_err = -EAGAIN;
- if (bus->master_or_slave == I2C_MASTER)
- complete(&bus->cmd_complete);
-
+ do_complete = true;
break;
case I2C_WAKE_UP_IND:
/* I2C wake up */
@@ -752,6 +747,8 @@ static void npcm_i2c_callback(struct npcm_i2c *bus,
if (bus->slave)
bus->master_or_slave = I2C_SLAVE;
#endif
+ if (do_complete)
+ complete(&bus->cmd_complete);
}
static u8 npcm_i2c_fifo_usage(struct npcm_i2c *bus)
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 313904be5f3b..57ff09f18c37 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -341,7 +341,7 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
priv->adap.lock_ops = &i2c_parent_lock_ops;
/* Sanity check on class */
- if (i2c_mux_parent_classes(parent) & class)
+ if (i2c_mux_parent_classes(parent) & class & ~I2C_CLASS_DEPRECATED)
dev_err(&parent->dev,
"Segment %d behind mux can't share classes with ancestors\n",
chan_id);
diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c
index 8c581c985aa7..7f314e58f3ce 100644
--- a/drivers/irqchip/irq-xtensa-mx.c
+++ b/drivers/irqchip/irq-xtensa-mx.c
@@ -12,6 +12,7 @@
#include <linux/irqdomain.h>
#include <linux/irq.h>
#include <linux/irqchip.h>
+#include <linux/irqchip/xtensa-mx.h>
#include <linux/of.h>
#include <asm/mxregs.h>
diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c
index 3dae5e3a1697..cd512284bfb3 100644
--- a/drivers/misc/cardreader/rts5227.c
+++ b/drivers/misc/cardreader/rts5227.c
@@ -83,63 +83,20 @@ static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr)
static void rts5227_init_from_cfg(struct rtsx_pcr *pcr)
{
- struct pci_dev *pdev = pcr->pci;
- int l1ss;
- u32 lval;
struct rtsx_cr_option *option = &pcr->option;
- l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
- if (!l1ss)
- return;
-
- pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
-
if (CHK_PCI_PID(pcr, 0x522A)) {
- if (0 == (lval & 0x0F))
- rtsx_pci_enable_oobs_polling(pcr);
- else
+ if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+ | PM_L1_1_EN | PM_L1_2_EN))
rtsx_pci_disable_oobs_polling(pcr);
+ else
+ rtsx_pci_enable_oobs_polling(pcr);
}
- if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
- rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
- rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
- rtsx_set_dev_flag(pcr, PM_L1_1_EN);
- else
- rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
- rtsx_set_dev_flag(pcr, PM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
-
if (option->ltr_en) {
- u16 val;
-
- pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
- if (val & PCI_EXP_DEVCTL2_LTR_EN) {
- option->ltr_enabled = true;
- option->ltr_active = true;
+ if (option->ltr_enabled)
rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
- } else {
- option->ltr_enabled = false;
- }
}
-
- if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
- | PM_L1_1_EN | PM_L1_2_EN))
- option->force_clkreq_0 = false;
- else
- option->force_clkreq_0 = true;
-
}
static int rts5227_extra_init_hw(struct rtsx_pcr *pcr)
@@ -195,7 +152,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr)
}
}
- if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG)
+ if (option->force_clkreq_0)
rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG,
FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
else
diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c
index f4ab09439da7..0c7f10bcf6f1 100644
--- a/drivers/misc/cardreader/rts5228.c
+++ b/drivers/misc/cardreader/rts5228.c
@@ -386,59 +386,25 @@ static void rts5228_process_ocp(struct rtsx_pcr *pcr)
static void rts5228_init_from_cfg(struct rtsx_pcr *pcr)
{
- struct pci_dev *pdev = pcr->pci;
- int l1ss;
- u32 lval;
struct rtsx_cr_option *option = &pcr->option;
- l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
- if (!l1ss)
- return;
-
- pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
-
- if (0 == (lval & 0x0F))
- rtsx_pci_enable_oobs_polling(pcr);
- else
+ if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+ | PM_L1_1_EN | PM_L1_2_EN))
rtsx_pci_disable_oobs_polling(pcr);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
- rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
- rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
- rtsx_set_dev_flag(pcr, PM_L1_1_EN);
else
- rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
- rtsx_set_dev_flag(pcr, PM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
+ rtsx_pci_enable_oobs_polling(pcr);
rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
- if (option->ltr_en) {
- u16 val;
- pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
- if (val & PCI_EXP_DEVCTL2_LTR_EN) {
- option->ltr_enabled = true;
- option->ltr_active = true;
+ if (option->ltr_en) {
+ if (option->ltr_enabled)
rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
- } else {
- option->ltr_enabled = false;
- }
}
}
static int rts5228_extra_init_hw(struct rtsx_pcr *pcr)
{
+ struct rtsx_cr_option *option = &pcr->option;
rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1,
CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
@@ -469,6 +435,17 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr)
else
rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+ /*
+ * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+ * to drive low, and we forcibly request clock.
+ */
+ if (option->force_clkreq_0)
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+ else
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB);
if (pcr->rtd3_en) {
diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index 47ab72a43256..6c81040e18be 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -86,64 +86,22 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
static void rts5249_init_from_cfg(struct rtsx_pcr *pcr)
{
- struct pci_dev *pdev = pcr->pci;
- int l1ss;
struct rtsx_cr_option *option = &(pcr->option);
- u32 lval;
-
- l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
- if (!l1ss)
- return;
-
- pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) {
- if (0 == (lval & 0x0F))
- rtsx_pci_enable_oobs_polling(pcr);
- else
+ if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+ | PM_L1_1_EN | PM_L1_2_EN))
rtsx_pci_disable_oobs_polling(pcr);
+ else
+ rtsx_pci_enable_oobs_polling(pcr);
}
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
- rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
- rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
- rtsx_set_dev_flag(pcr, PM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
- rtsx_set_dev_flag(pcr, PM_L1_2_EN);
-
if (option->ltr_en) {
- u16 val;
-
- pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
- if (val & PCI_EXP_DEVCTL2_LTR_EN) {
- option->ltr_enabled = true;
- option->ltr_active = true;
+ if (option->ltr_enabled)
rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
- } else {
- option->ltr_enabled = false;
- }
}
}
-static int rts5249_init_from_hw(struct rtsx_pcr *pcr)
-{
- struct rtsx_cr_option *option = &(pcr->option);
-
- if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
- | PM_L1_1_EN | PM_L1_2_EN))
- option->force_clkreq_0 = false;
- else
- option->force_clkreq_0 = true;
-
- return 0;
-}
-
static void rts52xa_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime)
{
/* Set relink_time to 0 */
@@ -276,7 +234,6 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr)
struct rtsx_cr_option *option = &(pcr->option);
rts5249_init_from_cfg(pcr);
- rts5249_init_from_hw(pcr);
rtsx_pci_init_cmd(pcr);
@@ -327,11 +284,12 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr)
}
}
+
/*
* If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
* to drive low, and we forcibly request clock.
*/
- if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG)
+ if (option->force_clkreq_0)
rtsx_pci_write_register(pcr, PETXCFG,
FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
else
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index 79b18f6f73a8..d2d3a6ccb8f7 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -480,47 +480,19 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr)
static void rts5260_init_from_cfg(struct rtsx_pcr *pcr)
{
- struct pci_dev *pdev = pcr->pci;
- int l1ss;
struct rtsx_cr_option *option = &pcr->option;
- u32 lval;
-
- l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
- if (!l1ss)
- return;
-
- pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
- rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
- rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
- rtsx_set_dev_flag(pcr, PM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
- rtsx_set_dev_flag(pcr, PM_L1_2_EN);
rts5260_pwr_saving_setting(pcr);
if (option->ltr_en) {
- u16 val;
-
- pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
- if (val & PCI_EXP_DEVCTL2_LTR_EN) {
- option->ltr_enabled = true;
- option->ltr_active = true;
+ if (option->ltr_enabled)
rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
- } else {
- option->ltr_enabled = false;
- }
}
}
static int rts5260_extra_init_hw(struct rtsx_pcr *pcr)
{
+ struct rtsx_cr_option *option = &pcr->option;
/* Set mcu_cnt to 7 to ensure data can be sampled properly */
rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07);
@@ -539,6 +511,17 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr)
rts5260_init_hw(pcr);
+ /*
+ * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+ * to drive low, and we forcibly request clock.
+ */
+ if (option->force_clkreq_0)
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+ else
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00);
return 0;
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 94af6bf8a25a..67252512a132 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -454,54 +454,17 @@ static void rts5261_init_from_hw(struct rtsx_pcr *pcr)
static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
{
- struct pci_dev *pdev = pcr->pci;
- int l1ss;
- u32 lval;
struct rtsx_cr_option *option = &pcr->option;
- l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
- if (!l1ss)
- return;
-
- pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
- rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
- rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
- rtsx_set_dev_flag(pcr, PM_L1_1_EN);
- else
- rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
-
- if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
- rtsx_set_dev_flag(pcr, PM_L1_2_EN);
- else
- rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
-
- rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
if (option->ltr_en) {
- u16 val;
-
- pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val);
- if (val & PCI_EXP_DEVCTL2_LTR_EN) {
- option->ltr_enabled = true;
- option->ltr_active = true;
+ if (option->ltr_enabled)
rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
- } else {
- option->ltr_enabled = false;
- }
}
}
static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
{
+ struct rtsx_cr_option *option = &pcr->option;
u32 val;
rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1,
@@ -547,6 +510,17 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
else
rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+ /*
+ * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+ * to drive low, and we forcibly request clock.
+ */
+ if (option->force_clkreq_0)
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+ else
+ rtsx_pci_write_register(pcr, PETXCFG,
+ FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB);
if (pcr->rtd3_en) {
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index a3f4b52bb159..a30751ad3733 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1326,11 +1326,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
return err;
}
- if (pcr->aspm_mode == ASPM_MODE_REG) {
+ if (pcr->aspm_mode == ASPM_MODE_REG)
rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30);
- rtsx_pci_write_register(pcr, PETXCFG,
- FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
- }
/* No CD interrupt if probing driver with card inserted.
* So we need to initialize pcr->card_exist here.
@@ -1345,7 +1342,9 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
{
- int err;
+ struct rtsx_cr_option *option = &(pcr->option);
+ int err, l1ss;
+ u32 lval;
u16 cfg_val;
u8 val;
@@ -1430,6 +1429,48 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
pcr->aspm_enabled = true;
}
+ l1ss = pci_find_ext_capability(pcr->pci, PCI_EXT_CAP_ID_L1SS);
+ if (l1ss) {
+ pci_read_config_dword(pcr->pci, l1ss + PCI_L1SS_CTL1, &lval);
+
+ if (lval & PCI_L1SS_CTL1_ASPM_L1_1)
+ rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
+ else
+ rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
+
+ if (lval & PCI_L1SS_CTL1_ASPM_L1_2)
+ rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
+ else
+ rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
+
+ if (lval & PCI_L1SS_CTL1_PCIPM_L1_1)
+ rtsx_set_dev_flag(pcr, PM_L1_1_EN);
+ else
+ rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
+
+ if (lval & PCI_L1SS_CTL1_PCIPM_L1_2)
+ rtsx_set_dev_flag(pcr, PM_L1_2_EN);
+ else
+ rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
+
+ pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &cfg_val);
+ if (cfg_val & PCI_EXP_DEVCTL2_LTR_EN) {
+ option->ltr_enabled = true;
+ option->ltr_active = true;
+ } else {
+ option->ltr_enabled = false;
+ }
+
+ if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+ | PM_L1_1_EN | PM_L1_2_EN))
+ option->force_clkreq_0 = false;
+ else
+ option->force_clkreq_0 = true;
+ } else {
+ option->ltr_enabled = false;
+ option->force_clkreq_0 = true;
+ }
+
if (pcr->ops->fetch_vendor_settings)
pcr->ops->fetch_vendor_settings(pcr);
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 59e1ebb7842e..411e00b255d6 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -300,7 +300,7 @@ config NVMEM_REBOOT_MODE
config POWER_MLXBF
tristate "Mellanox BlueField power handling driver"
- depends on (GPIO_MLXBF2 && ACPI)
+ depends on (GPIO_MLXBF2 || GPIO_MLXBF3) && ACPI
help
This driver supports reset or low power mode handling for Mellanox BlueField.
diff --git a/drivers/power/reset/pwr-mlxbf.c b/drivers/power/reset/pwr-mlxbf.c
index 12dedf841a44..de35d24bb7ef 100644
--- a/drivers/power/reset/pwr-mlxbf.c
+++ b/drivers/power/reset/pwr-mlxbf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only or BSD-3-Clause
+// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause
/*
* Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES.
diff --git a/drivers/power/reset/vexpress-poweroff.c b/drivers/power/reset/vexpress-poweroff.c
index 447ffdacddf9..17064d7b19f6 100644
--- a/drivers/power/reset/vexpress-poweroff.c
+++ b/drivers/power/reset/vexpress-poweroff.c
@@ -121,7 +121,7 @@ static int vexpress_reset_probe(struct platform_device *pdev)
return PTR_ERR(regmap);
dev_set_drvdata(&pdev->dev, regmap);
- switch ((enum vexpress_reset_func)match->data) {
+ switch ((uintptr_t)match->data) {
case FUNC_SHUTDOWN:
vexpress_power_off_device = &pdev->dev;
pm_power_off = vexpress_power_off;
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 663a1c423806..a61bb1283e19 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -769,6 +769,7 @@ config BATTERY_RT5033
config CHARGER_RT5033
tristate "RT5033 battery charger support"
depends on MFD_RT5033
+ depends on EXTCON || !EXTCON
help
This adds support for battery charger in Richtek RT5033 PMIC.
The device supports pre-charge mode, fast charge mode and
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 6f83e99d2eb7..ce36d6ca3422 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -115,7 +115,6 @@ struct ab8500_btemp {
static enum power_supply_property ab8500_btemp_props[] = {
POWER_SUPPLY_PROP_PRESENT,
POWER_SUPPLY_PROP_ONLINE,
- POWER_SUPPLY_PROP_TECHNOLOGY,
POWER_SUPPLY_PROP_TEMP,
};
@@ -532,12 +531,6 @@ static int ab8500_btemp_get_property(struct power_supply *psy,
else
val->intval = 1;
break;
- case POWER_SUPPLY_PROP_TECHNOLOGY:
- if (di->bm->bi)
- val->intval = di->bm->bi->technology;
- else
- val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
- break;
case POWER_SUPPLY_PROP_TEMP:
val->intval = ab8500_btemp_get_temp(di);
break;
@@ -662,7 +655,7 @@ static char *supply_interface[] = {
static const struct power_supply_desc ab8500_btemp_desc = {
.name = "ab8500_btemp",
- .type = POWER_SUPPLY_TYPE_BATTERY,
+ .type = POWER_SUPPLY_TYPE_UNKNOWN,
.properties = ab8500_btemp_props,
.num_properties = ARRAY_SIZE(ab8500_btemp_props),
.get_property = ab8500_btemp_get_property,
diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c
index ea4ad61d4c7e..2205ea0834a6 100644
--- a/drivers/power/supply/ab8500_chargalg.c
+++ b/drivers/power/supply/ab8500_chargalg.c
@@ -1720,7 +1720,7 @@ static char *supply_interface[] = {
static const struct power_supply_desc ab8500_chargalg_desc = {
.name = "ab8500_chargalg",
- .type = POWER_SUPPLY_TYPE_BATTERY,
+ .type = POWER_SUPPLY_TYPE_UNKNOWN,
.properties = ab8500_chargalg_props,
.num_properties = ARRAY_SIZE(ab8500_chargalg_props),
.get_property = ab8500_chargalg_get_property,
diff --git a/drivers/power/supply/mt6370-charger.c b/drivers/power/supply/mt6370-charger.c
index f27dae5043f5..a9641bd3d8cf 100644
--- a/drivers/power/supply/mt6370-charger.c
+++ b/drivers/power/supply/mt6370-charger.c
@@ -324,7 +324,7 @@ static int mt6370_chg_toggle_cfo(struct mt6370_priv *priv)
if (fl_strobe) {
dev_err(priv->dev, "Flash led is still in strobe mode\n");
- return ret;
+ return -EINVAL;
}
/* cfo off */
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 06e5b6b0e255..d483a81560ab 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -482,6 +482,13 @@ int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env)
if (ret)
return ret;
+ /*
+ * Kernel generates KOBJ_REMOVE uevent in device removal path, after
+ * resources have been freed. Exit early to avoid use-after-free.
+ */
+ if (psy->removing)
+ return 0;
+
prop_buf = (char *)get_zeroed_page(GFP_KERNEL);
if (!prop_buf)
return -ENOMEM;
diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c
index 8328bcea1a29..f64daf5a41d9 100644
--- a/drivers/power/supply/rk817_charger.c
+++ b/drivers/power/supply/rk817_charger.c
@@ -1045,6 +1045,13 @@ static void rk817_charging_monitor(struct work_struct *work)
queue_delayed_work(system_wq, &charger->work, msecs_to_jiffies(8000));
}
+static void rk817_cleanup_node(void *data)
+{
+ struct device_node *node = data;
+
+ of_node_put(node);
+}
+
static int rk817_charger_probe(struct platform_device *pdev)
{
struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent);
@@ -1061,11 +1068,13 @@ static int rk817_charger_probe(struct platform_device *pdev)
if (!node)
return -ENODEV;
+ ret = devm_add_action_or_reset(&pdev->dev, rk817_cleanup_node, node);
+ if (ret)
+ return ret;
+
charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL);
- if (!charger) {
- of_node_put(node);
+ if (!charger)
return -ENOMEM;
- }
charger->rk808 = rk808;
@@ -1211,3 +1220,4 @@ MODULE_DESCRIPTION("Battery power supply driver for RK817 PMIC");
MODULE_AUTHOR("Maya Matuszczyk <maccraft123mc@gmail.com>");
MODULE_AUTHOR("Chris Morgan <macromorgan@hotmail.com>");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:rk817-charger");
diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c
index 683adb18253d..fdfdc83ab045 100644
--- a/drivers/power/supply/rt9467-charger.c
+++ b/drivers/power/supply/rt9467-charger.c
@@ -598,8 +598,8 @@ static int rt9467_run_aicl(struct rt9467_chg_data *data)
reinit_completion(&data->aicl_done);
ret = wait_for_completion_timeout(&data->aicl_done, msecs_to_jiffies(3500));
- if (ret)
- return ret;
+ if (ret == 0)
+ return -ETIMEDOUT;
ret = rt9467_get_value_from_ranges(data, F_IAICR, RT9467_RANGE_IAICR, &aicr_get);
if (ret) {
diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c
index 954feba6600b..7970843a4f48 100644
--- a/drivers/power/supply/ucs1002_power.c
+++ b/drivers/power/supply/ucs1002_power.c
@@ -384,7 +384,8 @@ static int ucs1002_get_property(struct power_supply *psy,
case POWER_SUPPLY_PROP_USB_TYPE:
return ucs1002_get_usb_type(info, val);
case POWER_SUPPLY_PROP_HEALTH:
- return val->intval = info->health;
+ val->intval = info->health;
+ return 0;
case POWER_SUPPLY_PROP_PRESENT:
val->intval = info->present;
return 0;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index d0911bc28663..89367c4bf0ef 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -613,6 +613,17 @@ void scsi_cdl_check(struct scsi_device *sdev)
bool cdl_supported;
unsigned char *buf;
+ /*
+ * Support for CDL was defined in SPC-5. Ignore devices reporting an
+ * lower SPC version. This also avoids problems with old drives choking
+ * on MAINTENANCE_IN / MI_REPORT_SUPPORTED_OPERATION_CODES with a
+ * service action specified, as done in scsi_cdl_check_cmd().
+ */
+ if (sdev->scsi_level < SCSI_SPC_5) {
+ sdev->cdl_supported = 0;
+ return;
+ }
+
buf = kmalloc(SCSI_CDL_CHECK_BUF_LEN, GFP_KERNEL);
if (!buf) {
sdev->cdl_supported = 0;
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 52014b2d39e1..902655d75947 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -822,7 +822,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
* device is attached at LUN 0 (SCSI_SCAN_TARGET_PRESENT) so
* non-zero LUNs can be scanned.
*/
- sdev->scsi_level = inq_result[2] & 0x07;
+ sdev->scsi_level = inq_result[2] & 0x0f;
if (sdev->scsi_level >= 2 ||
(sdev->scsi_level == 1 && (inq_result[3] & 0x0f) == 1))
sdev->scsi_level++;
@@ -1619,12 +1619,24 @@ int scsi_add_device(struct Scsi_Host *host, uint channel,
}
EXPORT_SYMBOL(scsi_add_device);
-void scsi_rescan_device(struct scsi_device *sdev)
+int scsi_rescan_device(struct scsi_device *sdev)
{
struct device *dev = &sdev->sdev_gendev;
+ int ret = 0;
device_lock(dev);
+ /*
+ * Bail out if the device is not running. Otherwise, the rescan may
+ * block waiting for commands to be executed, with us holding the
+ * device lock. This can result in a potential deadlock in the power
+ * management core code when system resume is on-going.
+ */
+ if (sdev->sdev_state != SDEV_RUNNING) {
+ ret = -EWOULDBLOCK;
+ goto unlock;
+ }
+
scsi_attach_vpd(sdev);
scsi_cdl_check(sdev);
@@ -1638,7 +1650,11 @@ void scsi_rescan_device(struct scsi_device *sdev)
drv->rescan(dev);
module_put(dev->driver->owner);
}
+
+unlock:
device_unlock(dev);
+
+ return ret;
}
EXPORT_SYMBOL(scsi_rescan_device);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c92a317ba547..83b6a3f3863b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -201,18 +201,32 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
}
static ssize_t
-manage_start_stop_show(struct device *dev, struct device_attribute *attr,
- char *buf)
+manage_start_stop_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
- return sprintf(buf, "%u\n", sdp->manage_start_stop);
+ return sysfs_emit(buf, "%u\n",
+ sdp->manage_system_start_stop &&
+ sdp->manage_runtime_start_stop);
}
+static DEVICE_ATTR_RO(manage_start_stop);
static ssize_t
-manage_start_stop_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+manage_system_start_stop_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+ struct scsi_device *sdp = sdkp->device;
+
+ return sysfs_emit(buf, "%u\n", sdp->manage_system_start_stop);
+}
+
+static ssize_t
+manage_system_start_stop_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
@@ -224,11 +238,42 @@ manage_start_stop_store(struct device *dev, struct device_attribute *attr,
if (kstrtobool(buf, &v))
return -EINVAL;
- sdp->manage_start_stop = v;
+ sdp->manage_system_start_stop = v;
return count;
}
-static DEVICE_ATTR_RW(manage_start_stop);
+static DEVICE_ATTR_RW(manage_system_start_stop);
+
+static ssize_t
+manage_runtime_start_stop_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+ struct scsi_device *sdp = sdkp->device;
+
+ return sysfs_emit(buf, "%u\n", sdp->manage_runtime_start_stop);
+}
+
+static ssize_t
+manage_runtime_start_stop_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+ struct scsi_device *sdp = sdkp->device;
+ bool v;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ if (kstrtobool(buf, &v))
+ return -EINVAL;
+
+ sdp->manage_runtime_start_stop = v;
+
+ return count;
+}
+static DEVICE_ATTR_RW(manage_runtime_start_stop);
static ssize_t
allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -560,6 +605,8 @@ static struct attribute *sd_disk_attrs[] = {
&dev_attr_FUA.attr,
&dev_attr_allow_restart.attr,
&dev_attr_manage_start_stop.attr,
+ &dev_attr_manage_system_start_stop.attr,
+ &dev_attr_manage_runtime_start_stop.attr,
&dev_attr_protection_type.attr,
&dev_attr_protection_mode.attr,
&dev_attr_app_tag_own.attr,
@@ -3694,7 +3741,8 @@ static int sd_remove(struct device *dev)
device_del(&sdkp->disk_dev);
del_gendisk(sdkp->disk);
- sd_shutdown(dev);
+ if (!sdkp->suspended)
+ sd_shutdown(dev);
put_disk(sdkp->disk);
return 0;
@@ -3771,13 +3819,20 @@ static void sd_shutdown(struct device *dev)
sd_sync_cache(sdkp, NULL);
}
- if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
+ if (system_state != SYSTEM_RESTART &&
+ sdkp->device->manage_system_start_stop) {
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
sd_start_stop_device(sdkp, 0);
}
}
-static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
+static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime)
+{
+ return (sdev->manage_system_start_stop && !runtime) ||
+ (sdev->manage_runtime_start_stop && runtime);
+}
+
+static int sd_suspend_common(struct device *dev, bool runtime)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
struct scsi_sense_hdr sshdr;
@@ -3809,15 +3864,18 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
}
}
- if (sdkp->device->manage_start_stop) {
+ if (sd_do_start_stop(sdkp->device, runtime)) {
if (!sdkp->device->silence_suspend)
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
/* an error is not worth aborting a system sleep */
ret = sd_start_stop_device(sdkp, 0);
- if (ignore_stop_errors)
+ if (!runtime)
ret = 0;
}
+ if (!ret)
+ sdkp->suspended = true;
+
return ret;
}
@@ -3826,15 +3884,15 @@ static int sd_suspend_system(struct device *dev)
if (pm_runtime_suspended(dev))
return 0;
- return sd_suspend_common(dev, true);
+ return sd_suspend_common(dev, false);
}
static int sd_suspend_runtime(struct device *dev)
{
- return sd_suspend_common(dev, false);
+ return sd_suspend_common(dev, true);
}
-static int sd_resume(struct device *dev)
+static int sd_resume(struct device *dev, bool runtime)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
int ret = 0;
@@ -3842,16 +3900,21 @@ static int sd_resume(struct device *dev)
if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */
return 0;
- if (!sdkp->device->manage_start_stop)
+ if (!sd_do_start_stop(sdkp->device, runtime)) {
+ sdkp->suspended = false;
return 0;
+ }
if (!sdkp->device->no_start_on_resume) {
sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
ret = sd_start_stop_device(sdkp, 1);
}
- if (!ret)
+ if (!ret) {
opal_unlock_from_suspend(sdkp->opal_dev);
+ sdkp->suspended = false;
+ }
+
return ret;
}
@@ -3860,7 +3923,7 @@ static int sd_resume_system(struct device *dev)
if (pm_runtime_suspended(dev))
return 0;
- return sd_resume(dev);
+ return sd_resume(dev, false);
}
static int sd_resume_runtime(struct device *dev)
@@ -3887,7 +3950,7 @@ static int sd_resume_runtime(struct device *dev)
"Failed to clear sense data\n");
}
- return sd_resume(dev);
+ return sd_resume(dev, true);
}
static const struct dev_pm_ops sd_pm_ops = {
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 5eea762f84d1..409dda5350d1 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -131,6 +131,7 @@ struct scsi_disk {
u8 provisioning_mode;
u8 zeroing_mode;
u8 nr_actuators; /* Number of actuators */
+ bool suspended; /* Disk is suspended (stopped) */
unsigned ATO : 1; /* state of disk ATO bit */
unsigned cache_override : 1; /* temp override of WCE,RCD */
unsigned WCE : 1; /* state of disk WCE bit */
diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c
index 1dcd243df567..ec87d9d878f3 100644
--- a/drivers/soc/imx/soc-imx8m.c
+++ b/drivers/soc/imx/soc-imx8m.c
@@ -100,6 +100,7 @@ static void __init imx8mm_soc_uid(void)
{
void __iomem *ocotp_base;
struct device_node *np;
+ struct clk *clk;
u32 offset = of_machine_is_compatible("fsl,imx8mp") ?
IMX8MP_OCOTP_UID_OFFSET : 0;
@@ -109,11 +110,20 @@ static void __init imx8mm_soc_uid(void)
ocotp_base = of_iomap(np, 0);
WARN_ON(!ocotp_base);
+ clk = of_clk_get_by_name(np, NULL);
+ if (IS_ERR(clk)) {
+ WARN_ON(IS_ERR(clk));
+ return;
+ }
+
+ clk_prepare_enable(clk);
soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset);
soc_uid <<= 32;
soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset);
+ clk_disable_unprepare(clk);
+ clk_put(clk);
iounmap(ocotp_base);
of_node_put(np);
}
diff --git a/drivers/soc/loongson/Kconfig b/drivers/soc/loongson/Kconfig
index 314e13bb3e01..368344943a93 100644
--- a/drivers/soc/loongson/Kconfig
+++ b/drivers/soc/loongson/Kconfig
@@ -20,6 +20,7 @@ config LOONGSON2_GUTS
config LOONGSON2_PM
bool "Loongson-2 SoC Power Management Controller Driver"
depends on LOONGARCH && OF
+ depends on INPUT=y
help
The Loongson-2's power management controller was ACPI, supports ACPI
S2Idle (Suspend To Idle), ACPI S3 (Suspend To RAM), ACPI S4 (Suspend To
diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c
index bace4bc8e03b..9a469779eea7 100644
--- a/drivers/soc/loongson/loongson2_guts.c
+++ b/drivers/soc/loongson/loongson2_guts.c
@@ -70,7 +70,7 @@ static const struct loongson2_soc_die_attr *loongson2_soc_die_match(
if (matches->svr == (svr & matches->mask))
return matches;
matches++;
- };
+ }
return NULL;
}
@@ -94,7 +94,6 @@ static int loongson2_guts_probe(struct platform_device *pdev)
{
struct device_node *root, *np = pdev->dev.of_node;
struct device *dev = &pdev->dev;
- struct resource *res;
const struct loongson2_soc_die_attr *soc_die;
const char *machine;
u32 svr;
@@ -106,8 +105,7 @@ static int loongson2_guts_probe(struct platform_device *pdev)
guts->little_endian = of_property_read_bool(np, "little-endian");
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- guts->regs = ioremap(res->start, res->end - res->start + 1);
+ guts->regs = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(guts->regs))
return PTR_ERR(guts->regs);
diff --git a/drivers/soc/loongson/loongson2_pm.c b/drivers/soc/loongson/loongson2_pm.c
index 796add6e8b63..b8e5e1e3528a 100644
--- a/drivers/soc/loongson/loongson2_pm.c
+++ b/drivers/soc/loongson/loongson2_pm.c
@@ -11,6 +11,7 @@
#include <linux/input.h>
#include <linux/suspend.h>
#include <linux/interrupt.h>
+#include <linux/of_platform.h>
#include <linux/pm_wakeirq.h>
#include <linux/platform_device.h>
#include <asm/bootinfo.h>
@@ -192,12 +193,16 @@ static int loongson2_pm_probe(struct platform_device *pdev)
if (loongson_sysconf.suspend_addr)
suspend_set_ops(&loongson2_suspend_ops);
+ /* Populate children */
+ retval = devm_of_platform_populate(dev);
+ if (retval)
+ dev_err(dev, "Error populating children, reboot and poweroff might not work properly\n");
+
return 0;
}
static const struct of_device_id loongson2_pm_match[] = {
{ .compatible = "loongson,ls2k0500-pmc", },
- { .compatible = "loongson,ls2k1000-pmc", },
{},
};
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index 453a9b37ce78..d239fc5a49cc 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -256,7 +256,6 @@ static int cs42l43_spi_probe(struct platform_device *pdev)
ret = devm_spi_register_controller(priv->dev, priv->ctlr);
if (ret) {
- pm_runtime_disable(priv->dev);
dev_err(priv->dev, "Failed to register SPI controller: %d\n", ret);
}
diff --git a/drivers/spi/spi-gxp.c b/drivers/spi/spi-gxp.c
index fd2fac236bbd..3aff5a166c94 100644
--- a/drivers/spi/spi-gxp.c
+++ b/drivers/spi/spi-gxp.c
@@ -194,7 +194,7 @@ static ssize_t gxp_spi_write(struct gxp_spi_chip *chip, const struct spi_mem_op
return ret;
}
- return write_len;
+ return 0;
}
static int do_gxp_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h
index 72685ee0d53f..6bb5cae09688 100644
--- a/drivers/tee/optee/optee_private.h
+++ b/drivers/tee/optee/optee_private.h
@@ -238,8 +238,6 @@ int optee_notif_send(struct optee *optee, u_int key);
u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
struct tee_param *param);
-int optee_supp_read(struct tee_context *ctx, void __user *buf, size_t len);
-int optee_supp_write(struct tee_context *ctx, void __user *buf, size_t len);
void optee_supp_init(struct optee_supp *supp);
void optee_supp_uninit(struct optee_supp *supp);
void optee_supp_release(struct optee_supp *supp);
diff --git a/drivers/tee/tee_private.h b/drivers/tee/tee_private.h
index 409cadcc1cff..754e11dcb240 100644
--- a/drivers/tee/tee_private.h
+++ b/drivers/tee/tee_private.h
@@ -47,8 +47,6 @@ struct tee_device {
struct tee_shm_pool *pool;
};
-int tee_shm_init(void);
-
int tee_shm_get_fd(struct tee_shm *shm);
bool tee_device_get(struct tee_device *teedev);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index b3550ff9c494..1f3aba607cd5 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -3097,10 +3097,8 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc)
gsm->has_devices = false;
}
for (i = NUM_DLCI - 1; i >= 0; i--)
- if (gsm->dlci[i]) {
+ if (gsm->dlci[i])
gsm_dlci_release(gsm->dlci[i]);
- gsm->dlci[i] = NULL;
- }
mutex_unlock(&gsm->mutex);
/* Now wipe the queues */
tty_ldisc_flush(gsm->tty);
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index fb891b67968f..141627370aab 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1936,7 +1936,10 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
skip_rx = true;
if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) {
- if (irqd_is_wakeup_set(irq_get_irq_data(port->irq)))
+ struct irq_data *d;
+
+ d = irq_get_irq_data(port->irq);
+ if (d && irqd_is_wakeup_set(d))
pm_wakeup_event(tport->tty->dev, 0);
if (!up->dma || handle_rx_dma(up, iir))
status = serial8250_rx_chars(up, status);
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index e4490639d383..9d2738e10c0b 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -233,7 +233,8 @@ int parent_create_sysfs_files(struct mdev_parent *parent)
out_err:
while (--i >= 0)
mdev_type_remove(parent->types[i]);
- return 0;
+ kset_unregister(parent->mdev_types_kset);
+ return ret;
}
static ssize_t remove_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/vfio/pci/pds/Kconfig b/drivers/vfio/pci/pds/Kconfig
index 407b3fd32733..6eceef7b028a 100644
--- a/drivers/vfio/pci/pds/Kconfig
+++ b/drivers/vfio/pci/pds/Kconfig
@@ -3,7 +3,7 @@
config PDS_VFIO_PCI
tristate "VFIO support for PDS PCI devices"
- depends on PDS_CORE
+ depends on PDS_CORE && PCI_IOV
select VFIO_PCI_CORE
help
This provides generic PCI support for PDS devices using the VFIO
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index b46174f5eb09..649b18ee394b 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -162,7 +162,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
pci_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
dev_dbg(&pdev->dev,
"%s: PF %#04x VF %#04x vf_id %d domain %d pds_vfio %p\n",
- __func__, pci_dev_id(pdev->physfn), pci_id, vf_id,
+ __func__, pci_dev_id(pci_physfn(pdev)), pci_id, vf_id,
pci_domain_nr(pdev->bus), pds_vfio);
return 0;
diff --git a/fs/aio.c b/fs/aio.c
index a4c2a6bac72c..f8589caef9c1 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -80,7 +80,7 @@ struct aio_ring {
struct kioctx_table {
struct rcu_head rcu;
unsigned nr;
- struct kioctx __rcu *table[];
+ struct kioctx __rcu *table[] __counted_by(nr);
};
struct kioctx_cpu {
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 43b2a2851ba3..206812ce544a 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -345,10 +345,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
/* there's now no turning back... the old userspace image is dead,
* defunct, deceased, etc.
*/
+ SET_PERSONALITY(exec_params.hdr);
if (elf_check_fdpic(&exec_params.hdr))
- set_personality(PER_LINUX_FDPIC);
- else
- set_personality(PER_LINUX);
+ current->personality |= PER_LINUX_FDPIC;
if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 6a13cf00218b..9fe4ccca50a0 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -103,24 +103,17 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
* Transfer bytes to our delayed refs rsv.
*
* @fs_info: the filesystem
- * @src: source block rsv to transfer from
* @num_bytes: number of bytes to transfer
*
- * This transfers up to the num_bytes amount from the src rsv to the
+ * This transfers up to the num_bytes amount, previously reserved, to the
* delayed_refs_rsv. Any extra bytes are returned to the space info.
*/
void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *src,
u64 num_bytes)
{
struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
u64 to_free = 0;
- spin_lock(&src->lock);
- src->reserved -= num_bytes;
- src->size -= num_bytes;
- spin_unlock(&src->lock);
-
spin_lock(&delayed_refs_rsv->lock);
if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) {
u64 delta = delayed_refs_rsv->size -
@@ -163,6 +156,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1);
u64 num_bytes = 0;
+ u64 refilled_bytes;
+ u64 to_free;
int ret = -ENOSPC;
spin_lock(&block_rsv->lock);
@@ -178,9 +173,38 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, num_bytes, flush);
if (ret)
return ret;
- btrfs_block_rsv_add_bytes(block_rsv, num_bytes, false);
- trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
- 0, num_bytes, 1);
+
+ /*
+ * We may have raced with someone else, so check again if we the block
+ * reserve is still not full and release any excess space.
+ */
+ spin_lock(&block_rsv->lock);
+ if (block_rsv->reserved < block_rsv->size) {
+ u64 needed = block_rsv->size - block_rsv->reserved;
+
+ if (num_bytes >= needed) {
+ block_rsv->reserved += needed;
+ block_rsv->full = true;
+ to_free = num_bytes - needed;
+ refilled_bytes = needed;
+ } else {
+ block_rsv->reserved += num_bytes;
+ to_free = 0;
+ refilled_bytes = num_bytes;
+ }
+ } else {
+ to_free = num_bytes;
+ refilled_bytes = 0;
+ }
+ spin_unlock(&block_rsv->lock);
+
+ if (to_free > 0)
+ btrfs_space_info_free_bytes_may_use(fs_info, block_rsv->space_info,
+ to_free);
+
+ if (refilled_bytes > 0)
+ trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0,
+ refilled_bytes, 1);
return 0;
}
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index b8e14b0ba5f1..fd9bf2b709c0 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -407,7 +407,6 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans);
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
enum btrfs_reserve_flush_enum flush);
void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *src,
u64 num_bytes);
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f356f08b55cb..fc313fce5bbd 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1514,15 +1514,14 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
/* now insert the actual backref */
- if (owner < BTRFS_FIRST_FREE_OBJECTID) {
- BUG_ON(refs_to_add != 1);
+ if (owner < BTRFS_FIRST_FREE_OBJECTID)
ret = insert_tree_block_ref(trans, path, bytenr, parent,
root_objectid);
- } else {
+ else
ret = insert_extent_data_ref(trans, path, bytenr, parent,
root_objectid, owner, offset,
refs_to_add);
- }
+
if (ret)
btrfs_abort_transaction(trans, ret);
out:
@@ -1656,7 +1655,10 @@ again:
goto again;
}
} else {
- err = -EIO;
+ err = -EUCLEAN;
+ btrfs_err(fs_info,
+ "missing extent item for extent %llu num_bytes %llu level %d",
+ head->bytenr, head->num_bytes, extent_op->level);
goto out;
}
}
@@ -1699,12 +1701,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
parent = ref->parent;
ref_root = ref->root;
- if (node->ref_mod != 1) {
+ if (unlikely(node->ref_mod != 1)) {
btrfs_err(trans->fs_info,
- "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
+ "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu",
node->bytenr, node->ref_mod, node->action, ref_root,
parent);
- return -EIO;
+ return -EUCLEAN;
}
if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
BUG_ON(!extent_op || !extent_op->update_flags);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6954ae763b86..caccd0376342 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3995,8 +3995,14 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
char *dst = (char *)dstv;
unsigned long i = get_eb_page_index(start);
- if (check_eb_range(eb, start, len))
+ if (check_eb_range(eb, start, len)) {
+ /*
+ * Invalid range hit, reset the memory, so callers won't get
+ * some random garbage for their uninitialzed memory.
+ */
+ memset(dstv, 0, len);
return;
+ }
offset = get_eb_offset_in_page(eb, start);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index cffdd6f7f8e8..1a093ec0f7e3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2117,7 +2117,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
* calculated f_bavail.
*/
if (!mixed && block_rsv->space_info->full &&
- total_free_meta - thresh < block_rsv->size)
+ (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size))
buf->f_bavail = 0;
buf->f_type = BTRFS_SUPER_MAGIC;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0bf42dccb041..c780d3729463 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -631,14 +631,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
reloc_reserved = true;
}
- ret = btrfs_block_rsv_add(fs_info, rsv, num_bytes, flush);
+ ret = btrfs_reserve_metadata_bytes(fs_info, rsv, num_bytes, flush);
if (ret)
goto reserve_fail;
if (delayed_refs_bytes) {
- btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv,
- delayed_refs_bytes);
+ btrfs_migrate_to_delayed_refs_rsv(fs_info, delayed_refs_bytes);
num_bytes -= delayed_refs_bytes;
}
+ btrfs_block_rsv_add_bytes(rsv, num_bytes, true);
if (rsv->space_info->force_alloc)
do_chunk_alloc = true;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d1e46b839519..cbb17b542131 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4722,7 +4722,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
struct extent_buffer *leaf;
int slot;
int ins_nr = 0;
- int start_slot;
+ int start_slot = 0;
int ret;
if (!(inode->flags & BTRFS_INODE_PREALLOC))
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9621455edebc..5a5a8d488a7b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1594,7 +1594,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
u64 search_start;
u64 hole_size;
u64 max_hole_start;
- u64 max_hole_size;
+ u64 max_hole_size = 0;
u64 extent_end;
u64 search_end = device->total_bytes;
int ret;
@@ -1602,17 +1602,16 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
struct extent_buffer *l;
search_start = dev_extent_search_start(device);
+ max_hole_start = search_start;
WARN_ON(device->zone_info &&
!IS_ALIGNED(num_bytes, device->zone_info->zone_size));
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
- max_hole_start = search_start;
- max_hole_size = 0;
-
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
again:
if (search_start >= search_end ||
test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
diff --git a/fs/buffer.c b/fs/buffer.c
index a6785cd07081..12e9a71c693d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2058,8 +2058,17 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
fallthrough;
case IOMAP_MAPPED:
if ((iomap->flags & IOMAP_F_NEW) ||
- offset >= i_size_read(inode))
+ offset >= i_size_read(inode)) {
+ /*
+ * This can happen if truncating the block device races
+ * with the check in the caller as i_size updates on
+ * block devices aren't synchronized by i_rwsem for
+ * block devices.
+ */
+ if (S_ISBLK(inode->i_mode))
+ return -EIO;
set_buffer_new(bh);
+ }
bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
inode->i_blkbits;
set_buffer_mapped(bh);
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index e4d5cd56a80b..e1f31b86fd48 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -249,11 +249,9 @@ static struct inode *parse_longname(const struct inode *parent,
if (!dir) {
/* This can happen if we're not mounting cephfs on the root */
dir = ceph_get_inode(parent->i_sb, vino, NULL);
- if (!dir)
- dir = ERR_PTR(-ENOENT);
+ if (IS_ERR(dir))
+ dout("Can't find inode %s (%s)\n", inode_number, name);
}
- if (IS_ERR(dir))
- dout("Can't find inode %s (%s)\n", inode_number, name);
out:
kfree(inode_number);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 969ce991b0b0..c1af01b2c42d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1535,10 +1535,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
if (wbc->pages_skipped) {
/*
- * writeback is not making progress due to locked
- * buffers. Skip this inode for now.
+ * Writeback is not making progress due to locked buffers.
+ * Skip this inode for now. Although having skipped pages
+ * is odd for clean inodes, it can happen for some
+ * filesystems so handle that gracefully.
*/
- redirty_tail_locked(inode, wb);
+ if (inode->i_state & I_DIRTY_ALL)
+ redirty_tail_locked(inode, wb);
+ else
+ inode_cgwb_move_to_attached(inode, wb);
return;
}
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 644479ccefbd..5db54ca29a35 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1049,7 +1049,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio,
/*
* Scan the data range passed to us for dirty page cache folios. If we find a
- * dirty folio, punch out the preceeding range and update the offset from which
+ * dirty folio, punch out the preceding range and update the offset from which
* the next punch will start from.
*
* We can punch out storage reservations under clean pages because they either
diff --git a/fs/libfs.c b/fs/libfs.c
index a4eb12757886..37f2d34ee090 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1903,6 +1903,7 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
* We don't know how much we wrote, so just return the number of
* bytes which were direct-written
*/
+ iocb->ki_pos -= buffered_written;
if (direct_written)
return direct_written;
return err;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2e40c74d2f72..92c7dde148a4 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4113,6 +4113,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
struct file *file, unsigned long maxcount)
{
struct xdr_stream *xdr = resp->xdr;
+ unsigned int base = xdr->buf->page_len & ~PAGE_MASK;
unsigned int starting_len = xdr->buf->len;
__be32 zero = xdr_zero;
__be32 nfserr;
@@ -4121,8 +4122,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
return nfserr_resource;
nfserr = nfsd_iter_read(resp->rqstp, read->rd_fhp, file,
- read->rd_offset, &maxcount,
- xdr->buf->page_len & ~PAGE_MASK,
+ read->rd_offset, &maxcount, base,
&read->rd_eof);
read->rd_length = maxcount;
if (nfserr)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 48fe71d309cb..8beb2730929d 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn);
- if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */
- brelse(bh);
+ if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */
goto failed;
- }
}
lock_buffer(bh);
@@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
failed:
unlock_page(bh->b_page);
put_page(bh->b_page);
+ if (unlikely(err))
+ brelse(bh);
return err;
}
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index cfec5e0c7f66..5661a363005e 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -1562,6 +1562,7 @@ load_root:
put_inode_out:
iput(inode);
out:
+ ntfs3_put_sbi(sbi);
kfree(boot2);
return err;
}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index d1761ec5866a..ada3fcc9c6d5 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -337,7 +337,7 @@ static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry,
{
struct iattr attr = {
.ia_valid =
- ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET,
+ ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME,
.ia_atime = stat->atime,
.ia_mtime = stat->mtime,
};
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4193633c4c7a..693971d20280 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -391,6 +391,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
if (!ovl_should_sync(OVL_FS(inode->i_sb)))
ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
+ /*
+ * Overlayfs doesn't support deferred completions, don't copy
+ * this property in case it is set by the issuer.
+ */
+ ifl &= ~IOCB_DIO_CALLER_COMP;
+
old_cred = ovl_override_creds(file_inode(file)->i_sb);
if (is_sync_kiocb(iocb)) {
file_start_write(real.file);
diff --git a/fs/pipe.c b/fs/pipe.c
index 6c1a9b1db907..139190165a1c 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -537,7 +537,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
break;
}
ret += copied;
- buf->offset = 0;
buf->len = copied;
if (!iov_iter_count(from))
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index b81749492ef9..7d12b8c5b2fa 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -2699,7 +2699,7 @@ struct reiserfs_iget_args {
#define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12)
#define journal_trans_half(blocksize) \
- ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32))
+ ((blocksize - sizeof(struct reiserfs_journal_desc) - 12) / sizeof(__u32))
/* journal.c see journal.c for all the comments here */
@@ -2711,7 +2711,7 @@ struct reiserfs_journal_desc {
__le32 j_len;
__le32 j_mount_id; /* mount id of this trans */
- __le32 j_realblock[1]; /* real locations for each block */
+ __le32 j_realblock[]; /* real locations for each block */
};
#define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id)
@@ -2726,7 +2726,7 @@ struct reiserfs_journal_desc {
struct reiserfs_journal_commit {
__le32 j_trans_id; /* must match j_trans_id from the desc block */
__le32 j_len; /* ditto */
- __le32 j_realblock[1]; /* real locations for each block */
+ __le32 j_realblock[]; /* real locations for each block */
};
#define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id)
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index e45ce31bbda7..a3493da12ad1 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1541,6 +1541,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
cifs_parse_mount_err:
kfree_sensitive(ctx->password);
+ ctx->password = NULL;
return -EINVAL;
}
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index 0d990c2f33cd..db7fa704a3f6 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -197,6 +197,9 @@ int ksmbd_conn_write(struct ksmbd_work *work)
if (work->send_no_response)
return 0;
+ if (!work->iov_idx)
+ return -EINVAL;
+
ksmbd_conn_lock(conn);
sent = conn->transport->ops->writev(conn->transport, work->iov,
work->iov_cnt,
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index 5ab2f52f9b35..32347fec33c4 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -115,8 +115,10 @@ static int __process_request(struct ksmbd_work *work, struct ksmbd_conn *conn,
if (check_conn_state(work))
return SERVER_HANDLER_CONTINUE;
- if (ksmbd_verify_smb_message(work))
+ if (ksmbd_verify_smb_message(work)) {
+ conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER);
return SERVER_HANDLER_ABORT;
+ }
command = conn->ops->get_cmd_val(work);
*cmd = command;
diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c
index e881df1d10cb..23bd3d1209df 100644
--- a/fs/smb/server/smb2misc.c
+++ b/fs/smb/server/smb2misc.c
@@ -440,10 +440,8 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work)
validate_credit:
if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) &&
- smb2_validate_credit_charge(work->conn, hdr)) {
- work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER);
+ smb2_validate_credit_charge(work->conn, hdr))
return 1;
- }
return 0;
}
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 5f1714089884..8c8d64e76103 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -421,7 +421,7 @@ static int eventfs_release(struct inode *inode, struct file *file)
if (WARN_ON_ONCE(!dlist))
return -EINVAL;
- for (i = 0; dlist->dentries[i]; i++) {
+ for (i = 0; dlist->dentries && dlist->dentries[i]; i++) {
dput(dlist->dentries[i]);
}
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index f71ea786a6d2..7cd09c3a82cb 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -146,10 +146,18 @@ xfs_nfs_get_inode(
return ERR_PTR(error);
}
- error = xfs_inode_reload_unlinked(ip);
- if (error) {
- xfs_irele(ip);
- return ERR_PTR(error);
+ /*
+ * Reload the incore unlinked list to avoid failure in inodegc.
+ * Use an unlocked check here because unrecovered unlinked inodes
+ * should be somewhat rare.
+ */
+ if (xfs_inode_unlinked_incomplete(ip)) {
+ error = xfs_inode_reload_unlinked(ip);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ xfs_irele(ip);
+ return ERR_PTR(error);
+ }
}
if (VFS_I(ip)->i_generation != generation) {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f94f7b374041..4d55f58d99b7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1743,6 +1743,14 @@ xfs_inactive(
truncate = 1;
if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) {
+ /*
+ * If this inode is being inactivated during a quotacheck and
+ * has not yet been scanned by quotacheck, we /must/ remove
+ * the dquots from the inode before inactivation changes the
+ * block and inode counts. Most probably this is a result of
+ * reloading the incore iunlinked list to purge unrecovered
+ * unlinked inodes.
+ */
xfs_qm_dqdetach(ip);
} else {
error = xfs_qm_dqattach(ip);
@@ -3641,6 +3649,16 @@ xfs_inode_reload_unlinked_bucket(
if (error)
return error;
+ /*
+ * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the
+ * incore unlinked list pointers for this inode. Check once more to
+ * see if we raced with anyone else to reload the unlinked list.
+ */
+ if (!xfs_inode_unlinked_incomplete(ip)) {
+ foundit = true;
+ goto out_agibp;
+ }
+
bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
agi = agibp->b_addr;
@@ -3655,25 +3673,27 @@ xfs_inode_reload_unlinked_bucket(
while (next_agino != NULLAGINO) {
struct xfs_inode *next_ip = NULL;
+ /* Found this caller's inode, set its backlink. */
if (next_agino == agino) {
- /* Found this inode, set its backlink. */
next_ip = ip;
next_ip->i_prev_unlinked = prev_agino;
foundit = true;
+ goto next_inode;
}
- if (!next_ip) {
- /* Inode already in memory. */
- next_ip = xfs_iunlink_lookup(pag, next_agino);
- }
- if (!next_ip) {
- /* Inode not in memory, reload. */
- error = xfs_iunlink_reload_next(tp, agibp, prev_agino,
- next_agino);
- if (error)
- break;
- next_ip = xfs_iunlink_lookup(pag, next_agino);
- }
+ /* Try in-memory lookup first. */
+ next_ip = xfs_iunlink_lookup(pag, next_agino);
+ if (next_ip)
+ goto next_inode;
+
+ /* Inode not in memory, try reloading it. */
+ error = xfs_iunlink_reload_next(tp, agibp, prev_agino,
+ next_agino);
+ if (error)
+ break;
+
+ /* Grab the reloaded inode. */
+ next_ip = xfs_iunlink_lookup(pag, next_agino);
if (!next_ip) {
/* No incore inode at all? We reloaded it... */
ASSERT(next_ip != NULL);
@@ -3681,10 +3701,12 @@ xfs_inode_reload_unlinked_bucket(
break;
}
+next_inode:
prev_agino = next_agino;
next_agino = next_ip->i_next_unlinked;
}
+out_agibp:
xfs_trans_brelse(tp, agibp);
/* Should have found this inode somewhere in the iunlinked bucket. */
if (!error && !foundit)
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index ccf0c4ff4490..f5377ba5967a 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -80,10 +80,12 @@ xfs_bulkstat_one_int(
if (error)
goto out;
+ /* Reload the incore unlinked list to avoid failure in inodegc. */
if (xfs_inode_unlinked_incomplete(ip)) {
error = xfs_inode_reload_unlinked_bucket(tp, ip);
if (error) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
xfs_irele(ip);
return error;
}
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 7256090c3895..086e78a6143a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1160,9 +1160,18 @@ xfs_qm_dqusage_adjust(
if (error)
return error;
- error = xfs_inode_reload_unlinked(ip);
- if (error)
- goto error0;
+ /*
+ * Reload the incore unlinked list to avoid failure in inodegc.
+ * Use an unlocked check here because unrecovered unlinked inodes
+ * should be somewhat rare.
+ */
+ if (xfs_inode_unlinked_incomplete(ip)) {
+ error = xfs_inode_reload_unlinked(ip);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ goto error0;
+ }
+ }
ASSERT(ip->i_delayed_blks == 0);
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 4da02798a00b..6dcf4d576970 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -76,7 +76,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
#ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+ pte_t *ptep, pte_t pte, unsigned long sz)
{
set_pte_at(mm, addr, ptep, pte);
}
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 5f2301ee88bc..f3b3593254b9 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -467,19 +467,17 @@ union ceph_mds_request_args {
} __attribute__ ((packed));
union ceph_mds_request_args_ext {
- union {
- union ceph_mds_request_args old;
- struct {
- __le32 mode;
- __le32 uid;
- __le32 gid;
- struct ceph_timespec mtime;
- struct ceph_timespec atime;
- __le64 size, old_size; /* old_size needed by truncate */
- __le32 mask; /* CEPH_SETATTR_* */
- struct ceph_timespec btime;
- } __attribute__ ((packed)) setattr_ext;
- };
+ union ceph_mds_request_args old;
+ struct {
+ __le32 mode;
+ __le32 uid;
+ __le32 gid;
+ struct ceph_timespec mtime;
+ struct ceph_timespec atime;
+ __le64 size, old_size; /* old_size needed by truncate */
+ __le32 mask; /* CEPH_SETATTR_* */
+ struct ceph_timespec btime;
+ } __attribute__ ((packed)) setattr_ext;
};
#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5b2626063f4f..a30686e649f7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -984,7 +984,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ unsigned long psize = huge_page_size(hstate_vma(vma));
+
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
#endif
@@ -1173,7 +1175,7 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
}
static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+ pte_t *ptep, pte_t pte, unsigned long sz)
{
}
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a92bce40b04b..4a1dc88ddbff 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -569,8 +569,12 @@ enum
* 2) rcu_report_dead() reports the final quiescent states.
*
* _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue
+ *
+ * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue
*/
-#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ))
+#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\
+ BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ))
+
/* map softirq index to softirq name. update 'softirq_to_name' in
* kernel/softirq.c when adding a new softirq.
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bf4913f4d7ac..2a7d2af0ed80 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -192,6 +192,7 @@ enum {
ATA_PFLAG_UNLOADING = (1 << 9), /* driver is being unloaded */
ATA_PFLAG_UNLOADED = (1 << 10), /* driver is unloaded */
+ ATA_PFLAG_RESUMING = (1 << 16), /* port is being resumed */
ATA_PFLAG_SUSPENDED = (1 << 17), /* port is suspended (power) */
ATA_PFLAG_PM_PENDING = (1 << 18), /* PM operation pending */
ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */
@@ -259,7 +260,7 @@ enum {
* advised to wait only for the following duration before
* doing SRST.
*/
- ATA_TMOUT_PMP_SRST_WAIT = 5000,
+ ATA_TMOUT_PMP_SRST_WAIT = 10000,
/* When the LPM policy is set to ATA_LPM_MAX_POWER, there might
* be a spurious PHY event, so ignore the first PHY event that
@@ -318,9 +319,10 @@ enum {
ATA_EH_ENABLE_LINK = (1 << 3),
ATA_EH_PARK = (1 << 5), /* unload heads and stop I/O */
ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */
+ ATA_EH_SET_ACTIVE = (1 << 7), /* Set a device to active power mode */
ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK |
- ATA_EH_GET_SUCCESS_SENSE,
+ ATA_EH_GET_SUCCESS_SENSE | ATA_EH_SET_ACTIVE,
ATA_EH_ALL_ACTIONS = ATA_EH_REVALIDATE | ATA_EH_RESET |
ATA_EH_ENABLE_LINK,
@@ -357,7 +359,7 @@ enum {
/* This should match the actual table size of
* ata_eh_cmd_timeout_table in libata-eh.c.
*/
- ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7,
+ ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8,
/* Horkage types. May be set by libata or controller on drives
(some horkage may be drive/controller pair dependent */
@@ -1148,6 +1150,7 @@ extern int ata_std_bios_param(struct scsi_device *sdev,
struct block_device *bdev,
sector_t capacity, int geom[]);
extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev);
+extern int ata_scsi_slave_alloc(struct scsi_device *sdev);
extern int ata_scsi_slave_config(struct scsi_device *sdev);
extern void ata_scsi_slave_destroy(struct scsi_device *sdev);
extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
@@ -1396,6 +1399,7 @@ extern const struct attribute_group *ata_common_sdev_groups[];
.this_id = ATA_SHT_THIS_ID, \
.emulated = ATA_SHT_EMULATED, \
.proc_name = drv_name, \
+ .slave_alloc = ata_scsi_slave_alloc, \
.slave_destroy = ata_scsi_slave_destroy, \
.bios_param = ata_std_bios_param, \
.unlock_native_capacity = ata_scsi_unlock_native_capacity,\
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index e41c70ac7744..d01e850b570f 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -428,6 +428,8 @@ struct ma_wr_state {
#define MAS_ROOT ((struct maple_enode *)5UL)
#define MAS_NONE ((struct maple_enode *)9UL)
#define MAS_PAUSE ((struct maple_enode *)17UL)
+#define MAS_OVERFLOW ((struct maple_enode *)33UL)
+#define MAS_UNDERFLOW ((struct maple_enode *)65UL)
#define MA_ERROR(err) \
((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
@@ -511,6 +513,15 @@ static inline bool mas_is_paused(const struct ma_state *mas)
return mas->node == MAS_PAUSE;
}
+/* Check if the mas is pointing to a node or not */
+static inline bool mas_is_active(struct ma_state *mas)
+{
+ if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE)
+ return true;
+
+ return false;
+}
+
/**
* mas_reset() - Reset a Maple Tree operation state.
* @mas: Maple Tree operation state.
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 1fba072b3dac..af7639c3b0a3 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -206,6 +206,14 @@ static inline int pmd_young(pmd_t pmd)
#endif
#ifndef set_ptes
+
+#ifndef pte_next_pfn
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+ return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#endif
+
/**
* set_ptes - Map consecutive pages to a contiguous range of addresses.
* @mm: Address space to map the pages into.
@@ -231,7 +239,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
if (--nr == 0)
break;
ptep++;
- pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+ pte = pte_next_pfn(pte);
}
arch_leave_lazy_mmu_mode();
}
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index b4536626f8ff..ecde0312dd52 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -172,14 +172,23 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
if (!mem)
return false;
- if (IS_ENABLED(CONFIG_SWIOTLB_DYNAMIC)) {
- /* Pairs with smp_wmb() in swiotlb_find_slots() and
- * swiotlb_dyn_alloc(), which modify the RCU lists.
- */
- smp_rmb();
- return swiotlb_find_pool(dev, paddr);
- }
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+ /*
+ * All SWIOTLB buffer addresses must have been returned by
+ * swiotlb_tbl_map_single() and passed to a device driver.
+ * If a SWIOTLB address is checked on another CPU, then it was
+ * presumably loaded by the device driver from an unspecified private
+ * data structure. Make sure that this load is ordered before reading
+ * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool().
+ *
+ * This barrier pairs with smp_mb() in swiotlb_find_slots().
+ */
+ smp_rmb();
+ return READ_ONCE(dev->dma_uses_io_tlb) &&
+ swiotlb_find_pool(dev, paddr);
+#else
return paddr >= mem->defpool.start && paddr < mem->defpool.end;
+#endif
}
static inline bool is_swiotlb_force_bounce(struct device *dev)
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index ec093594ba53..4498f845b112 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -157,6 +157,9 @@ enum scsi_disposition {
#define SCSI_3 4 /* SPC */
#define SCSI_SPC_2 5
#define SCSI_SPC_3 6
+#define SCSI_SPC_4 7
+#define SCSI_SPC_5 8
+#define SCSI_SPC_6 14
/*
* INQ PERIPHERAL QUALIFIERS
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index b9230b6add04..fd41fdac0a8e 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -161,6 +161,10 @@ struct scsi_device {
* pass settings from slave_alloc to scsi
* core. */
unsigned int eh_timeout; /* Error handling timeout */
+
+ bool manage_system_start_stop; /* Let HLD (sd) manage system start/stop */
+ bool manage_runtime_start_stop; /* Let HLD (sd) manage runtime start/stop */
+
unsigned removable:1;
unsigned changed:1; /* Data invalid due to media change */
unsigned busy:1; /* Used to prevent races */
@@ -193,7 +197,6 @@ struct scsi_device {
unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */
unsigned no_start_on_add:1; /* do not issue start on add */
unsigned allow_restart:1; /* issue START_UNIT in error handler */
- unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */
unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */
unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */
unsigned no_uld_attach:1; /* disable connecting to upper level drivers */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 49f768d0ff37..4c2dc8150c6d 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -764,7 +764,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht);
#define scsi_template_proc_dir(sht) NULL
#endif
extern void scsi_scan_host(struct Scsi_Host *);
-extern void scsi_rescan_device(struct scsi_device *);
+extern int scsi_rescan_device(struct scsi_device *sdev);
extern void scsi_remove_host(struct Scsi_Host *);
extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *);
extern int scsi_host_busy(struct Scsi_Host *shost);
diff --git a/io_uring/fs.c b/io_uring/fs.c
index f6a69a549fd4..08e3b175469c 100644
--- a/io_uring/fs.c
+++ b/io_uring/fs.c
@@ -243,7 +243,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link);
const char __user *oldf, *newf;
- if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 03a7932cde0a..2f675ef045d4 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -740,6 +740,17 @@ subsys_initcall(crash_notes_memory_init);
#define pr_fmt(fmt) "crash hp: " fmt
/*
+ * Different than kexec/kdump loading/unloading/jumping/shrinking which
+ * usually rarely happen, there will be many crash hotplug events notified
+ * during one short period, e.g one memory board is hot added and memory
+ * regions are online. So mutex lock __crash_hotplug_lock is used to
+ * serialize the crash hotplug handling specifically.
+ */
+DEFINE_MUTEX(__crash_hotplug_lock);
+#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
+#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
+
+/*
* This routine utilized when the crash_hotplug sysfs node is read.
* It reflects the kernel's ability/permission to update the crash
* elfcorehdr directly.
@@ -748,9 +759,11 @@ int crash_check_update_elfcorehdr(void)
{
int rc = 0;
+ crash_hotplug_lock();
/* Obtain lock while reading crash information */
if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
return 0;
}
if (kexec_crash_image) {
@@ -761,6 +774,7 @@ int crash_check_update_elfcorehdr(void)
}
/* Release lock now that update complete */
kexec_unlock();
+ crash_hotplug_unlock();
return rc;
}
@@ -783,9 +797,11 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
{
struct kimage *image;
+ crash_hotplug_lock();
/* Obtain lock while changing crash information */
if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+ crash_hotplug_unlock();
return;
}
@@ -852,6 +868,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
out:
/* Release lock now that update complete */
kexec_unlock();
+ crash_hotplug_unlock();
}
static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 394494a6b1f3..01637677736f 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -399,14 +399,13 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
}
mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
- default_nareas), SMP_CACHE_BYTES);
+ nareas), SMP_CACHE_BYTES);
if (!mem->areas) {
pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
return;
}
- swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false,
- default_nareas);
+ swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas);
add_mem_pool(&io_tlb_default_mem, mem);
if (flags & SWIOTLB_VERBOSE)
@@ -729,9 +728,6 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
}
add_mem_pool(mem, pool);
-
- /* Pairs with smp_rmb() in is_swiotlb_buffer(). */
- smp_wmb();
}
/**
@@ -1152,9 +1148,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
found:
- dev->dma_uses_io_tlb = true;
- /* Pairs with smp_rmb() in is_swiotlb_buffer() */
- smp_wmb();
+ WRITE_ONCE(dev->dma_uses_io_tlb, true);
+
+ /*
+ * The general barrier orders reads and writes against a presumed store
+ * of the SWIOTLB buffer address by a device driver (to a driver private
+ * data structure). It serves two purposes.
+ *
+ * First, the store to dev->dma_uses_io_tlb must be ordered before the
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be passed to another CPU before updating dev->dma_uses_io_tlb.
+ *
+ * Second, the load from mem->pools must be ordered before the same
+ * presumed store. This guarantees that the returned buffer address
+ * cannot be observed by another CPU before an update of the RCU list
+ * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy
+ * atomicity).
+ *
+ * See also the comment in is_swiotlb_buffer().
+ */
+ smp_mb();
*retpool = pool;
return index;
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index a286e726eb4b..42c40cfdf836 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
+ cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
/*
* We have to ensure that we have at least one bit
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 28daf0ce95c5..515cafdb18d9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1137,6 +1137,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
if (full) {
poll_wait(filp, &work->full_waiters, poll_table);
work->full_waiters_pending = true;
+ if (!cpu_buffer->shortest_full ||
+ cpu_buffer->shortest_full > full)
+ cpu_buffer->shortest_full = full;
} else {
poll_wait(filp, &work->waiters, poll_table);
work->waiters_pending = true;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 91951d038ba4..f49d6ddb6342 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2770,6 +2770,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
update_event_fields(call, map[i]);
}
}
+ cond_resched();
}
up_write(&trace_event_sem);
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 6f046650e527..b87f41187c6a 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -127,8 +127,13 @@ struct user_event_enabler {
/* Bit 7 is for freeing status of enablement */
#define ENABLE_VAL_FREEING_BIT 7
-/* Only duplicate the bit value */
-#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK
+/* Bit 8 is for marking 32-bit on 64-bit */
+#define ENABLE_VAL_32_ON_64_BIT 8
+
+#define ENABLE_VAL_COMPAT_MASK (1 << ENABLE_VAL_32_ON_64_BIT)
+
+/* Only duplicate the bit and compat values */
+#define ENABLE_VAL_DUP_MASK (ENABLE_VAL_BIT_MASK | ENABLE_VAL_COMPAT_MASK)
#define ENABLE_BITOPS(e) (&(e)->values)
@@ -174,6 +179,30 @@ struct user_event_validator {
int flags;
};
+static inline void align_addr_bit(unsigned long *addr, int *bit,
+ unsigned long *flags)
+{
+ if (IS_ALIGNED(*addr, sizeof(long))) {
+#ifdef __BIG_ENDIAN
+ /* 32 bit on BE 64 bit requires a 32 bit offset when aligned. */
+ if (test_bit(ENABLE_VAL_32_ON_64_BIT, flags))
+ *bit += 32;
+#endif
+ return;
+ }
+
+ *addr = ALIGN_DOWN(*addr, sizeof(long));
+
+ /*
+ * We only support 32 and 64 bit values. The only time we need
+ * to align is a 32 bit value on a 64 bit kernel, which on LE
+ * is always 32 bits, and on BE requires no change when unaligned.
+ */
+#ifdef __LITTLE_ENDIAN
+ *bit += 32;
+#endif
+}
+
typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted);
@@ -482,6 +511,7 @@ static int user_event_enabler_write(struct user_event_mm *mm,
unsigned long *ptr;
struct page *page;
void *kaddr;
+ int bit = ENABLE_BIT(enabler);
int ret;
lockdep_assert_held(&event_mutex);
@@ -497,6 +527,8 @@ static int user_event_enabler_write(struct user_event_mm *mm,
test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))))
return -EBUSY;
+ align_addr_bit(&uaddr, &bit, ENABLE_BITOPS(enabler));
+
ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
&page, NULL);
@@ -515,9 +547,9 @@ static int user_event_enabler_write(struct user_event_mm *mm,
/* Update bit atomically, user tracers must be atomic as well */
if (enabler->event && enabler->event->status)
- set_bit(ENABLE_BIT(enabler), ptr);
+ set_bit(bit, ptr);
else
- clear_bit(ENABLE_BIT(enabler), ptr);
+ clear_bit(bit, ptr);
kunmap_local(kaddr);
unpin_user_pages_dirty_lock(&page, 1, true);
@@ -849,6 +881,12 @@ static struct user_event_enabler
enabler->event = user;
enabler->addr = uaddr;
enabler->values = reg->enable_bit;
+
+#if BITS_PER_LONG >= 64
+ if (reg->enable_size == 4)
+ set_bit(ENABLE_VAL_32_ON_64_BIT, ENABLE_BITOPS(enabler));
+#endif
+
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -2377,7 +2415,8 @@ static long user_unreg_get(struct user_unreg __user *ureg,
}
static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
- unsigned long uaddr, unsigned char bit)
+ unsigned long uaddr, unsigned char bit,
+ unsigned long flags)
{
struct user_event_enabler enabler;
int result;
@@ -2385,7 +2424,7 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
memset(&enabler, 0, sizeof(enabler));
enabler.addr = uaddr;
- enabler.values = bit;
+ enabler.values = bit | flags;
retry:
/* Prevents state changes from racing with new enablers */
mutex_lock(&event_mutex);
@@ -2415,6 +2454,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
struct user_event_mm *mm = current->user_event_mm;
struct user_event_enabler *enabler, *next;
struct user_unreg reg;
+ unsigned long flags;
long ret;
ret = user_unreg_get(ureg, &reg);
@@ -2425,6 +2465,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
if (!mm)
return -ENOENT;
+ flags = 0;
ret = -ENOENT;
/*
@@ -2441,6 +2482,9 @@ static long user_events_ioctl_unreg(unsigned long uarg)
ENABLE_BIT(enabler) == reg.disable_bit) {
set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler));
+ /* We must keep compat flags for the clear */
+ flags |= enabler->values & ENABLE_VAL_COMPAT_MASK;
+
if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))
user_event_enabler_destroy(enabler, true);
@@ -2454,7 +2498,7 @@ static long user_events_ioctl_unreg(unsigned long uarg)
/* Ensure bit is now cleared for user, regardless of event status */
if (!ret)
ret = user_event_mm_clear_bit(mm, reg.disable_addr,
- reg.disable_bit);
+ reg.disable_bit, flags);
return ret;
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c85825e17df8..b9f053a5a5f0 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6535,9 +6535,6 @@ void __init workqueue_init_early(void)
BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE));
- wq_update_pod_attrs_buf = alloc_workqueue_attrs();
- BUG_ON(!wq_update_pod_attrs_buf);
-
pt->nr_pods = 1;
cpumask_copy(pt->pod_cpus[0], cpu_possible_mask);
pt->pod_node[0] = NUMA_NO_NODE;
@@ -6605,13 +6602,13 @@ static void __init wq_cpu_intensive_thresh_init(void)
unsigned long thresh;
unsigned long bogo;
+ pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
+ BUG_ON(IS_ERR(pwq_release_worker));
+
/* if the user set it to a specific value, keep it */
if (wq_cpu_intensive_thresh_us != ULONG_MAX)
return;
- pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
- BUG_ON(IS_ERR(pwq_release_worker));
-
/*
* The default of 10ms is derived from the fact that most modern (as of
* 2023) processors can do a lot in 10ms and that it's just below what
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index ee1ff0c59fd7..0e00a84e8e8f 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -256,6 +256,22 @@ bool mas_is_err(struct ma_state *mas)
return xa_is_err(mas->node);
}
+static __always_inline bool mas_is_overflow(struct ma_state *mas)
+{
+ if (unlikely(mas->node == MAS_OVERFLOW))
+ return true;
+
+ return false;
+}
+
+static __always_inline bool mas_is_underflow(struct ma_state *mas)
+{
+ if (unlikely(mas->node == MAS_UNDERFLOW))
+ return true;
+
+ return false;
+}
+
static inline bool mas_searchable(struct ma_state *mas)
{
if (mas_is_none(mas))
@@ -4415,10 +4431,13 @@ no_entry:
*
* @mas: The maple state
* @max: The minimum starting range
+ * @empty: Can be empty
+ * @set_underflow: Set the @mas->node to underflow state on limit.
*
* Return: The entry in the previous slot which is possibly NULL
*/
-static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty)
+static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty,
+ bool set_underflow)
{
void *entry;
void __rcu **slots;
@@ -4435,7 +4454,6 @@ retry:
if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
-again:
if (mas->min <= min) {
pivot = mas_safe_min(mas, pivots, mas->offset);
@@ -4443,9 +4461,10 @@ again:
goto retry;
if (pivot <= min)
- return NULL;
+ goto underflow;
}
+again:
if (likely(mas->offset)) {
mas->offset--;
mas->last = mas->index - 1;
@@ -4457,7 +4476,7 @@ again:
}
if (mas_is_none(mas))
- return NULL;
+ goto underflow;
mas->last = mas->max;
node = mas_mn(mas);
@@ -4474,10 +4493,19 @@ again:
if (likely(entry))
return entry;
- if (!empty)
+ if (!empty) {
+ if (mas->index <= min)
+ goto underflow;
+
goto again;
+ }
return entry;
+
+underflow:
+ if (set_underflow)
+ mas->node = MAS_UNDERFLOW;
+ return NULL;
}
/*
@@ -4567,10 +4595,13 @@ no_entry:
* @mas: The maple state
* @max: The maximum starting range
* @empty: Can be empty
+ * @set_overflow: Should @mas->node be set to overflow when the limit is
+ * reached.
*
* Return: The entry in the next slot which is possibly NULL
*/
-static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty)
+static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty,
+ bool set_overflow)
{
void __rcu **slots;
unsigned long *pivots;
@@ -4589,22 +4620,22 @@ retry:
if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
-again:
if (mas->max >= max) {
if (likely(mas->offset < data_end))
pivot = pivots[mas->offset];
else
- return NULL; /* must be mas->max */
+ goto overflow;
if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
goto retry;
if (pivot >= max)
- return NULL;
+ goto overflow;
}
if (likely(mas->offset < data_end)) {
mas->index = pivots[mas->offset] + 1;
+again:
mas->offset++;
if (likely(mas->offset < data_end))
mas->last = pivots[mas->offset];
@@ -4616,8 +4647,11 @@ again:
goto retry;
}
- if (mas_is_none(mas))
+ if (WARN_ON_ONCE(mas_is_none(mas))) {
+ mas->node = MAS_OVERFLOW;
return NULL;
+ goto overflow;
+ }
mas->offset = 0;
mas->index = mas->min;
@@ -4636,12 +4670,20 @@ again:
return entry;
if (!empty) {
- if (!mas->offset)
- data_end = 2;
+ if (mas->last >= max)
+ goto overflow;
+
+ mas->index = mas->last + 1;
+ /* Node cannot end on NULL, so it's safe to short-cut here */
goto again;
}
return entry;
+
+overflow:
+ if (set_overflow)
+ mas->node = MAS_OVERFLOW;
+ return NULL;
}
/*
@@ -4651,17 +4693,20 @@ again:
*
* Set the @mas->node to the next entry and the range_start to
* the beginning value for the entry. Does not check beyond @limit.
- * Sets @mas->index and @mas->last to the limit if it is hit.
+ * Sets @mas->index and @mas->last to the range, Does not update @mas->index and
+ * @mas->last on overflow.
* Restarts on dead nodes.
*
* Return: the next entry or %NULL.
*/
static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit)
{
- if (mas->last >= limit)
+ if (mas->last >= limit) {
+ mas->node = MAS_OVERFLOW;
return NULL;
+ }
- return mas_next_slot(mas, limit, false);
+ return mas_next_slot(mas, limit, false, true);
}
/*
@@ -4837,7 +4882,7 @@ void *mas_walk(struct ma_state *mas)
{
void *entry;
- if (mas_is_none(mas) || mas_is_paused(mas) || mas_is_ptr(mas))
+ if (!mas_is_active(mas) || !mas_is_start(mas))
mas->node = MAS_START;
retry:
entry = mas_state_walk(mas);
@@ -5294,14 +5339,22 @@ static inline void mte_destroy_walk(struct maple_enode *enode,
static void mas_wr_store_setup(struct ma_wr_state *wr_mas)
{
- if (mas_is_start(wr_mas->mas))
- return;
+ if (!mas_is_active(wr_mas->mas)) {
+ if (mas_is_start(wr_mas->mas))
+ return;
- if (unlikely(mas_is_paused(wr_mas->mas)))
- goto reset;
+ if (unlikely(mas_is_paused(wr_mas->mas)))
+ goto reset;
- if (unlikely(mas_is_none(wr_mas->mas)))
- goto reset;
+ if (unlikely(mas_is_none(wr_mas->mas)))
+ goto reset;
+
+ if (unlikely(mas_is_overflow(wr_mas->mas)))
+ goto reset;
+
+ if (unlikely(mas_is_underflow(wr_mas->mas)))
+ goto reset;
+ }
/*
* A less strict version of mas_is_span_wr() where we allow spanning
@@ -5595,8 +5648,25 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max,
{
bool was_none = mas_is_none(mas);
- if (mas_is_none(mas) || mas_is_paused(mas))
+ if (unlikely(mas->last >= max)) {
+ mas->node = MAS_OVERFLOW;
+ return true;
+ }
+
+ if (mas_is_active(mas))
+ return false;
+
+ if (mas_is_none(mas) || mas_is_paused(mas)) {
+ mas->node = MAS_START;
+ } else if (mas_is_overflow(mas)) {
+ /* Overflowed before, but the max changed */
mas->node = MAS_START;
+ } else if (mas_is_underflow(mas)) {
+ mas->node = MAS_START;
+ *entry = mas_walk(mas);
+ if (*entry)
+ return true;
+ }
if (mas_is_start(mas))
*entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
@@ -5615,6 +5685,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max,
if (mas_is_none(mas))
return true;
+
return false;
}
@@ -5637,7 +5708,7 @@ void *mas_next(struct ma_state *mas, unsigned long max)
return entry;
/* Retries on dead nodes handled by mas_next_slot */
- return mas_next_slot(mas, max, false);
+ return mas_next_slot(mas, max, false, true);
}
EXPORT_SYMBOL_GPL(mas_next);
@@ -5660,7 +5731,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max)
return entry;
/* Retries on dead nodes handled by mas_next_slot */
- return mas_next_slot(mas, max, true);
+ return mas_next_slot(mas, max, true, true);
}
EXPORT_SYMBOL_GPL(mas_next_range);
@@ -5691,18 +5762,31 @@ EXPORT_SYMBOL_GPL(mt_next);
static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min,
void **entry)
{
- if (mas->index <= min)
- goto none;
+ if (unlikely(mas->index <= min)) {
+ mas->node = MAS_UNDERFLOW;
+ return true;
+ }
- if (mas_is_none(mas) || mas_is_paused(mas))
+ if (mas_is_active(mas))
+ return false;
+
+ if (mas_is_overflow(mas)) {
mas->node = MAS_START;
+ *entry = mas_walk(mas);
+ if (*entry)
+ return true;
+ }
- if (mas_is_start(mas)) {
- mas_walk(mas);
- if (!mas->index)
- goto none;
+ if (mas_is_none(mas) || mas_is_paused(mas)) {
+ mas->node = MAS_START;
+ } else if (mas_is_underflow(mas)) {
+ /* underflowed before but the min changed */
+ mas->node = MAS_START;
}
+ if (mas_is_start(mas))
+ mas_walk(mas);
+
if (unlikely(mas_is_ptr(mas))) {
if (!mas->index)
goto none;
@@ -5747,7 +5831,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min)
if (mas_prev_setup(mas, min, &entry))
return entry;
- return mas_prev_slot(mas, min, false);
+ return mas_prev_slot(mas, min, false, true);
}
EXPORT_SYMBOL_GPL(mas_prev);
@@ -5770,7 +5854,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min)
if (mas_prev_setup(mas, min, &entry))
return entry;
- return mas_prev_slot(mas, min, true);
+ return mas_prev_slot(mas, min, true, true);
}
EXPORT_SYMBOL_GPL(mas_prev_range);
@@ -5828,24 +5912,35 @@ EXPORT_SYMBOL_GPL(mas_pause);
static inline bool mas_find_setup(struct ma_state *mas, unsigned long max,
void **entry)
{
- *entry = NULL;
+ if (mas_is_active(mas)) {
+ if (mas->last < max)
+ return false;
- if (unlikely(mas_is_none(mas))) {
+ return true;
+ }
+
+ if (mas_is_paused(mas)) {
if (unlikely(mas->last >= max))
return true;
- mas->index = mas->last;
+ mas->index = ++mas->last;
mas->node = MAS_START;
- } else if (unlikely(mas_is_paused(mas))) {
+ } else if (mas_is_none(mas)) {
if (unlikely(mas->last >= max))
return true;
+ mas->index = mas->last;
mas->node = MAS_START;
- mas->index = ++mas->last;
- } else if (unlikely(mas_is_ptr(mas)))
- goto ptr_out_of_range;
+ } else if (mas_is_overflow(mas) || mas_is_underflow(mas)) {
+ if (mas->index > max) {
+ mas->node = MAS_OVERFLOW;
+ return true;
+ }
+
+ mas->node = MAS_START;
+ }
- if (unlikely(mas_is_start(mas))) {
+ if (mas_is_start(mas)) {
/* First run or continue */
if (mas->index > max)
return true;
@@ -5895,7 +5990,7 @@ void *mas_find(struct ma_state *mas, unsigned long max)
return entry;
/* Retries on dead nodes handled by mas_next_slot */
- return mas_next_slot(mas, max, false);
+ return mas_next_slot(mas, max, false, false);
}
EXPORT_SYMBOL_GPL(mas_find);
@@ -5913,13 +6008,13 @@ EXPORT_SYMBOL_GPL(mas_find);
*/
void *mas_find_range(struct ma_state *mas, unsigned long max)
{
- void *entry;
+ void *entry = NULL;
if (mas_find_setup(mas, max, &entry))
return entry;
/* Retries on dead nodes handled by mas_next_slot */
- return mas_next_slot(mas, max, true);
+ return mas_next_slot(mas, max, true, false);
}
EXPORT_SYMBOL_GPL(mas_find_range);
@@ -5934,26 +6029,36 @@ EXPORT_SYMBOL_GPL(mas_find_range);
static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
void **entry)
{
- *entry = NULL;
-
- if (unlikely(mas_is_none(mas))) {
- if (mas->index <= min)
- goto none;
+ if (mas_is_active(mas)) {
+ if (mas->index > min)
+ return false;
- mas->last = mas->index;
- mas->node = MAS_START;
+ return true;
}
- if (unlikely(mas_is_paused(mas))) {
+ if (mas_is_paused(mas)) {
if (unlikely(mas->index <= min)) {
mas->node = MAS_NONE;
return true;
}
mas->node = MAS_START;
mas->last = --mas->index;
+ } else if (mas_is_none(mas)) {
+ if (mas->index <= min)
+ goto none;
+
+ mas->last = mas->index;
+ mas->node = MAS_START;
+ } else if (mas_is_underflow(mas) || mas_is_overflow(mas)) {
+ if (mas->last <= min) {
+ mas->node = MAS_UNDERFLOW;
+ return true;
+ }
+
+ mas->node = MAS_START;
}
- if (unlikely(mas_is_start(mas))) {
+ if (mas_is_start(mas)) {
/* First run or continue */
if (mas->index < min)
return true;
@@ -6004,13 +6109,13 @@ none:
*/
void *mas_find_rev(struct ma_state *mas, unsigned long min)
{
- void *entry;
+ void *entry = NULL;
if (mas_find_rev_setup(mas, min, &entry))
return entry;
/* Retries on dead nodes handled by mas_prev_slot */
- return mas_prev_slot(mas, min, false);
+ return mas_prev_slot(mas, min, false, false);
}
EXPORT_SYMBOL_GPL(mas_find_rev);
@@ -6030,13 +6135,13 @@ EXPORT_SYMBOL_GPL(mas_find_rev);
*/
void *mas_find_range_rev(struct ma_state *mas, unsigned long min)
{
- void *entry;
+ void *entry = NULL;
if (mas_find_rev_setup(mas, min, &entry))
return entry;
/* Retries on dead nodes handled by mas_prev_slot */
- return mas_prev_slot(mas, min, true);
+ return mas_prev_slot(mas, min, true, false);
}
EXPORT_SYMBOL_GPL(mas_find_range_rev);
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 0674aebd4423..06959165e2f9 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -2166,7 +2166,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt)
MT_BUG_ON(mt, val != NULL);
MT_BUG_ON(mt, mas.index != 0);
MT_BUG_ON(mt, mas.last != 5);
- MT_BUG_ON(mt, mas.node != MAS_NONE);
+ MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
mas.index = 0;
mas.last = 5;
@@ -2917,6 +2917,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
* exists MAS_NONE active range
* exists active active range
* DNE active active set to last range
+ * ERANGE active MAS_OVERFLOW last range
*
* Function ENTRY Start Result index & last
* mas_prev()
@@ -2945,6 +2946,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
* any MAS_ROOT MAS_NONE 0
* exists active active range
* DNE active active last range
+ * ERANGE active MAS_UNDERFLOW last range
*
* Function ENTRY Start Result index & last
* mas_find()
@@ -2955,7 +2957,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
* DNE MAS_START MAS_NONE 0
* DNE MAS_PAUSE MAS_NONE 0
* DNE MAS_ROOT MAS_NONE 0
- * DNE MAS_NONE MAS_NONE 0
+ * DNE MAS_NONE MAS_NONE 1
* if index == 0
* exists MAS_START MAS_ROOT 0
* exists MAS_PAUSE MAS_ROOT 0
@@ -2967,7 +2969,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
* DNE MAS_START active set to max
* exists MAS_PAUSE active range
* DNE MAS_PAUSE active set to max
- * exists MAS_NONE active range
+ * exists MAS_NONE active range (start at last)
* exists active active range
* DNE active active last range (max < last)
*
@@ -2992,7 +2994,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
* DNE MAS_START active set to min
* exists MAS_PAUSE active range
* DNE MAS_PAUSE active set to min
- * exists MAS_NONE active range
+ * exists MAS_NONE active range (start at index)
* exists active active range
* DNE active active last range (min > index)
*
@@ -3039,10 +3041,10 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
mtree_store_range(mt, 0, 0, ptr, GFP_KERNEL);
mas_lock(&mas);
- /* prev: Start -> none */
+ /* prev: Start -> underflow*/
entry = mas_prev(&mas, 0);
MT_BUG_ON(mt, entry != NULL);
- MT_BUG_ON(mt, mas.node != MAS_NONE);
+ MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
/* prev: Start -> root */
mas_set(&mas, 10);
@@ -3069,7 +3071,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
MT_BUG_ON(mt, entry != NULL);
MT_BUG_ON(mt, mas.node != MAS_NONE);
- /* next: start -> none */
+ /* next: start -> none*/
mas_set(&mas, 10);
entry = mas_next(&mas, ULONG_MAX);
MT_BUG_ON(mt, mas.index != 1);
@@ -3268,25 +3270,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
MT_BUG_ON(mt, mas.last != 0x2500);
MT_BUG_ON(mt, !mas_active(mas));
- /* next:active -> active out of range*/
+ /* next:active -> active beyond data */
entry = mas_next(&mas, 0x2999);
MT_BUG_ON(mt, entry != NULL);
MT_BUG_ON(mt, mas.index != 0x2501);
MT_BUG_ON(mt, mas.last != 0x2fff);
MT_BUG_ON(mt, !mas_active(mas));
- /* Continue after out of range*/
+ /* Continue after last range ends after max */
entry = mas_next(&mas, ULONG_MAX);
MT_BUG_ON(mt, entry != ptr3);
MT_BUG_ON(mt, mas.index != 0x3000);
MT_BUG_ON(mt, mas.last != 0x3500);
MT_BUG_ON(mt, !mas_active(mas));
- /* next:active -> active out of range*/
+ /* next:active -> active continued */
+ entry = mas_next(&mas, ULONG_MAX);
+ MT_BUG_ON(mt, entry != NULL);
+ MT_BUG_ON(mt, mas.index != 0x3501);
+ MT_BUG_ON(mt, mas.last != ULONG_MAX);
+ MT_BUG_ON(mt, !mas_active(mas));
+
+ /* next:active -> overflow */
entry = mas_next(&mas, ULONG_MAX);
MT_BUG_ON(mt, entry != NULL);
MT_BUG_ON(mt, mas.index != 0x3501);
MT_BUG_ON(mt, mas.last != ULONG_MAX);
+ MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+
+ /* next:overflow -> overflow */
+ entry = mas_next(&mas, ULONG_MAX);
+ MT_BUG_ON(mt, entry != NULL);
+ MT_BUG_ON(mt, mas.index != 0x3501);
+ MT_BUG_ON(mt, mas.last != ULONG_MAX);
+ MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+
+ /* prev:overflow -> active */
+ entry = mas_prev(&mas, 0);
+ MT_BUG_ON(mt, entry != ptr3);
+ MT_BUG_ON(mt, mas.index != 0x3000);
+ MT_BUG_ON(mt, mas.last != 0x3500);
MT_BUG_ON(mt, !mas_active(mas));
/* next: none -> active, skip value at location */
@@ -3307,11 +3330,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
MT_BUG_ON(mt, mas.last != 0x1500);
MT_BUG_ON(mt, !mas_active(mas));
- /* prev:active -> active out of range*/
+ /* prev:active -> active spanning end range */
+ entry = mas_prev(&mas, 0x0100);
+ MT_BUG_ON(mt, entry != NULL);
+ MT_BUG_ON(mt, mas.index != 0);
+ MT_BUG_ON(mt, mas.last != 0x0FFF);
+ MT_BUG_ON(mt, !mas_active(mas));
+
+ /* prev:active -> underflow */
+ entry = mas_prev(&mas, 0);
+ MT_BUG_ON(mt, entry != NULL);
+ MT_BUG_ON(mt, mas.index != 0);
+ MT_BUG_ON(mt, mas.last != 0x0FFF);
+ MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+ /* prev:underflow -> underflow */
entry = mas_prev(&mas, 0);
MT_BUG_ON(mt, entry != NULL);
MT_BUG_ON(mt, mas.index != 0);
MT_BUG_ON(mt, mas.last != 0x0FFF);
+ MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+ /* next:underflow -> active */
+ entry = mas_next(&mas, ULONG_MAX);
+ MT_BUG_ON(mt, entry != ptr);
+ MT_BUG_ON(mt, mas.index != 0x1000);
+ MT_BUG_ON(mt, mas.last != 0x1500);
+ MT_BUG_ON(mt, !mas_active(mas));
+
+ /* prev:first value -> underflow */
+ entry = mas_prev(&mas, 0x1000);
+ MT_BUG_ON(mt, entry != NULL);
+ MT_BUG_ON(mt, mas.index != 0x1000);
+ MT_BUG_ON(mt, mas.last != 0x1500);
+ MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+
+ /* find:underflow -> first value */
+ entry = mas_find(&mas, ULONG_MAX);
+ MT_BUG_ON(mt, entry != ptr);
+ MT_BUG_ON(mt, mas.index != 0x1000);
+ MT_BUG_ON(mt, mas.last != 0x1500);
MT_BUG_ON(mt, !mas_active(mas));
/* prev: pause ->active */
@@ -3325,14 +3383,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
MT_BUG_ON(mt, mas.last != 0x2500);
MT_BUG_ON(mt, !mas_active(mas));
- /* prev:active -> active out of range*/
+ /* prev:active -> active spanning min */
entry = mas_prev(&mas, 0x1600);
MT_BUG_ON(mt, entry != NULL);
MT_BUG_ON(mt, mas.index != 0x1501);
MT_BUG_ON(mt, mas.last != 0x1FFF);
MT_BUG_ON(mt, !mas_active(mas));
- /* prev: active ->active, continue*/
+ /* prev: active ->active, continue */
entry = mas_prev(&mas, 0);
MT_BUG_ON(mt, entry != ptr);
MT_BUG_ON(mt, mas.index != 0x1000);
@@ -3379,7 +3437,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
MT_BUG_ON(mt, mas.last != 0x2FFF);
MT_BUG_ON(mt, !mas_active(mas));
- /* find: none ->active */
+ /* find: overflow ->active */
entry = mas_find(&mas, 0x5000);
MT_BUG_ON(mt, entry != ptr3);
MT_BUG_ON(mt, mas.index != 0x3000);
@@ -3778,7 +3836,6 @@ static int __init maple_tree_seed(void)
check_empty_area_fill(&tree);
mtree_destroy(&tree);
-
mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
check_state_handling(&tree);
mtree_destroy(&tree);
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index c4b455b5ee30..dcf1ca6b31cc 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -148,6 +148,8 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
}
+
+ damon_destroy_target(t);
}
/*
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 4c81a9dbd044..cf8a9fc5c9d1 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -341,13 +341,14 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm,
bool referenced = false;
pte_t entry = huge_ptep_get(pte);
struct folio *folio = pfn_folio(pte_pfn(entry));
+ unsigned long psize = huge_page_size(hstate_vma(vma));
folio_get(folio);
if (pte_young(entry)) {
referenced = true;
entry = pte_mkold(entry);
- set_huge_pte_at(mm, addr, pte, entry);
+ set_huge_pte_at(mm, addr, pte, entry, psize);
}
#ifdef CONFIG_MMU_NOTIFIER
diff --git a/mm/filemap.c b/mm/filemap.c
index 4ea4387053e8..f0a15ce1bd1b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3503,7 +3503,7 @@ skip:
if (count) {
set_pte_range(vmf, folio, page, count, addr);
folio_ref_add(folio, count);
- if (in_range(vmf->address, addr, count))
+ if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
@@ -3517,7 +3517,7 @@ skip:
if (count) {
set_pte_range(vmf, folio, page, count, addr);
folio_ref_add(folio, count);
- if (in_range(vmf->address, addr, count))
+ if (in_range(vmf->address, addr, count * PAGE_SIZE))
ret = VM_FAULT_NOPAGE;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ba6d39b71cb1..52d26072dfda 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4980,7 +4980,7 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
static void
hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
- struct folio *new_folio, pte_t old)
+ struct folio *new_folio, pte_t old, unsigned long sz)
{
pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
@@ -4988,7 +4988,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add
hugepage_add_new_anon_rmap(new_folio, vma, addr);
if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
newpte = huge_pte_mkuffd_wp(newpte);
- set_huge_pte_at(vma->vm_mm, addr, ptep, newpte);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz);
hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
folio_set_hugetlb_migratable(new_folio);
}
@@ -5065,7 +5065,7 @@ again:
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
- set_huge_pte_at(dst, addr, dst_pte, entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry, sz);
} else if (unlikely(is_hugetlb_entry_migration(entry))) {
swp_entry_t swp_entry = pte_to_swp_entry(entry);
bool uffd_wp = pte_swp_uffd_wp(entry);
@@ -5080,18 +5080,18 @@ again:
entry = swp_entry_to_pte(swp_entry);
if (userfaultfd_wp(src_vma) && uffd_wp)
entry = pte_swp_mkuffd_wp(entry);
- set_huge_pte_at(src, addr, src_pte, entry);
+ set_huge_pte_at(src, addr, src_pte, entry, sz);
}
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
- set_huge_pte_at(dst, addr, dst_pte, entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry, sz);
} else if (unlikely(is_pte_marker(entry))) {
pte_marker marker = copy_pte_marker(
pte_to_swp_entry(entry), dst_vma);
if (marker)
set_huge_pte_at(dst, addr, dst_pte,
- make_pte_marker(marker));
+ make_pte_marker(marker), sz);
} else {
entry = huge_ptep_get(src_pte);
pte_folio = page_folio(pte_page(entry));
@@ -5145,7 +5145,7 @@ again:
goto again;
}
hugetlb_install_folio(dst_vma, dst_pte, addr,
- new_folio, src_pte_old);
+ new_folio, src_pte_old, sz);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
continue;
@@ -5166,7 +5166,7 @@ again:
if (!userfaultfd_wp(dst_vma))
entry = huge_pte_clear_uffd_wp(entry);
- set_huge_pte_at(dst, addr, dst_pte, entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry, sz);
hugetlb_count_add(npages, dst);
}
spin_unlock(src_ptl);
@@ -5184,7 +5184,8 @@ again:
}
static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
- unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
+ unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte,
+ unsigned long sz)
{
struct hstate *h = hstate_vma(vma);
struct mm_struct *mm = vma->vm_mm;
@@ -5202,7 +5203,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
- set_huge_pte_at(mm, new_addr, dst_pte, pte);
+ set_huge_pte_at(mm, new_addr, dst_pte, pte, sz);
if (src_ptl != dst_ptl)
spin_unlock(src_ptl);
@@ -5259,7 +5260,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
if (!dst_pte)
break;
- move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
+ move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz);
}
if (shared_pmd)
@@ -5337,7 +5338,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
if (pte_swp_uffd_wp_any(pte) &&
!(zap_flags & ZAP_FLAG_DROP_MARKER))
set_huge_pte_at(mm, address, ptep,
- make_pte_marker(PTE_MARKER_UFFD_WP));
+ make_pte_marker(PTE_MARKER_UFFD_WP),
+ sz);
else
huge_pte_clear(mm, address, ptep, sz);
spin_unlock(ptl);
@@ -5371,7 +5373,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
if (huge_pte_uffd_wp(pte) &&
!(zap_flags & ZAP_FLAG_DROP_MARKER))
set_huge_pte_at(mm, address, ptep,
- make_pte_marker(PTE_MARKER_UFFD_WP));
+ make_pte_marker(PTE_MARKER_UFFD_WP),
+ sz);
hugetlb_count_sub(pages_per_huge_page(h), mm);
page_remove_rmap(page, vma, true);
@@ -5676,7 +5679,7 @@ retry_avoidcopy:
hugepage_add_new_anon_rmap(new_folio, vma, haddr);
if (huge_pte_uffd_wp(pte))
newpte = huge_pte_mkuffd_wp(newpte);
- set_huge_pte_at(mm, haddr, ptep, newpte);
+ set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h));
folio_set_hugetlb_migratable(new_folio);
/* Make the old page be freed below */
new_folio = old_folio;
@@ -5972,7 +5975,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
*/
if (unlikely(pte_marker_uffd_wp(old_pte)))
new_pte = huge_pte_mkuffd_wp(new_pte);
- set_huge_pte_at(mm, haddr, ptep, new_pte);
+ set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h));
hugetlb_count_add(pages_per_huge_page(h), mm);
if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
@@ -6261,7 +6264,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
}
_dst_pte = make_pte_marker(PTE_MARKER_POISONED);
- set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+ set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte,
+ huge_page_size(h));
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
@@ -6412,7 +6416,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
if (wp_enabled)
_dst_pte = huge_pte_mkuffd_wp(_dst_pte);
- set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+ set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h));
hugetlb_count_add(pages_per_huge_page(h), dst_mm);
@@ -6598,7 +6602,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
else if (uffd_wp_resolve)
newpte = pte_swp_clear_uffd_wp(newpte);
if (!pte_same(pte, newpte))
- set_huge_pte_at(mm, address, ptep, newpte);
+ set_huge_pte_at(mm, address, ptep, newpte, psize);
} else if (unlikely(is_pte_marker(pte))) {
/* No other markers apply for now. */
WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
@@ -6623,7 +6627,8 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
if (unlikely(uffd_wp))
/* Safe to modify directly (none->non-present). */
set_huge_pte_at(mm, address, ptep,
- make_pte_marker(PTE_MARKER_UFFD_WP));
+ make_pte_marker(PTE_MARKER_UFFD_WP),
+ psize);
}
spin_unlock(ptl);
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d13dde2f8b56..5b009b233ab8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3867,6 +3867,13 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
case _MEMSWAP:
ret = mem_cgroup_resize_max(memcg, nr_pages, true);
break;
+ case _KMEM:
+ pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
+ "Writing any value to this file has no effect. "
+ "Please report your usecase to linux-mm@kvack.org if you "
+ "depend on this functionality.\n");
+ ret = 0;
+ break;
case _TCP:
ret = memcg_update_tcp_max(memcg, nr_pages);
break;
@@ -5078,6 +5085,12 @@ static struct cftype mem_cgroup_legacy_files[] = {
},
#endif
{
+ .name = "kmem.limit_in_bytes",
+ .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+ .write = mem_cgroup_write,
+ .read_u64 = mem_cgroup_read_u64,
+ },
+ {
.name = "kmem.usage_in_bytes",
.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
.read_u64 = mem_cgroup_read_u64,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 42b5567e3773..f1b00d6ac7ee 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -426,6 +426,7 @@ struct queue_pages {
unsigned long start;
unsigned long end;
struct vm_area_struct *first;
+ bool has_unmovable;
};
/*
@@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio,
/*
* queue_folios_pmd() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. huge zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
* existing folio was already on a node that does not follow the
* policy.
@@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
if (!vma_migratable(walk->vma) ||
migrate_folio_add(folio, qp->pagelist, flags)) {
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
} else
@@ -495,9 +495,8 @@ unlock:
*
* queue_folios_pte_range() has three possible return values:
* 0 - folios are placed on the right node or queued successfully, or
- * special page is met, i.e. zero page.
- * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
- * specified.
+ * special page is met, i.e. zero page, or unmovable page is found
+ * but continue walking (indicated by queue_pages.has_unmovable).
* -EIO - only MPOL_MF_STRICT was specified and an existing folio was already
* on a node that does not follow the policy.
*/
@@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
struct folio *folio;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- bool has_unmovable = false;
pte_t *pte, *mapped_pte;
pte_t ptent;
spinlock_t *ptl;
@@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (!queue_folio_required(folio, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* MPOL_MF_STRICT must be specified if we get here */
- if (!vma_migratable(vma)) {
- has_unmovable = true;
- break;
- }
+ /*
+ * MPOL_MF_STRICT must be specified if we get here.
+ * Continue walking vmas due to MPOL_MF_MOVE* flags.
+ */
+ if (!vma_migratable(vma))
+ qp->has_unmovable = true;
/*
* Do not abort immediately since there may be
@@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
* need migrate other LRU pages.
*/
if (migrate_folio_add(folio, qp->pagelist, flags))
- has_unmovable = true;
+ qp->has_unmovable = true;
} else
break;
}
pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
- if (has_unmovable)
- return 1;
-
return addr != end ? -EIO : 0;
}
@@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Detecting misplaced folio but allow migrating folios which
* have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
goto unlock;
}
@@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
* Failed to isolate folio but allow migrating pages
* which have been queued.
*/
- ret = 1;
+ qp->has_unmovable = true;
}
unlock:
spin_unlock(ptl);
@@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
.start = start,
.end = end,
.first = NULL,
+ .has_unmovable = false,
};
const struct mm_walk_ops *ops = lock_vma ?
&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
err = walk_page_range(mm, start, end, ops, &qp);
+ if (qp.has_unmovable)
+ err = 1;
if (!qp.first)
/* whole range in hole */
err = -EFAULT;
@@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len,
putback_movable_pages(&pagelist);
}
- if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
+ if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT))
err = -EIO;
} else {
up_out:
diff --git a/mm/migrate.c b/mm/migrate.c
index b7fa020003f3..2053b54556ca 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -243,7 +243,9 @@ static bool remove_migration_pte(struct folio *folio,
#ifdef CONFIG_HUGETLB_PAGE
if (folio_test_hugetlb(folio)) {
- unsigned int shift = huge_page_shift(hstate_vma(vma));
+ struct hstate *h = hstate_vma(vma);
+ unsigned int shift = huge_page_shift(h);
+ unsigned long psize = huge_page_size(h);
pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
if (folio_test_anon(folio))
@@ -251,7 +253,8 @@ static bool remove_migration_pte(struct folio *folio,
rmap_flags);
else
page_dup_file_rmap(new, true);
- set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
+ set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte,
+ psize);
} else
#endif
{
diff --git a/mm/rmap.c b/mm/rmap.c
index ec7f8e6c9e48..9f795b93cf40 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1480,6 +1480,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
unsigned long pfn;
+ unsigned long hsz = 0;
/*
* When racing against e.g. zap_pte_range() on another cpu,
@@ -1511,6 +1512,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
+
+ /* We need the huge page size for set_huge_pte_at() */
+ hsz = huge_page_size(hstate_vma(vma));
}
mmu_notifier_invalidate_range_start(&range);
@@ -1628,7 +1632,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
- set_huge_pte_at(mm, address, pvmw.pte, pteval);
+ set_huge_pte_at(mm, address, pvmw.pte, pteval,
+ hsz);
} else {
dec_mm_counter(mm, mm_counter(&folio->page));
set_pte_at(mm, address, pvmw.pte, pteval);
@@ -1820,6 +1825,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
unsigned long pfn;
+ unsigned long hsz = 0;
/*
* When racing against e.g. zap_pte_range() on another cpu,
@@ -1855,6 +1861,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
+
+ /* We need the huge page size for set_huge_pte_at() */
+ hsz = huge_page_size(hstate_vma(vma));
}
mmu_notifier_invalidate_range_start(&range);
@@ -2020,7 +2029,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);
- set_huge_pte_at(mm, address, pvmw.pte, pteval);
+ set_huge_pte_at(mm, address, pvmw.pte, pteval,
+ hsz);
} else {
dec_mm_counter(mm, mm_counter(&folio->page));
set_pte_at(mm, address, pvmw.pte, pteval);
@@ -2044,7 +2054,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
if (arch_unmap_one(mm, vma, address, pteval) < 0) {
if (folio_test_hugetlb(folio))
- set_huge_pte_at(mm, address, pvmw.pte, pteval);
+ set_huge_pte_at(mm, address, pvmw.pte,
+ pteval, hsz);
else
set_pte_at(mm, address, pvmw.pte, pteval);
ret = false;
@@ -2058,7 +2069,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
if (anon_exclusive &&
page_try_share_anon_rmap(subpage)) {
if (folio_test_hugetlb(folio))
- set_huge_pte_at(mm, address, pvmw.pte, pteval);
+ set_huge_pte_at(mm, address, pvmw.pte,
+ pteval, hsz);
else
set_pte_at(mm, address, pvmw.pte, pteval);
ret = false;
@@ -2090,7 +2102,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
if (pte_uffd_wp(pteval))
swp_pte = pte_swp_mkuffd_wp(swp_pte);
if (folio_test_hugetlb(folio))
- set_huge_pte_at(mm, address, pvmw.pte, swp_pte);
+ set_huge_pte_at(mm, address, pvmw.pte, swp_pte,
+ hsz);
else
set_pte_at(mm, address, pvmw.pte, swp_pte);
trace_set_migration_pte(address, pte_val(swp_pte),
diff --git a/mm/slab_common.c b/mm/slab_common.c
index cd71f9581e67..8fda308e400d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -479,7 +479,7 @@ void slab_kmem_cache_release(struct kmem_cache *s)
void kmem_cache_destroy(struct kmem_cache *s)
{
- int refcnt;
+ int err = -EBUSY;
bool rcu_set;
if (unlikely(!s) || !kasan_check_byte(s))
@@ -490,17 +490,17 @@ void kmem_cache_destroy(struct kmem_cache *s)
rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU;
- refcnt = --s->refcount;
- if (refcnt)
+ s->refcount--;
+ if (s->refcount)
goto out_unlock;
- WARN(shutdown_cache(s),
- "%s %s: Slab cache still has objects when called from %pS",
+ err = shutdown_cache(s);
+ WARN(err, "%s %s: Slab cache still has objects when called from %pS",
__func__, s->name, (void *)_RET_IP_);
out_unlock:
mutex_unlock(&slab_mutex);
cpus_read_unlock();
- if (!refcnt && !rcu_set)
+ if (!err && !rcu_set)
kmem_cache_release(s);
}
EXPORT_SYMBOL(kmem_cache_destroy);
@@ -745,24 +745,24 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller)
size_t kmalloc_size_roundup(size_t size)
{
- struct kmem_cache *c;
+ if (size && size <= KMALLOC_MAX_CACHE_SIZE) {
+ /*
+ * The flags don't matter since size_index is common to all.
+ * Neither does the caller for just getting ->object_size.
+ */
+ return kmalloc_slab(size, GFP_KERNEL, 0)->object_size;
+ }
- /* Short-circuit the 0 size case. */
- if (unlikely(size == 0))
- return 0;
- /* Short-circuit saturated "too-large" case. */
- if (unlikely(size == SIZE_MAX))
- return SIZE_MAX;
/* Above the smaller buckets, size is a multiple of page size. */
- if (size > KMALLOC_MAX_CACHE_SIZE)
+ if (size && size <= KMALLOC_MAX_SIZE)
return PAGE_SIZE << get_order(size);
/*
- * The flags don't matter since size_index is common to all.
- * Neither does the caller for just getting ->object_size.
+ * Return 'size' for 0 - kmalloc() returns ZERO_SIZE_PTR
+ * and very large size - kmalloc() may fail.
*/
- c = kmalloc_slab(size, GFP_KERNEL, 0);
- return c ? c->object_size : 0;
+ return size;
+
}
EXPORT_SYMBOL(kmalloc_size_roundup);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ef8599d394fd..a3fedb3ee0db 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -111,7 +111,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t entry = pfn_pte(pfn, prot);
entry = arch_make_huge_pte(entry, ilog2(size), 0);
- set_huge_pte_at(&init_mm, addr, pte, entry);
+ set_huge_pte_at(&init_mm, addr, pte, entry, size);
pfn += PFN_DOWN(size);
continue;
}
diff --git a/mm/zswap.c b/mm/zswap.c
index 412b1409a0d7..083c693602b8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1219,6 +1219,19 @@ bool zswap_store(struct folio *folio)
return false;
/*
+ * If this is a duplicate, it must be removed before attempting to store
+ * it, otherwise, if the store fails the old page won't be removed from
+ * the tree, and it might be written back overriding the new data.
+ */
+ spin_lock(&tree->lock);
+ dupentry = zswap_rb_search(&tree->rbroot, offset);
+ if (dupentry) {
+ zswap_duplicate_entry++;
+ zswap_invalidate_entry(tree, dupentry);
+ }
+ spin_unlock(&tree->lock);
+
+ /*
* XXX: zswap reclaim does not work with cgroups yet. Without a
* cgroup-aware entry LRU, we will push out entries system-wide based on
* local cgroup limits.
@@ -1333,7 +1346,14 @@ insert_entry:
/* map */
spin_lock(&tree->lock);
+ /*
+ * A duplicate entry should have been removed at the beginning of this
+ * function. Since the swap entry should be pinned, if a duplicate is
+ * found again here it means that something went wrong in the swap
+ * cache.
+ */
while (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) {
+ WARN_ON(1);
zswap_duplicate_entry++;
zswap_invalidate_entry(tree, dupentry);
}
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index a00a53e15ab7..1d111350197f 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -57,6 +57,7 @@
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */
#define MSR_PPIN_CTL 0x0000004e
#define MSR_PPIN 0x0000004f
@@ -155,6 +156,15 @@
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
*/
+#define ARCH_CAP_GDS_CTRL BIT(25) /*
+ * CPU is vulnerable to Gather
+ * Data Sampling (GDS) and
+ * has controls for mitigation.
+ */
+#define ARCH_CAP_GDS_NO BIT(26) /*
+ * CPU is not vulnerable to Gather
+ * Data Sampling (GDS).
+ */
#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
* IA32_XAPIC_DISABLE_STATUS MSR
@@ -178,6 +188,8 @@
#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */
#define RTM_ALLOW BIT(1) /* TSX development mode */
#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */
+#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */
+#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index fd6c1cb585db..abe087c53b4b 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
#define __NR_cachestat 451
__SYSCALL(__NR_cachestat, sys_cachestat)
+#define __NR_fchmodat2 452
+__SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+
#undef __NR_syscalls
-#define __NR_syscalls 452
+#define __NR_syscalls 453
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index a87bbbbca2d4..794c1d857677 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -673,8 +673,11 @@ struct drm_gem_open {
* Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT
* and &DRM_PRIME_CAP_EXPORT.
*
- * PRIME buffers are exposed as dma-buf file descriptors. See
- * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing".
+ * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and
+ * &DRM_PRIME_CAP_EXPORT are always advertised.
+ *
+ * PRIME buffers are exposed as dma-buf file descriptors.
+ * See :ref:`prime_buffer_sharing`.
*/
#define DRM_CAP_PRIME 0x5
/**
@@ -682,6 +685,8 @@ struct drm_gem_open {
*
* If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME
* buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
*/
#define DRM_PRIME_CAP_IMPORT 0x1
/**
@@ -689,6 +694,8 @@ struct drm_gem_open {
*
* If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME
* buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
*/
#define DRM_PRIME_CAP_EXPORT 0x2
/**
@@ -756,15 +763,14 @@ struct drm_gem_open {
/**
* DRM_CAP_SYNCOBJ
*
- * If set to 1, the driver supports sync objects. See
- * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects".
+ * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`.
*/
#define DRM_CAP_SYNCOBJ 0x13
/**
* DRM_CAP_SYNCOBJ_TIMELINE
*
* If set to 1, the driver supports timeline operations on sync objects. See
- * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects".
+ * :ref:`drm_sync_objects`.
*/
#define DRM_CAP_SYNCOBJ_TIMELINE 0x14
@@ -909,6 +915,27 @@ struct drm_syncobj_timeline_wait {
__u32 pad;
};
+/**
+ * struct drm_syncobj_eventfd
+ * @handle: syncobj handle.
+ * @flags: Zero to wait for the point to be signalled, or
+ * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be
+ * available for the point.
+ * @point: syncobj timeline point (set to zero for binary syncobjs).
+ * @fd: Existing eventfd to sent events to.
+ * @pad: Must be zero.
+ *
+ * Register an eventfd to be signalled by a syncobj. The eventfd counter will
+ * be incremented by one.
+ */
+struct drm_syncobj_eventfd {
+ __u32 handle;
+ __u32 flags;
+ __u64 point;
+ __s32 fd;
+ __u32 pad;
+};
+
struct drm_syncobj_array {
__u64 handles;
@@ -1169,6 +1196,8 @@ extern "C" {
*/
#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
+#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
+
/*
* Device specific ioctls should only be in their respective headers
* The device specific ioctl range is from 0x40 to 0x9f.
@@ -1180,25 +1209,50 @@ extern "C" {
#define DRM_COMMAND_BASE 0x40
#define DRM_COMMAND_END 0xA0
-/*
- * Header for events written back to userspace on the drm fd. The
- * type defines the type of event, the length specifies the total
- * length of the event (including the header), and user_data is
- * typically a 64 bit value passed with the ioctl that triggered the
- * event. A read on the drm fd will always only return complete
- * events, that is, if for example the read buffer is 100 bytes, and
- * there are two 64 byte events pending, only one will be returned.
+/**
+ * struct drm_event - Header for DRM events
+ * @type: event type.
+ * @length: total number of payload bytes (including header).
*
- * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and
- * up are chipset specific.
+ * This struct is a header for events written back to user-space on the DRM FD.
+ * A read on the DRM FD will always only return complete events: e.g. if the
+ * read buffer is 100 bytes large and there are two 64 byte events pending,
+ * only one will be returned.
+ *
+ * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and
+ * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK,
+ * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE.
*/
struct drm_event {
__u32 type;
__u32 length;
};
+/**
+ * DRM_EVENT_VBLANK - vertical blanking event
+ *
+ * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the
+ * &_DRM_VBLANK_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
#define DRM_EVENT_VBLANK 0x01
+/**
+ * DRM_EVENT_FLIP_COMPLETE - page-flip completion event
+ *
+ * This event is sent in response to an atomic commit or legacy page-flip with
+ * the &DRM_MODE_PAGE_FLIP_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
#define DRM_EVENT_FLIP_COMPLETE 0x02
+/**
+ * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event
+ *
+ * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE.
+ *
+ * The event payload is a struct drm_event_crtc_sequence.
+ */
#define DRM_EVENT_CRTC_SEQUENCE 0x03
struct drm_event_vblank {
diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h
new file mode 100644
index 000000000000..dbfc9b37fcae
--- /dev/null
+++ b/tools/include/uapi/linux/seccomp.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SECCOMP_H
+#define _UAPI_LINUX_SECCOMP_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+
+/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
+#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */
+#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
+#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+#define SECCOMP_GET_ACTION_AVAIL 2
+#define SECCOMP_GET_NOTIF_SIZES 3
+
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
+#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
+/* Received notifications wait in killable state (only respond to fatal signals) */
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5)
+
+/*
+ * All BPF programs must return a 32-bit value.
+ * The bottom 16-bits are for optional return data.
+ * The upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
+ *
+ * The ordering ensures that a min_t() over composed return values always
+ * selects the least permissive choice.
+ */
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
+#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
+
+/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL 0xffff0000U
+#define SECCOMP_RET_ACTION 0x7fff0000U
+#define SECCOMP_RET_DATA 0x0000ffffU
+
+/**
+ * struct seccomp_data - the format the BPF program executes over.
+ * @nr: the system call number
+ * @arch: indicates system call convention as an AUDIT_ARCH_* value
+ * as defined in <linux/audit.h>.
+ * @instruction_pointer: at the time of the system call.
+ * @args: up to 6 system call arguments always stored as 64-bit values
+ * regardless of the architecture.
+ */
+struct seccomp_data {
+ int nr;
+ __u32 arch;
+ __u64 instruction_pointer;
+ __u64 args[6];
+};
+
+struct seccomp_notif_sizes {
+ __u16 seccomp_notif;
+ __u16 seccomp_notif_resp;
+ __u16 seccomp_data;
+};
+
+struct seccomp_notif {
+ __u64 id;
+ __u32 pid;
+ __u32 flags;
+ struct seccomp_data data;
+};
+
+/*
+ * Valid flags for struct seccomp_notif_resp
+ *
+ * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
+ * If set by the process supervising the syscalls of another process the
+ * syscall will continue. This is problematic because of an inherent TOCTOU.
+ * An attacker can exploit the time while the supervised process is waiting on
+ * a response from the supervising process to rewrite syscall arguments which
+ * are passed as pointers of the intercepted syscall.
+ * It should be absolutely clear that this means that the seccomp notifier
+ * _cannot_ be used to implement a security policy! It should only ever be used
+ * in scenarios where a more privileged process supervises the syscalls of a
+ * lesser privileged process to get around kernel-enforced security
+ * restrictions when the privileged process deems this safe. In other words,
+ * in order to continue a syscall the supervising process should be sure that
+ * another security mechanism or the kernel itself will sufficiently block
+ * syscalls if arguments are rewritten to something unsafe.
+ *
+ * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
+ * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
+ * same syscall, the most recently added filter takes precedence. This means
+ * that the new SECCOMP_RET_USER_NOTIF filter can override any
+ * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
+ * such filtered syscalls to be executed by sending the response
+ * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
+ * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
+ */
+#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)
+
+struct seccomp_notif_resp {
+ __u64 id;
+ __s64 val;
+ __s32 error;
+ __u32 flags;
+};
+
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
+#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */
+
+/**
+ * struct seccomp_notif_addfd
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: The O_* flags the remote FD should have applied
+ */
+struct seccomp_notif_addfd {
+ __u64 id;
+ __u32 flags;
+ __u32 srcfd;
+ __u32 newfd;
+ __u32 newfd_flags;
+};
+
+#define SECCOMP_IOC_MAGIC '!'
+#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
+#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type)
+
+/* Flags for seccomp notification fd ioctl. */
+#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif)
+#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
+ struct seccomp_notif_resp)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
+ struct seccomp_notif_addfd)
+
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64)
+
+#endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index cfda2511badf..cb5e757f6621 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -366,3 +366,4 @@
449 n64 futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 n64 cachestat sys_cachestat
+452 n64 fchmodat2 sys_fchmodat2
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 8c0b08b7a80e..20e50586e8a2 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -538,3 +538,4 @@
449 common futex_waitv sys_futex_waitv
450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index a6935af2235c..0122cc156952 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
449 common futex_waitv sys_futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2 sys_fchmodat2
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 227538b0ce80..1d6eee30eceb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -373,6 +373,8 @@
449 common futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2
+453 64 map_shadow_stack sys_map_shadow_stack
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c
index b04ebcde4036..a01c40131493 100644
--- a/tools/perf/bench/sched-seccomp-notify.c
+++ b/tools/perf/bench/sched-seccomp-notify.c
@@ -9,7 +9,7 @@
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <linux/time64.h>
-#include <linux/seccomp.h>
+#include <uapi/linux/seccomp.h>
#include <sys/prctl.h>
#include <unistd.h>
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 4314c9197850..e21caadda7c1 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -21,6 +21,7 @@ FILES=(
"include/uapi/linux/perf_event.h"
"include/uapi/linux/prctl.h"
"include/uapi/linux/sched.h"
+ "include/uapi/linux/seccomp.h"
"include/uapi/linux/stat.h"
"include/uapi/linux/usbdevice_fs.h"
"include/uapi/linux/vhost.h"
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index a7e88332276d..72ba4a9239c6 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -991,7 +991,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
}
}
free(cpuid);
- if (!pmu)
+ if (!pmu || !table)
return table;
for (i = 0; i < table->num_pmus; i++) {
diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py
index 0e9ec65d92ae..3e673f25d5fd 100644
--- a/tools/perf/pmu-events/metric.py
+++ b/tools/perf/pmu-events/metric.py
@@ -413,10 +413,10 @@ def has_event(event: Event) -> Function:
# pylint: disable=invalid-name
return Function('has_event', event)
-def strcmp_cpuid_str(event: str) -> Function:
+def strcmp_cpuid_str(cpuid: Event) -> Function:
# pylint: disable=redefined-builtin
# pylint: disable=invalid-name
- return Function('strcmp_cpuid_str', event)
+ return Function('strcmp_cpuid_str', cpuid)
class Metric:
"""An individual metric that will specifiable on the perf command line."""
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
deleted file mode 100644
index 9887ae09242d..000000000000
--- a/tools/perf/util/bpf-prologue.c
+++ /dev/null
@@ -1,508 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-prologue.c
- *
- * Copyright (C) 2015 He Kuang <hekuang@huawei.com>
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- */
-
-#include <bpf/libbpf.h>
-#include "debug.h"
-#include "bpf-loader.h"
-#include "bpf-prologue.h"
-#include "probe-finder.h"
-#include <errno.h>
-#include <stdlib.h>
-#include <dwarf-regs.h>
-#include <linux/filter.h>
-
-#define BPF_REG_SIZE 8
-
-#define JMP_TO_ERROR_CODE -1
-#define JMP_TO_SUCCESS_CODE -2
-#define JMP_TO_USER_CODE -3
-
-struct bpf_insn_pos {
- struct bpf_insn *begin;
- struct bpf_insn *end;
- struct bpf_insn *pos;
-};
-
-static inline int
-pos_get_cnt(struct bpf_insn_pos *pos)
-{
- return pos->pos - pos->begin;
-}
-
-static int
-append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos)
-{
- if (!pos->pos)
- return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-
- if (pos->pos + 1 >= pos->end) {
- pr_err("bpf prologue: prologue too long\n");
- pos->pos = NULL;
- return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
- }
-
- *(pos->pos)++ = new_insn;
- return 0;
-}
-
-static int
-check_pos(struct bpf_insn_pos *pos)
-{
- if (!pos->pos || pos->pos >= pos->end)
- return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
- return 0;
-}
-
-/*
- * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
- * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM
- * instruction (BPF_{B,H,W,DW}).
- */
-static int
-argtype_to_ldx_size(const char *type)
-{
- int arg_size = type ? atoi(&type[1]) : 64;
-
- switch (arg_size) {
- case 8:
- return BPF_B;
- case 16:
- return BPF_H;
- case 32:
- return BPF_W;
- case 64:
- default:
- return BPF_DW;
- }
-}
-
-static const char *
-insn_sz_to_str(int insn_sz)
-{
- switch (insn_sz) {
- case BPF_B:
- return "BPF_B";
- case BPF_H:
- return "BPF_H";
- case BPF_W:
- return "BPF_W";
- case BPF_DW:
- return "BPF_DW";
- default:
- return "UNKNOWN";
- }
-}
-
-/* Give it a shorter name */
-#define ins(i, p) append_insn((i), (p))
-
-/*
- * Give a register name (in 'reg'), generate instruction to
- * load register into an eBPF register rd:
- * 'ldd target_reg, offset(ctx_reg)', where:
- * ctx_reg is pre initialized to pointer of 'struct pt_regs'.
- */
-static int
-gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg,
- const char *reg, int target_reg)
-{
- int offset = regs_query_register_offset(reg);
-
- if (offset < 0) {
- pr_err("bpf: prologue: failed to get register %s\n",
- reg);
- return offset;
- }
- ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos);
-
- return check_pos(pos);
-}
-
-/*
- * Generate a BPF_FUNC_probe_read function call.
- *
- * src_base_addr_reg is a register holding base address,
- * dst_addr_reg is a register holding dest address (on stack),
- * result is:
- *
- * *[dst_addr_reg] = *([src_base_addr_reg] + offset)
- *
- * Arguments of BPF_FUNC_probe_read:
- * ARG1: ptr to stack (dest)
- * ARG2: size (8)
- * ARG3: unsafe ptr (src)
- */
-static int
-gen_read_mem(struct bpf_insn_pos *pos,
- int src_base_addr_reg,
- int dst_addr_reg,
- long offset,
- int probeid)
-{
- /* mov arg3, src_base_addr_reg */
- if (src_base_addr_reg != BPF_REG_ARG3)
- ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos);
- /* add arg3, #offset */
- if (offset)
- ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos);
-
- /* mov arg2, #reg_size */
- ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos);
-
- /* mov arg1, dst_addr_reg */
- if (dst_addr_reg != BPF_REG_ARG1)
- ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
-
- /* Call probe_read */
- ins(BPF_EMIT_CALL(probeid), pos);
- /*
- * Error processing: if read fail, goto error code,
- * will be relocated. Target should be the start of
- * error processing code.
- */
- ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE),
- pos);
-
- return check_pos(pos);
-}
-
-/*
- * Each arg should be bare register. Fetch and save them into argument
- * registers (r3 - r5).
- *
- * BPF_REG_1 should have been initialized with pointer to
- * 'struct pt_regs'.
- */
-static int
-gen_prologue_fastpath(struct bpf_insn_pos *pos,
- struct probe_trace_arg *args, int nargs)
-{
- int i, err = 0;
-
- for (i = 0; i < nargs; i++) {
- err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value,
- BPF_PROLOGUE_START_ARG_REG + i);
- if (err)
- goto errout;
- }
-
- return check_pos(pos);
-errout:
- return err;
-}
-
-/*
- * Slow path:
- * At least one argument has the form of 'offset($rx)'.
- *
- * Following code first stores them into stack, then loads all of then
- * to r2 - r5.
- * Before final loading, the final result should be:
- *
- * low address
- * BPF_REG_FP - 24 ARG3
- * BPF_REG_FP - 16 ARG2
- * BPF_REG_FP - 8 ARG1
- * BPF_REG_FP
- * high address
- *
- * For each argument (described as: offn(...off2(off1(reg)))),
- * generates following code:
- *
- * r7 <- fp
- * r7 <- r7 - stack_offset // Ideal code should initialize r7 using
- * // fp before generating args. However,
- * // eBPF won't regard r7 as stack pointer
- * // if it is generated by minus 8 from
- * // another stack pointer except fp.
- * // This is why we have to set r7
- * // to fp for each variable.
- * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx()
- * (r7) <- r3 // skip following instructions for bare reg
- * r3 <- r3 + off1 . // skip if off1 == 0
- * r2 <- 8 \
- * r1 <- r7 |-> generated by gen_read_mem()
- * call probe_read /
- * jnei r0, 0, err ./
- * r3 <- (r7)
- * r3 <- r3 + off2 . // skip if off2 == 0
- * r2 <- 8 \ // r2 may be broken by probe_read, so set again
- * r1 <- r7 |-> generated by gen_read_mem()
- * call probe_read /
- * jnei r0, 0, err ./
- * ...
- */
-static int
-gen_prologue_slowpath(struct bpf_insn_pos *pos,
- struct probe_trace_arg *args, int nargs)
-{
- int err, i, probeid;
-
- for (i = 0; i < nargs; i++) {
- struct probe_trace_arg *arg = &args[i];
- const char *reg = arg->value;
- struct probe_trace_arg_ref *ref = NULL;
- int stack_offset = (i + 1) * -8;
-
- pr_debug("prologue: fetch arg %d, base reg is %s\n",
- i, reg);
-
- /* value of base register is stored into ARG3 */
- err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg,
- BPF_REG_ARG3);
- if (err) {
- pr_err("prologue: failed to get offset of register %s\n",
- reg);
- goto errout;
- }
-
- /* Make r7 the stack pointer. */
- ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos);
- /* r7 += -8 */
- ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos);
- /*
- * Store r3 (base register) onto stack
- * Ensure fp[offset] is set.
- * fp is the only valid base register when storing
- * into stack. We are not allowed to use r7 as base
- * register here.
- */
- ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3,
- stack_offset), pos);
-
- ref = arg->ref;
- probeid = BPF_FUNC_probe_read_kernel;
- while (ref) {
- pr_debug("prologue: arg %d: offset %ld\n",
- i, ref->offset);
-
- if (ref->user_access)
- probeid = BPF_FUNC_probe_read_user;
-
- err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
- ref->offset, probeid);
- if (err) {
- pr_err("prologue: failed to generate probe_read function call\n");
- goto errout;
- }
-
- ref = ref->next;
- /*
- * Load previous result into ARG3. Use
- * BPF_REG_FP instead of r7 because verifier
- * allows FP based addressing only.
- */
- if (ref)
- ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3,
- BPF_REG_FP, stack_offset), pos);
- }
- }
-
- /* Final pass: read to registers */
- for (i = 0; i < nargs; i++) {
- int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW;
-
- pr_debug("prologue: load arg %d, insn_sz is %s\n",
- i, insn_sz_to_str(insn_sz));
- ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
- BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
- }
-
- ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
-
- return check_pos(pos);
-errout:
- return err;
-}
-
-static int
-prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code,
- struct bpf_insn *success_code, struct bpf_insn *user_code)
-{
- struct bpf_insn *insn;
-
- if (check_pos(pos))
- return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-
- for (insn = pos->begin; insn < pos->pos; insn++) {
- struct bpf_insn *target;
- u8 class = BPF_CLASS(insn->code);
- u8 opcode;
-
- if (class != BPF_JMP)
- continue;
- opcode = BPF_OP(insn->code);
- if (opcode == BPF_CALL)
- continue;
-
- switch (insn->off) {
- case JMP_TO_ERROR_CODE:
- target = error_code;
- break;
- case JMP_TO_SUCCESS_CODE:
- target = success_code;
- break;
- case JMP_TO_USER_CODE:
- target = user_code;
- break;
- default:
- pr_err("bpf prologue: internal error: relocation failed\n");
- return -BPF_LOADER_ERRNO__PROLOGUE;
- }
-
- insn->off = target - (insn + 1);
- }
- return 0;
-}
-
-int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
- struct bpf_insn *new_prog, size_t *new_cnt,
- size_t cnt_space)
-{
- struct bpf_insn *success_code = NULL;
- struct bpf_insn *error_code = NULL;
- struct bpf_insn *user_code = NULL;
- struct bpf_insn_pos pos;
- bool fastpath = true;
- int err = 0, i;
-
- if (!new_prog || !new_cnt)
- return -EINVAL;
-
- if (cnt_space > BPF_MAXINSNS)
- cnt_space = BPF_MAXINSNS;
-
- pos.begin = new_prog;
- pos.end = new_prog + cnt_space;
- pos.pos = new_prog;
-
- if (!nargs) {
- ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0),
- &pos);
-
- if (check_pos(&pos))
- goto errout;
-
- *new_cnt = pos_get_cnt(&pos);
- return 0;
- }
-
- if (nargs > BPF_PROLOGUE_MAX_ARGS) {
- pr_warning("bpf: prologue: %d arguments are dropped\n",
- nargs - BPF_PROLOGUE_MAX_ARGS);
- nargs = BPF_PROLOGUE_MAX_ARGS;
- }
-
- /* First pass: validation */
- for (i = 0; i < nargs; i++) {
- struct probe_trace_arg_ref *ref = args[i].ref;
-
- if (args[i].value[0] == '@') {
- /* TODO: fetch global variable */
- pr_err("bpf: prologue: global %s%+ld not support\n",
- args[i].value, ref ? ref->offset : 0);
- return -ENOTSUP;
- }
-
- while (ref) {
- /* fastpath is true if all args has ref == NULL */
- fastpath = false;
-
- /*
- * Instruction encodes immediate value using
- * s32, ref->offset is long. On systems which
- * can't fill long in s32, refuse to process if
- * ref->offset too large (or small).
- */
-#ifdef __LP64__
-#define OFFSET_MAX ((1LL << 31) - 1)
-#define OFFSET_MIN ((1LL << 31) * -1)
- if (ref->offset > OFFSET_MAX ||
- ref->offset < OFFSET_MIN) {
- pr_err("bpf: prologue: offset out of bound: %ld\n",
- ref->offset);
- return -BPF_LOADER_ERRNO__PROLOGUEOOB;
- }
-#endif
- ref = ref->next;
- }
- }
- pr_debug("prologue: pass validation\n");
-
- if (fastpath) {
- /* If all variables are registers... */
- pr_debug("prologue: fast path\n");
- err = gen_prologue_fastpath(&pos, args, nargs);
- if (err)
- goto errout;
- } else {
- pr_debug("prologue: slow path\n");
-
- /* Initialization: move ctx to a callee saved register. */
- ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos);
-
- err = gen_prologue_slowpath(&pos, args, nargs);
- if (err)
- goto errout;
- /*
- * start of ERROR_CODE (only slow pass needs error code)
- * mov r2 <- 1 // r2 is error number
- * mov r3 <- 0 // r3, r4... should be touched or
- * // verifier would complain
- * mov r4 <- 0
- * ...
- * goto usercode
- */
- error_code = pos.pos;
- ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1),
- &pos);
-
- for (i = 0; i < nargs; i++)
- ins(BPF_ALU64_IMM(BPF_MOV,
- BPF_PROLOGUE_START_ARG_REG + i,
- 0),
- &pos);
- ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE),
- &pos);
- }
-
- /*
- * start of SUCCESS_CODE:
- * mov r2 <- 0
- * goto usercode // skip
- */
- success_code = pos.pos;
- ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos);
-
- /*
- * start of USER_CODE:
- * Restore ctx to r1
- */
- user_code = pos.pos;
- if (!fastpath) {
- /*
- * Only slow path needs restoring of ctx. In fast path,
- * register are loaded directly from r1.
- */
- ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos);
- err = prologue_relocate(&pos, error_code, success_code,
- user_code);
- if (err)
- goto errout;
- }
-
- err = check_pos(&pos);
- if (err)
- goto errout;
-
- *new_cnt = pos_get_cnt(&pos);
- return 0;
-errout:
- return err;
-}
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 90ce22f9c1a9..939ec769bf4a 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -23,7 +23,9 @@
#define MAX_CPUS 4096
// FIXME: These should come from system headers
+#ifndef bool
typedef char bool;
+#endif
typedef int pid_t;
typedef long long int __s64;
typedef __s64 time64_t;
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index 0a5bf1937a7c..c12f8320e668 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -80,16 +80,6 @@ struct hashmap {
size_t sz;
};
-#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \
- .hash_fn = (hash_fn), \
- .equal_fn = (equal_fn), \
- .ctx = (ctx), \
- .buckets = NULL, \
- .cap = 0, \
- .cap_bits = 0, \
- .sz = 0, \
-}
-
void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
hashmap_equal_fn equal_fn, void *ctx);
struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d85602aa4b9f..8de6f39abd1b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -520,7 +520,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
pmu_name = pe->pmu;
}
- alias = malloc(sizeof(*alias));
+ alias = zalloc(sizeof(*alias));
if (!alias)
return -ENOMEM;
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index a5cb4b09a46c..0899019a7fcb 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -25,7 +25,7 @@ if [[ "$1" == "-cgroup-v2" ]]; then
fi
if [[ $cgroup2 ]]; then
- cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
cgroup_path=/dev/cgroup/memory
mount -t cgroup2 none $cgroup_path
@@ -33,7 +33,7 @@ if [[ $cgroup2 ]]; then
fi
echo "+hugetlb" >$cgroup_path/cgroup.subtree_control
else
- cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
cgroup_path=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $cgroup_path
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index bf2d2a684edf..14d26075c863 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -20,7 +20,7 @@ fi
if [[ $cgroup2 ]]; then
- CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$CGROUP_ROOT" ]]; then
CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup2 none $CGROUP_ROOT
@@ -28,7 +28,7 @@ if [[ $cgroup2 ]]; then
fi
echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
else
- CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
if [[ -z "$CGROUP_ROOT" ]]; then
CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $CGROUP_ROOT
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 49f2ad1793fd..7ea42fa02eab 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -59,12 +59,11 @@ override define INSTALL_RULE
done;
endef
-override define EMIT_TESTS
+emit_tests:
+@for TARGET in $(SUB_DIRS); do \
BUILD_TARGET=$(OUTPUT)/$$TARGET; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET $@;\
done;
-endef
override define CLEAN
+@for TARGET in $(SUB_DIRS); do \
@@ -77,4 +76,4 @@ endef
tags:
find . -name '*.c' -o -name '*.h' | xargs ctags
-.PHONY: tags $(SUB_DIRS)
+.PHONY: tags $(SUB_DIRS) emit_tests
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index 2b95e44d20ff..a284fa874a9f 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -30,13 +30,14 @@ override define RUN_TESTS
+TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests
endef
-DEFAULT_EMIT_TESTS := $(EMIT_TESTS)
-override define EMIT_TESTS
- $(DEFAULT_EMIT_TESTS)
+emit_tests:
+ for TEST in $(TEST_GEN_PROGS); do \
+ BASENAME_TEST=`basename $$TEST`; \
+ echo "$(COLLECTION):$$BASENAME_TEST"; \
+ done
+TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests
+TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests
+TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests
-endef
DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
override define INSTALL_RULE
@@ -64,4 +65,4 @@ sampling_tests:
event_code_tests:
TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all
-.PHONY: all run_tests ebb sampling_tests event_code_tests
+.PHONY: all run_tests ebb sampling_tests event_code_tests emit_tests
diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c
index 22374d29ffdd..8202f1327c39 100644
--- a/tools/testing/selftests/user_events/abi_test.c
+++ b/tools/testing/selftests/user_events/abi_test.c
@@ -91,16 +91,18 @@ static int reg_disable(long *enable, int bit)
FIXTURE(user) {
long check;
+ bool umount;
};
FIXTURE_SETUP(user) {
- USER_EVENT_FIXTURE_SETUP(return);
+ USER_EVENT_FIXTURE_SETUP(return, self->umount);
change_event(false);
self->check = 0;
}
FIXTURE_TEARDOWN(user) {
+ USER_EVENT_FIXTURE_TEARDOWN(self->umount);
}
TEST_F(user, enablement) {
diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c
index 32c827a52d7d..a85980190bea 100644
--- a/tools/testing/selftests/user_events/dyn_test.c
+++ b/tools/testing/selftests/user_events/dyn_test.c
@@ -144,13 +144,16 @@ do { \
FIXTURE(user) {
int check;
+ bool umount;
};
FIXTURE_SETUP(user) {
- USER_EVENT_FIXTURE_SETUP(return);
+ USER_EVENT_FIXTURE_SETUP(return, self->umount);
}
FIXTURE_TEARDOWN(user) {
+ USER_EVENT_FIXTURE_TEARDOWN(self->umount);
+
wait_for_delete();
}
diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c
index 6a260caeeddc..dcd7509fe2e0 100644
--- a/tools/testing/selftests/user_events/ftrace_test.c
+++ b/tools/testing/selftests/user_events/ftrace_test.c
@@ -204,10 +204,11 @@ FIXTURE(user) {
int data_fd;
int enable_fd;
int check;
+ bool umount;
};
FIXTURE_SETUP(user) {
- USER_EVENT_FIXTURE_SETUP(return);
+ USER_EVENT_FIXTURE_SETUP(return, self->umount);
self->status_fd = open(status_file, O_RDONLY);
ASSERT_NE(-1, self->status_fd);
@@ -219,6 +220,8 @@ FIXTURE_SETUP(user) {
}
FIXTURE_TEARDOWN(user) {
+ USER_EVENT_FIXTURE_TEARDOWN(self->umount);
+
close(self->status_fd);
close(self->data_fd);
diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c
index f893398cda05..5288e768b207 100644
--- a/tools/testing/selftests/user_events/perf_test.c
+++ b/tools/testing/selftests/user_events/perf_test.c
@@ -111,16 +111,19 @@ static int clear(int *check)
FIXTURE(user) {
int data_fd;
int check;
+ bool umount;
};
FIXTURE_SETUP(user) {
- USER_EVENT_FIXTURE_SETUP(return);
+ USER_EVENT_FIXTURE_SETUP(return, self->umount);
self->data_fd = open(data_file, O_RDWR);
ASSERT_NE(-1, self->data_fd);
}
FIXTURE_TEARDOWN(user) {
+ USER_EVENT_FIXTURE_TEARDOWN(self->umount);
+
close(self->data_fd);
if (clear(&self->check) != 0)
diff --git a/tools/testing/selftests/user_events/user_events_selftests.h b/tools/testing/selftests/user_events/user_events_selftests.h
index 690378942f82..e1c3c063c031 100644
--- a/tools/testing/selftests/user_events/user_events_selftests.h
+++ b/tools/testing/selftests/user_events/user_events_selftests.h
@@ -11,13 +11,19 @@
#include "../kselftest.h"
-static inline bool tracefs_enabled(char **message, bool *fail)
+static inline void tracefs_unmount(void)
+{
+ umount("/sys/kernel/tracing");
+}
+
+static inline bool tracefs_enabled(char **message, bool *fail, bool *umount)
{
struct stat buf;
int ret;
*message = "";
*fail = false;
+ *umount = false;
/* Ensure tracefs is installed */
ret = stat("/sys/kernel/tracing", &buf);
@@ -37,6 +43,8 @@ static inline bool tracefs_enabled(char **message, bool *fail)
return false;
}
+ *umount = true;
+
ret = stat("/sys/kernel/tracing/README", &buf);
}
@@ -49,13 +57,14 @@ static inline bool tracefs_enabled(char **message, bool *fail)
return true;
}
-static inline bool user_events_enabled(char **message, bool *fail)
+static inline bool user_events_enabled(char **message, bool *fail, bool *umount)
{
struct stat buf;
int ret;
*message = "";
*fail = false;
+ *umount = false;
if (getuid() != 0) {
*message = "Must be run as root";
@@ -63,7 +72,7 @@ static inline bool user_events_enabled(char **message, bool *fail)
return false;
}
- if (!tracefs_enabled(message, fail))
+ if (!tracefs_enabled(message, fail, umount))
return false;
/* Ensure user_events is installed */
@@ -85,10 +94,10 @@ static inline bool user_events_enabled(char **message, bool *fail)
return true;
}
-#define USER_EVENT_FIXTURE_SETUP(statement) do { \
+#define USER_EVENT_FIXTURE_SETUP(statement, umount) do { \
char *message; \
bool fail; \
- if (!user_events_enabled(&message, &fail)) { \
+ if (!user_events_enabled(&message, &fail, &(umount))) { \
if (fail) { \
TH_LOG("Setup failed due to: %s", message); \
ASSERT_FALSE(fail); \
@@ -97,4 +106,9 @@ static inline bool user_events_enabled(char **message, bool *fail)
} \
} while (0)
+#define USER_EVENT_FIXTURE_TEARDOWN(umount) do { \
+ if ((umount)) \
+ tracefs_unmount(); \
+} while (0)
+
#endif /* _USER_EVENTS_SELFTESTS_H */