summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/testing/sysfs-devices-system-cpu1
-rw-r--r--Documentation/admin-guide/hw-vuln/index.rst1
-rw-r--r--Documentation/admin-guide/hw-vuln/vmscape.rst110
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt11
-rw-r--r--Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml5
-rw-r--r--Documentation/netlink/specs/mptcp_pm.yaml2
-rw-r--r--Documentation/networking/can.rst2
-rw-r--r--Documentation/networking/mptcp.rst8
-rw-r--r--MAINTAINERS6
-rw-r--r--Makefile2
-rw-r--r--arch/arm64/include/asm/module.h1
-rw-r--r--arch/arm64/include/asm/module.lds.h1
-rw-r--r--arch/arm64/include/uapi/asm/bitsperlong.h5
-rw-r--r--arch/arm64/kernel/ftrace.c13
-rw-r--r--arch/arm64/kernel/machine_kexec_file.c2
-rw-r--r--arch/arm64/kernel/module-plts.c12
-rw-r--r--arch/arm64/kernel/module.c11
-rw-r--r--arch/riscv/Kconfig2
-rw-r--r--arch/riscv/include/asm/asm.h2
-rw-r--r--arch/riscv/include/asm/uaccess.h8
-rw-r--r--arch/riscv/kernel/entry.S2
-rw-r--r--arch/riscv/kernel/kexec_elf.c4
-rw-r--r--arch/riscv/kernel/kexec_image.c2
-rw-r--r--arch/riscv/kernel/machine_kexec_file.c2
-rw-r--r--arch/riscv/net/bpf_jit_comp64.c4
-rw-r--r--arch/s390/kernel/kexec_elf.c2
-rw-r--r--arch/s390/kernel/kexec_image.c2
-rw-r--r--arch/s390/kernel/machine_kexec_file.c6
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c4
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c4
-rw-r--r--arch/s390/kernel/perf_pai_ext.c2
-rw-r--r--arch/s390/mm/pgtable.c2
-rw-r--r--arch/x86/Kconfig9
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/entry-common.h7
-rw-r--r--arch/x86/include/asm/nospec-branch.h2
-rw-r--r--arch/x86/kernel/cpu/bugs.c285
-rw-r--r--arch/x86/kernel/cpu/common.c86
-rw-r--r--arch/x86/kvm/x86.c9
-rw-r--r--block/fops.c13
-rw-r--r--crypto/sha1.c39
-rw-r--r--crypto/sha256.c71
-rw-r--r--crypto/sha512.c71
-rw-r--r--drivers/accel/ivpu/ivpu_drv.c2
-rw-r--r--drivers/accel/ivpu/ivpu_pm.c4
-rw-r--r--drivers/accel/ivpu/ivpu_pm.h2
-rw-r--r--drivers/acpi/arm64/iort.c4
-rw-r--r--drivers/acpi/riscv/cppc.c4
-rw-r--r--drivers/base/cpu.c3
-rw-r--r--drivers/cpufreq/amd-pstate.c19
-rw-r--r--drivers/cpufreq/intel_pstate.c4
-rw-r--r--drivers/edac/altera_edac.c1
-rw-r--r--drivers/gpio/Kconfig6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_v10_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_v11_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_v6_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/dce_v8_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mes_v11_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c6
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c9
-rw-r--r--drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h2
-rw-r--r--drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c72
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h2
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h3
-rw-r--r--drivers/gpu/drm/bridge/ti-sn65dsi86.c11
-rw-r--r--drivers/gpu/drm/nouveau/gv100_fence.c7
-rw-r--r--drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h85
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c23
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c1
-rw-r--r--drivers/gpu/drm/scheduler/sched_entity.c11
-rw-r--r--drivers/gpu/drm/xe/xe_bo.c3
-rw-r--r--drivers/hwmon/ina238.c9
-rw-r--r--drivers/hwmon/mlxreg-fan.c5
-rw-r--r--drivers/i2c/busses/i2c-i801.c2
-rw-r--r--drivers/i2c/busses/i2c-rtl9300.c22
-rw-r--r--drivers/md/md.c5
-rw-r--r--drivers/md/raid1.c2
-rw-r--r--drivers/net/can/rcar/rcar_can.c8
-rw-r--r--drivers/net/can/xilinx_can.c16
-rw-r--r--drivers/net/dsa/b53/b53_common.c17
-rw-r--r--drivers/net/ethernet/freescale/fec_main.c3
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h1
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_common.c34
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_main.c18
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_prototype.h2
-rw-r--r--drivers/net/ethernet/intel/igb/igb_ethtool.c5
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c3
-rw-r--r--drivers/net/ethernet/ti/icssg/icssg_prueth.c20
-rw-r--r--drivers/net/ethernet/wangxun/libwx/wx_hw.c4
-rw-r--r--drivers/net/macsec.c1
-rw-r--r--drivers/net/phy/Kconfig2
-rw-r--r--drivers/net/phy/phy.c12
-rw-r--r--drivers/net/phy/phy_device.c5
-rw-r--r--drivers/net/phy/phylink.c28
-rw-r--r--drivers/nvme/host/core.c18
-rw-r--r--drivers/pcmcia/Kconfig3
-rw-r--r--drivers/pcmcia/Makefile1
-rw-r--r--drivers/pcmcia/cs.c17
-rw-r--r--drivers/pcmcia/cs_internal.h1
-rw-r--r--drivers/pcmcia/ds.c2
-rw-r--r--drivers/pcmcia/omap_cf.c10
-rw-r--r--drivers/pcmcia/rsrc_iodyn.c168
-rw-r--r--drivers/pcmcia/rsrc_nonstatic.c4
-rw-r--r--drivers/pcmcia/socket_sysfs.c5
-rw-r--r--drivers/platform/x86/acer-wmi.c71
-rw-r--r--drivers/platform/x86/amd/hfi/hfi.c14
-rw-r--r--drivers/platform/x86/amd/pmc/pmc-quirks.c14
-rw-r--r--drivers/platform/x86/asus-nb-wmi.c28
-rw-r--r--drivers/platform/x86/asus-wmi.c9
-rw-r--r--drivers/platform/x86/asus-wmi.h3
-rw-r--r--drivers/platform/x86/hp/hp-wmi.c4
-rw-r--r--drivers/platform/x86/intel/pmc/core.c1
-rw-r--r--drivers/platform/x86/intel/tpmi_power_domains.c2
-rw-r--r--drivers/scsi/lpfc/lpfc_nvmet.c10
-rw-r--r--drivers/scsi/sr.c16
-rw-r--r--drivers/spi/spi-cadence-quadspi.c33
-rw-r--r--drivers/spi/spi-fsl-lpspi.c47
-rw-r--r--drivers/spi/spi-microchip-core-qspi.c12
-rw-r--r--drivers/spi/spi-qpic-snand.c6
-rw-r--r--fs/btrfs/extent_io.c40
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/qgroup.c6
-rw-r--r--fs/btrfs/super.c9
-rw-r--r--fs/btrfs/volumes.c5
-rw-r--r--fs/coredump.c4
-rw-r--r--fs/exec.c2
-rw-r--r--fs/fhandle.c8
-rw-r--r--fs/fuse/dev.c2
-rw-r--r--fs/fuse/dir.c3
-rw-r--r--fs/fuse/file.c5
-rw-r--r--fs/fuse/fuse_i.h14
-rw-r--r--fs/fuse/inode.c16
-rw-r--r--fs/fuse/passthrough.c5
-rw-r--r--fs/fuse/virtio_fs.c2
-rw-r--r--fs/namespace.c2
-rw-r--r--fs/nfs/client.c2
-rw-r--r--fs/nfs/file.c40
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c21
-rw-r--r--fs/nfs/inode.c13
-rw-r--r--fs/nfs/internal.h12
-rw-r--r--fs/nfs/io.c13
-rw-r--r--fs/nfs/localio.c21
-rw-r--r--fs/nfs/nfs42proc.c35
-rw-r--r--fs/nfs/nfs4file.c2
-rw-r--r--fs/nfs/nfs4proc.c7
-rw-r--r--fs/nfs/nfstrace.h1
-rw-r--r--fs/nfs/write.c53
-rw-r--r--fs/ocfs2/extent_map.c10
-rw-r--r--fs/proc/generic.c3
-rw-r--r--fs/smb/client/cifs_debug.c31
-rw-r--r--fs/smb/client/cifs_unicode.c3
-rw-r--r--fs/smb/client/reparse.c2
-rw-r--r--fs/smb/client/smb1ops.c4
-rw-r--r--fs/smb/client/smb2misc.c19
-rw-r--r--fs/smb/client/smb2pdu.c4
-rw-r--r--fs/smb/client/trace.h52
-rw-r--r--include/linux/compiler-clang.h29
-rw-r--r--include/linux/cpu.h1
-rw-r--r--include/linux/energy_model.h10
-rw-r--r--include/linux/ethtool.h4
-rw-r--r--include/linux/fs.h3
-rw-r--r--include/linux/kasan.h6
-rw-r--r--include/linux/timekeeper_internal.h9
-rw-r--r--include/net/netfilter/nf_tables.h1
-rw-r--r--include/net/netfilter/nf_tables_core.h10
-rw-r--r--include/net/netns/nftables.h1
-rw-r--r--include/pcmcia/ss.h8
-rw-r--r--init/Kconfig3
-rw-r--r--init/main.c2
-rw-r--r--io_uring/rw.c3
-rw-r--r--kernel/auditfilter.c2
-rw-r--r--kernel/bpf/Makefile1
-rw-r--r--kernel/bpf/core.c21
-rw-r--r--kernel/bpf/cpumap.c4
-rw-r--r--kernel/bpf/crypto.c2
-rw-r--r--kernel/bpf/helpers.c16
-rw-r--r--kernel/bpf/rqspinlock.c2
-rw-r--r--kernel/bpf/verifier.c6
-rw-r--r--kernel/dma/debug.c48
-rw-r--r--kernel/dma/debug.h20
-rw-r--r--kernel/dma/mapping.c4
-rw-r--r--kernel/events/core.c1
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/futex/core.c16
-rw-r--r--kernel/power/energy_model.c29
-rw-r--r--kernel/power/hibernate.c1
-rw-r--r--kernel/time/timekeeping.c10
-rw-r--r--kernel/time/vsyscall.c4
-rw-r--r--kernel/trace/fgraph.c3
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace_events_user.c2
-rw-r--r--kernel/trace/trace_osnoise.c3
-rw-r--r--mm/damon/core.c4
-rw-r--r--mm/damon/lru_sort.c5
-rw-r--r--mm/damon/reclaim.c5
-rw-r--r--mm/damon/sysfs.c14
-rw-r--r--mm/hugetlb.c9
-rw-r--r--mm/kasan/shadow.c31
-rw-r--r--mm/khugepaged.c4
-rw-r--r--mm/memory-failure.c20
-rw-r--r--mm/memory_hotplug.c10
-rw-r--r--mm/mremap.c9
-rw-r--r--mm/percpu.c20
-rw-r--r--mm/vmalloc.c8
-rw-r--r--net/bridge/br.c7
-rw-r--r--net/can/j1939/bus.c5
-rw-r--r--net/can/j1939/j1939-priv.h1
-rw-r--r--net/can/j1939/main.c3
-rw-r--r--net/can/j1939/socket.c52
-rw-r--r--net/core/dev_ioctl.c22
-rw-r--r--net/hsr/hsr_device.c28
-rw-r--r--net/hsr/hsr_main.c4
-rw-r--r--net/hsr/hsr_main.h3
-rw-r--r--net/ipv4/ip_tunnel_core.c6
-rw-r--r--net/ipv4/tcp_bpf.c5
-rw-r--r--net/mptcp/sockopt.c11
-rw-r--r--net/netfilter/nf_tables_api.c66
-rw-r--r--net/netfilter/nft_lookup.c46
-rw-r--r--net/netfilter/nft_set_bitmap.c3
-rw-r--r--net/netfilter/nft_set_pipapo.c20
-rw-r--r--net/netfilter/nft_set_pipapo_avx2.c4
-rw-r--r--net/netfilter/nft_set_rbtree.c6
-rw-r--r--net/netlink/genetlink.c3
-rw-r--r--net/sunrpc/sched.c2
-rw-r--r--net/sunrpc/xprtsock.c6
-rw-r--r--net/wireless/nl80211.c2
-rw-r--r--net/xdp/xsk.c113
-rw-r--r--net/xdp/xsk_queue.h12
-rw-r--r--rust/kernel/lib.rs15
-rw-r--r--samples/ftrace/ftrace-direct-modify.c2
-rw-r--r--scripts/generate_rust_target.rs12
-rw-r--r--tools/gpio/Makefile2
-rw-r--r--tools/perf/tests/pe-file-parsing.c4
-rwxr-xr-xtools/perf/tests/shell/test_bpf_metadata.sh2
-rw-r--r--tools/perf/util/bpf-event.c39
-rw-r--r--tools/perf/util/bpf-utils.c61
-rw-r--r--tools/perf/util/symbol-elf.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/free_timer.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_crash.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_lockup.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_mim.c4
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h4
-rw-r--r--tools/testing/selftests/bpf/progs/crypto_sanity.c46
-rw-r--r--tools/testing/selftests/bpf/progs/linked_list_fail.c5
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_success.c8
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c17
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c18
-rw-r--r--tools/testing/selftests/net/Makefile1
-rwxr-xr-xtools/testing/selftests/net/broadcast_ether_dst.sh83
-rw-r--r--tools/testing/selftests/net/can/config3
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_sockopt.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/pm_netlink.sh5
-rwxr-xr-xtools/testing/selftests/net/mptcp/simult_flows.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/userspace_pm.sh2
265 files changed, 2542 insertions, 1055 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index ab8cd337f43a..8aed6d94c4cd 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -586,6 +586,7 @@ What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/srbds
/sys/devices/system/cpu/vulnerabilities/tsa
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+ /sys/devices/system/cpu/vulnerabilities/vmscape
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 89ca636081b7..55d747511f83 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -26,3 +26,4 @@ are configurable at compile, boot or run time.
rsb
old_microcode
indirect-target-selection
+ vmscape
diff --git a/Documentation/admin-guide/hw-vuln/vmscape.rst b/Documentation/admin-guide/hw-vuln/vmscape.rst
new file mode 100644
index 000000000000..d9b9a2b6c114
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/vmscape.rst
@@ -0,0 +1,110 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+VMSCAPE
+=======
+
+VMSCAPE is a vulnerability that may allow a guest to influence the branch
+prediction in host userspace. It particularly affects hypervisors like QEMU.
+
+Even if a hypervisor may not have any sensitive data like disk encryption keys,
+guest-userspace may be able to attack the guest-kernel using the hypervisor as
+a confused deputy.
+
+Affected processors
+-------------------
+
+The following CPU families are affected by VMSCAPE:
+
+**Intel processors:**
+ - Skylake generation (Parts without Enhanced-IBRS)
+ - Cascade Lake generation - (Parts affected by ITS guest/host separation)
+ - Alder Lake and newer (Parts affected by BHI)
+
+Note that, BHI affected parts that use BHB clearing software mitigation e.g.
+Icelake are not vulnerable to VMSCAPE.
+
+**AMD processors:**
+ - Zen series (families 0x17, 0x19, 0x1a)
+
+** Hygon processors:**
+ - Family 0x18
+
+Mitigation
+----------
+
+Conditional IBPB
+----------------
+
+Kernel tracks when a CPU has run a potentially malicious guest and issues an
+IBPB before the first exit to userspace after VM-exit. If userspace did not run
+between VM-exit and the next VM-entry, no IBPB is issued.
+
+Note that the existing userspace mitigation against Spectre-v2 is effective in
+protecting the userspace. They are insufficient to protect the userspace VMMs
+from a malicious guest. This is because Spectre-v2 mitigations are applied at
+context switch time, while the userspace VMM can run after a VM-exit without a
+context switch.
+
+Vulnerability enumeration and mitigation is not applied inside a guest. This is
+because nested hypervisors should already be deploying IBPB to isolate
+themselves from nested guests.
+
+SMT considerations
+------------------
+
+When Simultaneous Multi-Threading (SMT) is enabled, hypervisors can be
+vulnerable to cross-thread attacks. For complete protection against VMSCAPE
+attacks in SMT environments, STIBP should be enabled.
+
+The kernel will issue a warning if SMT is enabled without adequate STIBP
+protection. Warning is not issued when:
+
+- SMT is disabled
+- STIBP is enabled system-wide
+- Intel eIBRS is enabled (which implies STIBP protection)
+
+System information and options
+------------------------------
+
+The sysfs file showing VMSCAPE mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/vmscape
+
+The possible values in this file are:
+
+ * 'Not affected':
+
+ The processor is not vulnerable to VMSCAPE attacks.
+
+ * 'Vulnerable':
+
+ The processor is vulnerable and no mitigation has been applied.
+
+ * 'Mitigation: IBPB before exit to userspace':
+
+ Conditional IBPB mitigation is enabled. The kernel tracks when a CPU has
+ run a potentially malicious guest and issues an IBPB before the first
+ exit to userspace after VM-exit.
+
+ * 'Mitigation: IBPB on VMEXIT':
+
+ IBPB is issued on every VM-exit. This occurs when other mitigations like
+ RETBLEED or SRSO are already issuing IBPB on VM-exit.
+
+Mitigation control on the kernel command line
+----------------------------------------------
+
+The mitigation can be controlled via the ``vmscape=`` command line parameter:
+
+ * ``vmscape=off``:
+
+ Disable the VMSCAPE mitigation.
+
+ * ``vmscape=ibpb``:
+
+ Enable conditional IBPB mitigation (default when CONFIG_MITIGATION_VMSCAPE=y).
+
+ * ``vmscape=force``:
+
+ Force vulnerability detection and mitigation even on processors that are
+ not known to be affected.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 747a55abf494..5a7a83c411e9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3829,6 +3829,7 @@
srbds=off [X86,INTEL]
ssbd=force-off [ARM64]
tsx_async_abort=off [X86]
+ vmscape=off [X86]
Exceptions:
This does not have any effect on
@@ -8041,6 +8042,16 @@
vmpoff= [KNL,S390] Perform z/VM CP command after power off.
Format: <command>
+ vmscape= [X86] Controls mitigation for VMscape attacks.
+ VMscape attacks can leak information from a userspace
+ hypervisor to a guest via speculative side-channels.
+
+ off - disable the mitigation
+ ibpb - use Indirect Branch Prediction Barrier
+ (IBPB) mitigation (default)
+ force - force vulnerability detection even on
+ unaffected processors
+
vsyscall= [X86-64,EARLY]
Controls the behavior of vsyscalls (i.e. calls to
fixed addresses of 0xffffffffff600x00 from legacy
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
index a65a42ccaafe..a82360bed188 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
@@ -20,6 +20,7 @@ properties:
- enum:
- fsl,imx7ulp-spi
- fsl,imx8qxp-spi
+ - nxp,s32g2-lpspi
- items:
- enum:
- fsl,imx8ulp-spi
@@ -27,6 +28,10 @@ properties:
- fsl,imx94-spi
- fsl,imx95-spi
- const: fsl,imx7ulp-spi
+ - items:
+ - const: nxp,s32g3-lpspi
+ - const: nxp,s32g2-lpspi
+
reg:
maxItems: 1
diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index 02f1ddcfbf1c..d15335684ec3 100644
--- a/Documentation/netlink/specs/mptcp_pm.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -256,7 +256,7 @@ attribute-sets:
type: u32
-
name: if-idx
- type: u32
+ type: s32
-
name: reset-reason
type: u32
diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index bc1b585355f7..7650c4b5be5f 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -742,7 +742,7 @@ The broadcast manager sends responses to user space in the same form:
struct timeval ival1, ival2; /* count and subsequent interval */
canid_t can_id; /* unique can_id for task */
__u32 nframes; /* number of can_frames following */
- struct can_frame frames[0];
+ struct can_frame frames[];
};
The aligned payload 'frames' uses the same basic CAN frame structure defined
diff --git a/Documentation/networking/mptcp.rst b/Documentation/networking/mptcp.rst
index 17f2bab61164..2e31038d6462 100644
--- a/Documentation/networking/mptcp.rst
+++ b/Documentation/networking/mptcp.rst
@@ -60,10 +60,10 @@ address announcements. Typically, it is the client side that initiates subflows,
and the server side that announces additional addresses via the ``ADD_ADDR`` and
``REMOVE_ADDR`` options.
-Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see
-mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the
-same rules are applied for all the connections (see: ``ip mptcp``) ; and the
-userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd
+Path managers are controlled by the ``net.mptcp.path_manager`` sysctl knob --
+see mptcp-sysctl.rst. There are two types: the in-kernel one (``kernel``) where
+the same rules are applied for all the connections (see: ``ip mptcp``) ; and the
+userspace one (``userspace``), controlled by a userspace daemon (i.e. `mptcpd
<https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each
connection. The path managers can be controlled via a Netlink API; see
netlink_spec/mptcp_pm.rst.
diff --git a/MAINTAINERS b/MAINTAINERS
index 2df02e4374ed..ea95802d87e1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4683,7 +4683,6 @@ F: security/bpf/
BPF [SELFTESTS] (Test Runners & Infrastructure)
M: Andrii Nakryiko <andrii@kernel.org>
M: Eduard Zingerman <eddyz87@gmail.com>
-R: Mykola Lysenko <mykolal@fb.com>
L: bpf@vger.kernel.org
S: Maintained
F: tools/testing/selftests/bpf/
@@ -5259,7 +5258,6 @@ F: drivers/gpio/gpio-bt8xx.c
BTRFS FILE SYSTEM
M: Chris Mason <clm@fb.com>
-M: Josef Bacik <josef@toxicpanda.com>
M: David Sterba <dsterba@suse.com>
L: linux-btrfs@vger.kernel.org
S: Maintained
@@ -7821,7 +7819,7 @@ Q: https://patchwork.freedesktop.org/project/nouveau/
Q: https://gitlab.freedesktop.org/drm/nouveau/-/merge_requests
B: https://gitlab.freedesktop.org/drm/nouveau/-/issues
C: irc://irc.oftc.net/nouveau
-T: git https://gitlab.freedesktop.org/drm/nouveau.git
+T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
F: drivers/gpu/drm/nouveau/
F: include/uapi/drm/nouveau_drm.h
@@ -16128,6 +16126,7 @@ M: Andrew Morton <akpm@linux-foundation.org>
M: Mike Rapoport <rppt@kernel.org>
L: linux-mm@kvack.org
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git
F: include/linux/numa_memblks.h
F: mm/numa.c
F: mm/numa_emulation.c
@@ -17480,6 +17479,7 @@ NETFILTER
M: Pablo Neira Ayuso <pablo@netfilter.org>
M: Jozsef Kadlecsik <kadlec@netfilter.org>
M: Florian Westphal <fw@strlen.de>
+R: Phil Sutter <phil@nwl.cc>
L: netfilter-devel@vger.kernel.org
L: coreteam@netfilter.org
S: Maintained
diff --git a/Makefile b/Makefile
index b9c661913250..cf37b9407821 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 17
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
NAME = Baby Opossum Posse
# *DOCUMENTATION*
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 79550b22ba19..fb9b88eebeb1 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -19,6 +19,7 @@ struct mod_arch_specific {
/* for CONFIG_DYNAMIC_FTRACE */
struct plt_entry *ftrace_trampolines;
+ struct plt_entry *init_ftrace_trampolines;
};
u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index b9ae8349e35d..fb944b46846d 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -2,6 +2,7 @@ SECTIONS {
.plt 0 : { BYTE(0) }
.init.plt 0 : { BYTE(0) }
.text.ftrace_trampoline 0 : { BYTE(0) }
+ .init.text.ftrace_trampoline 0 : { BYTE(0) }
#ifdef CONFIG_KASAN_SW_TAGS
/*
diff --git a/arch/arm64/include/uapi/asm/bitsperlong.h b/arch/arm64/include/uapi/asm/bitsperlong.h
index 485d60bee26c..d59730975f30 100644
--- a/arch/arm64/include/uapi/asm/bitsperlong.h
+++ b/arch/arm64/include/uapi/asm/bitsperlong.h
@@ -17,7 +17,12 @@
#ifndef __ASM_BITSPERLONG_H
#define __ASM_BITSPERLONG_H
+#if defined(__KERNEL__) && !defined(__aarch64__)
+/* Used by the compat vDSO */
+#define __BITS_PER_LONG 32
+#else
#define __BITS_PER_LONG 64
+#endif
#include <asm-generic/bitsperlong.h>
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 5a890714ee2e..5adad37ab4fa 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -258,10 +258,17 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
return ftrace_modify_code(pc, 0, new, false);
}
-static struct plt_entry *get_ftrace_plt(struct module *mod)
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
{
#ifdef CONFIG_MODULES
- struct plt_entry *plt = mod->arch.ftrace_trampolines;
+ struct plt_entry *plt = NULL;
+
+ if (within_module_mem_type(addr, mod, MOD_INIT_TEXT))
+ plt = mod->arch.init_ftrace_trampolines;
+ else if (within_module_mem_type(addr, mod, MOD_TEXT))
+ plt = mod->arch.ftrace_trampolines;
+ else
+ return NULL;
return &plt[FTRACE_PLT_IDX];
#else
@@ -332,7 +339,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
if (WARN_ON(!mod))
return false;
- plt = get_ftrace_plt(mod);
+ plt = get_ftrace_plt(mod, pc);
if (!plt) {
pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
return false;
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index af1ca875c52c..410060ebd86d 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -94,7 +94,7 @@ int load_other_segments(struct kimage *image,
char *initrd, unsigned long initrd_len,
char *cmdline)
{
- struct kexec_buf kbuf;
+ struct kexec_buf kbuf = {};
void *dtb = NULL;
unsigned long initrd_load_addr = 0, dtb_len,
orig_segments = image->nr_segments;
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index bde32979c06a..7afd370da9f4 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -283,7 +283,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
unsigned long core_plts = 0;
unsigned long init_plts = 0;
Elf64_Sym *syms = NULL;
- Elf_Shdr *pltsec, *tramp = NULL;
+ Elf_Shdr *pltsec, *tramp = NULL, *init_tramp = NULL;
int i;
/*
@@ -298,6 +298,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
else if (!strcmp(secstrings + sechdrs[i].sh_name,
".text.ftrace_trampoline"))
tramp = sechdrs + i;
+ else if (!strcmp(secstrings + sechdrs[i].sh_name,
+ ".init.text.ftrace_trampoline"))
+ init_tramp = sechdrs + i;
else if (sechdrs[i].sh_type == SHT_SYMTAB)
syms = (Elf64_Sym *)sechdrs[i].sh_addr;
}
@@ -363,5 +366,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
}
+ if (init_tramp) {
+ init_tramp->sh_type = SHT_NOBITS;
+ init_tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ init_tramp->sh_addralign = __alignof__(struct plt_entry);
+ init_tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
+ }
+
return 0;
}
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 40148d2725ce..d6d443c4a01a 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -466,6 +466,17 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
mod->arch.ftrace_trampolines = plts;
+
+ s = find_section(hdr, sechdrs, ".init.text.ftrace_trampoline");
+ if (!s)
+ return -ENOEXEC;
+
+ plts = (void *)s->sh_addr;
+
+ __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
+
+ mod->arch.init_ftrace_trampolines = plts;
+
#endif
return 0;
}
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a4b233a0659e..51dcd8eaa243 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -65,7 +65,7 @@ config RISCV
select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_HUGETLBFS if MMU
# LLD >= 14: https://github.com/llvm/llvm-project/issues/50505
- select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000
+ select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000 && CMODEL_MEDANY
select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000
select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index a8a2af6dfe9d..2a16e88e13de 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -91,7 +91,7 @@
#endif
.macro asm_per_cpu dst sym tmp
- REG_L \tmp, TASK_TI_CPU_NUM(tp)
+ lw \tmp, TASK_TI_CPU_NUM(tp)
slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT
la \dst, __per_cpu_offset
add \dst, \dst, \tmp
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index b88a6218b7f2..f5f4f7f85543 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -209,7 +209,7 @@ do { \
err = 0; \
break; \
__gu_failed: \
- x = 0; \
+ x = (__typeof__(x))0; \
err = -EFAULT; \
} while (0)
@@ -311,7 +311,7 @@ do { \
do { \
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
!IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \
- __inttype(x) ___val = (__inttype(x))x; \
+ __typeof__(*(__gu_ptr)) ___val = (x); \
if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \
goto label; \
break; \
@@ -438,10 +438,10 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
}
#define __get_kernel_nofault(dst, src, type, err_label) \
- __get_user_nocheck(*((type *)(dst)), (type *)(src), err_label)
+ __get_user_nocheck(*((type *)(dst)), (__force __user type *)(src), err_label)
#define __put_kernel_nofault(dst, src, type, err_label) \
- __put_user_nocheck(*((type *)(src)), (type *)(dst), err_label)
+ __put_user_nocheck(*((type *)(src)), (__force __user type *)(dst), err_label)
static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
{
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 3a0ec6fd5956..d0ded2438533 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -46,7 +46,7 @@
* a0 = &new_vmalloc[BIT_WORD(cpu)]
* a1 = BIT_MASK(cpu)
*/
- REG_L a2, TASK_TI_CPU(tp)
+ lw a2, TASK_TI_CPU(tp)
/*
* Compute the new_vmalloc element position:
* (cpu / 64) * 8 = (cpu >> 6) << 3
diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c
index 56444c7bd34e..531d348db84d 100644
--- a/arch/riscv/kernel/kexec_elf.c
+++ b/arch/riscv/kernel/kexec_elf.c
@@ -28,7 +28,7 @@ static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
int i;
int ret = 0;
size_t size;
- struct kexec_buf kbuf;
+ struct kexec_buf kbuf = {};
const struct elf_phdr *phdr;
kbuf.image = image;
@@ -66,7 +66,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
{
int i;
int ret;
- struct kexec_buf kbuf;
+ struct kexec_buf kbuf = {};
const struct elf_phdr *phdr;
unsigned long lowest_paddr = ULONG_MAX;
unsigned long lowest_vaddr = ULONG_MAX;
diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c
index 26a81774a78a..8f2eb900910b 100644
--- a/arch/riscv/kernel/kexec_image.c
+++ b/arch/riscv/kernel/kexec_image.c
@@ -41,7 +41,7 @@ static void *image_load(struct kimage *image,
struct riscv_image_header *h;
u64 flags;
bool be_image, be_kernel;
- struct kexec_buf kbuf;
+ struct kexec_buf kbuf = {};
int ret;
/* Check Image header */
diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c
index e36104af2e24..b9eb41b0a975 100644
--- a/arch/riscv/kernel/machine_kexec_file.c
+++ b/arch/riscv/kernel/machine_kexec_file.c
@@ -261,7 +261,7 @@ int load_extra_segments(struct kimage *image, unsigned long kernel_start,
int ret;
void *fdt;
unsigned long initrd_pbase = 0UL;
- struct kexec_buf kbuf;
+ struct kexec_buf kbuf = {};
char *modified_cmdline = NULL;
kbuf.image = image;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 10e01ff06312..9883a55d61b5 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1356,7 +1356,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
emit_mv(rd, rs, ctx);
#ifdef CONFIG_SMP
/* Load current CPU number in T1 */
- emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
+ emit_lw(RV_REG_T1, offsetof(struct thread_info, cpu),
RV_REG_TP, ctx);
/* Load address of __per_cpu_offset array in T2 */
emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
@@ -1763,7 +1763,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
*/
if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
/* Load current CPU number in R0 */
- emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
+ emit_lw(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
RV_REG_TP, ctx);
break;
}
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 4d364de43799..143e34a4eca5 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -16,7 +16,7 @@
static int kexec_file_add_kernel_elf(struct kimage *image,
struct s390_load_data *data)
{
- struct kexec_buf buf;
+ struct kexec_buf buf = {};
const Elf_Ehdr *ehdr;
const Elf_Phdr *phdr;
Elf_Addr entry;
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index a32ce8bea745..9a439175723c 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -16,7 +16,7 @@
static int kexec_file_add_kernel_image(struct kimage *image,
struct s390_load_data *data)
{
- struct kexec_buf buf;
+ struct kexec_buf buf = {};
buf.image = image;
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index c2bac14dd668..a36d7311c668 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -129,7 +129,7 @@ static int kexec_file_update_purgatory(struct kimage *image,
static int kexec_file_add_purgatory(struct kimage *image,
struct s390_load_data *data)
{
- struct kexec_buf buf;
+ struct kexec_buf buf = {};
int ret;
buf.image = image;
@@ -152,7 +152,7 @@ static int kexec_file_add_purgatory(struct kimage *image,
static int kexec_file_add_initrd(struct kimage *image,
struct s390_load_data *data)
{
- struct kexec_buf buf;
+ struct kexec_buf buf = {};
int ret;
buf.image = image;
@@ -184,7 +184,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
{
__u32 *lc_ipl_parmblock_ptr;
unsigned int len, ncerts;
- struct kexec_buf buf;
+ struct kexec_buf buf = {};
unsigned long addr;
void *ptr, *end;
int ret;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 4d09954ebf49..04457d88e589 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -760,8 +760,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
break;
case PERF_TYPE_HARDWARE:
- if (is_sampling_event(event)) /* No sampling support */
- return -ENOENT;
ev = attr->config;
if (!attr->exclude_user && attr->exclude_kernel) {
/*
@@ -859,6 +857,8 @@ static int cpumf_pmu_event_init(struct perf_event *event)
unsigned int type = event->attr.type;
int err = -ENOENT;
+ if (is_sampling_event(event)) /* No sampling support */
+ return err;
if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
err = __hw_perf_event_init(event, type);
else if (event->pmu->type == type)
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index f373a1009c45..9455f213dc20 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -285,10 +285,10 @@ static int paicrypt_event_init(struct perf_event *event)
/* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */
if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type)
return -ENOENT;
- /* PAI crypto event must be in valid range */
+ /* PAI crypto event must be in valid range, try others if not */
if (a->config < PAI_CRYPTO_BASE ||
a->config > PAI_CRYPTO_BASE + paicrypt_cnt)
- return -EINVAL;
+ return -ENOENT;
/* Allow only CRYPTO_ALL for sampling */
if (a->sample_period && a->config != PAI_CRYPTO_BASE)
return -EINVAL;
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index d827473e7f87..7b32935273ce 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -265,7 +265,7 @@ static int paiext_event_valid(struct perf_event *event)
event->hw.config_base = offsetof(struct paiext_cb, acc);
return 0;
}
- return -EINVAL;
+ return -ENOENT;
}
/* Might be called on different CPU than the one the event is intended for. */
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 60688be4e876..50eb57c976bc 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -335,7 +335,6 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
int nodat;
struct mm_struct *mm = vma->vm_mm;
- preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
old = ptep_flush_lazy(mm, addr, ptep, nodat);
@@ -360,7 +359,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
} else {
set_pte(ptep, pte);
}
- preempt_enable();
}
static inline void pmdp_idte_local(struct mm_struct *mm,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 58d890fe2100..52c8910ba2ef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2701,6 +2701,15 @@ config MITIGATION_TSA
security vulnerability on AMD CPUs which can lead to forwarding of
invalid info to subsequent instructions and thus can affect their
timing and thereby cause a leakage.
+
+config MITIGATION_VMSCAPE
+ bool "Mitigate VMSCAPE"
+ depends on KVM
+ default y
+ help
+ Enable mitigation for VMSCAPE attacks. VMSCAPE is a hardware security
+ vulnerability on Intel and AMD CPUs that may allow a guest to do
+ Spectre v2 style attacks on userspace hypervisor.
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 06fc0479a23f..751ca35386b0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -495,6 +495,7 @@
#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */
+#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
/*
* BUG word(s)
@@ -551,4 +552,5 @@
#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
+#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index d535a97c7284..ce3eb6d5fdf9 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -93,6 +93,13 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
* 8 (ia32) bits.
*/
choose_random_kstack_offset(rdtsc());
+
+ /* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */
+ if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) &&
+ this_cpu_read(x86_ibpb_exit_to_user)) {
+ indirect_branch_prediction_barrier();
+ this_cpu_write(x86_ibpb_exit_to_user, false);
+ }
}
#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 10f261678749..e29f82466f43 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -530,6 +530,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
: "memory");
}
+DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user);
+
static inline void indirect_branch_prediction_barrier(void)
{
asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index af838b8d845c..36dcfc5105be 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -96,6 +96,9 @@ static void __init its_update_mitigation(void);
static void __init its_apply_mitigation(void);
static void __init tsa_select_mitigation(void);
static void __init tsa_apply_mitigation(void);
+static void __init vmscape_select_mitigation(void);
+static void __init vmscape_update_mitigation(void);
+static void __init vmscape_apply_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -105,6 +108,14 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
+/*
+ * Set when the CPU has run a potentially malicious guest. An IBPB will
+ * be needed to before running userspace. That IBPB will flush the branch
+ * predictor content.
+ */
+DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user);
+EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user);
+
u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
static u64 __ro_after_init x86_arch_cap_msr;
@@ -262,6 +273,7 @@ void __init cpu_select_mitigations(void)
its_select_mitigation();
bhi_select_mitigation();
tsa_select_mitigation();
+ vmscape_select_mitigation();
/*
* After mitigations are selected, some may need to update their
@@ -293,6 +305,7 @@ void __init cpu_select_mitigations(void)
bhi_update_mitigation();
/* srso_update_mitigation() depends on retbleed_update_mitigation(). */
srso_update_mitigation();
+ vmscape_update_mitigation();
spectre_v1_apply_mitigation();
spectre_v2_apply_mitigation();
@@ -310,6 +323,7 @@ void __init cpu_select_mitigations(void)
its_apply_mitigation();
bhi_apply_mitigation();
tsa_apply_mitigation();
+ vmscape_apply_mitigation();
}
/*
@@ -2538,88 +2552,6 @@ static void update_mds_branch_idle(void)
}
}
-#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
-#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
-#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
-
-void cpu_bugs_smt_update(void)
-{
- mutex_lock(&spec_ctrl_mutex);
-
- if (sched_smt_active() && unprivileged_ebpf_enabled() &&
- spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
- pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG);
-
- switch (spectre_v2_user_stibp) {
- case SPECTRE_V2_USER_NONE:
- break;
- case SPECTRE_V2_USER_STRICT:
- case SPECTRE_V2_USER_STRICT_PREFERRED:
- update_stibp_strict();
- break;
- case SPECTRE_V2_USER_PRCTL:
- case SPECTRE_V2_USER_SECCOMP:
- update_indir_branch_cond();
- break;
- }
-
- switch (mds_mitigation) {
- case MDS_MITIGATION_FULL:
- case MDS_MITIGATION_AUTO:
- case MDS_MITIGATION_VMWERV:
- if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
- pr_warn_once(MDS_MSG_SMT);
- update_mds_branch_idle();
- break;
- case MDS_MITIGATION_OFF:
- break;
- }
-
- switch (taa_mitigation) {
- case TAA_MITIGATION_VERW:
- case TAA_MITIGATION_AUTO:
- case TAA_MITIGATION_UCODE_NEEDED:
- if (sched_smt_active())
- pr_warn_once(TAA_MSG_SMT);
- break;
- case TAA_MITIGATION_TSX_DISABLED:
- case TAA_MITIGATION_OFF:
- break;
- }
-
- switch (mmio_mitigation) {
- case MMIO_MITIGATION_VERW:
- case MMIO_MITIGATION_AUTO:
- case MMIO_MITIGATION_UCODE_NEEDED:
- if (sched_smt_active())
- pr_warn_once(MMIO_MSG_SMT);
- break;
- case MMIO_MITIGATION_OFF:
- break;
- }
-
- switch (tsa_mitigation) {
- case TSA_MITIGATION_USER_KERNEL:
- case TSA_MITIGATION_VM:
- case TSA_MITIGATION_AUTO:
- case TSA_MITIGATION_FULL:
- /*
- * TSA-SQ can potentially lead to info leakage between
- * SMT threads.
- */
- if (sched_smt_active())
- static_branch_enable(&cpu_buf_idle_clear);
- else
- static_branch_disable(&cpu_buf_idle_clear);
- break;
- case TSA_MITIGATION_NONE:
- case TSA_MITIGATION_UCODE_NEEDED:
- break;
- }
-
- mutex_unlock(&spec_ctrl_mutex);
-}
-
#undef pr_fmt
#define pr_fmt(fmt) "Speculative Store Bypass: " fmt
@@ -3331,8 +3263,184 @@ static void __init srso_apply_mitigation(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "VMSCAPE: " fmt
+
+enum vmscape_mitigations {
+ VMSCAPE_MITIGATION_NONE,
+ VMSCAPE_MITIGATION_AUTO,
+ VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER,
+ VMSCAPE_MITIGATION_IBPB_ON_VMEXIT,
+};
+
+static const char * const vmscape_strings[] = {
+ [VMSCAPE_MITIGATION_NONE] = "Vulnerable",
+ /* [VMSCAPE_MITIGATION_AUTO] */
+ [VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER] = "Mitigation: IBPB before exit to userspace",
+ [VMSCAPE_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT",
+};
+
+static enum vmscape_mitigations vmscape_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_VMSCAPE) ? VMSCAPE_MITIGATION_AUTO : VMSCAPE_MITIGATION_NONE;
+
+static int __init vmscape_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off")) {
+ vmscape_mitigation = VMSCAPE_MITIGATION_NONE;
+ } else if (!strcmp(str, "ibpb")) {
+ vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER;
+ } else if (!strcmp(str, "force")) {
+ setup_force_cpu_bug(X86_BUG_VMSCAPE);
+ vmscape_mitigation = VMSCAPE_MITIGATION_AUTO;
+ } else {
+ pr_err("Ignoring unknown vmscape=%s option.\n", str);
+ }
+
+ return 0;
+}
+early_param("vmscape", vmscape_parse_cmdline);
+
+static void __init vmscape_select_mitigation(void)
+{
+ if (cpu_mitigations_off() ||
+ !boot_cpu_has_bug(X86_BUG_VMSCAPE) ||
+ !boot_cpu_has(X86_FEATURE_IBPB)) {
+ vmscape_mitigation = VMSCAPE_MITIGATION_NONE;
+ return;
+ }
+
+ if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO)
+ vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER;
+}
+
+static void __init vmscape_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_VMSCAPE))
+ return;
+
+ if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB ||
+ srso_mitigation == SRSO_MITIGATION_IBPB_ON_VMEXIT)
+ vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_ON_VMEXIT;
+
+ pr_info("%s\n", vmscape_strings[vmscape_mitigation]);
+}
+
+static void __init vmscape_apply_mitigation(void)
+{
+ if (vmscape_mitigation == VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER)
+ setup_force_cpu_cap(X86_FEATURE_IBPB_EXIT_TO_USER);
+}
+
+#undef pr_fmt
#define pr_fmt(fmt) fmt
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
+#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
+#define VMSCAPE_MSG_SMT "VMSCAPE: SMT on, STIBP is required for full protection. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/vmscape.html for more details.\n"
+
+void cpu_bugs_smt_update(void)
+{
+ mutex_lock(&spec_ctrl_mutex);
+
+ if (sched_smt_active() && unprivileged_ebpf_enabled() &&
+ spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
+ pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG);
+
+ switch (spectre_v2_user_stibp) {
+ case SPECTRE_V2_USER_NONE:
+ break;
+ case SPECTRE_V2_USER_STRICT:
+ case SPECTRE_V2_USER_STRICT_PREFERRED:
+ update_stibp_strict();
+ break;
+ case SPECTRE_V2_USER_PRCTL:
+ case SPECTRE_V2_USER_SECCOMP:
+ update_indir_branch_cond();
+ break;
+ }
+
+ switch (mds_mitigation) {
+ case MDS_MITIGATION_FULL:
+ case MDS_MITIGATION_AUTO:
+ case MDS_MITIGATION_VMWERV:
+ if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+ pr_warn_once(MDS_MSG_SMT);
+ update_mds_branch_idle();
+ break;
+ case MDS_MITIGATION_OFF:
+ break;
+ }
+
+ switch (taa_mitigation) {
+ case TAA_MITIGATION_VERW:
+ case TAA_MITIGATION_AUTO:
+ case TAA_MITIGATION_UCODE_NEEDED:
+ if (sched_smt_active())
+ pr_warn_once(TAA_MSG_SMT);
+ break;
+ case TAA_MITIGATION_TSX_DISABLED:
+ case TAA_MITIGATION_OFF:
+ break;
+ }
+
+ switch (mmio_mitigation) {
+ case MMIO_MITIGATION_VERW:
+ case MMIO_MITIGATION_AUTO:
+ case MMIO_MITIGATION_UCODE_NEEDED:
+ if (sched_smt_active())
+ pr_warn_once(MMIO_MSG_SMT);
+ break;
+ case MMIO_MITIGATION_OFF:
+ break;
+ }
+
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ case TSA_MITIGATION_VM:
+ case TSA_MITIGATION_AUTO:
+ case TSA_MITIGATION_FULL:
+ /*
+ * TSA-SQ can potentially lead to info leakage between
+ * SMT threads.
+ */
+ if (sched_smt_active())
+ static_branch_enable(&cpu_buf_idle_clear);
+ else
+ static_branch_disable(&cpu_buf_idle_clear);
+ break;
+ case TSA_MITIGATION_NONE:
+ case TSA_MITIGATION_UCODE_NEEDED:
+ break;
+ }
+
+ switch (vmscape_mitigation) {
+ case VMSCAPE_MITIGATION_NONE:
+ case VMSCAPE_MITIGATION_AUTO:
+ break;
+ case VMSCAPE_MITIGATION_IBPB_ON_VMEXIT:
+ case VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER:
+ /*
+ * Hypervisors can be attacked across-threads, warn for SMT when
+ * STIBP is not already enabled system-wide.
+ *
+ * Intel eIBRS (!AUTOIBRS) implies STIBP on.
+ */
+ if (!sched_smt_active() ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+ (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
+ !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
+ break;
+ pr_warn_once(VMSCAPE_MSG_SMT);
+ break;
+ }
+
+ mutex_unlock(&spec_ctrl_mutex);
+}
+
#ifdef CONFIG_SYSFS
#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
@@ -3578,6 +3686,11 @@ static ssize_t tsa_show_state(char *buf)
return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
}
+static ssize_t vmscape_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", vmscape_strings[vmscape_mitigation]);
+}
+
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
@@ -3644,6 +3757,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_TSA:
return tsa_show_state(buf);
+ case X86_BUG_VMSCAPE:
+ return vmscape_show_state(buf);
+
default:
break;
}
@@ -3735,6 +3851,11 @@ ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *bu
{
return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
}
+
+ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_VMSCAPE);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 34a054181c4d..f98ec9c7fc07 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1236,55 +1236,71 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define ITS_NATIVE_ONLY BIT(9)
/* CPU is affected by Transient Scheduler Attacks */
#define TSA BIT(10)
+/* CPU is affected by VMSCAPE */
+#define VMSCAPE BIT(11)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
- VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO),
- VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO),
- VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO),
- VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS),
- VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED),
+ VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE_X, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE_X, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED | VMSCAPE),
VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS),
- VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE),
VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY),
VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED),
VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
- VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS),
- VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS),
- VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS),
- VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS),
- VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS),
- VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS | VMSCAPE),
+ VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS | VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_METEORLAKE_L, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_H, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ARROWLAKE, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_U, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_LUNARLAKE_M, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_SAPPHIRERAPIDS_X, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_GRANITERAPIDS_X, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_EMERALDRAPIDS_X, X86_STEP_MAX, VMSCAPE),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS | VMSCAPE),
VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS),
VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS),
VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS),
VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS),
VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS),
VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS),
+ VULNBL_INTEL_STEPS(INTEL_ATOM_CRESTMONT_X, X86_STEP_MAX, VMSCAPE),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
- VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
- VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
- VULNBL_AMD(0x19, SRSO | TSA),
- VULNBL_AMD(0x1a, SRSO),
+ VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO | VMSCAPE),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO | VMSCAPE),
+ VULNBL_AMD(0x19, SRSO | TSA | VMSCAPE),
+ VULNBL_AMD(0x1a, SRSO | VMSCAPE),
{}
};
@@ -1543,6 +1559,14 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
}
}
+ /*
+ * Set the bug only on bare-metal. A nested hypervisor should already be
+ * deploying IBPB to isolate itself from nested guests.
+ */
+ if (cpu_matches(cpu_vuln_blacklist, VMSCAPE) &&
+ !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ setup_force_cpu_bug(X86_BUG_VMSCAPE);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 604490b1cb19..706b6fd56d3c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11011,6 +11011,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
wrmsrq(MSR_IA32_XFD_ERR, 0);
/*
+ * Mark this CPU as needing a branch predictor flush before running
+ * userspace. Must be done before enabling preemption to ensure it gets
+ * set for the CPU that actually ran the guest, and not the CPU that it
+ * may migrate to.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER))
+ this_cpu_write(x86_ibpb_exit_to_user, true);
+
+ /*
* Consume any pending interrupts, including the possible source of
* VM-Exit on SVM and any ticks that occur between VM-Exit and now.
* An instruction is required after local_irq_enable() to fully unblock
diff --git a/block/fops.c b/block/fops.c
index 82451ac8ff25..ddbc69c0922b 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -7,6 +7,7 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/uio.h>
@@ -54,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
struct bio bio;
ssize_t ret;
- WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA);
if (nr_pages <= DIO_INLINE_BIO_VECS)
vecs = inline_vecs;
else {
@@ -131,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio)
if (bio->bi_status && !dio->bio.bi_status)
dio->bio.bi_status = bio->bi_status;
- if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA))
+ if (bio_integrity(bio))
bio_integrity_unmap_user(bio);
if (atomic_dec_and_test(&dio->ref)) {
@@ -233,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
}
bio->bi_opf |= REQ_NOWAIT;
}
- if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) {
+ if (iocb->ki_flags & IOCB_HAS_METADATA) {
ret = bio_integrity_map_iter(bio, iocb->private);
if (unlikely(ret))
goto fail;
@@ -301,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio)
ret = blk_status_to_errno(bio->bi_status);
}
- if (iocb->ki_flags & IOCB_HAS_METADATA)
+ if (bio_integrity(bio))
bio_integrity_unmap_user(bio);
iocb->ki_complete(iocb, ret);
@@ -422,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
}
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
- if (likely(nr_pages <= BIO_MAX_VECS)) {
+ if (likely(nr_pages <= BIO_MAX_VECS &&
+ !(iocb->ki_flags & IOCB_HAS_METADATA))) {
if (is_sync_kiocb(iocb))
return __blkdev_direct_IO_simple(iocb, iter, bdev,
nr_pages);
@@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp)
if (bdev_can_atomic_write(bdev))
filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+ if (blk_get_integrity(bdev->bd_disk))
+ filp->f_mode |= FMODE_HAS_METADATA;
ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
if (ret)
diff --git a/crypto/sha1.c b/crypto/sha1.c
index ecef4bf2d9c0..4fbf61cf0370 100644
--- a/crypto/sha1.c
+++ b/crypto/sha1.c
@@ -49,6 +49,18 @@ static int __crypto_sha1_import(struct sha1_ctx *ctx, const void *in)
return 0;
}
+static int __crypto_sha1_export_core(const struct sha1_ctx *ctx, void *out)
+{
+ memcpy(out, ctx, offsetof(struct sha1_ctx, buf));
+ return 0;
+}
+
+static int __crypto_sha1_import_core(struct sha1_ctx *ctx, const void *in)
+{
+ memcpy(ctx, in, offsetof(struct sha1_ctx, buf));
+ return 0;
+}
+
const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE] = {
0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
@@ -94,6 +106,16 @@ static int crypto_sha1_import(struct shash_desc *desc, const void *in)
return __crypto_sha1_import(SHA1_CTX(desc), in);
}
+static int crypto_sha1_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha1_export_core(SHA1_CTX(desc), out);
+}
+
+static int crypto_sha1_import_core(struct shash_desc *desc, const void *in)
+{
+ return __crypto_sha1_import_core(SHA1_CTX(desc), in);
+}
+
#define HMAC_SHA1_KEY(tfm) ((struct hmac_sha1_key *)crypto_shash_ctx(tfm))
#define HMAC_SHA1_CTX(desc) ((struct hmac_sha1_ctx *)shash_desc_ctx(desc))
@@ -143,6 +165,19 @@ static int crypto_hmac_sha1_import(struct shash_desc *desc, const void *in)
return __crypto_sha1_import(&ctx->sha_ctx, in);
}
+static int crypto_hmac_sha1_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha1_export_core(&HMAC_SHA1_CTX(desc)->sha_ctx, out);
+}
+
+static int crypto_hmac_sha1_import_core(struct shash_desc *desc, const void *in)
+{
+ struct hmac_sha1_ctx *ctx = HMAC_SHA1_CTX(desc);
+
+ ctx->ostate = HMAC_SHA1_KEY(desc->tfm)->ostate;
+ return __crypto_sha1_import_core(&ctx->sha_ctx, in);
+}
+
static struct shash_alg algs[] = {
{
.base.cra_name = "sha1",
@@ -157,6 +192,8 @@ static struct shash_alg algs[] = {
.digest = crypto_sha1_digest,
.export = crypto_sha1_export,
.import = crypto_sha1_import,
+ .export_core = crypto_sha1_export_core,
+ .import_core = crypto_sha1_import_core,
.descsize = sizeof(struct sha1_ctx),
.statesize = SHA1_SHASH_STATE_SIZE,
},
@@ -175,6 +212,8 @@ static struct shash_alg algs[] = {
.digest = crypto_hmac_sha1_digest,
.export = crypto_hmac_sha1_export,
.import = crypto_hmac_sha1_import,
+ .export_core = crypto_hmac_sha1_export_core,
+ .import_core = crypto_hmac_sha1_import_core,
.descsize = sizeof(struct hmac_sha1_ctx),
.statesize = SHA1_SHASH_STATE_SIZE,
},
diff --git a/crypto/sha256.c b/crypto/sha256.c
index 052806559f06..fb81defe084c 100644
--- a/crypto/sha256.c
+++ b/crypto/sha256.c
@@ -50,6 +50,19 @@ static int __crypto_sha256_import(struct __sha256_ctx *ctx, const void *in)
return 0;
}
+static int __crypto_sha256_export_core(const struct __sha256_ctx *ctx,
+ void *out)
+{
+ memcpy(out, ctx, offsetof(struct __sha256_ctx, buf));
+ return 0;
+}
+
+static int __crypto_sha256_import_core(struct __sha256_ctx *ctx, const void *in)
+{
+ memcpy(ctx, in, offsetof(struct __sha256_ctx, buf));
+ return 0;
+}
+
/* SHA-224 */
const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE] = {
@@ -98,6 +111,16 @@ static int crypto_sha224_import(struct shash_desc *desc, const void *in)
return __crypto_sha256_import(&SHA224_CTX(desc)->ctx, in);
}
+static int crypto_sha224_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha256_export_core(&SHA224_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha224_import_core(struct shash_desc *desc, const void *in)
+{
+ return __crypto_sha256_import_core(&SHA224_CTX(desc)->ctx, in);
+}
+
/* SHA-256 */
const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE] = {
@@ -146,6 +169,16 @@ static int crypto_sha256_import(struct shash_desc *desc, const void *in)
return __crypto_sha256_import(&SHA256_CTX(desc)->ctx, in);
}
+static int crypto_sha256_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha256_export_core(&SHA256_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha256_import_core(struct shash_desc *desc, const void *in)
+{
+ return __crypto_sha256_import_core(&SHA256_CTX(desc)->ctx, in);
+}
+
/* HMAC-SHA224 */
#define HMAC_SHA224_KEY(tfm) ((struct hmac_sha224_key *)crypto_shash_ctx(tfm))
@@ -198,6 +231,21 @@ static int crypto_hmac_sha224_import(struct shash_desc *desc, const void *in)
return __crypto_sha256_import(&ctx->ctx.sha_ctx, in);
}
+static int crypto_hmac_sha224_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha256_export_core(&HMAC_SHA224_CTX(desc)->ctx.sha_ctx,
+ out);
+}
+
+static int crypto_hmac_sha224_import_core(struct shash_desc *desc,
+ const void *in)
+{
+ struct hmac_sha224_ctx *ctx = HMAC_SHA224_CTX(desc);
+
+ ctx->ctx.ostate = HMAC_SHA224_KEY(desc->tfm)->key.ostate;
+ return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in);
+}
+
/* HMAC-SHA256 */
#define HMAC_SHA256_KEY(tfm) ((struct hmac_sha256_key *)crypto_shash_ctx(tfm))
@@ -250,6 +298,21 @@ static int crypto_hmac_sha256_import(struct shash_desc *desc, const void *in)
return __crypto_sha256_import(&ctx->ctx.sha_ctx, in);
}
+static int crypto_hmac_sha256_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha256_export_core(&HMAC_SHA256_CTX(desc)->ctx.sha_ctx,
+ out);
+}
+
+static int crypto_hmac_sha256_import_core(struct shash_desc *desc,
+ const void *in)
+{
+ struct hmac_sha256_ctx *ctx = HMAC_SHA256_CTX(desc);
+
+ ctx->ctx.ostate = HMAC_SHA256_KEY(desc->tfm)->key.ostate;
+ return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in);
+}
+
/* Algorithm definitions */
static struct shash_alg algs[] = {
@@ -266,6 +329,8 @@ static struct shash_alg algs[] = {
.digest = crypto_sha224_digest,
.export = crypto_sha224_export,
.import = crypto_sha224_import,
+ .export_core = crypto_sha224_export_core,
+ .import_core = crypto_sha224_import_core,
.descsize = sizeof(struct sha224_ctx),
.statesize = SHA256_SHASH_STATE_SIZE,
},
@@ -282,6 +347,8 @@ static struct shash_alg algs[] = {
.digest = crypto_sha256_digest,
.export = crypto_sha256_export,
.import = crypto_sha256_import,
+ .export_core = crypto_sha256_export_core,
+ .import_core = crypto_sha256_import_core,
.descsize = sizeof(struct sha256_ctx),
.statesize = SHA256_SHASH_STATE_SIZE,
},
@@ -300,6 +367,8 @@ static struct shash_alg algs[] = {
.digest = crypto_hmac_sha224_digest,
.export = crypto_hmac_sha224_export,
.import = crypto_hmac_sha224_import,
+ .export_core = crypto_hmac_sha224_export_core,
+ .import_core = crypto_hmac_sha224_import_core,
.descsize = sizeof(struct hmac_sha224_ctx),
.statesize = SHA256_SHASH_STATE_SIZE,
},
@@ -318,6 +387,8 @@ static struct shash_alg algs[] = {
.digest = crypto_hmac_sha256_digest,
.export = crypto_hmac_sha256_export,
.import = crypto_hmac_sha256_import,
+ .export_core = crypto_hmac_sha256_export_core,
+ .import_core = crypto_hmac_sha256_import_core,
.descsize = sizeof(struct hmac_sha256_ctx),
.statesize = SHA256_SHASH_STATE_SIZE,
},
diff --git a/crypto/sha512.c b/crypto/sha512.c
index fb1c520978ef..d320fe53913f 100644
--- a/crypto/sha512.c
+++ b/crypto/sha512.c
@@ -50,6 +50,19 @@ static int __crypto_sha512_import(struct __sha512_ctx *ctx, const void *in)
return 0;
}
+static int __crypto_sha512_export_core(const struct __sha512_ctx *ctx,
+ void *out)
+{
+ memcpy(out, ctx, offsetof(struct __sha512_ctx, buf));
+ return 0;
+}
+
+static int __crypto_sha512_import_core(struct __sha512_ctx *ctx, const void *in)
+{
+ memcpy(ctx, in, offsetof(struct __sha512_ctx, buf));
+ return 0;
+}
+
/* SHA-384 */
const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = {
@@ -100,6 +113,16 @@ static int crypto_sha384_import(struct shash_desc *desc, const void *in)
return __crypto_sha512_import(&SHA384_CTX(desc)->ctx, in);
}
+static int crypto_sha384_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha512_export_core(&SHA384_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha384_import_core(struct shash_desc *desc, const void *in)
+{
+ return __crypto_sha512_import_core(&SHA384_CTX(desc)->ctx, in);
+}
+
/* SHA-512 */
const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = {
@@ -152,6 +175,16 @@ static int crypto_sha512_import(struct shash_desc *desc, const void *in)
return __crypto_sha512_import(&SHA512_CTX(desc)->ctx, in);
}
+static int crypto_sha512_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha512_export_core(&SHA512_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha512_import_core(struct shash_desc *desc, const void *in)
+{
+ return __crypto_sha512_import_core(&SHA512_CTX(desc)->ctx, in);
+}
+
/* HMAC-SHA384 */
#define HMAC_SHA384_KEY(tfm) ((struct hmac_sha384_key *)crypto_shash_ctx(tfm))
@@ -204,6 +237,21 @@ static int crypto_hmac_sha384_import(struct shash_desc *desc, const void *in)
return __crypto_sha512_import(&ctx->ctx.sha_ctx, in);
}
+static int crypto_hmac_sha384_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha512_export_core(&HMAC_SHA384_CTX(desc)->ctx.sha_ctx,
+ out);
+}
+
+static int crypto_hmac_sha384_import_core(struct shash_desc *desc,
+ const void *in)
+{
+ struct hmac_sha384_ctx *ctx = HMAC_SHA384_CTX(desc);
+
+ ctx->ctx.ostate = HMAC_SHA384_KEY(desc->tfm)->key.ostate;
+ return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in);
+}
+
/* HMAC-SHA512 */
#define HMAC_SHA512_KEY(tfm) ((struct hmac_sha512_key *)crypto_shash_ctx(tfm))
@@ -256,6 +304,21 @@ static int crypto_hmac_sha512_import(struct shash_desc *desc, const void *in)
return __crypto_sha512_import(&ctx->ctx.sha_ctx, in);
}
+static int crypto_hmac_sha512_export_core(struct shash_desc *desc, void *out)
+{
+ return __crypto_sha512_export_core(&HMAC_SHA512_CTX(desc)->ctx.sha_ctx,
+ out);
+}
+
+static int crypto_hmac_sha512_import_core(struct shash_desc *desc,
+ const void *in)
+{
+ struct hmac_sha512_ctx *ctx = HMAC_SHA512_CTX(desc);
+
+ ctx->ctx.ostate = HMAC_SHA512_KEY(desc->tfm)->key.ostate;
+ return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in);
+}
+
/* Algorithm definitions */
static struct shash_alg algs[] = {
@@ -272,6 +335,8 @@ static struct shash_alg algs[] = {
.digest = crypto_sha384_digest,
.export = crypto_sha384_export,
.import = crypto_sha384_import,
+ .export_core = crypto_sha384_export_core,
+ .import_core = crypto_sha384_import_core,
.descsize = sizeof(struct sha384_ctx),
.statesize = SHA512_SHASH_STATE_SIZE,
},
@@ -288,6 +353,8 @@ static struct shash_alg algs[] = {
.digest = crypto_sha512_digest,
.export = crypto_sha512_export,
.import = crypto_sha512_import,
+ .export_core = crypto_sha512_export_core,
+ .import_core = crypto_sha512_import_core,
.descsize = sizeof(struct sha512_ctx),
.statesize = SHA512_SHASH_STATE_SIZE,
},
@@ -306,6 +373,8 @@ static struct shash_alg algs[] = {
.digest = crypto_hmac_sha384_digest,
.export = crypto_hmac_sha384_export,
.import = crypto_hmac_sha384_import,
+ .export_core = crypto_hmac_sha384_export_core,
+ .import_core = crypto_hmac_sha384_import_core,
.descsize = sizeof(struct hmac_sha384_ctx),
.statesize = SHA512_SHASH_STATE_SIZE,
},
@@ -324,6 +393,8 @@ static struct shash_alg algs[] = {
.digest = crypto_hmac_sha512_digest,
.export = crypto_hmac_sha512_export,
.import = crypto_hmac_sha512_import,
+ .export_core = crypto_hmac_sha512_export_core,
+ .import_core = crypto_hmac_sha512_import_core,
.descsize = sizeof(struct hmac_sha512_ctx),
.statesize = SHA512_SHASH_STATE_SIZE,
},
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 3d6d52492536..3289751b4757 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -677,7 +677,7 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
static void ivpu_dev_fini(struct ivpu_device *vdev)
{
ivpu_jobs_abort_all(vdev);
- ivpu_pm_cancel_recovery(vdev);
+ ivpu_pm_disable_recovery(vdev);
ivpu_pm_disable(vdev);
ivpu_prepare_for_reset(vdev);
ivpu_shutdown(vdev);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index eacda1dbe840..475ddc94f1cf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -417,10 +417,10 @@ void ivpu_pm_init(struct ivpu_device *vdev)
ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay);
}
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev)
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev)
{
drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work));
- cancel_work_sync(&vdev->pm->recovery_work);
+ disable_work_sync(&vdev->pm->recovery_work);
}
void ivpu_pm_enable(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 89b264cc0e3e..a2aa7a27f32e 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -25,7 +25,7 @@ struct ivpu_pm_info {
void ivpu_pm_init(struct ivpu_device *vdev);
void ivpu_pm_enable(struct ivpu_device *vdev);
void ivpu_pm_disable(struct ivpu_device *vdev);
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev);
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev);
int ivpu_pm_suspend_cb(struct device *dev);
int ivpu_pm_resume_cb(struct device *dev);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 98759d6199d3..65f0f56ad753 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -937,8 +937,10 @@ static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start,
new_sids = krealloc_array(sids, count + new_count,
sizeof(*new_sids), GFP_KERNEL);
- if (!new_sids)
+ if (!new_sids) {
+ kfree(sids);
return NULL;
+ }
for (i = count; i < total_count; i++)
new_sids[i] = id_start++;
diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c
index 440cf9fb91aa..42c1a9052470 100644
--- a/drivers/acpi/riscv/cppc.c
+++ b/drivers/acpi/riscv/cppc.c
@@ -119,7 +119,7 @@ int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
*val = data.ret.value;
- return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+ return data.ret.error;
}
return -EINVAL;
@@ -148,7 +148,7 @@ int cpc_write_ffh(int cpu, struct cpc_reg *reg, u64 val)
smp_call_function_single(cpu, cppc_ffh_csr_write, &data, 1);
- return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+ return data.ret.error;
}
return -EINVAL;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index efc575a00edd..008da0354fba 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -603,6 +603,7 @@ CPU_SHOW_VULN_FALLBACK(ghostwrite);
CPU_SHOW_VULN_FALLBACK(old_microcode);
CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
CPU_SHOW_VULN_FALLBACK(tsa);
+CPU_SHOW_VULN_FALLBACK(vmscape);
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -622,6 +623,7 @@ static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL);
static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
+static DEVICE_ATTR(vmscape, 0444, cpu_show_vmscape, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@@ -642,6 +644,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_old_microcode.attr,
&dev_attr_indirect_target_selection.attr,
&dev_attr_tsa.attr,
+ &dev_attr_vmscape.attr,
NULL
};
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index bbc27ef9edf7..b4c79fde1979 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1554,13 +1554,15 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
pr_debug("CPU %d exiting\n", policy->cpu);
}
-static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
+static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy, bool policy_change)
{
struct amd_cpudata *cpudata = policy->driver_data;
union perf_cached perf;
u8 epp;
- if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+ if (policy_change ||
+ policy->min != cpudata->min_limit_freq ||
+ policy->max != cpudata->max_limit_freq)
amd_pstate_update_min_max_limit(policy);
if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1584,7 +1586,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
cpudata->policy = policy->policy;
- ret = amd_pstate_epp_update_limit(policy);
+ ret = amd_pstate_epp_update_limit(policy, true);
if (ret)
return ret;
@@ -1626,13 +1628,14 @@ static int amd_pstate_suspend(struct cpufreq_policy *policy)
* min_perf value across kexec reboots. If this CPU is just resumed back without kexec,
* the limits, epp and desired perf will get reset to the cached values in cpudata struct
*/
- ret = amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
+ ret = amd_pstate_update_perf(policy, perf.bios_min_perf,
+ FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached),
+ FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached),
+ FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached),
+ false);
if (ret)
return ret;
- /* invalidate to ensure it's rewritten during resume */
- cpudata->cppc_req_cached = 0;
-
/* set this flag to avoid setting core offline*/
cpudata->suspended = true;
@@ -1658,7 +1661,7 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
int ret;
/* enable amd pstate from suspend state*/
- ret = amd_pstate_epp_update_limit(policy);
+ ret = amd_pstate_epp_update_limit(policy, false);
if (ret)
return ret;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f366d35c5840..0d5d283a5429 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1034,8 +1034,8 @@ static bool hybrid_register_perf_domain(unsigned int cpu)
if (!cpu_dev)
return false;
- if (em_dev_register_perf_domain(cpu_dev, HYBRID_EM_STATE_COUNT, &cb,
- cpumask_of(cpu), false))
+ if (em_dev_register_pd_no_update(cpu_dev, HYBRID_EM_STATE_COUNT, &cb,
+ cpumask_of(cpu), false))
return false;
cpudata->pd_registered = true;
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index cae52c654a15..7685a8550d4b 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -128,7 +128,6 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
ptemp = dma_alloc_coherent(mci->pdev, 16, &dma_handle, GFP_KERNEL);
if (!ptemp) {
- dma_free_coherent(mci->pdev, 16, ptemp, dma_handle);
edac_printk(KERN_ERR, EDAC_MC,
"Inject: Buffer Allocation error\n");
return -ENOMEM;
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index e43abb322fa6..d8ac40d0eb6f 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -3,6 +3,9 @@
# GPIO infrastructure and drivers
#
+config GPIOLIB_LEGACY
+ def_bool y
+
menuconfig GPIOLIB
bool "GPIO Support"
help
@@ -12,9 +15,6 @@ menuconfig GPIOLIB
If unsure, say N.
-config GPIOLIB_LEGACY
- def_bool y
-
if GPIOLIB
config GPIOLIB_FASTPATH_LIMIT
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 23484317a5fa..693357caa9a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block)
psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
if (!psp->cmd) {
dev_err(adev->dev, "Failed to allocate memory to command buffer!\n");
- ret = -ENOMEM;
+ return -ENOMEM;
}
adev->psp.xgmi_context.supports_extended_data =
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index bf7c22f81cda..ba73518f5cdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1462,17 +1462,12 @@ static int dce_v10_0_audio_init(struct amdgpu_device *adev)
static void dce_v10_0_audio_fini(struct amdgpu_device *adev)
{
- int i;
-
if (!amdgpu_audio)
return;
if (!adev->mode_info.audio.enabled)
return;
- for (i = 0; i < adev->mode_info.audio.num_pins; i++)
- dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
adev->mode_info.audio.enabled = false;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 47e05783c4a0..b01d88d078fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1511,17 +1511,12 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev)
static void dce_v11_0_audio_fini(struct amdgpu_device *adev)
{
- int i;
-
if (!amdgpu_audio)
return;
if (!adev->mode_info.audio.enabled)
return;
- for (i = 0; i < adev->mode_info.audio.num_pins; i++)
- dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
adev->mode_info.audio.enabled = false;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 276c025c4c03..81760a26f2ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1451,17 +1451,12 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev)
static void dce_v6_0_audio_fini(struct amdgpu_device *adev)
{
- int i;
-
if (!amdgpu_audio)
return;
if (!adev->mode_info.audio.enabled)
return;
- for (i = 0; i < adev->mode_info.audio.num_pins; i++)
- dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
adev->mode_info.audio.enabled = false;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index e62ccf9eb73d..19a265bd4d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1443,17 +1443,12 @@ static int dce_v8_0_audio_init(struct amdgpu_device *adev)
static void dce_v8_0_audio_fini(struct amdgpu_device *adev)
{
- int i;
-
if (!amdgpu_audio)
return;
if (!adev->mode_info.audio.enabled)
return;
- for (i = 0; i < adev->mode_info.audio.num_pins; i++)
- dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
adev->mode_info.audio.enabled = false;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 28eb846280dd..3f6a828cad8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -641,8 +641,9 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes,
break;
case MES_MISC_OP_CHANGE_CONFIG:
if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) {
- dev_err(mes->adev->dev, "MES FW version must be larger than 0x63 to support limit single process feature.\n");
- return -EINVAL;
+ dev_warn_once(mes->adev->dev,
+ "MES FW version must be larger than 0x63 to support limit single process feature.\n");
+ return 0;
}
misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG;
misc_pkt.change_config.opcode =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index e6d8eddda2bf..db6e41967f12 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1377,7 +1377,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
case IP_VERSION(6, 0, 0):
- if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq)
+ if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
break;
case IP_VERSION(6, 0, 1):
@@ -1385,11 +1385,11 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
break;
case IP_VERSION(6, 0, 2):
- if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq)
+ if ((adev->sdma.instance[0].fw_version >= 23) && !adev->sdma.disable_uq)
adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
break;
case IP_VERSION(6, 0, 3):
- if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq)
+ if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
break;
case IP_VERSION(6, 1, 0):
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a0ca3b2c6bd8..7808a647a306 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8381,8 +8381,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
drm_add_modes_noedid(connector, 1920, 1080);
} else {
amdgpu_dm_connector_ddc_get_modes(connector, drm_edid);
- if (encoder && (connector->connector_type != DRM_MODE_CONNECTOR_eDP) &&
- (connector->connector_type != DRM_MODE_CONNECTOR_LVDS))
+ if (encoder)
amdgpu_dm_connector_add_common_modes(encoder, connector);
amdgpu_dm_connector_add_freesync_modes(connector, drm_edid);
}
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
index 75fb77bca83b..01480a04f85e 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
@@ -520,6 +520,15 @@ void dpp1_dppclk_control(
REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0);
}
+void dpp_force_disable_cursor(struct dpp *dpp_base)
+{
+ struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+ /* Force disable cursor */
+ REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, 0);
+ dpp_base->pos.cur0_ctl.bits.cur0_enable = 0;
+}
+
static const struct dpp_funcs dcn10_dpp_funcs = {
.dpp_read_state = dpp_read_state,
.dpp_reset = dpp_reset,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
index c48139bed11f..f466182963f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
@@ -1525,4 +1525,6 @@ void dpp1_construct(struct dcn10_dpp *dpp1,
void dpp1_cm_get_gamut_remap(struct dpp *dpp_base,
struct dpp_grph_csc_adjustment *adjust);
+void dpp_force_disable_cursor(struct dpp *dpp_base);
+
#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
index 2d70586cef40..09be2a90cc79 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
@@ -1494,6 +1494,7 @@ static struct dpp_funcs dcn30_dpp_funcs = {
.dpp_dppclk_control = dpp1_dppclk_control,
.dpp_set_hdr_multiplier = dpp3_set_hdr_multiplier,
.dpp_get_gamut_remap = dpp3_cm_get_gamut_remap,
+ .dpp_force_disable_cursor = dpp_force_disable_cursor,
};
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index e68f21fd5f0f..560984533950 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -528,3 +528,75 @@ void dcn314_disable_link_output(struct dc_link *link,
apply_symclk_on_tx_off_wa(link);
}
+
+/**
+ * dcn314_dpp_pg_control - DPP power gate control.
+ *
+ * @hws: dce_hwseq reference.
+ * @dpp_inst: DPP instance reference.
+ * @power_on: true if we want to enable power gate, false otherwise.
+ *
+ * Enable or disable power gate in the specific DPP instance.
+ * If power gating is disabled, will force disable cursor in the DPP instance.
+ */
+void dcn314_dpp_pg_control(
+ struct dce_hwseq *hws,
+ unsigned int dpp_inst,
+ bool power_on)
+{
+ uint32_t power_gate = power_on ? 0 : 1;
+ uint32_t pwr_status = power_on ? 0 : 2;
+
+
+ if (hws->ctx->dc->debug.disable_dpp_power_gate) {
+ /* Workaround for DCN314 with disabled power gating */
+ if (!power_on) {
+
+ /* Force disable cursor if power gating is disabled */
+ struct dpp *dpp = hws->ctx->dc->res_pool->dpps[dpp_inst];
+ if (dpp && dpp->funcs->dpp_force_disable_cursor)
+ dpp->funcs->dpp_force_disable_cursor(dpp);
+ }
+ return;
+ }
+ if (REG(DOMAIN1_PG_CONFIG) == 0)
+ return;
+
+ switch (dpp_inst) {
+ case 0: /* DPP0 */
+ REG_UPDATE(DOMAIN1_PG_CONFIG,
+ DOMAIN1_POWER_GATE, power_gate);
+
+ REG_WAIT(DOMAIN1_PG_STATUS,
+ DOMAIN1_PGFSM_PWR_STATUS, pwr_status,
+ 1, 1000);
+ break;
+ case 1: /* DPP1 */
+ REG_UPDATE(DOMAIN3_PG_CONFIG,
+ DOMAIN3_POWER_GATE, power_gate);
+
+ REG_WAIT(DOMAIN3_PG_STATUS,
+ DOMAIN3_PGFSM_PWR_STATUS, pwr_status,
+ 1, 1000);
+ break;
+ case 2: /* DPP2 */
+ REG_UPDATE(DOMAIN5_PG_CONFIG,
+ DOMAIN5_POWER_GATE, power_gate);
+
+ REG_WAIT(DOMAIN5_PG_STATUS,
+ DOMAIN5_PGFSM_PWR_STATUS, pwr_status,
+ 1, 1000);
+ break;
+ case 3: /* DPP3 */
+ REG_UPDATE(DOMAIN7_PG_CONFIG,
+ DOMAIN7_POWER_GATE, power_gate);
+
+ REG_WAIT(DOMAIN7_PG_STATUS,
+ DOMAIN7_PGFSM_PWR_STATUS, pwr_status,
+ 1, 1000);
+ break;
+ default:
+ BREAK_TO_DEBUGGER();
+ break;
+ }
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
index 2305ad282f21..6c072d0274ea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
@@ -47,4 +47,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal);
+void dcn314_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on);
+
#endif /* __DC_HWSS_DCN314_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
index f5112742edf9..9f454fa90e65 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
@@ -141,6 +141,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
.enable_power_gating_plane = dcn314_enable_power_gating_plane,
.dpp_root_clock_control = dcn314_dpp_root_clock_control,
.hubp_pg_control = dcn31_hubp_pg_control,
+ .dpp_pg_control = dcn314_dpp_pg_control,
.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
.update_odm = dcn314_update_odm,
.dsc_pg_control = dcn314_dsc_pg_control,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 0c5675d1c593..1b7c085dc2cc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -349,6 +349,9 @@ struct dpp_funcs {
struct dpp *dpp_base,
enum dc_color_space color_space,
struct dc_csc_transform cursor_csc_color_matrix);
+
+ void (*dpp_force_disable_cursor)(struct dpp *dpp_base);
+
};
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 464390372b34..ae0d08e5e960 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -393,6 +393,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev)
gpiod_set_value_cansleep(pdata->enable_gpio, 1);
/*
+ * After EN is deasserted and an external clock is detected, the bridge
+ * will sample GPIO3:1 to determine its frequency. The driver will
+ * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is
+ * racy. Thus we have to wait a couple of us. According to the datasheet
+ * the GPIO lines has to be stable at least 5 us (td5) but it seems that
+ * is not enough and the refclk frequency value is still lost or
+ * overwritten by the bridge itself. Waiting for 20us seems to work.
+ */
+ usleep_range(20, 30);
+
+ /*
* If we have a reference clock we can enable communication w/ the
* panel (including the aux channel) w/out any need for an input clock
* so we can do it in resume which lets us read the EDID before
diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c
index cccdeca72002..317e516c4ec7 100644
--- a/drivers/gpu/drm/nouveau/gv100_fence.c
+++ b/drivers/gpu/drm/nouveau/gv100_fence.c
@@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence)
struct nvif_push *push = &chan->chan.push;
int ret;
- ret = PUSH_WAIT(push, 8);
+ ret = PUSH_WAIT(push, 13);
if (ret)
return ret;
@@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence)
NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) |
NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS));
+ PUSH_MTHD(push, NVC36F, MEM_OP_A, 0,
+ MEM_OP_B, 0,
+ MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR),
+ MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR));
+
PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0);
PUSH_KICK(push);
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
index 8735dda4c8a7..338f74b9f501 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
@@ -7,6 +7,91 @@
#define NVC36F_NON_STALL_INTERRUPT (0x00000020)
#define NVC36F_NON_STALL_INTERRUPT_HANDLE 31:0
+// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for
+// specifying the page address for a targeted TLB invalidate and the uTLB for
+// a targeted REPLAY_CANCEL for UVM.
+// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly
+// rearranged fields.
+#define NVC36F_MEM_OP_A (0x00000028)
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID 5:0 // only relevant for REPLAY_CANCEL_TARGETED
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE 5:0 // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID 10:6 // only relevant for REPLAY_CANCEL_TARGETED
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID 6:0 // only relevant for REPLAY_CANCEL_VA_GLOBAL
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR 11:11
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN 0x00000001
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS 0x00000000
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO 31:12
+#define NVC36F_MEM_OP_B (0x0000002c)
+#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI 31:0
+#define NVC36F_MEM_OP_C (0x00000030)
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE 2:0
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR 0x00000000
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB 0:0
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE 0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL 0x00000001 // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC 1:1
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE 0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY 4:2 // only relevant if GPC ENABLE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE 0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL 0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED 0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL 0x00000004
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL 0x00000005
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE 6:5 // only relevant if GPC ENABLE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE 0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE 0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE 9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ 0
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE 1
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG 2
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD 3
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK 4
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL 5
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC 6
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL 7
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL 9:7 // Invalidate affects this level and all below
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL 0x00000000 // Invalidate tlb caches at all levels of the page table
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0 0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1 0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2 0x00000004
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3 0x00000005
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4 0x00000006
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5 0x00000007
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE 11:10 // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM 0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT 0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO 31:12 // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG 19:0
+// MEM_OP_D MUST be preceded by MEM_OPs A-C.
+#define NVC36F_MEM_OP_D (0x00000034)
+#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI 26:0 // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_D_OPERATION 31:27
+#define NVC36F_MEM_OP_D_OPERATION_MEMBAR 0x00000005
+#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE 0x00000009
+#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED 0x0000000a
+#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE 0x0000000d
+#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE 0x0000000e
+// CLEAN_LINES is an alias for Tegra/GPU IP usage
+#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES 0x0000000e
+#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS 0x0000000f
+#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY 0x00000010
+#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS 0x00000015
+#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR 0x00000016
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE 1:0
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC 0x00000000
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC 0x00000001
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL 0x00000002
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED 0x00000003
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE 2:2
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC 0x00000000
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC 0x00000001
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK 6:3
#define NVC36F_SEM_ADDR_LO (0x0000005c)
#define NVC36F_SEM_ADDR_LO_OFFSET 31:2
#define NVC36F_SEM_ADDR_HI (0x00000060)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
index fdffa0391b31..6fd4e60634fb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
@@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine)
nvkm_chid_unref(&fifo->chid);
nvkm_event_fini(&fifo->nonstall.event);
+ if (fifo->func->nonstall_dtor)
+ fifo->func->nonstall_dtor(fifo);
mutex_destroy(&fifo->mutex);
if (fifo->func->dtor)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
index e74493a4569e..6848a56f20c0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth)
static void
ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index)
{
- struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
- struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
- nvkm_inth_block(&runl->nonstall.inth);
}
static void
ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index)
{
- struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
- struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
- nvkm_inth_allow(&runl->nonstall.inth);
}
const struct nvkm_event_func
@@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
if (ret)
return ret;
+ nvkm_inth_allow(&runl->nonstall.inth);
+
nr = max(nr, runl->id + 1);
}
return nr;
}
+void
+ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo)
+{
+ struct nvkm_runl *runl;
+
+ nvkm_runl_foreach(runl, fifo) {
+ if (runl->nonstall.vector < 0)
+ continue;
+ nvkm_inth_block(&runl->nonstall.inth);
+ }
+}
+
int
ga100_fifo_runl_ctor(struct nvkm_fifo *fifo)
{
@@ -599,6 +605,7 @@ ga100_fifo = {
.runl_ctor = ga100_fifo_runl_ctor,
.mmu_fault = &tu102_fifo_mmu_fault,
.nonstall_ctor = ga100_fifo_nonstall_ctor,
+ .nonstall_dtor = ga100_fifo_nonstall_dtor,
.nonstall = &ga100_fifo_nonstall,
.runl = &ga100_runl,
.runq = &ga100_runq,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
index 755235f55b3a..18a0b1f4eab7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
@@ -30,6 +30,7 @@ ga102_fifo = {
.runl_ctor = ga100_fifo_runl_ctor,
.mmu_fault = &tu102_fifo_mmu_fault,
.nonstall_ctor = ga100_fifo_nonstall_ctor,
+ .nonstall_dtor = ga100_fifo_nonstall_dtor,
.nonstall = &ga100_fifo_nonstall,
.runl = &ga100_runl,
.runq = &ga100_runq,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
index 5e81ae195329..fff1428ef267 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
@@ -41,6 +41,7 @@ struct nvkm_fifo_func {
void (*start)(struct nvkm_fifo *, unsigned long *);
int (*nonstall_ctor)(struct nvkm_fifo *);
+ void (*nonstall_dtor)(struct nvkm_fifo *);
const struct nvkm_event_func *nonstall;
const struct nvkm_runl_func *runl;
@@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *);
int ga100_fifo_runl_ctor(struct nvkm_fifo *);
int ga100_fifo_nonstall_ctor(struct nvkm_fifo *);
+void ga100_fifo_nonstall_dtor(struct nvkm_fifo *);
extern const struct nvkm_event_func ga100_fifo_nonstall;
extern const struct nvkm_runl_func ga100_runl;
extern const struct nvkm_runq_func ga100_runq;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
index 1ac5628c5140..4ed54b386a60 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
@@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device,
rm->chan.func = &r535_chan;
rm->nonstall = &ga100_fifo_nonstall;
rm->nonstall_ctor = ga100_fifo_nonstall_ctor;
+ rm->nonstall_dtor = ga100_fifo_nonstall_dtor;
return nvkm_fifo_new_(rm, device, type, inst, pfifo);
}
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 8867b95ab089..3d06f72531ba 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority);
* Add a callback to the current dependency of the entity to wake up the
* scheduler when the entity becomes available.
*/
-static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
+static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity,
+ struct drm_sched_job *sched_job)
{
struct drm_gpu_scheduler *sched = entity->rq->sched;
struct dma_fence *fence = entity->dependency;
@@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
entity->dependency = fence;
}
+ if (trace_drm_sched_job_unschedulable_enabled() &&
+ !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags))
+ trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+
if (!dma_fence_add_callback(entity->dependency, &entity->cb,
drm_sched_entity_wakeup))
return true;
@@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
while ((entity->dependency =
drm_sched_job_dependency(sched_job, entity))) {
- if (drm_sched_entity_add_dependency_cb(entity)) {
- trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+ if (drm_sched_entity_add_dependency_cb(entity, sched_job))
return NULL;
- }
}
/* skip jobs from entity that marked guilty */
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 1be2415966df..9954bb458ce1 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -819,8 +819,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
return ret;
}
- tt_has_data = ttm && (ttm_tt_is_populated(ttm) ||
- (ttm->page_flags & TTM_TT_FLAG_SWAPPED));
+ tt_has_data = ttm && (ttm_tt_is_populated(ttm) || ttm_tt_is_swapped(ttm));
move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) :
(!mem_type_is_vram(old_mem_type) && !tt_has_data));
diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c
index 5a394eeff676..59a2c8889fa2 100644
--- a/drivers/hwmon/ina238.c
+++ b/drivers/hwmon/ina238.c
@@ -379,7 +379,7 @@ static int ina238_write_in(struct device *dev, u32 attr, int channel,
regval = clamp_val(val, -163, 163);
regval = (regval * 1000 * 4) /
(INA238_SHUNT_VOLTAGE_LSB * data->gain);
- regval = clamp_val(regval, S16_MIN, S16_MAX);
+ regval = clamp_val(regval, S16_MIN, S16_MAX) & 0xffff;
switch (attr) {
case hwmon_in_max:
@@ -517,9 +517,10 @@ static int ina238_write_power(struct device *dev, u32 attr, long val)
* Unsigned postive values. Compared against the 24-bit power register,
* lower 8-bits are truncated. Same conversion to/from uW as POWER
* register.
+ * The first clamp_val() is to establish a baseline to avoid overflows.
*/
- regval = clamp_val(val, 0, LONG_MAX);
- regval = div_u64(val * 4 * 100 * data->rshunt, data->config->power_calculate_factor *
+ regval = clamp_val(val, 0, LONG_MAX / 2);
+ regval = div_u64(regval * 4 * 100 * data->rshunt, data->config->power_calculate_factor *
1000ULL * INA238_FIXED_SHUNT * data->gain);
regval = clamp_val(regval >> 8, 0, U16_MAX);
@@ -572,7 +573,7 @@ static int ina238_write_temp(struct device *dev, u32 attr, long val)
return -EOPNOTSUPP;
/* Signed */
- regval = clamp_val(val, -40000, 125000);
+ val = clamp_val(val, -40000, 125000);
regval = div_s64(val * 10000, data->config->temp_lsb) << data->config->temp_shift;
regval = clamp_val(regval, S16_MIN, S16_MAX) & (0xffff << data->config->temp_shift);
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
index a5f89aab3fb4..c25a54d5b39a 100644
--- a/drivers/hwmon/mlxreg-fan.c
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -561,15 +561,14 @@ static int mlxreg_fan_cooling_config(struct device *dev, struct mlxreg_fan *fan)
if (!pwm->connected)
continue;
pwm->fan = fan;
+ /* Set minimal PWM speed. */
+ pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY);
pwm->cdev = devm_thermal_of_cooling_device_register(dev, NULL, mlxreg_fan_name[i],
pwm, &mlxreg_fan_cooling_ops);
if (IS_ERR(pwm->cdev)) {
dev_err(dev, "Failed to register cooling device\n");
return PTR_ERR(pwm->cdev);
}
-
- /* Set minimal PWM speed. */
- pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY);
}
return 0;
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index a7f89946dad4..e94ac746a741 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1052,7 +1052,7 @@ static const struct pci_device_id i801_ids[] = {
{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_SOC_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_PCH_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
- { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
+ { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5) },
{ PCI_DEVICE_DATA(INTEL, ARROW_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
{ PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
{ PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) },
diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index cfafe089102a..9e1f71fed0fe 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -99,6 +99,9 @@ static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c
{
u32 val, mask;
+ if (len < 1 || len > 16)
+ return -EINVAL;
+
val = chan->bus_freq << RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS;
mask = RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK;
@@ -222,15 +225,6 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
}
switch (size) {
- case I2C_SMBUS_QUICK:
- ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0);
- if (ret)
- goto out_unlock;
- ret = rtl9300_i2c_reg_addr_set(i2c, 0, 0);
- if (ret)
- goto out_unlock;
- break;
-
case I2C_SMBUS_BYTE:
if (read_write == I2C_SMBUS_WRITE) {
ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0);
@@ -312,9 +306,9 @@ out_unlock:
static u32 rtl9300_i2c_func(struct i2c_adapter *a)
{
- return I2C_FUNC_SMBUS_QUICK | I2C_FUNC_SMBUS_BYTE |
- I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA |
- I2C_FUNC_SMBUS_BLOCK_DATA;
+ return I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_BYTE_DATA |
+ I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_DATA |
+ I2C_FUNC_SMBUS_I2C_BLOCK;
}
static const struct i2c_algorithm rtl9300_i2c_algo = {
@@ -323,7 +317,7 @@ static const struct i2c_algorithm rtl9300_i2c_algo = {
};
static struct i2c_adapter_quirks rtl9300_i2c_quirks = {
- .flags = I2C_AQ_NO_CLK_STRETCH,
+ .flags = I2C_AQ_NO_CLK_STRETCH | I2C_AQ_NO_ZERO_LEN,
.max_read_len = 16,
.max_write_len = 16,
};
@@ -353,7 +347,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, i2c);
- if (device_get_child_node_count(dev) >= RTL9300_I2C_MUX_NCHAN)
+ if (device_get_child_node_count(dev) > RTL9300_I2C_MUX_NCHAN)
return dev_err_probe(dev, -EINVAL, "Too many channels\n");
device_for_each_child_node(dev, child) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1baaf52c603c..4e033c26fdd4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9125,6 +9125,11 @@ void md_do_sync(struct md_thread *thread)
}
action = md_sync_action(mddev);
+ if (action == ACTION_FROZEN || action == ACTION_IDLE) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ goto skip;
+ }
+
desc = md_sync_action_name(action);
mddev->last_sync_action = action;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 408c26398321..bf44878ec640 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1225,7 +1225,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
int i = 0;
struct bio *behind_bio = NULL;
- behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO,
+ behind_bio = bio_alloc_bioset(NULL, vcnt, bio->bi_opf, GFP_NOIO,
&r1_bio->mddev->bio_set);
/* discard op, we don't support writezero/writesame yet */
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 64e664f5adcc..87c134bcd48d 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -861,7 +861,6 @@ static int rcar_can_resume(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
struct rcar_can_priv *priv = netdev_priv(ndev);
- u16 ctlr;
int err;
if (!netif_running(ndev))
@@ -873,12 +872,7 @@ static int rcar_can_resume(struct device *dev)
return err;
}
- ctlr = readw(&priv->regs->ctlr);
- ctlr &= ~RCAR_CAN_CTLR_SLPM;
- writew(ctlr, &priv->regs->ctlr);
- ctlr &= ~RCAR_CAN_CTLR_CANM;
- writew(ctlr, &priv->regs->ctlr);
- priv->can.state = CAN_STATE_ERROR_ACTIVE;
+ rcar_can_start(ndev);
netif_device_attach(ndev);
netif_start_queue(ndev);
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 81baec8eb1e5..a25a3ca62c12 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
dlc |= XCAN_DLCR_EDL_MASK;
}
- if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
- (priv->devtype.flags & XCAN_FLAG_TXFEMP))
- can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
- else
- can_put_echo_skb(skb, ndev, 0, 0);
-
- priv->tx_head++;
-
priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
/* If the CAN frame is RTR frame this write triggers transmission
* (not on CAN FD)
@@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
data[1]);
}
}
+
+ if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
+ (priv->devtype.flags & XCAN_FLAG_TXFEMP))
+ can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
+ else
+ can_put_echo_skb(skb, ndev, 0, 0);
+
+ priv->tx_head++;
}
/**
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 829b1f087e9e..2f846381d5a7 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1273,9 +1273,15 @@ static int b53_setup(struct dsa_switch *ds)
*/
ds->untag_vlan_aware_bridge_pvid = true;
- /* Ageing time is set in seconds */
- ds->ageing_time_min = 1 * 1000;
- ds->ageing_time_max = AGE_TIME_MAX * 1000;
+ if (dev->chip_id == BCM53101_DEVICE_ID) {
+ /* BCM53101 uses 0.5 second increments */
+ ds->ageing_time_min = 1 * 500;
+ ds->ageing_time_max = AGE_TIME_MAX * 500;
+ } else {
+ /* Everything else uses 1 second increments */
+ ds->ageing_time_min = 1 * 1000;
+ ds->ageing_time_max = AGE_TIME_MAX * 1000;
+ }
ret = b53_reset_switch(dev);
if (ret) {
@@ -2559,7 +2565,10 @@ int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
else
reg = B53_AGING_TIME_CONTROL;
- atc = DIV_ROUND_CLOSEST(msecs, 1000);
+ if (dev->chip_id == BCM53101_DEVICE_ID)
+ atc = DIV_ROUND_CLOSEST(msecs, 500);
+ else
+ atc = DIV_ROUND_CLOSEST(msecs, 1000);
if (!is5325(dev) && !is5365(dev))
atc |= AGE_CHANGE;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1383918f8a3f..adf1f2bbcbb1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2363,7 +2363,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev)
*/
phy_dev = of_phy_find_device(fep->phy_node);
phy_reset_after_clk_enable(phy_dev);
- put_device(&phy_dev->mdio.dev);
+ if (phy_dev)
+ put_device(&phy_dev->mdio.dev);
}
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 76d872b91a38..cc02a85ad42b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1561,6 +1561,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
struct i40e_aq_set_mac_config {
__le16 max_frame_size;
u8 params;
+#define I40E_AQ_SET_MAC_CONFIG_CRC_EN BIT(2)
u8 tx_timer_priority; /* bitmap */
__le16 tx_timer_value;
__le16 fc_refresh_threshold;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 270e7e8cf9cf..59f5c1e810eb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1190,6 +1190,40 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
}
/**
+ * i40e_aq_set_mac_config - Configure MAC settings
+ * @hw: pointer to the hw struct
+ * @max_frame_size: Maximum Frame Size to be supported by the port
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Set MAC configuration (0x0603). Note that max_frame_size must be greater
+ * than zero.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+ struct i40e_asq_cmd_details *cmd_details)
+{
+ struct i40e_aq_set_mac_config *cmd;
+ struct libie_aq_desc desc;
+
+ cmd = libie_aq_raw(&desc);
+
+ if (max_frame_size == 0)
+ return -EINVAL;
+
+ i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_mac_config);
+
+ cmd->max_frame_size = cpu_to_le16(max_frame_size);
+ cmd->params = I40E_AQ_SET_MAC_CONFIG_CRC_EN;
+
+#define I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD 0x7FFF
+ cmd->fc_refresh_threshold =
+ cpu_to_le16(I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD);
+
+ return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+}
+
+/**
* i40e_aq_clear_pxe_mode
* @hw: pointer to the hw struct
* @cmd_details: pointer to command details structure or NULL
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b83f823e4917..b14019d44b58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4156,7 +4156,7 @@ free_queue_irqs:
irq_num = pf->msix_entries[base + vector].vector;
irq_set_affinity_notifier(irq_num, NULL);
irq_update_affinity_hint(irq_num, NULL);
- free_irq(irq_num, &vsi->q_vectors[vector]);
+ free_irq(irq_num, vsi->q_vectors[vector]);
}
return err;
}
@@ -16045,13 +16045,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
dev_dbg(&pf->pdev->dev, "get supported phy types ret = %pe last_status = %s\n",
ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
- /* make sure the MFS hasn't been set lower than the default */
#define MAX_FRAME_SIZE_DEFAULT 0x2600
- val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK,
- rd32(&pf->hw, I40E_PRTGL_SAH));
- if (val < MAX_FRAME_SIZE_DEFAULT)
- dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n",
- pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT);
+
+ err = i40e_aq_set_mac_config(hw, MAX_FRAME_SIZE_DEFAULT, NULL);
+ if (err)
+ dev_warn(&pdev->dev, "set mac config ret = %pe last_status = %s\n",
+ ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
+
+ /* Make sure the MFS is set to the expected value */
+ val = rd32(hw, I40E_PRTGL_SAH);
+ FIELD_MODIFY(I40E_PRTGL_SAH_MFS_MASK, &val, MAX_FRAME_SIZE_DEFAULT);
+ wr32(hw, I40E_PRTGL_SAH, val);
/* Add a filter to drop all Flow control frames from any VSI from being
* transmitted. By doing so we stop a malicious VF from sending out
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index aef5de53ce3b..26bb7bffe361 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -98,6 +98,8 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw,
struct i40e_asq_cmd_details *cmd_details);
int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask,
struct i40e_asq_cmd_details *cmd_details);
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+ struct i40e_asq_cmd_details *cmd_details);
int i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
struct i40e_asq_cmd_details *cmd_details);
int i40e_aq_set_link_restart_an(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 92ef33459aec..7b8f32c5169a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev,
} else {
dev_info(&adapter->pdev->dev, "online testing starting\n");
- /* PHY is powered down when interface is down */
- if (if_running && igb_link_test(adapter, &data[TEST_LINK]))
+ if (igb_link_test(adapter, &data[TEST_LINK]))
eth_test->flags |= ETH_TEST_FL_FAILED;
- else
- data[TEST_LINK] = 0;
/* Online tests aren't run; pass by default */
data[TEST_REG] = 0;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a9a7a94ae61e..453deb6d14b3 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4453,8 +4453,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
- rx_ring->queue_index,
- rx_ring->q_vector->napi.napi_id);
+ rx_ring->queue_index, 0);
if (res < 0) {
dev_err(dev, "Failed to register xdp_rxq index %u\n",
rx_ring->queue_index);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index dadce6009791..e42d0fdefee1 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -654,7 +654,7 @@ static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac,
static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
{
- struct net_device *real_dev;
+ struct net_device *real_dev, *port_dev;
struct prueth_emac *emac;
u8 vlan_id, i;
@@ -663,11 +663,15 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
if (is_hsr_master(real_dev)) {
for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
- emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
- if (!emac)
+ port_dev = hsr_get_port_ndev(real_dev, i);
+ emac = netdev_priv(port_dev);
+ if (!emac) {
+ dev_put(port_dev);
return -EINVAL;
+ }
icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
true);
+ dev_put(port_dev);
}
} else {
emac = netdev_priv(real_dev);
@@ -679,7 +683,7 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
{
- struct net_device *real_dev;
+ struct net_device *real_dev, *port_dev;
struct prueth_emac *emac;
u8 vlan_id, i;
@@ -688,11 +692,15 @@ static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
if (is_hsr_master(real_dev)) {
for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
- emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
- if (!emac)
+ port_dev = hsr_get_port_ndev(real_dev, i);
+ emac = netdev_priv(port_dev);
+ if (!emac) {
+ dev_put(port_dev);
return -EINVAL;
+ }
icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
false);
+ dev_put(port_dev);
}
} else {
emac = netdev_priv(real_dev);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index bcd07a715752..5cb353a97d6d 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -2078,10 +2078,6 @@ static void wx_setup_mrqc(struct wx *wx)
{
u32 rss_field = 0;
- /* VT, and RSS do not coexist at the same time */
- if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
- return;
-
/* Disable indicating checksum in descriptor, enables RSS hash */
wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 01329fe7451a..0eca96eeed58 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4286,6 +4286,7 @@ static int macsec_newlink(struct net_device *dev,
if (err < 0)
goto del_dev;
+ netdev_update_features(dev);
netif_stacked_transfer_operstate(real_dev, dev);
linkwatch_fire_event(dev);
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 28acc6392cfc..392749aae54d 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -361,7 +361,7 @@ config NXP_TJA11XX_PHY
tristate "NXP TJA11xx PHYs support"
depends on HWMON
help
- Currently supports the NXP TJA1100 and TJA1101 PHY.
+ Currently supports the NXP TJA1100, TJA1101 and TJA1102 PHYs.
config NCN26000_PHY
tristate "Onsemi 10BASE-T1S Ethernet PHY"
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 13df28445f02..c02da57a4da5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1065,23 +1065,19 @@ EXPORT_SYMBOL_GPL(phy_inband_caps);
*/
int phy_config_inband(struct phy_device *phydev, unsigned int modes)
{
- int err;
+ lockdep_assert_held(&phydev->lock);
if (!!(modes & LINK_INBAND_DISABLE) +
!!(modes & LINK_INBAND_ENABLE) +
!!(modes & LINK_INBAND_BYPASS) != 1)
return -EINVAL;
- mutex_lock(&phydev->lock);
if (!phydev->drv)
- err = -EIO;
+ return -EIO;
else if (!phydev->drv->config_inband)
- err = -EOPNOTSUPP;
- else
- err = phydev->drv->config_inband(phydev, modes);
- mutex_unlock(&phydev->lock);
+ return -EOPNOTSUPP;
- return err;
+ return phydev->drv->config_inband(phydev, modes);
}
EXPORT_SYMBOL(phy_config_inband);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7556aa3dd7ee..c82c1997147b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -287,8 +287,7 @@ static bool phy_uses_state_machine(struct phy_device *phydev)
if (phydev->phy_link_change == phy_link_change)
return phydev->attached_dev && phydev->adjust_link;
- /* phydev->phy_link_change is implicitly phylink_phy_change() */
- return true;
+ return !!phydev->phy_link_change;
}
static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
@@ -1864,6 +1863,8 @@ void phy_detach(struct phy_device *phydev)
phydev->attached_dev = NULL;
phy_link_topo_del_phy(dev, phydev);
}
+
+ phydev->phy_link_change = NULL;
phydev->phylink = NULL;
if (!phydev->is_on_sfp_module)
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index c7cb95aa8007..1988b7d2089a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -67,6 +67,8 @@ struct phylink {
struct timer_list link_poll;
struct mutex state_mutex;
+ /* Serialize updates to pl->phydev with phylink_resolve() */
+ struct mutex phydev_mutex;
struct phylink_link_state phy_state;
unsigned int phy_ib_mode;
struct work_struct resolve;
@@ -1432,6 +1434,7 @@ static void phylink_get_fixed_state(struct phylink *pl,
static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
{
struct phylink_link_state link_state;
+ struct phy_device *phy = pl->phydev;
switch (pl->req_link_an_mode) {
case MLO_AN_PHY:
@@ -1455,7 +1458,11 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
link_state.link = false;
phylink_apply_manual_flow(pl, &link_state);
+ if (phy)
+ mutex_lock(&phy->lock);
phylink_major_config(pl, force_restart, &link_state);
+ if (phy)
+ mutex_unlock(&phy->lock);
}
static const char *phylink_pause_to_str(int pause)
@@ -1591,8 +1598,13 @@ static void phylink_resolve(struct work_struct *w)
struct phylink_link_state link_state;
bool mac_config = false;
bool retrigger = false;
+ struct phy_device *phy;
bool cur_link_state;
+ mutex_lock(&pl->phydev_mutex);
+ phy = pl->phydev;
+ if (phy)
+ mutex_lock(&phy->lock);
mutex_lock(&pl->state_mutex);
cur_link_state = phylink_link_is_up(pl);
@@ -1626,11 +1638,11 @@ static void phylink_resolve(struct work_struct *w)
/* If we have a phy, the "up" state is the union of both the
* PHY and the MAC
*/
- if (pl->phydev)
+ if (phy)
link_state.link &= pl->phy_state.link;
/* Only update if the PHY link is up */
- if (pl->phydev && pl->phy_state.link) {
+ if (phy && pl->phy_state.link) {
/* If the interface has changed, force a link down
* event if the link isn't already down, and re-resolve.
*/
@@ -1694,6 +1706,9 @@ static void phylink_resolve(struct work_struct *w)
queue_work(system_power_efficient_wq, &pl->resolve);
}
mutex_unlock(&pl->state_mutex);
+ if (phy)
+ mutex_unlock(&phy->lock);
+ mutex_unlock(&pl->phydev_mutex);
}
static void phylink_run_resolve(struct phylink *pl)
@@ -1829,6 +1844,7 @@ struct phylink *phylink_create(struct phylink_config *config,
if (!pl)
return ERR_PTR(-ENOMEM);
+ mutex_init(&pl->phydev_mutex);
mutex_init(&pl->state_mutex);
INIT_WORK(&pl->resolve, phylink_resolve);
@@ -2089,6 +2105,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
dev_name(&phy->mdio.dev), phy->drv->name, irq_str);
kfree(irq_str);
+ mutex_lock(&pl->phydev_mutex);
mutex_lock(&phy->lock);
mutex_lock(&pl->state_mutex);
pl->phydev = phy;
@@ -2134,6 +2151,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
mutex_unlock(&pl->state_mutex);
mutex_unlock(&phy->lock);
+ mutex_unlock(&pl->phydev_mutex);
phylink_dbg(pl,
"phy: %s setting supported %*pb advertising %*pb\n",
@@ -2312,6 +2330,7 @@ void phylink_disconnect_phy(struct phylink *pl)
ASSERT_RTNL();
+ mutex_lock(&pl->phydev_mutex);
phy = pl->phydev;
if (phy) {
mutex_lock(&phy->lock);
@@ -2321,8 +2340,11 @@ void phylink_disconnect_phy(struct phylink *pl)
pl->mac_tx_clk_stop = false;
mutex_unlock(&pl->state_mutex);
mutex_unlock(&phy->lock);
- flush_work(&pl->resolve);
+ }
+ mutex_unlock(&pl->phydev_mutex);
+ if (phy) {
+ flush_work(&pl->resolve);
phy_disconnect(phy);
}
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 812c1565114f..6b7493934535 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -903,6 +903,15 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
u32 upper, lower;
u64 ref48;
+ /* only type1 and type 2 PI formats have a reftag */
+ switch (ns->head->pi_type) {
+ case NVME_NS_DPS_PI_TYPE1:
+ case NVME_NS_DPS_PI_TYPE2:
+ break;
+ default:
+ return;
+ }
+
/* both rw and write zeroes share the same reftag format */
switch (ns->head->guard_type) {
case NVME_NVM_NS_16B_GUARD:
@@ -942,13 +951,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
if (nvme_ns_has_pi(ns->head)) {
cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
-
- switch (ns->head->pi_type) {
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- nvme_set_ref_tag(ns, cmnd, req);
- break;
- }
+ nvme_set_ref_tag(ns, cmnd, req);
}
return BLK_STS_OK;
@@ -1039,6 +1042,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head)))
return BLK_STS_NOTSUPP;
control |= NVME_RW_PRINFO_PRACT;
+ nvme_set_ref_tag(ns, cmnd, req);
}
if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD))
diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig
index dddb235dd020..660a95805524 100644
--- a/drivers/pcmcia/Kconfig
+++ b/drivers/pcmcia/Kconfig
@@ -250,7 +250,4 @@ config ELECTRA_CF
config PCCARD_NONSTATIC
bool
-config PCCARD_IODYN
- bool
-
endif # PCCARD
diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile
index c9d51b150682..d16a0317ce43 100644
--- a/drivers/pcmcia/Makefile
+++ b/drivers/pcmcia/Makefile
@@ -12,7 +12,6 @@ obj-$(CONFIG_PCMCIA) += pcmcia.o
pcmcia_rsrc-y += rsrc_mgr.o
pcmcia_rsrc-$(CONFIG_PCCARD_NONSTATIC) += rsrc_nonstatic.o
-pcmcia_rsrc-$(CONFIG_PCCARD_IODYN) += rsrc_iodyn.o
obj-$(CONFIG_PCCARD) += pcmcia_rsrc.o
diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index c75f55e1250a..adbc486af2ea 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -229,23 +229,6 @@ void pcmcia_unregister_socket(struct pcmcia_socket *socket)
EXPORT_SYMBOL(pcmcia_unregister_socket);
-struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr)
-{
- struct pcmcia_socket *s;
-
- down_read(&pcmcia_socket_list_rwsem);
- list_for_each_entry(s, &pcmcia_socket_list, socket_list)
- if (s->sock == nr) {
- up_read(&pcmcia_socket_list_rwsem);
- return s;
- }
- up_read(&pcmcia_socket_list_rwsem);
-
- return NULL;
-
-}
-EXPORT_SYMBOL(pcmcia_get_socket_by_nr);
-
static int socket_reset(struct pcmcia_socket *skt)
{
int status, i;
diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h
index 02a83ca44e77..5ac810ffda31 100644
--- a/drivers/pcmcia/cs_internal.h
+++ b/drivers/pcmcia/cs_internal.h
@@ -116,7 +116,6 @@ extern struct list_head pcmcia_socket_list;
extern const struct class pcmcia_socket_class;
int pccard_register_pcmcia(struct pcmcia_socket *s, struct pcmcia_callback *c);
-struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr);
void pcmcia_parse_uevents(struct pcmcia_socket *socket, unsigned int events);
#define PCMCIA_UEVENT_EJECT 0x0001
diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index da6f66f357cc..18f4eef28dbc 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -1308,7 +1308,7 @@ static int pcmcia_bus_early_resume(struct pcmcia_socket *skt)
* physically present, even if the call to this function returns
* non-NULL. Furthermore, the device driver most likely is unbound
* almost immediately, so the timeframe where pcmcia_dev_present
- * returns NULL is probably really really small.
+ * returns NULL is probably really, really small.
*/
struct pcmcia_device *pcmcia_dev_present(struct pcmcia_device *_p_dev)
{
diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index 1b1dff56ec7b..d6f24c7d1562 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -215,6 +215,8 @@ static int __init omap_cf_probe(struct platform_device *pdev)
return -EINVAL;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -EINVAL;
cf = kzalloc(sizeof *cf, GFP_KERNEL);
if (!cf)
@@ -302,7 +304,13 @@ static void __exit omap_cf_remove(struct platform_device *pdev)
kfree(cf);
}
-static struct platform_driver omap_cf_driver = {
+/*
+ * omap_cf_remove() lives in .exit.text. For drivers registered via
+ * platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver omap_cf_driver __refdata = {
.driver = {
.name = driver_name,
},
diff --git a/drivers/pcmcia/rsrc_iodyn.c b/drivers/pcmcia/rsrc_iodyn.c
deleted file mode 100644
index b04b16496b0c..000000000000
--- a/drivers/pcmcia/rsrc_iodyn.c
+++ /dev/null
@@ -1,168 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * rsrc_iodyn.c -- Resource management routines for MEM-static sockets.
- *
- * The initial developer of the original code is David A. Hinds
- * <dahinds@users.sourceforge.net>. Portions created by David A. Hinds
- * are Copyright (C) 1999 David A. Hinds. All Rights Reserved.
- *
- * (C) 1999 David A. Hinds
- */
-
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-
-#include <pcmcia/ss.h>
-#include <pcmcia/cistpl.h>
-#include "cs_internal.h"
-
-
-struct pcmcia_align_data {
- unsigned long mask;
- unsigned long offset;
-};
-
-static resource_size_t pcmcia_align(void *align_data,
- const struct resource *res,
- resource_size_t size, resource_size_t align)
-{
- struct pcmcia_align_data *data = align_data;
- resource_size_t start;
-
- start = (res->start & ~data->mask) + data->offset;
- if (start < res->start)
- start += data->mask + 1;
-
-#ifdef CONFIG_X86
- if (res->flags & IORESOURCE_IO) {
- if (start & 0x300)
- start = (start + 0x3ff) & ~0x3ff;
- }
-#endif
-
-#ifdef CONFIG_M68K
- if (res->flags & IORESOURCE_IO) {
- if ((res->start + size - 1) >= 1024)
- start = res->end;
- }
-#endif
-
- return start;
-}
-
-
-static struct resource *__iodyn_find_io_region(struct pcmcia_socket *s,
- unsigned long base, int num,
- unsigned long align)
-{
- struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_IO,
- dev_name(&s->dev));
- struct pcmcia_align_data data;
- unsigned long min = base;
- int ret;
-
- data.mask = align - 1;
- data.offset = base & data.mask;
-
-#ifdef CONFIG_PCI
- if (s->cb_dev) {
- ret = pci_bus_alloc_resource(s->cb_dev->bus, res, num, 1,
- min, 0, pcmcia_align, &data);
- } else
-#endif
- ret = allocate_resource(&ioport_resource, res, num, min, ~0UL,
- 1, pcmcia_align, &data);
-
- if (ret != 0) {
- kfree(res);
- res = NULL;
- }
- return res;
-}
-
-static int iodyn_find_io(struct pcmcia_socket *s, unsigned int attr,
- unsigned int *base, unsigned int num,
- unsigned int align, struct resource **parent)
-{
- int i, ret = 0;
-
- /* Check for an already-allocated window that must conflict with
- * what was asked for. It is a hack because it does not catch all
- * potential conflicts, just the most obvious ones.
- */
- for (i = 0; i < MAX_IO_WIN; i++) {
- if (!s->io[i].res)
- continue;
-
- if (!*base)
- continue;
-
- if ((s->io[i].res->start & (align-1)) == *base)
- return -EBUSY;
- }
-
- for (i = 0; i < MAX_IO_WIN; i++) {
- struct resource *res = s->io[i].res;
- unsigned int try;
-
- if (res && (res->flags & IORESOURCE_BITS) !=
- (attr & IORESOURCE_BITS))
- continue;
-
- if (!res) {
- if (align == 0)
- align = 0x10000;
-
- res = s->io[i].res = __iodyn_find_io_region(s, *base,
- num, align);
- if (!res)
- return -EINVAL;
-
- *base = res->start;
- s->io[i].res->flags =
- ((res->flags & ~IORESOURCE_BITS) |
- (attr & IORESOURCE_BITS));
- s->io[i].InUse = num;
- *parent = res;
- return 0;
- }
-
- /* Try to extend top of window */
- try = res->end + 1;
- if ((*base == 0) || (*base == try)) {
- if (adjust_resource(s->io[i].res, res->start,
- resource_size(res) + num))
- continue;
- *base = try;
- s->io[i].InUse += num;
- *parent = res;
- return 0;
- }
-
- /* Try to extend bottom of window */
- try = res->start - num;
- if ((*base == 0) || (*base == try)) {
- if (adjust_resource(s->io[i].res,
- res->start - num,
- resource_size(res) + num))
- continue;
- *base = try;
- s->io[i].InUse += num;
- *parent = res;
- return 0;
- }
- }
-
- return -EINVAL;
-}
-
-
-struct pccard_resource_ops pccard_iodyn_ops = {
- .validate_mem = NULL,
- .find_io = iodyn_find_io,
- .find_mem = NULL,
- .init = static_init,
- .exit = NULL,
-};
-EXPORT_SYMBOL(pccard_iodyn_ops);
diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c
index bf9d070a4496..da494fe451ba 100644
--- a/drivers/pcmcia/rsrc_nonstatic.c
+++ b/drivers/pcmcia/rsrc_nonstatic.c
@@ -375,7 +375,9 @@ static int do_validate_mem(struct pcmcia_socket *s,
if (validate && !s->fake_cis) {
/* move it to the validated data set */
- add_interval(&s_data->mem_db_valid, base, size);
+ ret = add_interval(&s_data->mem_db_valid, base, size);
+ if (ret)
+ return ret;
sub_interval(&s_data->mem_db, base, size);
}
diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c
index c7a906664c36..4eadd0485066 100644
--- a/drivers/pcmcia/socket_sysfs.c
+++ b/drivers/pcmcia/socket_sysfs.c
@@ -10,6 +10,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <linux/string_choices.h>
#include <linux/major.h>
#include <linux/errno.h>
#include <linux/mm.h>
@@ -98,7 +99,7 @@ static ssize_t pccard_show_card_pm_state(struct device *dev,
char *buf)
{
struct pcmcia_socket *s = to_socket(dev);
- return sysfs_emit(buf, "%s\n", s->state & SOCKET_SUSPEND ? "off" : "on");
+ return sysfs_emit(buf, "%s\n", str_off_on(s->state & SOCKET_SUSPEND));
}
static ssize_t pccard_store_card_pm_state(struct device *dev,
@@ -177,7 +178,7 @@ static ssize_t pccard_show_resource(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pcmcia_socket *s = to_socket(dev);
- return sysfs_emit(buf, "%s\n", s->resource_setup_done ? "yes" : "no");
+ return sysfs_emit(buf, "%s\n", str_yes_no(s->resource_setup_done));
}
static ssize_t pccard_store_resource(struct device *dev,
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 69336bd778ee..13eb22b35aa8 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -129,6 +129,7 @@ enum acer_wmi_predator_v4_oc {
enum acer_wmi_gaming_misc_setting {
ACER_WMID_MISC_SETTING_OC_1 = 0x0005,
ACER_WMID_MISC_SETTING_OC_2 = 0x0007,
+ /* Unreliable on some models */
ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES = 0x000A,
ACER_WMID_MISC_SETTING_PLATFORM_PROFILE = 0x000B,
};
@@ -794,9 +795,6 @@ static bool platform_profile_support;
*/
static int last_non_turbo_profile = INT_MIN;
-/* The most performant supported profile */
-static int acer_predator_v4_max_perf;
-
enum acer_predator_v4_thermal_profile {
ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET = 0x00,
ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED = 0x01,
@@ -2014,7 +2012,7 @@ acer_predator_v4_platform_profile_set(struct device *dev,
if (err)
return err;
- if (tp != acer_predator_v4_max_perf)
+ if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
last_non_turbo_profile = tp;
return 0;
@@ -2023,55 +2021,14 @@ acer_predator_v4_platform_profile_set(struct device *dev,
static int
acer_predator_v4_platform_profile_probe(void *drvdata, unsigned long *choices)
{
- unsigned long supported_profiles;
- int err;
+ set_bit(PLATFORM_PROFILE_PERFORMANCE, choices);
+ set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
+ set_bit(PLATFORM_PROFILE_BALANCED, choices);
+ set_bit(PLATFORM_PROFILE_QUIET, choices);
+ set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
- err = WMID_gaming_get_misc_setting(ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES,
- (u8 *)&supported_profiles);
- if (err)
- return err;
-
- /* Iterate through supported profiles in order of increasing performance */
- if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_ECO, &supported_profiles)) {
- set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
- acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO;
- last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO;
- }
-
- if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET, &supported_profiles)) {
- set_bit(PLATFORM_PROFILE_QUIET, choices);
- acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET;
- last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET;
- }
-
- if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED, &supported_profiles)) {
- set_bit(PLATFORM_PROFILE_BALANCED, choices);
- acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
- last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
- }
-
- if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE, &supported_profiles)) {
- set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
- acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE;
-
- /* We only use this profile as a fallback option in case no prior
- * profile is supported.
- */
- if (last_non_turbo_profile < 0)
- last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE;
- }
-
- if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO, &supported_profiles)) {
- set_bit(PLATFORM_PROFILE_PERFORMANCE, choices);
- acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
-
- /* We need to handle the hypothetical case where only the turbo profile
- * is supported. In this case the turbo toggle will essentially be a
- * no-op.
- */
- if (last_non_turbo_profile < 0)
- last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
- }
+ /* Set default non-turbo profile */
+ last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
return 0;
}
@@ -2108,19 +2065,15 @@ static int acer_thermal_profile_change(void)
if (cycle_gaming_thermal_profile) {
platform_profile_cycle();
} else {
- /* Do nothing if no suitable platform profiles where found */
- if (last_non_turbo_profile < 0)
- return 0;
-
err = WMID_gaming_get_misc_setting(
ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, &current_tp);
if (err)
return err;
- if (current_tp == acer_predator_v4_max_perf)
+ if (current_tp == ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
tp = last_non_turbo_profile;
else
- tp = acer_predator_v4_max_perf;
+ tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
err = WMID_gaming_set_misc_setting(
ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, tp);
@@ -2128,7 +2081,7 @@ static int acer_thermal_profile_change(void)
return err;
/* Store last profile for toggle */
- if (current_tp != acer_predator_v4_max_perf)
+ if (current_tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
last_non_turbo_profile = current_tp;
platform_profile_notify(platform_profile_device);
diff --git a/drivers/platform/x86/amd/hfi/hfi.c b/drivers/platform/x86/amd/hfi/hfi.c
index 4f56149b3774..a465ac6f607e 100644
--- a/drivers/platform/x86/amd/hfi/hfi.c
+++ b/drivers/platform/x86/amd/hfi/hfi.c
@@ -385,12 +385,16 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev,
amd_hfi_data->pcct_entry = pcct_entry;
pcct_ext = (struct acpi_pcct_ext_pcc_slave *)pcct_entry;
- if (pcct_ext->length <= 0)
- return -EINVAL;
+ if (pcct_ext->length <= 0) {
+ ret = -EINVAL;
+ goto out;
+ }
amd_hfi_data->shmem = devm_kzalloc(amd_hfi_data->dev, pcct_ext->length, GFP_KERNEL);
- if (!amd_hfi_data->shmem)
- return -ENOMEM;
+ if (!amd_hfi_data->shmem) {
+ ret = -ENOMEM;
+ goto out;
+ }
pcc_chan->shmem_base_addr = pcct_ext->base_address;
pcc_chan->shmem_size = pcct_ext->length;
@@ -398,6 +402,8 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev,
/* parse the shared memory info from the PCCT table */
ret = amd_hfi_fill_metadata(amd_hfi_data);
+out:
+ /* Don't leak any ACPI memory */
acpi_put_table(pcct_tbl);
return ret;
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 7ffc659b2794..18fb44139de2 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -248,6 +248,20 @@ static const struct dmi_system_id fwbug_list[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
}
},
+ {
+ .ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10",
+ .driver_data = &quirk_spurious_8042,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"),
+ }
+ },
+ {
+ .ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10",
+ .driver_data = &quirk_spurious_8042,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"),
+ }
+ },
{}
};
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index f84c3d03c1de..3a488cf9ca06 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -147,7 +147,12 @@ static struct quirk_entry quirk_asus_ignore_fan = {
};
static struct quirk_entry quirk_asus_zenbook_duo_kbd = {
- .ignore_key_wlan = true,
+ .key_wlan_event = ASUS_WMI_KEY_IGNORE,
+};
+
+static struct quirk_entry quirk_asus_z13 = {
+ .key_wlan_event = ASUS_WMI_KEY_ARMOURY,
+ .tablet_switch_mode = asus_wmi_kbd_dock_devid,
};
static int dmi_matched(const struct dmi_system_id *dmi)
@@ -539,6 +544,15 @@ static const struct dmi_system_id asus_quirks[] = {
},
.driver_data = &quirk_asus_zenbook_duo_kbd,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS ROG Z13",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow Z13"),
+ },
+ .driver_data = &quirk_asus_z13,
+ },
{},
};
@@ -618,6 +632,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
{ KE_KEY, 0x93, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV + DVI */
{ KE_KEY, 0x95, { KEY_MEDIA } },
{ KE_KEY, 0x99, { KEY_PHONE } }, /* Conflicts with fan mode switch */
+ { KE_KEY, 0X9D, { KEY_FN_F } },
{ KE_KEY, 0xA0, { KEY_SWITCHVIDEOMODE } }, /* SDSP HDMI only */
{ KE_KEY, 0xA1, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + HDMI */
{ KE_KEY, 0xA2, { KEY_SWITCHVIDEOMODE } }, /* SDSP CRT + HDMI */
@@ -632,10 +647,13 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
{ KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */
{ KE_KEY, 0xC4, { KEY_KBDILLUMUP } },
{ KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } },
+ { KE_KEY, 0xCA, { KEY_F13 } }, /* Noise cancelling on Expertbook B9 */
+ { KE_KEY, 0xCB, { KEY_F14 } }, /* Fn+noise-cancel */
{ KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */
{ KE_IGNORE, 0xCF, }, /* AC mode */
{ KE_KEY, 0xFA, { KEY_PROG2 } }, /* Lid flip action */
{ KE_KEY, 0xBD, { KEY_PROG2 } }, /* Lid flip action on ROG xflow laptops */
+ { KE_KEY, ASUS_WMI_KEY_ARMOURY, { KEY_PROG3 } },
{ KE_END, 0},
};
@@ -655,11 +673,9 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
if (atkbd_reports_vol_keys)
*code = ASUS_WMI_KEY_IGNORE;
break;
- case 0x5D: /* Wireless console Toggle */
- case 0x5E: /* Wireless console Enable */
- case 0x5F: /* Wireless console Disable */
- if (quirks->ignore_key_wlan)
- *code = ASUS_WMI_KEY_IGNORE;
+ case 0x5F: /* Wireless console Disable / Special Key */
+ if (quirks->key_wlan_event)
+ *code = quirks->key_wlan_event;
break;
}
}
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index f7191fdded14..e72a2b5d158e 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -5088,16 +5088,22 @@ static int asus_wmi_probe(struct platform_device *pdev)
asus_s2idle_check_register();
- return asus_wmi_add(pdev);
+ ret = asus_wmi_add(pdev);
+ if (ret)
+ asus_s2idle_check_unregister();
+
+ return ret;
}
static bool used;
+static DEFINE_MUTEX(register_mutex);
int __init_or_module asus_wmi_register_driver(struct asus_wmi_driver *driver)
{
struct platform_driver *platform_driver;
struct platform_device *platform_device;
+ guard(mutex)(&register_mutex);
if (used)
return -EBUSY;
@@ -5120,6 +5126,7 @@ EXPORT_SYMBOL_GPL(asus_wmi_register_driver);
void asus_wmi_unregister_driver(struct asus_wmi_driver *driver)
{
+ guard(mutex)(&register_mutex);
asus_s2idle_check_unregister();
platform_device_unregister(driver->platform_device);
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 018dfde4025e..5cd4392b964e 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -18,6 +18,7 @@
#include <linux/i8042.h>
#define ASUS_WMI_KEY_IGNORE (-1)
+#define ASUS_WMI_KEY_ARMOURY 0xffff01
#define ASUS_WMI_BRN_DOWN 0x2e
#define ASUS_WMI_BRN_UP 0x2f
@@ -40,7 +41,7 @@ struct quirk_entry {
bool wmi_force_als_set;
bool wmi_ignore_fan;
bool filter_i8042_e1_extended_codes;
- bool ignore_key_wlan;
+ int key_wlan_event;
enum asus_wmi_tablet_switch_mode tablet_switch_mode;
int wapf;
/*
diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 60c8ac8d902c..8b3533d6ba09 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -122,6 +122,7 @@ enum hp_wmi_event_ids {
HPWMI_BATTERY_CHARGE_PERIOD = 0x10,
HPWMI_SANITIZATION_MODE = 0x17,
HPWMI_CAMERA_TOGGLE = 0x1A,
+ HPWMI_FN_P_HOTKEY = 0x1B,
HPWMI_OMEN_KEY = 0x1D,
HPWMI_SMART_EXPERIENCE_APP = 0x21,
};
@@ -981,6 +982,9 @@ static void hp_wmi_notify(union acpi_object *obj, void *context)
key_code, 1, true))
pr_info("Unknown key code - 0x%x\n", key_code);
break;
+ case HPWMI_FN_P_HOTKEY:
+ platform_profile_cycle();
+ break;
case HPWMI_OMEN_KEY:
if (event_data) /* Only should be true for HP Omen */
key_code = event_data;
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 540cd2fb0673..d040290e80ff 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -1625,6 +1625,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &tgl_l_pmc_dev),
X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_pmc_dev),
X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_pmc_dev),
+ X86_MATCH_VFM(INTEL_BARTLETTLAKE, &adl_pmc_dev),
X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_pmc_dev),
X86_MATCH_VFM(INTEL_ARROWLAKE, &arl_pmc_dev),
X86_MATCH_VFM(INTEL_ARROWLAKE_H, &arl_h_pmc_dev),
diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c
index 9d8247bb9cfa..8641353b2e06 100644
--- a/drivers/platform/x86/intel/tpmi_power_domains.c
+++ b/drivers/platform/x86/intel/tpmi_power_domains.c
@@ -178,7 +178,7 @@ static int tpmi_get_logical_id(unsigned int cpu, struct tpmi_cpu_info *info)
info->punit_thread_id = FIELD_GET(LP_ID_MASK, data);
info->punit_core_id = FIELD_GET(MODULE_ID_MASK, data);
- info->pkg_id = topology_physical_package_id(cpu);
+ info->pkg_id = topology_logical_package_id(cpu);
info->linux_cpu = cpu;
return 0;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index fba2e62027b7..4cfc928bcf2d 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1243,7 +1243,7 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
struct lpfc_nvmet_tgtport *tgtp;
struct lpfc_async_xchg_ctx *ctxp =
container_of(rsp, struct lpfc_async_xchg_ctx, hdlrctx.fcp_req);
- struct rqb_dmabuf *nvmebuf = ctxp->rqb_buffer;
+ struct rqb_dmabuf *nvmebuf;
struct lpfc_hba *phba = ctxp->phba;
unsigned long iflag;
@@ -1251,13 +1251,18 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n",
ctxp->oxid, ctxp->size, raw_smp_processor_id());
+ spin_lock_irqsave(&ctxp->ctxlock, iflag);
+ nvmebuf = ctxp->rqb_buffer;
if (!nvmebuf) {
+ spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
"6425 Defer rcv: no buffer oxid x%x: "
"flg %x ste %x\n",
ctxp->oxid, ctxp->flag, ctxp->state);
return;
}
+ ctxp->rqb_buffer = NULL;
+ spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
tgtp = phba->targetport->private;
if (tgtp)
@@ -1265,9 +1270,6 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
/* Free the nvmebuf since a new buffer already replaced it */
nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
- spin_lock_irqsave(&ctxp->ctxlock, iflag);
- ctxp->rqb_buffer = NULL;
- spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
}
/**
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index b17796d5ee66..add13e306898 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -475,13 +475,21 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
static int sr_revalidate_disk(struct scsi_cd *cd)
{
+ struct request_queue *q = cd->device->request_queue;
struct scsi_sense_hdr sshdr;
+ struct queue_limits lim;
+ int sector_size;
/* if the unit is not ready, nothing more to do */
if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr))
return 0;
sr_cd_check(&cd->cdi);
- return get_sectorsize(cd);
+ sector_size = get_sectorsize(cd);
+
+ lim = queue_limits_start_update(q);
+ lim.logical_block_size = sector_size;
+ lim.features |= BLK_FEAT_ROTATIONAL;
+ return queue_limits_commit_update_frozen(q, &lim);
}
static int sr_block_open(struct gendisk *disk, blk_mode_t mode)
@@ -721,10 +729,8 @@ fail:
static int get_sectorsize(struct scsi_cd *cd)
{
- struct request_queue *q = cd->device->request_queue;
static const u8 cmd[10] = { READ_CAPACITY };
unsigned char buffer[8] = { };
- struct queue_limits lim;
int err;
int sector_size;
struct scsi_failure failure_defs[] = {
@@ -795,9 +801,7 @@ static int get_sectorsize(struct scsi_cd *cd)
set_capacity(cd->disk, cd->capacity);
}
- lim = queue_limits_start_update(q);
- lim.logical_block_size = sector_size;
- return queue_limits_commit_update_frozen(q, &lim);
+ return sector_size;
}
static int get_capabilities(struct scsi_cd *cd)
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 177f9a33f3a2..9bf823348cd3 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -108,6 +108,8 @@ struct cqspi_st {
bool is_jh7110; /* Flag for StarFive JH7110 SoC */
bool disable_stig_mode;
+ refcount_t refcount;
+ refcount_t inflight_ops;
const struct cqspi_driver_platdata *ddata;
};
@@ -735,6 +737,9 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
u8 *rxbuf_end = rxbuf + n_rx;
int ret = 0;
+ if (!refcount_read(&cqspi->refcount))
+ return -ENODEV;
+
writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
writel(remaining, reg_base + CQSPI_REG_INDIRECTRDBYTES);
@@ -1071,6 +1076,9 @@ static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata,
unsigned int write_bytes;
int ret;
+ if (!refcount_read(&cqspi->refcount))
+ return -ENODEV;
+
writel(to_addr, reg_base + CQSPI_REG_INDIRECTWRSTARTADDR);
writel(remaining, reg_base + CQSPI_REG_INDIRECTWRBYTES);
@@ -1461,12 +1469,26 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
struct cqspi_st *cqspi = spi_controller_get_devdata(mem->spi->controller);
struct device *dev = &cqspi->pdev->dev;
+ if (refcount_read(&cqspi->inflight_ops) == 0)
+ return -ENODEV;
+
ret = pm_runtime_resume_and_get(dev);
if (ret) {
dev_err(&mem->spi->dev, "resume failed with %d\n", ret);
return ret;
}
+ if (!refcount_read(&cqspi->refcount))
+ return -EBUSY;
+
+ refcount_inc(&cqspi->inflight_ops);
+
+ if (!refcount_read(&cqspi->refcount)) {
+ if (refcount_read(&cqspi->inflight_ops))
+ refcount_dec(&cqspi->inflight_ops);
+ return -EBUSY;
+ }
+
ret = cqspi_mem_process(mem, op);
pm_runtime_put_autosuspend(dev);
@@ -1474,6 +1496,9 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
if (ret)
dev_err(&mem->spi->dev, "operation failed with %d\n", ret);
+ if (refcount_read(&cqspi->inflight_ops) > 1)
+ refcount_dec(&cqspi->inflight_ops);
+
return ret;
}
@@ -1925,6 +1950,9 @@ static int cqspi_probe(struct platform_device *pdev)
}
}
+ refcount_set(&cqspi->refcount, 1);
+ refcount_set(&cqspi->inflight_ops, 1);
+
ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,
pdev->name, cqspi);
if (ret) {
@@ -1987,6 +2015,11 @@ static void cqspi_remove(struct platform_device *pdev)
{
struct cqspi_st *cqspi = platform_get_drvdata(pdev);
+ refcount_set(&cqspi->refcount, 0);
+
+ if (!refcount_dec_and_test(&cqspi->inflight_ops))
+ cqspi_wait_idle(cqspi);
+
spi_unregister_controller(cqspi->host);
cqspi_controller_enable(cqspi, 0);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 313e444a34f3..431439d4cdda 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -3,8 +3,9 @@
// Freescale i.MX7ULP LPSPI driver
//
// Copyright 2016 Freescale Semiconductor, Inc.
-// Copyright 2018 NXP Semiconductors
+// Copyright 2018, 2023, 2025 NXP
+#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/completion.h>
#include <linux/delay.h>
@@ -70,7 +71,7 @@
#define DER_TDDE BIT(0)
#define CFGR1_PCSCFG BIT(27)
#define CFGR1_PINCFG (BIT(24)|BIT(25))
-#define CFGR1_PCSPOL BIT(8)
+#define CFGR1_PCSPOL_MASK GENMASK(11, 8)
#define CFGR1_NOSTALL BIT(3)
#define CFGR1_HOST BIT(0)
#define FSR_TXCOUNT (0xFF)
@@ -82,8 +83,11 @@
#define TCR_RXMSK BIT(19)
#define TCR_TXMSK BIT(18)
+#define SR_CLEAR_MASK GENMASK(13, 8)
+
struct fsl_lpspi_devtype_data {
- u8 prescale_max;
+ u8 prescale_max : 3; /* 0 == no limit */
+ bool query_hw_for_num_cs : 1;
};
struct lpspi_config {
@@ -129,20 +133,26 @@ struct fsl_lpspi_data {
};
/*
- * ERR051608 fixed or not:
- * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
+ * Devices with ERR051608 have a max TCR_PRESCALE value of 1, otherwise there is
+ * no prescale limit: https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
*/
-static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
+static const struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
.prescale_max = 1,
+ .query_hw_for_num_cs = true,
+};
+
+static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
+ /* All defaults */
};
-static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
- .prescale_max = 7,
+static const struct fsl_lpspi_devtype_data s32g_lpspi_devtype_data = {
+ .query_hw_for_num_cs = true,
};
static const struct of_device_id fsl_lpspi_dt_ids[] = {
{ .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,},
{ .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,},
+ { .compatible = "nxp,s32g2-lpspi", .data = &s32g_lpspi_devtype_data,},
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);
@@ -321,7 +331,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
int scldiv;
perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
- prescale_max = fsl_lpspi->devtype_data->prescale_max;
+ prescale_max = fsl_lpspi->devtype_data->prescale_max ?: 7;
if (!config.speed_hz) {
dev_err(fsl_lpspi->dev,
@@ -423,7 +433,9 @@ static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi)
else
temp = CFGR1_PINCFG;
if (fsl_lpspi->config.mode & SPI_CS_HIGH)
- temp |= CFGR1_PCSPOL;
+ temp |= FIELD_PREP(CFGR1_PCSPOL_MASK,
+ BIT(fsl_lpspi->config.chip_select));
+
writel(temp, fsl_lpspi->base + IMX7ULP_CFGR1);
temp = readl(fsl_lpspi->base + IMX7ULP_CR);
@@ -532,14 +544,13 @@ static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi)
fsl_lpspi_intctrl(fsl_lpspi, 0);
}
- /* W1C for all flags in SR */
- temp = 0x3F << 8;
- writel(temp, fsl_lpspi->base + IMX7ULP_SR);
-
/* Clear FIFO and disable module */
temp = CR_RRF | CR_RTF;
writel(temp, fsl_lpspi->base + IMX7ULP_CR);
+ /* W1C for all flags in SR */
+ writel(SR_CLEAR_MASK, fsl_lpspi->base + IMX7ULP_SR);
+
return 0;
}
@@ -730,12 +741,10 @@ static int fsl_lpspi_pio_transfer(struct spi_controller *controller,
fsl_lpspi_write_tx_fifo(fsl_lpspi);
ret = fsl_lpspi_wait_for_completion(controller);
- if (ret)
- return ret;
fsl_lpspi_reset(fsl_lpspi);
- return 0;
+ return ret;
}
static int fsl_lpspi_transfer_one(struct spi_controller *controller,
@@ -785,7 +794,7 @@ static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
if (temp_SR & SR_MBF ||
readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_TXCOUNT) {
writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR);
- fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE);
+ fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE | (temp_IER & IER_TDIE));
return IRQ_HANDLED;
}
@@ -930,7 +939,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
fsl_lpspi->rxfifosize = 1 << ((temp >> 8) & 0x0f);
if (of_property_read_u32((&pdev->dev)->of_node, "num-cs",
&num_cs)) {
- if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx93-spi"))
+ if (devtype_data->query_hw_for_num_cs)
num_cs = ((temp >> 16) & 0xf);
else
num_cs = 1;
diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c
index d13a9b755c7f..8dc98b17f77b 100644
--- a/drivers/spi/spi-microchip-core-qspi.c
+++ b/drivers/spi/spi-microchip-core-qspi.c
@@ -531,10 +531,6 @@ error:
static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op)
{
- struct mchp_coreqspi *qspi = spi_controller_get_devdata(mem->spi->controller);
- unsigned long clk_hz;
- u32 baud_rate_val;
-
if (!spi_mem_default_supports_op(mem, op))
return false;
@@ -557,14 +553,6 @@ static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_
return false;
}
- clk_hz = clk_get_rate(qspi->clk);
- if (!clk_hz)
- return false;
-
- baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * op->max_freq);
- if (baud_rate_val > MAX_DIVIDER || baud_rate_val < MIN_DIVIDER)
- return false;
-
return true;
}
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 0ceaad7dba3c..780abb967822 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -1615,11 +1615,13 @@ static int qcom_spi_probe(struct platform_device *pdev)
ret = spi_register_controller(ctlr);
if (ret) {
dev_err(&pdev->dev, "spi_register_controller failed.\n");
- goto err_spi_init;
+ goto err_register_controller;
}
return 0;
+err_register_controller:
+ nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng);
err_spi_init:
qcom_nandc_unalloc(snandc);
err_snand_alloc:
@@ -1641,7 +1643,7 @@ static void qcom_spi_remove(struct platform_device *pdev)
struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
spi_unregister_controller(ctlr);
-
+ nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng);
qcom_nandc_unalloc(snandc);
clk_disable_unprepare(snandc->aon_clk);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c953297aa89a..b21cb72835cc 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -111,6 +111,24 @@ struct btrfs_bio_ctrl {
*/
unsigned long submit_bitmap;
struct readahead_control *ractl;
+
+ /*
+ * The start offset of the last used extent map by a read operation.
+ *
+ * This is for proper compressed read merge.
+ * U64_MAX means we are starting the read and have made no progress yet.
+ *
+ * The current btrfs_bio_is_contig() only uses disk_bytenr as
+ * the condition to check if the read can be merged with previous
+ * bio, which is not correct. E.g. two file extents pointing to the
+ * same extent but with different offset.
+ *
+ * So here we need to do extra checks to only merge reads that are
+ * covered by the same extent map.
+ * Just extent_map::start will be enough, as they are unique
+ * inside the same inode.
+ */
+ u64 last_em_start;
};
static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
@@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl,
* return 0 on success, otherwise return error
*/
static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
- struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start)
+ struct btrfs_bio_ctrl *bio_ctrl)
{
struct inode *inode = folio->mapping->host;
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
@@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
* non-optimal behavior (submitting 2 bios for the same extent).
*/
if (compress_type != BTRFS_COMPRESS_NONE &&
- prev_em_start && *prev_em_start != (u64)-1 &&
- *prev_em_start != em->start)
+ bio_ctrl->last_em_start != U64_MAX &&
+ bio_ctrl->last_em_start != em->start)
force_bio_submit = true;
- if (prev_em_start)
- *prev_em_start = em->start;
+ bio_ctrl->last_em_start = em->start;
btrfs_free_extent_map(em);
em = NULL;
@@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio)
const u64 start = folio_pos(folio);
const u64 end = start + folio_size(folio) - 1;
struct extent_state *cached_state = NULL;
- struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
+ struct btrfs_bio_ctrl bio_ctrl = {
+ .opf = REQ_OP_READ,
+ .last_em_start = U64_MAX,
+ };
struct extent_map *em_cached = NULL;
int ret;
lock_extents_for_read(inode, start, end, &cached_state);
- ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
+ ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
btrfs_free_extent_map(em_cached);
@@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac)
{
struct btrfs_bio_ctrl bio_ctrl = {
.opf = REQ_OP_READ | REQ_RAHEAD,
- .ractl = rac
+ .ractl = rac,
+ .last_em_start = U64_MAX,
};
struct folio *folio;
struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
@@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac)
const u64 end = start + readahead_length(rac) - 1;
struct extent_state *cached_state = NULL;
struct extent_map *em_cached = NULL;
- u64 prev_em_start = (u64)-1;
lock_extents_for_read(inode, start, end, &cached_state);
while ((folio = readahead_folio(rac)) != NULL)
- btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
+ btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dd82dcc7b2b7..e7218e78bff4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5696,7 +5696,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode)
bool empty = false;
xa_lock(&root->inodes);
- entry = __xa_erase(&root->inodes, btrfs_ino(inode));
+ /*
+ * This btrfs_inode is being freed and has already been unhashed at this
+ * point. It's possible that another btrfs_inode has already been
+ * allocated for the same inode and inserted itself into the root, so
+ * don't delete it in that case.
+ *
+ * Note that this shouldn't need to allocate memory, so the gfp flags
+ * don't really matter.
+ */
+ entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL,
+ GFP_ATOMIC);
if (entry == inode)
empty = xa_empty(&root->inodes);
xa_unlock(&root->inodes);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index ccaa9a3cf1ce..da102da169fd 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup *qgroup;
LIST_HEAD(qgroup_list);
u64 num_bytes = src->excl;
+ u64 num_bytes_cmpr = src->excl_cmpr;
int ret = 0;
qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup_list *glist;
qgroup->rfer += sign * num_bytes;
- qgroup->rfer_cmpr += sign * num_bytes;
+ qgroup->rfer_cmpr += sign * num_bytes_cmpr;
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
+ WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr);
qgroup->excl += sign * num_bytes;
- qgroup->excl_cmpr += sign * num_bytes;
+ qgroup->excl_cmpr += sign * num_bytes_cmpr;
if (sign > 0)
qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a262b494a89f..df1f6cc3fe21 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -299,9 +299,12 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx,
btrfs_set_opt(ctx->mount_opt, COMPRESS);
btrfs_clear_opt(ctx->mount_opt, NODATACOW);
btrfs_clear_opt(ctx->mount_opt, NODATASUM);
- } else if (btrfs_match_compress_type(string, "lzo", false)) {
+ } else if (btrfs_match_compress_type(string, "lzo", true)) {
ctx->compress_type = BTRFS_COMPRESS_LZO;
- ctx->compress_level = 0;
+ ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_LZO,
+ string + 3);
+ if (string[3] == ':' && string[4])
+ btrfs_warn(NULL, "Compression level ignored for LZO");
btrfs_set_opt(ctx->mount_opt, COMPRESS);
btrfs_clear_opt(ctx->mount_opt, NODATACOW);
btrfs_clear_opt(ctx->mount_opt, NODATASUM);
@@ -1079,7 +1082,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_printf(seq, ",compress-force=%s", compress_type);
else
seq_printf(seq, ",compress=%s", compress_type);
- if (info->compress_level)
+ if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO)
seq_printf(seq, ":%d", info->compress_level);
}
if (btrfs_test_opt(info, NOSSD))
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fa7a929a0461..c6e3efd6f602 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
goto error;
}
+ if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) {
+ ret = -EINVAL;
+ goto error;
+ }
+
if (fs_devices->seeding) {
seeding_dev = true;
down_write(&sb->s_umount);
diff --git a/fs/coredump.c b/fs/coredump.c
index 5dce257c67fc..60bc9685e149 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
ssize_t retval;
char old_core_pattern[CORENAME_MAX_SIZE];
+ if (write)
+ return proc_dostring(table, write, buffer, lenp, ppos);
+
retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE);
error = proc_dostring(table, write, buffer, lenp, ppos);
if (error)
return error;
+
if (!check_coredump_socket()) {
strscpy(core_pattern, old_core_pattern, retval + 1);
return -EINVAL;
diff --git a/fs/exec.c b/fs/exec.c
index 2a1e5e4042a1..e861a4b7ffda 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
{
int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
- if (!error)
+ if (!error && !write)
validate_coredump_safety();
return error;
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 68a7d2861c58..a907ddfac4d5 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
return 1;
/*
+ * Verify that the decoded dentry itself has a valid id mapping.
+ * In case the decoded dentry is the mountfd root itself, this
+ * verifies that the mountfd inode itself has a valid id mapping.
+ */
+ if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry)))
+ return 0;
+
+ /*
* It's racy as we're not taking rename_lock but we're able to ignore
* permissions and we just need an approximation whether we were able
* to follow a path to the file.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e80cd8f2c049..5150aa25e64b 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
index = outarg->offset >> PAGE_SHIFT;
- while (num) {
+ while (num && ap->num_folios < num_pages) {
struct folio *folio;
unsigned int folio_offset;
unsigned int nr_bytes;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 2d817d7cab26..5c569c3cb53f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode,
if (attr->blksize != 0)
blkbits = ilog2(attr->blksize);
else
- blkbits = inode->i_sb->s_blocksize_bits;
+ blkbits = fc->blkbits;
stat->blksize = 1 << blkbits;
}
@@ -1377,6 +1377,7 @@ retry:
generic_fillattr(idmap, request_mask, inode, stat);
stat->mode = fi->orig_i_mode;
stat->ino = fi->orig_ino;
+ stat->blksize = 1 << fi->cached_i_blkbits;
if (test_bit(FUSE_I_BTIME, &fi->state)) {
stat->btime = fi->i_btime;
stat->result_mask |= STATX_BTIME;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5525a4520b0f..4adcf09d4b01 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
.nodeid_out = ff_out->nodeid,
.fh_out = ff_out->fh,
.off_out = pos_out,
- .len = len,
+ .len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
.flags = flags
};
struct fuse_write_out outarg;
@@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
fc->no_copy_file_range = 1;
err = -EOPNOTSUPP;
}
+ if (!err && outarg.size > len)
+ err = -EIO;
+
if (err)
goto out;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ec248d13c8bf..cc428d04be3e 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -210,6 +210,12 @@ struct fuse_inode {
/** Reference to backing file in passthrough mode */
struct fuse_backing *fb;
#endif
+
+ /*
+ * The underlying inode->i_blkbits value will not be modified,
+ * so preserve the blocksize specified by the server.
+ */
+ u8 cached_i_blkbits;
};
/** FUSE inode state bits */
@@ -969,6 +975,14 @@ struct fuse_conn {
/* Request timeout (in jiffies). 0 = no timeout */
unsigned int req_timeout;
} timeout;
+
+ /*
+ * This is a workaround until fuse uses iomap for reads.
+ * For fuseblk servers, this represents the blocksize passed in at
+ * mount time and for regular fuse servers, this is equivalent to
+ * inode->i_blkbits.
+ */
+ u8 blkbits;
};
/*
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 67c2318bfc42..7ddfd2b3cc9c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
}
}
+ if (attr->blksize)
+ fi->cached_i_blkbits = ilog2(attr->blksize);
+ else
+ fi->cached_i_blkbits = fc->blkbits;
+
/*
* Don't set the sticky bit in i_mode, unless we want the VFS
* to check permissions. This prevents failures due to the
@@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
err = -EINVAL;
if (!sb_set_blocksize(sb, ctx->blksize))
goto err;
+ /*
+ * This is a workaround until fuse hooks into iomap for reads.
+ * Use PAGE_SIZE for the blocksize else if the writeback cache
+ * is enabled, buffered writes go through iomap and a read may
+ * overwrite partially written data if blocksize < PAGE_SIZE
+ */
+ fc->blkbits = sb->s_blocksize_bits;
+ if (ctx->blksize != PAGE_SIZE &&
+ !sb_set_blocksize(sb, PAGE_SIZE))
+ goto err;
#endif
} else {
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
+ fc->blkbits = sb->s_blocksize_bits;
}
sb->s_subtype = ctx->subtype;
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 607ef735ad4a..eb97ac009e75 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
if (!file)
goto out;
+ /* read/write/splice/mmap passthrough only relevant for regular files */
+ res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL;
+ if (!d_is_reg(file->f_path.dentry))
+ goto out_fput;
+
backing_sb = file_inode(file)->i_sb;
res = -ELOOP;
if (backing_sb->s_stack_depth >= fc->max_stack_depth)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index c826e7ca49f5..76c8fd0bfc75 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
if (kaddr)
*kaddr = fs->window_kaddr + offset;
if (pfn)
- *pfn = fs->window_phys_addr + offset;
+ *pfn = PHYS_PFN(fs->window_phys_addr + offset);
return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index ae6d1312b184..51f77c65c0c6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
return ERR_PTR(-EINVAL);
}
- if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+ if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
if (__has_locked_children(old_mnt, path->dentry))
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8fb4a950dd55..4e3dcc157a83 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
if (fsinfo->xattr_support)
server->caps |= NFS_CAP_XATTR;
+ else
+ server->caps &= ~NFS_CAP_XATTR;
#endif
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 86e36c630f09..8059ece82468 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -28,6 +28,7 @@
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/gfp.h>
+#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/compaction.h>
@@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
}
EXPORT_SYMBOL_GPL(nfs_file_fsync);
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+ loff_t to)
+{
+ struct folio *folio;
+
+ if (from >= to)
+ return;
+
+ folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT);
+ if (IS_ERR(folio))
+ return;
+
+ if (folio_mkclean(folio))
+ folio_mark_dirty(folio);
+
+ if (folio_test_uptodate(folio)) {
+ loff_t fpos = folio_pos(folio);
+ size_t offset = from - fpos;
+ size_t end = folio_size(folio);
+
+ if (to - fpos < end)
+ end = to - fpos;
+ folio_zero_segment(folio, offset, end);
+ trace_nfs_size_truncate_folio(mapping->host, to);
+ }
+
+ folio_unlock(folio);
+ folio_put(folio);
+}
+EXPORT_SYMBOL_GPL(nfs_truncate_last_folio);
+
/*
* Decide whether a read/modify/write cycle may be more efficient
* then a modify/write/read cycle when writing to a page in the
@@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb,
dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
+ nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos);
fgp |= fgf_set_order(len);
start:
@@ -442,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
folio->index, offset, length);
- if (offset != 0 || length < folio_size(folio))
- return;
/* Cancel any unstarted writes on this page */
- nfs_wb_folio_cancel(inode, folio);
+ if (offset != 0 || length < folio_size(folio))
+ nfs_wb_folio(inode, folio);
+ else
+ nfs_wb_folio_cancel(inode, folio);
folio_wait_private_2(folio); /* [DEPRECATED] */
trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 8dc921d83538..9edb5f9b0c4e 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1,
struct pnfs_layout_segment *l2)
{
const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1);
- const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1);
+ const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2);
u32 i;
if (fl1->mirror_array_cnt != fl2->mirror_array_cnt)
@@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
continue;
if (check_device &&
- nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+ nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) {
+ // reinitialize the error state in case if this is the last iteration
+ ds = ERR_PTR(-EINVAL);
continue;
+ }
*best_idx = idx;
break;
@@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
struct nfs4_pnfs_ds *ds;
ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
- if (ds)
+ if (!IS_ERR(ds))
return ds;
return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
}
@@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
best_idx);
- if (ds || !pgio->pg_mirror_idx)
+ if (!IS_ERR(ds) || !pgio->pg_mirror_idx)
return ds;
return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
}
@@ -868,7 +871,7 @@ retry:
req->wb_nio = 0;
ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
- if (!ds) {
+ if (IS_ERR(ds)) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
pnfs_generic_pg_cleanup(pgio);
@@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
{
u32 idx = hdr->pgio_mirror_idx + 1;
u32 new_idx = 0;
+ struct nfs4_pnfs_ds *ds;
- if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx))
- ff_layout_send_layouterror(hdr->lseg);
- else
+ ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx);
+ if (IS_ERR(ds))
pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+ else
+ ff_layout_send_layouterror(hdr->lseg);
pnfs_read_resend_pnfs(hdr, new_idx);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 338ef77ae423..49df9debb1a6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -716,6 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
{
struct inode *inode = d_inode(dentry);
struct nfs_fattr *fattr;
+ loff_t oldsize = i_size_read(inode);
int error = 0;
nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
@@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (error)
return error;
- if (attr->ia_size == i_size_read(inode))
+ if (attr->ia_size == oldsize)
attr->ia_valid &= ~ATTR_SIZE;
}
@@ -767,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
trace_nfs_setattr_enter(inode);
/* Write all dirty data */
- if (S_ISREG(inode->i_mode))
+ if (S_ISREG(inode->i_mode)) {
+ nfs_file_block_o_direct(NFS_I(inode));
nfs_sync_inode(inode);
+ }
fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
if (fattr == NULL) {
@@ -777,8 +780,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
}
error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
- if (error == 0)
+ if (error == 0) {
+ if (attr->ia_valid & ATTR_SIZE)
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ attr->ia_size);
error = nfs_refresh_inode(inode, fattr);
+ }
nfs_free_fattr(fattr);
out:
trace_nfs_setattr_exit(inode, error);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 74d712b58423..c0a44f389f8f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *);
int nfs_lock(struct file *, int, struct file_lock *);
int nfs_flock(struct file *, int, struct file_lock *);
int nfs_check_flags(int);
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+ loff_t to);
/* inode.c */
extern struct workqueue_struct *nfsiod_workqueue;
@@ -530,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
}
+/* Must be called with exclusively locked inode->i_rwsem */
+static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi)
+{
+ if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+ clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+ inode_dio_wait(&nfsi->vfs_inode);
+ }
+}
+
+
/* namespace.c */
#define NFS_PATH_CANONICAL 1
extern char *nfs_path(char **p, struct dentry *dentry,
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 3388faf2acb9..d275b0a250bf 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -14,15 +14,6 @@
#include "internal.h"
-/* Call with exclusively locked inode->i_rwsem */
-static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
-{
- if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
- clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
- inode_dio_wait(inode);
- }
-}
-
/**
* nfs_start_io_read - declare the file is being used for buffered reads
* @inode: file inode
@@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode)
err = down_write_killable(&inode->i_rwsem);
if (err)
return err;
- nfs_block_o_direct(nfsi, inode);
+ nfs_file_block_o_direct(nfsi);
downgrade_write(&inode->i_rwsem);
return 0;
@@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode)
err = down_write_killable(&inode->i_rwsem);
if (!err)
- nfs_block_o_direct(NFS_I(inode), inode);
+ nfs_file_block_o_direct(NFS_I(inode));
return err;
}
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index bd5fca285899..97abf62f109d 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp)
return;
}
- if (nfs_client_is_local(clp)) {
- /* If already enabled, disable and re-enable */
- nfs_localio_disable_client(clp);
- }
+ if (nfs_client_is_local(clp))
+ return;
if (!nfs_uuid_begin(&clp->cl_uuid))
return;
@@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
case -ENOMEM:
case -ENXIO:
case -ENOENT:
- /* Revalidate localio, will disable if unsupported */
+ /* Revalidate localio */
+ nfs_localio_disable_client(clp);
nfs_local_probe(clp);
}
}
@@ -453,12 +452,13 @@ static void nfs_local_call_read(struct work_struct *work)
nfs_local_iter_init(&iter, iocb, READ);
status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+
+ revert_creds(save_cred);
+
if (status != -EIOCBQUEUED) {
nfs_local_read_done(iocb, status);
nfs_local_pgio_release(iocb);
}
-
- revert_creds(save_cred);
}
static int
@@ -648,14 +648,15 @@ static void nfs_local_call_write(struct work_struct *work)
file_start_write(filp);
status = filp->f_op->write_iter(&iocb->kiocb, &iter);
file_end_write(filp);
+
+ revert_creds(save_cred);
+ current->flags = old_flags;
+
if (status != -EIOCBQUEUED) {
nfs_local_write_done(iocb, status);
nfs_local_vfs_getattr(iocb);
nfs_local_pgio_release(iocb);
}
-
- revert_creds(save_cred);
- current->flags = old_flags;
}
static int
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 01c01f45358b..6a0b5871ba3b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -114,6 +114,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
exception.inode = inode;
exception.state = lock->open_context->state;
+ nfs_file_block_o_direct(NFS_I(inode));
err = nfs_sync_inode(inode);
if (err)
goto out;
@@ -137,6 +138,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE],
};
struct inode *inode = file_inode(filep);
+ loff_t oldsize = i_size_read(inode);
int err;
if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
@@ -145,7 +147,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
inode_lock(inode);
err = nfs42_proc_fallocate(&msg, filep, offset, len);
- if (err == -EOPNOTSUPP)
+
+ if (err == 0)
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ offset + len);
+ else if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE |
NFS_CAP_ZERO_RANGE);
@@ -183,6 +189,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE],
};
struct inode *inode = file_inode(filep);
+ loff_t oldsize = i_size_read(inode);
int err;
if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE))
@@ -191,9 +198,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
inode_lock(inode);
err = nfs42_proc_fallocate(&msg, filep, offset, len);
- if (err == 0)
+ if (err == 0) {
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ offset + len);
truncate_pagecache_range(inode, offset, (offset + len) -1);
- if (err == -EOPNOTSUPP)
+ } else if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE;
inode_unlock(inode);
@@ -354,22 +363,27 @@ out:
/**
* nfs42_copy_dest_done - perform inode cache updates after clone/copy offload
- * @inode: pointer to destination inode
+ * @file: pointer to destination file
* @pos: destination offset
* @len: copy length
+ * @oldsize: length of the file prior to clone/copy
*
* Punch a hole in the inode page cache, so that the NFS client will
* know to retrieve new data.
* Update the file size if necessary, and then mark the inode as having
* invalid cached values for change attribute, ctime, mtime and space used.
*/
-static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
+static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len,
+ loff_t oldsize)
{
+ struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
loff_t newsize = pos + len;
loff_t end = newsize - 1;
- WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping,
- pos >> PAGE_SHIFT, end >> PAGE_SHIFT));
+ nfs_truncate_last_folio(mapping, oldsize, pos);
+ WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+ end >> PAGE_SHIFT));
spin_lock(&inode->i_lock);
if (newsize > i_size_read(inode))
@@ -402,6 +416,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
struct nfs_server *src_server = NFS_SERVER(src_inode);
loff_t pos_src = args->src_pos;
loff_t pos_dst = args->dst_pos;
+ loff_t oldsize_dst = i_size_read(dst_inode);
size_t count = args->count;
ssize_t status;
@@ -430,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
return status;
}
+ nfs_file_block_o_direct(NFS_I(dst_inode));
status = nfs_sync_inode(dst_inode);
if (status)
return status;
@@ -475,7 +491,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
goto out;
}
- nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count);
+ nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst);
nfs_invalidate_atime(src_inode);
status = res->write_res.count;
out:
@@ -1242,6 +1258,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
struct nfs42_clone_res res = {
.server = server,
};
+ loff_t oldsize_dst = i_size_read(dst_inode);
int status;
msg->rpc_argp = &args;
@@ -1276,7 +1293,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
/* a zero-length count means clone to EOF in src */
if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE)
count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset;
- nfs42_copy_dest_done(dst_inode, dst_offset, count);
+ nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst);
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1d6b5f4230c9..c9a0d1e420c6 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
lock_two_nondirectories(src_inode, dst_inode);
/* flush all pending writes on both src and dst so that server
* has the latest data */
+ nfs_file_block_o_direct(NFS_I(src_inode));
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
+ nfs_file_block_o_direct(NFS_I(dst_inode));
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7d2b67e06cc3..ce61253efd45 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4013,8 +4013,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
res.attr_bitmask[2];
}
memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
- server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
- NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+ server->caps &=
+ ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
+ NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS |
+ NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME);
server->fattr_valid = NFS_ATTR_FATTR_V4;
if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
@@ -4092,7 +4094,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
};
int err;
- nfs_server_set_init_caps(server);
do {
err = nfs4_handle_exception(server,
_nfs4_server_capabilities(server, fhandle),
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 96b1323318c2..627115179795 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class,
TP_ARGS(inode, new_size))
DEFINE_NFS_UPDATE_SIZE_EVENT(truncate);
+DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio);
DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
DEFINE_NFS_UPDATE_SIZE_EVENT(update);
DEFINE_NFS_UPDATE_SIZE_EVENT(grow);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8b7c04737967..647c53d1418a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error)
}
/*
- * nfs_page_group_search_locked
- * @head - head request of page group
- * @page_offset - offset into page
+ * nfs_page_covers_folio
+ * @req: struct nfs_page
*
- * Search page group with head @head to find a request that contains the
- * page offset @page_offset.
- *
- * Returns a pointer to the first matching nfs request, or NULL if no
- * match is found.
- *
- * Must be called with the page group lock held
- */
-static struct nfs_page *
-nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
-{
- struct nfs_page *req;
-
- req = head;
- do {
- if (page_offset >= req->wb_pgbase &&
- page_offset < (req->wb_pgbase + req->wb_bytes))
- return req;
-
- req = req->wb_this_page;
- } while (req != head);
-
- return NULL;
-}
-
-/*
- * nfs_page_group_covers_page
- * @head - head request of page group
- *
- * Return true if the page group with head @head covers the whole page,
- * returns false otherwise
+ * Return true if the request covers the whole folio.
+ * Note that the caller should ensure all subrequests have been joined
*/
static bool nfs_page_group_covers_page(struct nfs_page *req)
{
unsigned int len = nfs_folio_length(nfs_page_to_folio(req));
- struct nfs_page *tmp;
- unsigned int pos = 0;
-
- nfs_page_group_lock(req);
- for (;;) {
- tmp = nfs_page_group_search_locked(req->wb_head, pos);
- if (!tmp)
- break;
- pos = tmp->wb_pgbase + tmp->wb_bytes;
- }
-
- nfs_page_group_unlock(req);
- return pos >= len;
+ return req->wb_pgbase == 0 && req->wb_bytes == len;
}
/* We can set the PG_uptodate flag if we see that a write request
@@ -2045,6 +2003,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
* release it */
nfs_inode_remove_request(req);
nfs_unlock_and_release_request(req);
+ folio_cancel_dirty(folio);
}
return ret;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 930150ed5db1..ef147e8b3271 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -706,6 +706,8 @@ out:
* it not only handles the fiemap for inlined files, but also deals
* with the fast symlink, cause they have no difference for extent
* mapping per se.
+ *
+ * Must be called with ip_alloc_sem semaphore held.
*/
static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
struct fiemap_extent_info *fieinfo,
@@ -717,6 +719,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
u64 phys;
u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ lockdep_assert_held_read(&oi->ip_alloc_sem);
di = (struct ocfs2_dinode *)di_bh->b_data;
if (ocfs2_inode_is_fast_symlink(inode))
@@ -732,8 +735,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
phys += offsetof(struct ocfs2_dinode,
id2.i_data.id_data);
+ /* Release the ip_alloc_sem to prevent deadlock on page fault */
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
flags);
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret < 0)
return ret;
}
@@ -802,9 +808,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
-
+ /* Release the ip_alloc_sem to prevent deadlock on page fault */
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
len_bytes, fe_flags);
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret)
break;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index bd0c099cfdd2..176281112273 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -393,7 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
if (proc_alloc_inum(&dp->low_ino))
goto out_free_entry;
- pde_set_flags(dp);
+ if (!S_ISDIR(dp->mode))
+ pde_set_flags(dp);
write_lock(&proc_subdir_lock);
dp->parent = dir;
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index beb4f18f05ef..2337cf795db3 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -304,6 +304,8 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v)
list_for_each(tmp1, &ses->tcon_list) {
tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
cfids = tcon->cfids;
+ if (!cfids)
+ continue;
spin_lock(&cfids->cfid_list_lock); /* check lock ordering */
seq_printf(m, "Num entries: %d\n", cfids->num_entries);
list_for_each_entry(cfid, &cfids->entries, entry) {
@@ -319,8 +321,6 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v)
seq_printf(m, "\n");
}
spin_unlock(&cfids->cfid_list_lock);
-
-
}
}
}
@@ -347,6 +347,22 @@ static __always_inline const char *compression_alg_str(__le16 alg)
}
}
+static __always_inline const char *cipher_alg_str(__le16 cipher)
+{
+ switch (cipher) {
+ case SMB2_ENCRYPTION_AES128_CCM:
+ return "AES128-CCM";
+ case SMB2_ENCRYPTION_AES128_GCM:
+ return "AES128-GCM";
+ case SMB2_ENCRYPTION_AES256_CCM:
+ return "AES256-CCM";
+ case SMB2_ENCRYPTION_AES256_GCM:
+ return "AES256-GCM";
+ default:
+ return "UNKNOWN";
+ }
+}
+
static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
{
struct mid_q_entry *mid_entry;
@@ -539,6 +555,11 @@ skip_rdma:
else
seq_puts(m, "disabled (not supported by this server)");
+ /* Show negotiated encryption cipher, even if not required */
+ seq_puts(m, "\nEncryption: ");
+ if (server->cipher_type)
+ seq_printf(m, "Negotiated cipher (%s)", cipher_alg_str(server->cipher_type));
+
seq_printf(m, "\n\n\tSessions: ");
i = 0;
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
@@ -576,12 +597,8 @@ skip_rdma:
/* dump session id helpful for use with network trace */
seq_printf(m, " SessionId: 0x%llx", ses->Suid);
- if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) {
+ if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
seq_puts(m, " encrypted");
- /* can help in debugging to show encryption type */
- if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
- seq_puts(m, "(gcm256)");
- }
if (ses->sign)
seq_puts(m, " signed");
diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c
index 4cc6e0896fad..f8659d36793f 100644
--- a/fs/smb/client/cifs_unicode.c
+++ b/fs/smb/client/cifs_unicode.c
@@ -629,6 +629,9 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len,
int len;
__le16 *dst;
+ if (!src)
+ return NULL;
+
len = cifs_local_to_utf16_bytes(src, maxlen, cp);
len += 2; /* NULL */
dst = kmalloc(len, GFP_KERNEL);
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 7869cec58f52..10c84c095fe7 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -278,7 +278,7 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb,
}
/*
- * For absolute symlinks it is not possible to determinate
+ * For absolute symlinks it is not possible to determine
* if it should point to directory or file.
*/
if (symname[0] == '/') {
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 893a1ea8c000..a02d41d1ce4a 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -1005,7 +1005,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
rc = -EOPNOTSUPP;
}
- /* Fallback to SMB_COM_SETATTR command when absolutelty needed. */
+ /* Fallback to SMB_COM_SETATTR command when absolutely needed. */
if (rc == -EOPNOTSUPP) {
cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n");
rc = SMBSetInformation(xid, tcon, full_path,
@@ -1039,7 +1039,7 @@ set_via_filehandle:
cifsFileInfo_put(open_file);
/*
- * Setting the read-only bit is not honered on non-NT servers when done
+ * Setting the read-only bit is not honored on non-NT servers when done
* via open-semantics. So for setting it, use SMB_COM_SETATTR command.
* This command works only after the file is closed, so use it only when
* operation was called without the filehandle.
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index cddf273c14ae..89d933b4a8bc 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -614,6 +614,15 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
struct cifs_tcon *tcon;
struct cifs_pending_open *open;
+ /* Trace receipt of lease break request from server */
+ trace_smb3_lease_break_enter(le32_to_cpu(rsp->CurrentLeaseState),
+ le32_to_cpu(rsp->Flags),
+ le16_to_cpu(rsp->Epoch),
+ le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
+ le64_to_cpu(rsp->hdr.SessionId),
+ *((u64 *)rsp->LeaseKey),
+ *((u64 *)&rsp->LeaseKey[8]));
+
cifs_dbg(FYI, "Checking for lease break\n");
/* If server is a channel, select the primary channel */
@@ -660,10 +669,12 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
spin_unlock(&cifs_tcp_ses_lock);
cifs_dbg(FYI, "Can not process lease break - no lease matched\n");
trace_smb3_lease_not_found(le32_to_cpu(rsp->CurrentLeaseState),
- le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
- le64_to_cpu(rsp->hdr.SessionId),
- *((u64 *)rsp->LeaseKey),
- *((u64 *)&rsp->LeaseKey[8]));
+ le32_to_cpu(rsp->Flags),
+ le16_to_cpu(rsp->Epoch),
+ le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
+ le64_to_cpu(rsp->hdr.SessionId),
+ *((u64 *)rsp->LeaseKey),
+ *((u64 *)&rsp->LeaseKey[8]));
return false;
}
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 2df93a75e3b8..c3b9d3f6210f 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -6192,11 +6192,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
please_key_high = (__u64 *)(lease_key+8);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
- trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid,
+ trace_smb3_lease_ack_err(le32_to_cpu(lease_state), tcon->tid,
ses->Suid, *please_key_low, *please_key_high, rc);
cifs_dbg(FYI, "Send error in Lease Break = %d\n", rc);
} else
- trace_smb3_lease_done(le32_to_cpu(lease_state), tcon->tid,
+ trace_smb3_lease_ack_done(le32_to_cpu(lease_state), tcon->tid,
ses->Suid, *please_key_low, *please_key_high);
return rc;
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 93e5b2bb9f28..fe0e075bc63c 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -1171,8 +1171,54 @@ DEFINE_EVENT(smb3_lease_done_class, smb3_##name, \
__u64 lease_key_high), \
TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high))
-DEFINE_SMB3_LEASE_DONE_EVENT(lease_done);
-DEFINE_SMB3_LEASE_DONE_EVENT(lease_not_found);
+DEFINE_SMB3_LEASE_DONE_EVENT(lease_ack_done);
+/* Tracepoint when a lease break request is received/entered (includes epoch and flags) */
+DECLARE_EVENT_CLASS(smb3_lease_enter_class,
+ TP_PROTO(__u32 lease_state,
+ __u32 flags,
+ __u16 epoch,
+ __u32 tid,
+ __u64 sesid,
+ __u64 lease_key_low,
+ __u64 lease_key_high),
+ TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high),
+ TP_STRUCT__entry(
+ __field(__u32, lease_state)
+ __field(__u32, flags)
+ __field(__u16, epoch)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u64, lease_key_low)
+ __field(__u64, lease_key_high)
+ ),
+ TP_fast_assign(
+ __entry->lease_state = lease_state;
+ __entry->flags = flags;
+ __entry->epoch = epoch;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->lease_key_low = lease_key_low;
+ __entry->lease_key_high = lease_key_high;
+ ),
+ TP_printk("sid=0x%llx tid=0x%x lease_key=0x%llx%llx lease_state=0x%x flags=0x%x epoch=%u",
+ __entry->sesid, __entry->tid, __entry->lease_key_high,
+ __entry->lease_key_low, __entry->lease_state, __entry->flags, __entry->epoch)
+)
+
+#define DEFINE_SMB3_LEASE_ENTER_EVENT(name) \
+DEFINE_EVENT(smb3_lease_enter_class, smb3_##name, \
+ TP_PROTO(__u32 lease_state, \
+ __u32 flags, \
+ __u16 epoch, \
+ __u32 tid, \
+ __u64 sesid, \
+ __u64 lease_key_low, \
+ __u64 lease_key_high), \
+ TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high))
+
+DEFINE_SMB3_LEASE_ENTER_EVENT(lease_break_enter);
+/* Lease not found: reuse lease_enter payload (includes epoch and flags) */
+DEFINE_SMB3_LEASE_ENTER_EVENT(lease_not_found);
DECLARE_EVENT_CLASS(smb3_lease_err_class,
TP_PROTO(__u32 lease_state,
@@ -1213,7 +1259,7 @@ DEFINE_EVENT(smb3_lease_err_class, smb3_##name, \
int rc), \
TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high, rc))
-DEFINE_SMB3_LEASE_ERR_EVENT(lease_err);
+DEFINE_SMB3_LEASE_ERR_EVENT(lease_ack_err);
DECLARE_EVENT_CLASS(smb3_connect_class,
TP_PROTO(char *hostname,
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index fa4ffe037bc7..8720a0705900 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -18,23 +18,42 @@
#define KASAN_ABI_VERSION 5
/*
+ * Clang 22 added preprocessor macros to match GCC, in hopes of eventually
+ * dropping __has_feature support for sanitizers:
+ * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c
+ * Create these macros for older versions of clang so that it is easy to clean
+ * up once the minimum supported version of LLVM for building the kernel always
+ * creates these macros.
+ *
* Note: Checking __has_feature(*_sanitizer) is only true if the feature is
* enabled. Therefore it is not required to additionally check defined(CONFIG_*)
* to avoid adding redundant attributes in other configurations.
*/
+#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__)
+#define __SANITIZE_ADDRESS__
+#endif
+#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__)
+#define __SANITIZE_HWADDRESS__
+#endif
+#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__)
+#define __SANITIZE_THREAD__
+#endif
-#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer)
-/* Emulate GCC's __SANITIZE_ADDRESS__ flag */
+/*
+ * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel.
+ */
+#ifdef __SANITIZE_HWADDRESS__
#define __SANITIZE_ADDRESS__
+#endif
+
+#ifdef __SANITIZE_ADDRESS__
#define __no_sanitize_address \
__attribute__((no_sanitize("address", "hwaddress")))
#else
#define __no_sanitize_address
#endif
-#if __has_feature(thread_sanitizer)
-/* emulate gcc's __SANITIZE_THREAD__ flag */
-#define __SANITIZE_THREAD__
+#ifdef __SANITIZE_THREAD__
#define __no_sanitize_thread \
__attribute__((no_sanitize("thread")))
#else
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b91b993f58ee..487b3bf2e1ea 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev,
extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 7fa1eb3cc823..61d50571ad88 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev,
int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
const struct em_data_callback *cb,
const cpumask_t *cpus, bool microwatts);
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+ const struct em_data_callback *cb,
+ const cpumask_t *cpus, bool microwatts);
void em_dev_unregister_perf_domain(struct device *dev);
struct em_perf_table *em_table_alloc(struct em_perf_domain *pd);
void em_table_free(struct em_perf_table *table);
@@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
{
return -EINVAL;
}
+static inline
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+ const struct em_data_callback *cb,
+ const cpumask_t *cpus, bool microwatts)
+{
+ return -EINVAL;
+}
static inline void em_dev_unregister_perf_domain(struct device *dev)
{
}
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index de5bd76a400c..d7d757e72554 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -856,8 +856,8 @@ struct kernel_ethtool_ts_info {
enum hwtstamp_provider_qualifier phc_qualifier;
enum hwtstamp_source phc_source;
int phc_phyindex;
- enum hwtstamp_tx_types tx_types;
- enum hwtstamp_rx_filters rx_filters;
+ u32 tx_types;
+ u32 rx_filters;
};
/**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d7ab4f96d705..601d036a6c78 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)(1 << 12))
-/* FMODE_* bit 13 */
+/* Supports IOCB_HAS_METADATA */
+#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13))
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH ((__force fmode_t)(1 << 14))
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 890011071f2b..fe5ce9215821 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { }
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask);
void kasan_release_vmalloc(unsigned long start, unsigned long end,
unsigned long free_region_start,
unsigned long free_region_end,
@@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start,
unsigned long size)
{ }
static inline int kasan_populate_vmalloc(unsigned long start,
- unsigned long size)
+ unsigned long size, gfp_t gfp_mask)
{
return 0;
}
@@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start,
static inline void kasan_populate_early_vm_area_shadow(void *start,
unsigned long size) { }
static inline int kasan_populate_vmalloc(unsigned long start,
- unsigned long size)
+ unsigned long size, gfp_t gfp_mask)
{
return 0;
}
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index c27aac67cb3f..b8ae89ea28ab 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -76,6 +76,7 @@ struct tk_read_base {
* @cs_was_changed_seq: The sequence number of clocksource change events
* @clock_valid: Indicator for valid clock
* @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
+ * @monotonic_to_aux: CLOCK_MONOTONIC to CLOCK_AUX offset
* @cycle_interval: Number of clock cycles in one NTP interval
* @xtime_interval: Number of clock shifted nano seconds in one NTP
* interval.
@@ -117,6 +118,9 @@ struct tk_read_base {
* @offs_aux is used by the auxiliary timekeepers which do not utilize any
* of the regular timekeeper offset fields.
*
+ * @monotonic_to_aux is a timespec64 representation of @offs_aux to
+ * accelerate the VDSO update for CLOCK_AUX.
+ *
* The cacheline ordering of the structure is optimized for in kernel usage of
* the ktime_get() and ktime_get_ts64() family of time accessors. Struct
* timekeeper is prepended in the core timekeeping code with a sequence count,
@@ -159,7 +163,10 @@ struct timekeeper {
u8 cs_was_changed_seq;
u8 clock_valid;
- struct timespec64 monotonic_to_boot;
+ union {
+ struct timespec64 monotonic_to_boot;
+ struct timespec64 monotonic_to_aux;
+ };
u64 cycle_interval;
u64 xtime_interval;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 891e43a01bdc..3faa80f5d801 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1912,7 +1912,6 @@ struct nftables_pernet {
struct mutex commit_mutex;
u64 table_handle;
u64 tstamp;
- unsigned int base_seq;
unsigned int gc_seq;
u8 validate_state;
struct work_struct destroy_work;
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 6c2f483d9828..656e784714f3 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set,
const struct nft_set_ext *
nft_hash_lookup(const struct net *net, const struct nft_set *set,
const u32 *key);
+#endif
+
const struct nft_set_ext *
nft_set_do_lookup(const struct net *net, const struct nft_set *set,
const u32 *key);
-#else
-static inline const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
- const u32 *key)
-{
- return set->ops->lookup(net, set, key);
-}
-#endif
/* called from nft_pipapo_avx2.c */
const struct nft_set_ext *
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index cc8060c017d5..99dd166c5d07 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -3,6 +3,7 @@
#define _NETNS_NFTABLES_H_
struct netns_nftables {
+ unsigned int base_seq;
u8 gencursor;
};
diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h
index 7cf7dbbfa131..89aed99bfeae 100644
--- a/include/pcmcia/ss.h
+++ b/include/pcmcia/ss.h
@@ -227,12 +227,8 @@ struct pcmcia_socket {
/* socket drivers must define the resource operations type they use. There
- * are three options:
+ * are two options:
* - pccard_static_ops iomem and ioport areas are assigned statically
- * - pccard_iodyn_ops iomem areas is assigned statically, ioport
- * areas dynamically
- * If this option is selected, use
- * "select PCCARD_IODYN" in Kconfig.
* - pccard_nonstatic_ops iomem and ioport areas are assigned dynamically.
* If this option is selected, use
* "select PCCARD_NONSTATIC" in Kconfig.
@@ -240,13 +236,11 @@ struct pcmcia_socket {
*/
extern struct pccard_resource_ops pccard_static_ops;
#if defined(CONFIG_PCMCIA) || defined(CONFIG_PCMCIA_MODULE)
-extern struct pccard_resource_ops pccard_iodyn_ops;
extern struct pccard_resource_ops pccard_nonstatic_ops;
#else
/* If PCMCIA is not used, but only CARDBUS, these functions are not used
* at all. Therefore, do not use the large (240K!) rsrc_nonstatic module
*/
-#define pccard_iodyn_ops pccard_static_ops
#define pccard_nonstatic_ops pccard_static_ops
#endif
diff --git a/init/Kconfig b/init/Kconfig
index d811cad02a75..e3eb63eadc87 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -146,6 +146,9 @@ config RUSTC_HAS_UNNECESSARY_TRANSMUTES
config RUSTC_HAS_FILE_WITH_NUL
def_bool RUSTC_VERSION >= 108900
+config RUSTC_HAS_FILE_AS_C_STR
+ def_bool RUSTC_VERSION >= 109100
+
config PAHOLE_VERSION
int
default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
diff --git a/init/main.c b/init/main.c
index 0ee0ee7b7c2c..5753e9539ae6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -956,6 +956,7 @@ void start_kernel(void)
sort_main_extable();
trap_init();
mm_core_init();
+ maple_tree_init();
poking_init();
ftrace_init();
@@ -973,7 +974,6 @@ void start_kernel(void)
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
- maple_tree_init();
/*
* Set up housekeeping before setting up workqueues to allow the unbound
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 52a5b950b2e5..af5a54b5db12 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
if (req->flags & REQ_F_HAS_METADATA) {
struct io_async_rw *io = req->async_data;
+ if (!(file->f_mode & FMODE_HAS_METADATA))
+ return -EINVAL;
+
/*
* We have a union of meta fields with wpq used for buffered-io
* in io_async_rw, so fail it here.
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index e3f42018ed46..f7708fe2c457 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1326,7 +1326,7 @@ int audit_compare_dname_path(const struct qstr *dname, const char *path, int par
/* handle trailing slashes */
pathlen -= parentlen;
- while (p[pathlen - 1] == '/')
+ while (pathlen > 0 && p[pathlen - 1] == '/')
pathlen--;
if (pathlen != dlen)
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 269c04a24664..f6cf8c2af5f7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -62,3 +62,4 @@ CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5d1650af899d..e4568d44e827 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2366,8 +2366,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
const struct bpf_insn *insn)
{
/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
- * is not working properly, or interpreter is being used when
- * prog->jit_requested is not 0, so warn about it!
+ * is not working properly, so warn about it!
*/
WARN_ON_ONCE(1);
return 0;
@@ -2468,8 +2467,9 @@ out:
return ret;
}
-static void bpf_prog_select_func(struct bpf_prog *fp)
+static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
{
+ bool select_interpreter = false;
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
u32 idx = (round_up(stack_depth, 32) / 32) - 1;
@@ -2478,15 +2478,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
* But for non-JITed programs, we don't need bpf_func, so no bounds
* check needed.
*/
- if (!fp->jit_requested &&
- !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+ if (idx < ARRAY_SIZE(interpreters)) {
fp->bpf_func = interpreters[idx];
+ select_interpreter = true;
} else {
fp->bpf_func = __bpf_prog_ret0_warn;
}
#else
fp->bpf_func = __bpf_prog_ret0_warn;
#endif
+ return select_interpreter;
}
/**
@@ -2505,7 +2506,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
/* In case of BPF to BPF calls, verifier did all the prep
* work with regards to JITing, etc.
*/
- bool jit_needed = fp->jit_requested;
+ bool jit_needed = false;
if (fp->bpf_func)
goto finalize;
@@ -2514,7 +2515,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
bpf_prog_has_kfunc_call(fp))
jit_needed = true;
- bpf_prog_select_func(fp);
+ if (!bpf_prog_select_interpreter(fp))
+ jit_needed = true;
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -3024,7 +3026,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output);
/* Always built-in helper functions. */
const struct bpf_func_proto bpf_tail_call_proto = {
- .func = NULL,
+ /* func is unused for tail_call, we set it to pass the
+ * get_helper_proto check
+ */
+ .func = BPF_PTR_POISON,
.gpl_only = false,
.ret_type = RET_VOID,
.arg1_type = ARG_PTR_TO_CTX,
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index b2b7b8ec2c2a..c46360b27871 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -186,7 +186,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
struct xdp_buff xdp;
int i, nframes = 0;
- xdp_set_return_frame_no_direct();
xdp.rxq = &rxq;
for (i = 0; i < n; i++) {
@@ -231,7 +230,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
}
}
- xdp_clear_return_frame_no_direct();
stats->pass += nframes;
return nframes;
@@ -255,6 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
rcu_read_lock();
bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+ xdp_set_return_frame_no_direct();
ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats);
if (unlikely(ret->skb_n))
@@ -264,6 +263,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
if (stats->redirect)
xdp_do_flush();
+ xdp_clear_return_frame_no_direct();
bpf_net_ctx_clear(bpf_net_ctx);
rcu_read_unlock();
diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 94854cd9c4cc..83c4d9943084 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
siv_len = siv ? __bpf_dynptr_size(siv) : 0;
src_len = __bpf_dynptr_size(src);
dst_len = __bpf_dynptr_size(dst);
- if (!src_len || !dst_len)
+ if (!src_len || !dst_len || src_len > dst_len)
return -EINVAL;
if (siv_len != ctx->siv_len)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6b4877e85a68..8af62cb243d9 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1274,8 +1274,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
goto out;
}
- /* allocate hrtimer via map_kmalloc to use memcg accounting */
- cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node);
+ /* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
+ * kmalloc_nolock() is available, avoid locking issues by using
+ * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
+ */
+ cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
if (!cb) {
ret = -ENOMEM;
goto out;
@@ -3664,10 +3667,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len
guard(pagefault)();
for (i = 0; i < XATTR_SIZE_MAX; i++) {
- for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) {
+ for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) {
__get_kernel_nofault(&c2, s2__ign + j, char, err_out);
if (c2 == '\0')
return i;
+ /*
+ * We allow reading an extra byte from s2 (note the
+ * `i + j <= len` above) to cover the case when s2 is
+ * a suffix of the first len chars of s1.
+ */
+ if (i + j == len)
+ break;
__get_kernel_nofault(&c1, s1__ign + j, char, err_out);
if (c1 == '\0')
return -ENOENT;
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index 5ab354d55d82..a00561b1d3e5 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -471,7 +471,7 @@ queue:
* any MCS node. This is not the most elegant solution, but is
* simple enough.
*/
- if (unlikely(idx >= _Q_MAX_NODES)) {
+ if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) {
lockevent_inc(lock_no_node);
RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT);
while (!queued_spin_trylock(lock)) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4f69a9e9af6..9fb1f957a093 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8547,6 +8547,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
verifier_bug(env, "Two map pointers in a timer helper");
return -EFAULT;
}
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n");
+ return -EOPNOTSUPP;
+ }
meta->map_uid = reg->map_uid;
meta->map_ptr = map;
return 0;
@@ -11354,7 +11358,7 @@ static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
return -EINVAL;
*ptr = env->ops->get_func_proto(func_id, env->prog);
- return *ptr ? 0 : -EINVAL;
+ return *ptr && (*ptr)->func ? 0 : -EINVAL;
}
static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index e43c6de2bce4..b82399437db0 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -39,6 +39,7 @@ enum {
dma_debug_sg,
dma_debug_coherent,
dma_debug_resource,
+ dma_debug_noncoherent,
};
enum map_err_types {
@@ -141,6 +142,7 @@ static const char *type2name[] = {
[dma_debug_sg] = "scatter-gather",
[dma_debug_coherent] = "coherent",
[dma_debug_resource] = "resource",
+ [dma_debug_noncoherent] = "noncoherent",
};
static const char *dir2name[] = {
@@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref)
"[mapped as %s] [unmapped as %s]\n",
ref->dev_addr, ref->size,
type2name[entry->type], type2name[ref->type]);
- } else if (entry->type == dma_debug_coherent &&
+ } else if ((entry->type == dma_debug_coherent ||
+ entry->type == dma_debug_noncoherent) &&
ref->paddr != entry->paddr) {
err_printk(ref->dev, entry, "device driver frees "
"DMA memory with different CPU address "
@@ -1581,6 +1584,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
}
}
+void debug_dma_alloc_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_noncoherent;
+ entry->dev = dev;
+ entry->paddr = page_to_phys(page);
+ entry->size = size;
+ entry->dev_addr = dma_addr;
+ entry->direction = direction;
+
+ add_dma_entry(entry, attrs);
+}
+
+void debug_dma_free_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_noncoherent,
+ .dev = dev,
+ .paddr = page_to_phys(page),
+ .dev_addr = dma_addr,
+ .size = size,
+ .direction = direction,
+ };
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ check_unmap(&ref);
+}
+
static int __init dma_debug_driver_setup(char *str)
{
int i;
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index f525197d3cae..48757ca13f31 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev,
extern void debug_dma_sync_sg_for_device(struct device *dev,
struct scatterlist *sg,
int nelems, int direction);
+extern void debug_dma_alloc_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr,
+ unsigned long attrs);
+extern void debug_dma_free_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr);
#else /* CONFIG_DMA_API_DEBUG */
static inline void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
@@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev,
int nelems, int direction)
{
}
+
+static inline void debug_dma_alloc_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+}
+
+static inline void debug_dma_free_pages(struct device *dev, struct page *page,
+ size_t size, int direction,
+ dma_addr_t dma_addr)
+{
+}
#endif /* CONFIG_DMA_API_DEBUG */
#endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 107e4a4d251d..56de28a3b179 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -712,7 +712,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
if (page) {
trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
size, dir, gfp, 0);
- debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
+ debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0);
} else {
trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0);
}
@@ -738,7 +738,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page,
dma_addr_t dma_handle, enum dma_data_direction dir)
{
trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0);
- debug_dma_unmap_page(dev, dma_handle, size, dir);
+ debug_dma_free_pages(dev, page, size, dir, dma_handle);
__dma_free_pages(dev, size, page, dma_handle, dir);
}
EXPORT_SYMBOL_GPL(dma_free_pages);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 872122e074e5..820127536e62 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10330,6 +10330,7 @@ static int __perf_event_overflow(struct perf_event *event,
ret = 1;
event->pending_kill = POLL_HUP;
perf_event_disable_inatomic(event);
+ event->pmu->stop(event, 0);
}
if (event->attr.sigtrap) {
diff --git a/kernel/fork.c b/kernel/fork.c
index af673856499d..c4ada32598bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -689,7 +689,6 @@ void __mmdrop(struct mm_struct *mm)
mm_pasid_drop(mm);
mm_destroy_cid(mm);
percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
- futex_hash_free(mm);
free_mm(mm);
}
@@ -1138,6 +1137,7 @@ static inline void __mmput(struct mm_struct *mm)
if (mm->binfmt)
module_put(mm->binfmt->module);
lru_gen_del_mm(mm);
+ futex_hash_free(mm);
mmdrop(mm);
}
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index d9bb5567af0c..125804fbb5cb 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1722,12 +1722,9 @@ int futex_mm_init(struct mm_struct *mm)
RCU_INIT_POINTER(mm->futex_phash, NULL);
mm->futex_phash_new = NULL;
/* futex-ref */
+ mm->futex_ref = NULL;
atomic_long_set(&mm->futex_atomic, 0);
mm->futex_batches = get_state_synchronize_rcu();
- mm->futex_ref = alloc_percpu(unsigned int);
- if (!mm->futex_ref)
- return -ENOMEM;
- this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
return 0;
}
@@ -1801,6 +1798,17 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
}
}
+ if (!mm->futex_ref) {
+ /*
+ * This will always be allocated by the first thread and
+ * therefore requires no locking.
+ */
+ mm->futex_ref = alloc_percpu(unsigned int);
+ if (!mm->futex_ref)
+ return -ENOMEM;
+ this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
+ }
+
fph = kvzalloc(struct_size(fph, queues, hash_slots),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!fph)
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index ea7995a25780..8df55397414a 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -553,6 +553,30 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
const struct em_data_callback *cb,
const cpumask_t *cpus, bool microwatts)
{
+ int ret = em_dev_register_pd_no_update(dev, nr_states, cb, cpus, microwatts);
+
+ if (_is_cpu_device(dev))
+ em_check_capacity_update();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+
+/**
+ * em_dev_register_pd_no_update() - Register a perf domain for a device
+ * @dev : Device to register the PD for
+ * @nr_states : Number of performance states in the new PD
+ * @cb : Callback functions for populating the energy model
+ * @cpus : CPUs to include in the new PD (mandatory if @dev is a CPU device)
+ * @microwatts : Whether or not the power values in the EM will be in uW
+ *
+ * Like em_dev_register_perf_domain(), but does not trigger a CPU capacity
+ * update after registering the PD, even if @dev is a CPU device.
+ */
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+ const struct em_data_callback *cb,
+ const cpumask_t *cpus, bool microwatts)
+{
struct em_perf_table *em_table;
unsigned long cap, prev_cap = 0;
unsigned long flags = 0;
@@ -636,12 +660,9 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
unlock:
mutex_unlock(&em_pd_mutex);
- if (_is_cpu_device(dev))
- em_check_capacity_update();
-
return ret;
}
-EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+EXPORT_SYMBOL_GPL(em_dev_register_pd_no_update);
/**
* em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 1f1f30cca573..2f66ab453823 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -449,6 +449,7 @@ int hibernation_snapshot(int platform_mode)
shrink_shmem_memory();
console_suspend_all();
+ pm_restrict_gfp_mask();
error = dpm_suspend(PMSG_FREEZE);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 059fa8b79be6..b6974fce800c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -83,6 +83,12 @@ static inline bool tk_is_aux(const struct timekeeper *tk)
}
#endif
+static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs)
+{
+ tk->offs_aux = offs;
+ tk->monotonic_to_aux = ktime_to_timespec64(offs);
+}
+
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
@@ -1506,7 +1512,7 @@ static int __timekeeping_inject_offset(struct tk_data *tkd, const struct timespe
timekeeping_restore_shadow(tkd);
return -EINVAL;
}
- tks->offs_aux = offs;
+ tk_update_aux_offs(tks, offs);
}
timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL);
@@ -2937,7 +2943,7 @@ static int aux_clock_set(const clockid_t id, const struct timespec64 *tnew)
* xtime ("realtime") is not applicable for auxiliary clocks and
* kept in sync with "monotonic".
*/
- aux_tks->offs_aux = ktime_sub(timespec64_to_ktime(*tnew), tnow);
+ tk_update_aux_offs(aux_tks, ktime_sub(timespec64_to_ktime(*tnew), tnow));
timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL);
return 0;
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 8ba8b0d8a387..aa59919b8f2c 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -159,10 +159,10 @@ void vdso_time_update_aux(struct timekeeper *tk)
if (clock_mode != VDSO_CLOCKMODE_NONE) {
fill_clock_configuration(vc, &tk->tkr_mono);
- vdso_ts->sec = tk->xtime_sec;
+ vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec;
nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
- nsec += tk->offs_aux;
+ nsec += tk->monotonic_to_aux.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
nsec = nsec << tk->tkr_mono.shift;
vdso_ts->nsec = nsec;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 2a42c1036ea8..1e3b32b1e82c 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1397,7 +1397,8 @@ error:
ftrace_graph_active--;
gops->saved_func = NULL;
fgraph_lru_release_index(i);
- unregister_pm_notifier(&ftrace_suspend_notifier);
+ if (!ftrace_graph_active)
+ unregister_pm_notifier(&ftrace_suspend_notifier);
}
return ret;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1b7db732c0b1..b3c94fbaf002 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -834,7 +834,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
/* copy the current bits to the new max */
ret = trace_pid_list_first(filtered_pids, &pid);
while (!ret) {
- trace_pid_list_set(pid_list, pid);
+ ret = trace_pid_list_set(pid_list, pid);
+ if (ret < 0)
+ goto out;
+
ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
nr_pids++;
}
@@ -871,6 +874,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
trace_parser_clear(&parser);
ret = 0;
}
+ out:
trace_parser_put(&parser);
if (ret < 0) {
@@ -7209,7 +7213,7 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user
entry = ring_buffer_event_data(event);
entry->ip = ip;
- len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
+ len = copy_from_user_nofault(&entry->buf, ubuf, cnt);
if (len) {
memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
cnt = FAULTED_SIZE;
@@ -7306,7 +7310,7 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
entry = ring_buffer_event_data(event);
- len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
+ len = copy_from_user_nofault(&entry->id, ubuf, cnt);
if (len) {
entry->id = -1;
memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index af42aaa3d172..2ab283fd3032 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -496,7 +496,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm,
{
struct user_event_enabler_fault *fault;
- fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN);
+ fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT);
if (!fault)
return false;
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index fd259da0aa64..337bc0eb5d71 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2322,6 +2322,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
int running, err;
char *buf __free(kfree) = NULL;
+ if (count < 1)
+ return 0;
+
buf = kmalloc(count, GFP_KERNEL);
if (!buf)
return -ENOMEM;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 106ee8b0f2d5..c2e0b469fd43 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2111,6 +2111,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
if (!quota->ms && !quota->sz && list_empty(&quota->goals))
return;
+ /* First charge window */
+ if (!quota->total_charged_sz && !quota->charged_from)
+ quota->charged_from = jiffies;
+
/* New charge window starts */
if (time_after_eq(jiffies, quota->charged_from +
msecs_to_jiffies(quota->reset_interval))) {
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index 151a9de5ad8b..b5a5ed16a7a5 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -198,6 +198,11 @@ static int damon_lru_sort_apply_parameters(void)
if (err)
return err;
+ if (!damon_lru_sort_mon_attrs.sample_interval) {
+ err = -EINVAL;
+ goto out;
+ }
+
err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs);
if (err)
goto out;
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index 3c71b4596676..fb7c982a0018 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -194,6 +194,11 @@ static int damon_reclaim_apply_parameters(void)
if (err)
return err;
+ if (!damon_reclaim_mon_attrs.aggr_interval) {
+ err = -EINVAL;
+ goto out;
+ }
+
err = damon_set_attrs(param_ctx, &damon_reclaim_mon_attrs);
if (err)
goto out;
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 6d2b0dab50cb..7b9254cadd5f 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1260,14 +1260,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
{
struct damon_sysfs_kdamond *kdamond = container_of(kobj,
struct damon_sysfs_kdamond, kobj);
- struct damon_ctx *ctx = kdamond->damon_ctx;
- bool running;
+ struct damon_ctx *ctx;
+ bool running = false;
- if (!ctx)
- running = false;
- else
+ if (!mutex_trylock(&damon_sysfs_lock))
+ return -EBUSY;
+
+ ctx = kdamond->damon_ctx;
+ if (ctx)
running = damon_is_running(ctx);
+ mutex_unlock(&damon_sysfs_lock);
+
return sysfs_emit(buf, "%s\n", running ?
damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] :
damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 753f99b4c718..eed59cfb5d21 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
spinlock_t *ptl;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- bool adjust_reservation = false;
+ bool adjust_reservation;
unsigned long last_addr_mask;
bool force_flush = false;
@@ -5944,6 +5944,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
sz);
hugetlb_count_sub(pages_per_huge_page(h), mm);
hugetlb_remove_rmap(folio);
+ spin_unlock(ptl);
/*
* Restore the reservation for anonymous page, otherwise the
@@ -5951,14 +5952,16 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
* If there we are freeing a surplus, do not set the restore
* reservation bit.
*/
+ adjust_reservation = false;
+
+ spin_lock_irq(&hugetlb_lock);
if (!h->surplus_huge_pages && __vma_private_lock(vma) &&
folio_test_anon(folio)) {
folio_set_hugetlb_restore_reserve(folio);
/* Reservation to be adjusted after the spin lock */
adjust_reservation = true;
}
-
- spin_unlock(ptl);
+ spin_unlock_irq(&hugetlb_lock);
/*
* Adjust the reservation for the region that will have the
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index e2ceebf737ef..11d472a5c4e8 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -336,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages)
}
}
-static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
+static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask)
{
unsigned long nr_populated, nr_total = nr_pages;
struct page **page_array = pages;
while (nr_pages) {
- nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages);
+ nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages);
if (!nr_populated) {
___free_pages_bulk(page_array, nr_total - nr_pages);
return -ENOMEM;
@@ -354,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
return 0;
}
-static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
+static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask)
{
unsigned long nr_pages, nr_total = PFN_UP(end - start);
struct vmalloc_populate_data data;
+ unsigned int flags;
int ret = 0;
- data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO);
if (!data.pages)
return -ENOMEM;
while (nr_total) {
nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0]));
- ret = ___alloc_pages_bulk(data.pages, nr_pages);
+ ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask);
if (ret)
break;
data.start = start;
+
+ /*
+ * page tables allocations ignore external gfp mask, enforce it
+ * by the scope API
+ */
+ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+ flags = memalloc_nofs_save();
+ else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+ flags = memalloc_noio_save();
+
ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE,
kasan_populate_vmalloc_pte, &data);
+
+ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+ memalloc_nofs_restore(flags);
+ else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+ memalloc_noio_restore(flags);
+
___free_pages_bulk(data.pages, nr_pages);
if (ret)
break;
@@ -386,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
return ret;
}
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask)
{
unsigned long shadow_start, shadow_end;
int ret;
@@ -415,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
shadow_start = PAGE_ALIGN_DOWN(shadow_start);
shadow_end = PAGE_ALIGN(shadow_end);
- ret = __kasan_populate_vmalloc(shadow_start, shadow_end);
+ ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask);
if (ret)
return ret;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6b40bdfd224c..b486c1d19b2d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
*/
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
- folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
- address)))
+ folio_test_referenced(folio) ||
+ mmu_notifier_test_young(vma->vm_mm, _address)))
referenced++;
}
if (!writable) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fc30ca4804bf..df6ee59527dd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -956,7 +956,7 @@ static const char * const action_page_types[] = {
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_DAX] = "dax page",
[MF_MSG_UNSPLIT_THP] = "unsplit thp",
- [MF_MSG_ALREADY_POISONED] = "already poisoned",
+ [MF_MSG_ALREADY_POISONED] = "already poisoned page",
[MF_MSG_UNKNOWN] = "unknown page",
};
@@ -1349,9 +1349,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
{
trace_memory_failure_event(pfn, type, result);
- num_poisoned_pages_inc(pfn);
-
- update_per_node_mf_stats(pfn, result);
+ if (type != MF_MSG_ALREADY_POISONED) {
+ num_poisoned_pages_inc(pfn);
+ update_per_node_mf_stats(pfn, result);
+ }
pr_err("%#lx: recovery action for %s: %s\n",
pfn, action_page_types[type], action_name[result]);
@@ -2094,12 +2095,11 @@ retry:
*hugetlb = 0;
return 0;
} else if (res == -EHWPOISON) {
- pr_err("%#lx: already hardware poisoned\n", pfn);
if (flags & MF_ACTION_REQUIRED) {
folio = page_folio(p);
res = kill_accessing_process(current, folio_pfn(folio), flags);
- action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
}
+ action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
return res;
} else if (res == -EBUSY) {
if (!(flags & MF_NO_RETRY)) {
@@ -2285,7 +2285,6 @@ try_again:
goto unlock_mutex;
if (TestSetPageHWPoison(p)) {
- pr_err("%#lx: already hardware poisoned\n", pfn);
res = -EHWPOISON;
if (flags & MF_ACTION_REQUIRED)
res = kill_accessing_process(current, pfn, flags);
@@ -2569,10 +2568,9 @@ int unpoison_memory(unsigned long pfn)
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
- if (!pfn_valid(pfn))
- return -ENXIO;
-
- p = pfn_to_page(pfn);
+ p = pfn_to_online_page(pfn);
+ if (!p)
+ return -EIO;
folio = page_folio(p);
mutex_lock(&mf_mutex);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1f15af712bc3..74318c787715 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1815,8 +1815,14 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
if (folio_contain_hwpoisoned_page(folio)) {
- if (WARN_ON(folio_test_lru(folio)))
- folio_isolate_lru(folio);
+ /*
+ * unmap_poisoned_folio() cannot handle large folios
+ * in all cases yet.
+ */
+ if (folio_test_large(folio) && !folio_test_hugetlb(folio))
+ goto put_folio;
+ if (folio_test_lru(folio) && !folio_isolate_lru(folio))
+ goto put_folio;
if (folio_mapped(folio)) {
folio_lock(folio);
unmap_poisoned_folio(folio, pfn, false);
diff --git a/mm/mremap.c b/mm/mremap.c
index e618a706aff5..35de0a7b910e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1774,15 +1774,18 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm)
if (!vrm->new_len)
return -EINVAL;
- /* Is the new length or address silly? */
- if (vrm->new_len > TASK_SIZE ||
- vrm->new_addr > TASK_SIZE - vrm->new_len)
+ /* Is the new length silly? */
+ if (vrm->new_len > TASK_SIZE)
return -EINVAL;
/* Remainder of checks are for cases with specific new_addr. */
if (!vrm_implies_new_addr(vrm))
return 0;
+ /* Is the new address silly? */
+ if (vrm->new_addr > TASK_SIZE - vrm->new_len)
+ return -EINVAL;
+
/* The new address must be page-aligned. */
if (offset_in_page(vrm->new_addr))
return -EINVAL;
diff --git a/mm/percpu.c b/mm/percpu.c
index a56f35dcc417..81462ce5866e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1734,7 +1734,7 @@ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
bool is_atomic;
bool do_warn;
struct obj_cgroup *objcg = NULL;
- static int warn_limit = 10;
+ static atomic_t warn_limit = ATOMIC_INIT(10);
struct pcpu_chunk *chunk, *next;
const char *err;
int slot, off, cpu, ret;
@@ -1904,13 +1904,17 @@ fail_unlock:
fail:
trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
- if (do_warn && warn_limit) {
- pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
- size, align, is_atomic, err);
- if (!is_atomic)
- dump_stack();
- if (!--warn_limit)
- pr_info("limit reached, disable warning\n");
+ if (do_warn) {
+ int remaining = atomic_dec_if_positive(&warn_limit);
+
+ if (remaining >= 0) {
+ pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
+ size, align, is_atomic, err);
+ if (!is_atomic)
+ dump_stack();
+ if (remaining == 0)
+ pr_info("limit reached, disable warning\n");
+ }
}
if (is_atomic) {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6dbcdceecae1..5edd536ba9d2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2026,6 +2026,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
if (unlikely(!vmap_initialized))
return ERR_PTR(-EBUSY);
+ /* Only reclaim behaviour flags are relevant. */
+ gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
might_sleep();
/*
@@ -2038,8 +2040,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
*/
va = node_alloc(size, align, vstart, vend, &addr, &vn_id);
if (!va) {
- gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
-
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
if (unlikely(!va))
return ERR_PTR(-ENOMEM);
@@ -2089,7 +2089,7 @@ retry:
BUG_ON(va->va_start < vstart);
BUG_ON(va->va_end > vend);
- ret = kasan_populate_vmalloc(addr, size);
+ ret = kasan_populate_vmalloc(addr, size, gfp_mask);
if (ret) {
free_vmap_area(va);
return ERR_PTR(ret);
@@ -4826,7 +4826,7 @@ retry:
/* populate the kasan shadow space */
for (area = 0; area < nr_vms; area++) {
- if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
+ if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL))
goto err_free_shadow;
}
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 1885d0c315f0..c683baa3847f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br,
int err = 0;
int opt_id;
+ opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX);
+ if (opt_id != BITS_PER_LONG) {
+ NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d",
+ opt_id);
+ return -EINVAL;
+ }
+
for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) {
bool on = !!(bm->optval & BIT(opt_id));
diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c
index 39844f14eed8..797719cb227e 100644
--- a/net/can/j1939/bus.c
+++ b/net/can/j1939/bus.c
@@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa)
if (!ecu)
ecu = j1939_ecu_create_locked(priv, name);
err = PTR_ERR_OR_ZERO(ecu);
- if (err)
+ if (err) {
+ if (j1939_address_is_unicast(sa))
+ priv->ents[sa].nusers--;
goto done;
+ }
ecu->nusers++;
/* TODO: do we care if ecu->addr != sa? */
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 31a93cae5111..81f58924b4ac 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv);
/* notify/alert all j1939 sockets bound to ifindex */
void j1939_sk_netdev_event_netdown(struct j1939_priv *priv);
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv);
int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk);
void j1939_tp_init(struct j1939_priv *priv);
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 7e8a20f2fc42..3706a872ecaf 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb,
j1939_sk_netdev_event_netdown(priv);
j1939_ecu_unmap_all(priv);
break;
+ case NETDEV_UNREGISTER:
+ j1939_sk_netdev_event_unregister(priv);
+ break;
}
j1939_priv_put(priv);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 3d8b588822f9..88e7160d4248 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa);
if (ret) {
j1939_netdev_stop(priv);
+ jsk->priv = NULL;
+ synchronize_rcu();
+ j1939_priv_put(priv);
goto out_release_sock;
}
@@ -1300,6 +1303,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
read_unlock_bh(&priv->j1939_socks_lock);
}
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv)
+{
+ struct sock *sk;
+ struct j1939_sock *jsk;
+ bool wait_rcu = false;
+
+rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */
+ read_lock_bh(&priv->j1939_socks_lock);
+ list_for_each_entry(jsk, &priv->j1939_socks, list) {
+ /* Skip if j1939_jsk_add() is not called on this socket. */
+ if (!(jsk->state & J1939_SOCK_BOUND))
+ continue;
+ sk = &jsk->sk;
+ sock_hold(sk);
+ read_unlock_bh(&priv->j1939_socks_lock);
+ /* Check if j1939_jsk_del() is not yet called on this socket after holding
+ * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call
+ * j1939_jsk_del() with socket's lock held.
+ */
+ lock_sock(sk);
+ if (jsk->state & J1939_SOCK_BOUND) {
+ /* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del().
+ * Make this socket no longer bound, by pretending as if j1939_sk_bind()
+ * dropped old references but did not get new references.
+ */
+ j1939_jsk_del(priv, jsk);
+ j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa);
+ j1939_netdev_stop(priv);
+ /* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from
+ * calling the corresponding j1939_priv_put().
+ *
+ * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after
+ * an RCU grace period. But since the caller is holding a ref on this
+ * "priv", we can defer synchronize_rcu() until immediately before
+ * the caller calls j1939_priv_put().
+ */
+ j1939_priv_put(priv);
+ jsk->priv = NULL;
+ wait_rcu = true;
+ }
+ release_sock(sk);
+ sock_put(sk);
+ goto rescan;
+ }
+ read_unlock_bh(&priv->j1939_socks_lock);
+ if (wait_rcu)
+ synchronize_rcu();
+}
+
static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 9c0ad7f4b5d8..ad54b12d4b4c 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
if (!netif_device_present(dev))
return -ENODEV;
- if (ops->ndo_hwtstamp_get)
- return dev_get_hwtstamp_phylib(dev, kernel_cfg);
+ if (ops->ndo_hwtstamp_get) {
+ int err;
+
+ netdev_lock_ops(dev);
+ err = dev_get_hwtstamp_phylib(dev, kernel_cfg);
+ netdev_unlock_ops(dev);
+
+ return err;
+ }
/* Legacy path: unconverted lower driver */
return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
@@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev,
if (!netif_device_present(dev))
return -ENODEV;
- if (ops->ndo_hwtstamp_set)
- return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+ if (ops->ndo_hwtstamp_set) {
+ int err;
+
+ netdev_lock_ops(dev);
+ err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+ netdev_unlock_ops(dev);
+
+ return err;
+ }
/* Legacy path: unconverted lower driver */
return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 88657255fec1..fbbc3ccf9df6 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master)
ASSERT_RTNL();
- hsr_for_each_port(master->hsr, port) {
+ hsr_for_each_port_rtnl(master->hsr, port) {
if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) {
netif_carrier_on(master->dev);
return true;
@@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr)
struct hsr_port *port;
mtu_max = ETH_DATA_LEN;
- hsr_for_each_port(hsr, port)
+ hsr_for_each_port_rtnl(hsr, port)
if (port->type != HSR_PT_MASTER)
mtu_max = min(port->dev->mtu, mtu_max);
@@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev)
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
if (port->type == HSR_PT_MASTER)
continue;
switch (port->type) {
@@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev)
struct hsr_priv *hsr;
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
if (port->type == HSR_PT_MASTER)
continue;
switch (port->type) {
@@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr,
* may become enabled.
*/
features &= ~NETIF_F_ONE_FOR_ALL;
- hsr_for_each_port(hsr, port)
+ hsr_for_each_port_rtnl(hsr, port)
features = netdev_increment_features(features,
port->dev->features,
mask);
@@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
struct hsr_priv *hsr = netdev_priv(dev);
struct hsr_port *master;
+ rcu_read_lock();
master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
if (master) {
skb->dev = master->dev;
@@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
dev_core_stats_tx_dropped_inc(dev);
dev_kfree_skb_any(skb);
}
+ rcu_read_unlock();
+
return NETDEV_TX_OK;
}
@@ -484,7 +487,7 @@ static void hsr_set_rx_mode(struct net_device *dev)
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
if (port->type == HSR_PT_MASTER)
continue;
switch (port->type) {
@@ -506,7 +509,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change)
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
if (port->type == HSR_PT_MASTER)
continue;
switch (port->type) {
@@ -534,7 +537,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
if (port->type == HSR_PT_MASTER ||
port->type == HSR_PT_INTERLINK)
continue;
@@ -580,7 +583,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev,
hsr = netdev_priv(dev);
- hsr_for_each_port(hsr, port) {
+ hsr_for_each_port_rtnl(hsr, port) {
switch (port->type) {
case HSR_PT_SLAVE_A:
case HSR_PT_SLAVE_B:
@@ -672,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev,
struct hsr_priv *hsr = netdev_priv(ndev);
struct hsr_port *port;
+ rcu_read_lock();
hsr_for_each_port(hsr, port)
- if (port->type == pt)
+ if (port->type == pt) {
+ dev_hold(port->dev);
+ rcu_read_unlock();
return port->dev;
+ }
+ rcu_read_unlock();
return NULL;
}
EXPORT_SYMBOL(hsr_get_port_ndev);
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index 192893c3f2ec..bc94b07101d8 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr)
{
struct hsr_port *port;
- hsr_for_each_port(hsr, port)
+ hsr_for_each_port_rtnl(hsr, port)
if (port->type != HSR_PT_MASTER)
return false;
return true;
@@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt)
{
struct hsr_port *port;
- hsr_for_each_port(hsr, port)
+ hsr_for_each_port_rtnl(hsr, port)
if (port->type == pt)
return port;
return NULL;
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 135ec5fce019..33b0d2460c9b 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -224,6 +224,9 @@ struct hsr_priv {
#define hsr_for_each_port(hsr, port) \
list_for_each_entry_rcu((port), &(hsr)->ports, port_list)
+#define hsr_for_each_port_rtnl(hsr, port) \
+ list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held())
+
struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt);
/* Caller must ensure skb is a valid HSR frame */
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index cc9915543637..2e61ac137128 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -206,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
return -EINVAL;
+ if (skb_is_gso(skb))
+ skb_gso_reset(skb);
+
skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
pskb_pull(skb, ETH_HLEN);
skb_reset_network_header(skb);
@@ -300,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
return -EINVAL;
+ if (skb_is_gso(skb))
+ skb_gso_reset(skb);
+
skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
pskb_pull(skb, ETH_HLEN);
skb_reset_network_header(skb);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ba581785adb4..a268e1595b22 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -408,8 +408,11 @@ more_data:
if (!psock->cork) {
psock->cork = kzalloc(sizeof(*psock->cork),
GFP_ATOMIC | __GFP_NOWARN);
- if (!psock->cork)
+ if (!psock->cork) {
+ sk_msg_free(sk, msg);
+ *copied = 0;
return -ENOMEM;
+ }
}
memcpy(psock->cork, msg, sizeof(*msg));
return 0;
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 2c267aff95be..2abe6f1e9940 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1532,13 +1532,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
{
static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
struct sock *sk = (struct sock *)msk;
+ bool keep_open;
- if (ssk->sk_prot->keepalive) {
- if (sock_flag(sk, SOCK_KEEPOPEN))
- ssk->sk_prot->keepalive(ssk, 1);
- else
- ssk->sk_prot->keepalive(ssk, 0);
- }
+ keep_open = sock_flag(sk, SOCK_KEEPOPEN);
+ if (ssk->sk_prot->keepalive)
+ ssk->sk_prot->keepalive(ssk, keep_open);
+ sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open);
ssk->sk_priority = sk->sk_priority;
ssk->sk_bound_dev_if = sk->sk_bound_dev_if;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c1082de09656..c3c73411c40c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1131,11 +1131,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
return ERR_PTR(-ENOENT);
}
-static __be16 nft_base_seq(const struct net *net)
+static unsigned int nft_base_seq(const struct net *net)
{
- struct nftables_pernet *nft_net = nft_pernet(net);
+ return READ_ONCE(net->nft.base_seq);
+}
- return htons(nft_net->base_seq & 0xffff);
+static __be16 nft_base_seq_be16(const struct net *net)
+{
+ return htons(nft_base_seq(net) & 0xffff);
}
static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
@@ -1155,7 +1158,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
nlh = nfnl_msg_put(skb, portid, seq,
nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
- flags, family, NFNETLINK_V0, nft_base_seq(net));
+ flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -1248,7 +1251,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
@@ -2030,7 +2033,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
nlh = nfnl_msg_put(skb, portid, seq,
nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
- flags, family, NFNETLINK_V0, nft_base_seq(net));
+ flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -2133,7 +2136,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
@@ -3671,7 +3674,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0,
- nft_base_seq(net));
+ nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -3839,7 +3842,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
@@ -4050,7 +4053,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb,
buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
nla_len(nla[NFTA_RULE_TABLE]),
(char *)nla_data(nla[NFTA_RULE_TABLE]),
- nft_net->base_seq);
+ nft_base_seq(net));
audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC);
kfree(buf);
@@ -4887,7 +4890,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
nlh = nfnl_msg_put(skb, portid, seq,
nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
flags, ctx->family, NFNETLINK_V0,
- nft_base_seq(ctx->net));
+ nft_base_seq_be16(ctx->net));
if (!nlh)
goto nla_put_failure;
@@ -5032,7 +5035,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (ctx->family != NFPROTO_UNSPEC &&
@@ -6209,7 +6212,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
@@ -6238,7 +6241,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
seq = cb->nlh->nlmsg_seq;
nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI,
- table->family, NFNETLINK_V0, nft_base_seq(net));
+ table->family, NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -6331,7 +6334,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
- NFNETLINK_V0, nft_base_seq(ctx->net));
+ NFNETLINK_V0, nft_base_seq_be16(ctx->net));
if (!nlh)
goto nla_put_failure;
@@ -6630,7 +6633,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb,
}
nelems++;
}
- audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems);
+ audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems);
out_unlock:
rcu_read_unlock();
@@ -8381,7 +8384,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
nlh = nfnl_msg_put(skb, portid, seq,
nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
- flags, family, NFNETLINK_V0, nft_base_seq(net));
+ flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -8446,7 +8449,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
@@ -8480,7 +8483,7 @@ cont:
idx++;
}
if (ctx->reset && entries)
- audit_log_obj_reset(table, nft_net->base_seq, entries);
+ audit_log_obj_reset(table, nft_base_seq(net), entries);
if (rc < 0)
break;
}
@@ -8649,7 +8652,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb,
buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
nla_len(nla[NFTA_OBJ_TABLE]),
(char *)nla_data(nla[NFTA_OBJ_TABLE]),
- nft_net->base_seq);
+ nft_base_seq(net));
audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
kfree(buf);
@@ -8754,9 +8757,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
struct nft_object *obj, u32 portid, u32 seq, int event,
u16 flags, int family, int report, gfp_t gfp)
{
- struct nftables_pernet *nft_net = nft_pernet(net);
char *buf = kasprintf(gfp, "%s:%u",
- table->name, nft_net->base_seq);
+ table->name, nft_base_seq(net));
audit_log_nfcfg(buf,
family,
@@ -9442,7 +9444,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
nlh = nfnl_msg_put(skb, portid, seq,
nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
- flags, family, NFNETLINK_V0, nft_base_seq(net));
+ flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
@@ -9511,7 +9513,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
rcu_read_lock();
nft_net = nft_pernet(net);
- cb->seq = READ_ONCE(nft_net->base_seq);
+ cb->seq = nft_base_seq(net);
list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
@@ -9696,17 +9698,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq)
{
- struct nftables_pernet *nft_net = nft_pernet(net);
struct nlmsghdr *nlh;
char buf[TASK_COMM_LEN];
int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN);
nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC,
- NFNETLINK_V0, nft_base_seq(net));
+ NFNETLINK_V0, nft_base_seq_be16(net));
if (!nlh)
goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) ||
+ if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) ||
nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) ||
nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current)))
goto nla_put_failure;
@@ -10968,11 +10969,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
* Bump generation counter, invalidate any dump in progress.
* Cannot fail after this point.
*/
- base_seq = READ_ONCE(nft_net->base_seq);
+ base_seq = nft_base_seq(net);
while (++base_seq == 0)
;
- WRITE_ONCE(nft_net->base_seq, base_seq);
+ /* pairs with smp_load_acquire in nft_lookup_eval */
+ smp_store_release(&net->nft.base_seq, base_seq);
gc_seq = nft_gc_seq_begin(nft_net);
@@ -11181,7 +11183,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nft_commit_notify(net, NETLINK_CB(skb).portid);
nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
- nf_tables_commit_audit_log(&adl, nft_net->base_seq);
+ nf_tables_commit_audit_log(&adl, nft_base_seq(net));
nft_gc_seq_end(nft_net, gc_seq);
nft_net->validate_state = NFT_VALIDATE_SKIP;
@@ -11506,7 +11508,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
mutex_lock(&nft_net->commit_mutex);
nft_net->tstamp = get_jiffies_64();
- genid_ok = genid == 0 || nft_net->base_seq == genid;
+ genid_ok = genid == 0 || nft_base_seq(net) == genid;
if (!genid_ok)
mutex_unlock(&nft_net->commit_mutex);
@@ -12143,7 +12145,7 @@ static int __net_init nf_tables_init_net(struct net *net)
INIT_LIST_HEAD(&nft_net->module_list);
INIT_LIST_HEAD(&nft_net->notify_list);
mutex_init(&nft_net->commit_mutex);
- nft_net->base_seq = 1;
+ net->nft.base_seq = 1;
nft_net->gc_seq = 0;
nft_net->validate_state = NFT_VALIDATE_SKIP;
INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work);
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 40c602ffbcba..58c5b14889c4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -24,11 +24,11 @@ struct nft_lookup {
struct nft_set_binding binding;
};
-#ifdef CONFIG_MITIGATION_RETPOLINE
-const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
- const u32 *key)
+static const struct nft_set_ext *
+__nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+ const u32 *key)
{
+#ifdef CONFIG_MITIGATION_RETPOLINE
if (set->ops == &nft_set_hash_fast_type.ops)
return nft_hash_lookup_fast(net, set, key);
if (set->ops == &nft_set_hash_type.ops)
@@ -51,10 +51,46 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set,
return nft_rbtree_lookup(net, set, key);
WARN_ON_ONCE(1);
+#endif
return set->ops->lookup(net, set, key);
}
+
+static unsigned int nft_base_seq(const struct net *net)
+{
+ /* pairs with smp_store_release() in nf_tables_commit() */
+ return smp_load_acquire(&net->nft.base_seq);
+}
+
+static bool nft_lookup_should_retry(const struct net *net, unsigned int seq)
+{
+ return unlikely(seq != nft_base_seq(net));
+}
+
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+ const u32 *key)
+{
+ const struct nft_set_ext *ext;
+ unsigned int base_seq;
+
+ do {
+ base_seq = nft_base_seq(net);
+
+ ext = __nft_set_do_lookup(net, set, key);
+ if (ext)
+ break;
+ /* No match? There is a small chance that lookup was
+ * performed in the old generation, but nf_tables_commit()
+ * already unlinked a (matching) element.
+ *
+ * We need to repeat the lookup to make sure that we didn't
+ * miss a matching element in the new generation.
+ */
+ } while (nft_lookup_should_retry(net, base_seq));
+
+ return ext;
+}
EXPORT_SYMBOL_GPL(nft_set_do_lookup);
-#endif
void nft_lookup_eval(const struct nft_expr *expr,
struct nft_regs *regs,
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index c24c922f895d..8d3f040a904a 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
const struct nft_bitmap *priv = nft_set_priv(set);
struct nft_bitmap_elem *be;
- list_for_each_entry_rcu(be, &priv->list, head) {
+ list_for_each_entry_rcu(be, &priv->list, head,
+ lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) {
if (iter->count < iter->skip)
goto cont;
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 9a10251228fd..793790d79d13 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -510,6 +510,23 @@ out:
*
* This function is called from the data path. It will search for
* an element matching the given key in the current active copy.
+ * Unlike other set types, this uses NFT_GENMASK_ANY instead of
+ * nft_genmask_cur().
+ *
+ * This is because new (future) elements are not reachable from
+ * priv->match, they get added to priv->clone instead.
+ * When the commit phase flips the generation bitmask, the
+ * 'now old' entries are skipped but without the 'now current'
+ * elements becoming visible. Using nft_genmask_cur() thus creates
+ * inconsistent state: matching old entries get skipped but thew
+ * newly matching entries are unreachable.
+ *
+ * GENMASK will still find the 'now old' entries which ensures consistent
+ * priv->match view.
+ *
+ * nft_pipapo_commit swaps ->clone and ->match shortly after the
+ * genbit flip. As ->clone doesn't contain the old entries in the first
+ * place, lookup will only find the now-current ones.
*
* Return: ntables API extension pointer or NULL if no match.
*/
@@ -518,12 +535,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
const u32 *key)
{
struct nft_pipapo *priv = nft_set_priv(set);
- u8 genmask = nft_genmask_cur(net);
const struct nft_pipapo_match *m;
const struct nft_pipapo_elem *e;
m = rcu_dereference(priv->match);
- e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64());
+ e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64());
return e ? &e->ext : NULL;
}
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 2f090e253caf..c0884fa68c79 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1152,7 +1152,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
struct nft_pipapo *priv = nft_set_priv(set);
const struct nft_set_ext *ext = NULL;
struct nft_pipapo_scratch *scratch;
- u8 genmask = nft_genmask_cur(net);
const struct nft_pipapo_match *m;
const struct nft_pipapo_field *f;
const u8 *rp = (const u8 *)key;
@@ -1248,8 +1247,7 @@ next_match:
if (last) {
const struct nft_set_ext *e = &f->mt[ret].e->ext;
- if (unlikely(nft_set_elem_expired(e) ||
- !nft_set_elem_active(e, genmask)))
+ if (unlikely(nft_set_elem_expired(e)))
goto next_match;
ext = e;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 938a257c069e..b1f04168ec93 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_start(interval))
continue;
- interval = rbe;
+ if (nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_rbtree_elem_expired(rbe))
+ interval = rbe;
} else if (d > 0)
parent = rcu_dereference_raw(parent->rb_right);
else {
@@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
}
if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
- nft_set_elem_active(&interval->ext, genmask) &&
- !nft_rbtree_elem_expired(interval) &&
nft_rbtree_interval_start(interval))
return &interval->ext;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 104732d34543..978c129c6095 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group)
!ns_capable(net->user_ns, CAP_SYS_ADMIN))
ret = -EPERM;
+ if (ret)
+ break;
+
if (family->bind)
family->bind(i);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 73bc39281ef5..9b45fbdc90ca 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
{
- if (unlikely(current->flags & PF_EXITING))
- return -EINTR;
schedule();
if (signal_pending_state(mode, current))
return -ERESTARTSYS;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c5f7bbf5775f..3aa987e7f072 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
alert_kvec.iov_len);
ret = sock_recvmsg(sock, &msg, flags);
- if (ret > 0 &&
- tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
- iov_iter_revert(&msg.msg_iter, ret);
+ if (ret > 0) {
+ if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT)
+ iov_iter_revert(&msg.msg_iter, ret);
ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
-EAGAIN);
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f2f7424e930c..852573423e52 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7575,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
rdev, wdev->netdev, mac_addr,
- &sinfo, true) < 0)
+ &sinfo, false) < 0)
goto out;
sta_idx++;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9c3acecc14b1..72e34bd2d925 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,6 +36,20 @@
#define TX_BATCH_SIZE 32
#define MAX_PER_SOCKET_BUDGET 32
+struct xsk_addr_node {
+ u64 addr;
+ struct list_head addr_node;
+};
+
+struct xsk_addr_head {
+ u32 num_descs;
+ struct list_head addrs_list;
+};
+
+static struct kmem_cache *xsk_tx_generic_cache;
+
+#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb))
+
void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
}
-static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr)
+static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&pool->cq_lock, flags);
- ret = xskq_prod_reserve_addr(pool->cq, addr);
+ ret = xskq_prod_reserve(pool->cq);
spin_unlock_irqrestore(&pool->cq_lock, flags);
return ret;
}
-static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n)
+static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
+ struct sk_buff *skb)
{
+ struct xsk_addr_node *pos, *tmp;
+ u32 descs_processed = 0;
unsigned long flags;
+ u32 idx;
spin_lock_irqsave(&pool->cq_lock, flags);
- xskq_prod_submit_n(pool->cq, n);
+ idx = xskq_get_prod(pool->cq);
+
+ xskq_prod_write_addr(pool->cq, idx,
+ (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg);
+ descs_processed++;
+
+ if (unlikely(XSKCB(skb)->num_descs > 1)) {
+ list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+ xskq_prod_write_addr(pool->cq, idx + descs_processed,
+ pos->addr);
+ descs_processed++;
+ list_del(&pos->addr_node);
+ kmem_cache_free(xsk_tx_generic_cache, pos);
+ }
+ }
+ xskq_prod_submit_n(pool->cq, descs_processed);
spin_unlock_irqrestore(&pool->cq_lock, flags);
}
@@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
spin_unlock_irqrestore(&pool->cq_lock, flags);
}
+static void xsk_inc_num_desc(struct sk_buff *skb)
+{
+ XSKCB(skb)->num_descs++;
+}
+
static u32 xsk_get_num_desc(struct sk_buff *skb)
{
- return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+ return XSKCB(skb)->num_descs;
}
static void xsk_destruct_skb(struct sk_buff *skb)
@@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb)
*compl->tx_timestamp = ktime_get_tai_fast_ns();
}
- xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb));
+ xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb);
sock_wfree(skb);
}
-static void xsk_set_destructor_arg(struct sk_buff *skb)
+static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr)
{
- long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
-
- skb_shinfo(skb)->destructor_arg = (void *)num;
+ BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb));
+ INIT_LIST_HEAD(&XSKCB(skb)->addrs_list);
+ XSKCB(skb)->num_descs = 0;
+ skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr;
}
static void xsk_consume_skb(struct sk_buff *skb)
{
struct xdp_sock *xs = xdp_sk(skb->sk);
+ u32 num_descs = xsk_get_num_desc(skb);
+ struct xsk_addr_node *pos, *tmp;
+
+ if (unlikely(num_descs > 1)) {
+ list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+ list_del(&pos->addr_node);
+ kmem_cache_free(xsk_tx_generic_cache, pos);
+ }
+ }
skb->destructor = sock_wfree;
- xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb));
+ xsk_cq_cancel_locked(xs->pool, num_descs);
/* Free skb without triggering the perf drop trace */
consume_skb(skb);
xs->skb = NULL;
@@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
{
struct xsk_buff_pool *pool = xs->pool;
u32 hr, len, ts, offset, copy, copied;
+ struct xsk_addr_node *xsk_addr;
struct sk_buff *skb = xs->skb;
struct page *page;
void *buffer;
@@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
return ERR_PTR(err);
skb_reserve(skb, hr);
+
+ xsk_set_destructor_arg(skb, desc->addr);
+ } else {
+ xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+ if (!xsk_addr)
+ return ERR_PTR(-ENOMEM);
+
+ /* in case of -EOVERFLOW that could happen below,
+ * xsk_consume_skb() will release this node as whole skb
+ * would be dropped, which implies freeing all list elements
+ */
+ xsk_addr->addr = desc->addr;
+ list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
}
addr = desc->addr;
@@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
err = skb_store_bits(skb, 0, buffer, len);
if (unlikely(err))
goto free_err;
+
+ xsk_set_destructor_arg(skb, desc->addr);
} else {
int nr_frags = skb_shinfo(skb)->nr_frags;
+ struct xsk_addr_node *xsk_addr;
struct page *page;
u8 *vaddr;
@@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
goto free_err;
}
+ xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+ if (!xsk_addr) {
+ __free_page(page);
+ err = -ENOMEM;
+ goto free_err;
+ }
+
vaddr = kmap_local_page(page);
memcpy(vaddr, buffer, len);
kunmap_local(vaddr);
skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
+
+ xsk_addr->addr = desc->addr;
+ list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
}
if (first_frag && desc->options & XDP_TX_METADATA) {
@@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
skb->mark = READ_ONCE(xs->sk.sk_mark);
skb->destructor = xsk_destruct_skb;
xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
- xsk_set_destructor_arg(skb);
+ xsk_inc_num_desc(skb);
return skb;
@@ -769,7 +844,7 @@ free_err:
if (err == -EOVERFLOW) {
/* Drop the packet */
- xsk_set_destructor_arg(xs->skb);
+ xsk_inc_num_desc(xs->skb);
xsk_drop_skb(xs->skb);
xskq_cons_release(xs->tx);
} else {
@@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk)
* if there is space in it. This avoids having to implement
* any buffering in the Tx path.
*/
- err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
+ err = xsk_cq_reserve_locked(xs->pool);
if (err) {
err = -EAGAIN;
goto out;
@@ -1815,8 +1890,18 @@ static int __init xsk_init(void)
if (err)
goto out_pernet;
+ xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache",
+ sizeof(struct xsk_addr_node),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!xsk_tx_generic_cache) {
+ err = -ENOMEM;
+ goto out_unreg_notif;
+ }
+
return 0;
+out_unreg_notif:
+ unregister_netdevice_notifier(&xsk_netdev_notifier);
out_pernet:
unregister_pernet_subsys(&xsk_net_ops);
out_sk:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 46d87e961ad6..f16f390370dc 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
/* Functions for producers */
+static inline u32 xskq_get_prod(struct xsk_queue *q)
+{
+ return READ_ONCE(q->ring->producer);
+}
+
static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
{
u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
@@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
return 0;
}
+static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr)
+{
+ struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+ ring->desc[idx & q->ring_mask] = addr;
+}
+
static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
u32 nb_entries)
{
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index ed53169e795c..fef97f2a5098 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -296,7 +296,7 @@ macro_rules! asm {
/// Gets the C string file name of a [`Location`].
///
-/// If `file_with_nul()` is not available, returns a string that warns about it.
+/// If `Location::file_as_c_str()` is not available, returns a string that warns about it.
///
/// [`Location`]: core::panic::Location
///
@@ -310,8 +310,8 @@ macro_rules! asm {
/// let caller = core::panic::Location::caller();
///
/// // Output:
-/// // - A path like "rust/kernel/example.rs" if file_with_nul() is available.
-/// // - "<Location::file_with_nul() not supported>" otherwise.
+/// // - A path like "rust/kernel/example.rs" if `file_as_c_str()` is available.
+/// // - "<Location::file_as_c_str() not supported>" otherwise.
/// let caller_file = file_from_location(caller);
///
/// // Prints out the message with caller's file name.
@@ -326,7 +326,12 @@ macro_rules! asm {
/// ```
#[inline]
pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::ffi::CStr {
- #[cfg(CONFIG_RUSTC_HAS_FILE_WITH_NUL)]
+ #[cfg(CONFIG_RUSTC_HAS_FILE_AS_C_STR)]
+ {
+ loc.file_as_c_str()
+ }
+
+ #[cfg(all(CONFIG_RUSTC_HAS_FILE_WITH_NUL, not(CONFIG_RUSTC_HAS_FILE_AS_C_STR)))]
{
loc.file_with_nul()
}
@@ -334,6 +339,6 @@ pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::f
#[cfg(not(CONFIG_RUSTC_HAS_FILE_WITH_NUL))]
{
let _ = loc;
- c"<Location::file_with_nul() not supported>"
+ c"<Location::file_as_c_str() not supported>"
}
}
diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index cfea7a38befb..da3a9f2091f5 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -75,8 +75,8 @@ asm (
CALL_DEPTH_ACCOUNT
" call my_direct_func1\n"
" leave\n"
-" .size my_tramp1, .-my_tramp1\n"
ASM_RET
+" .size my_tramp1, .-my_tramp1\n"
" .type my_tramp2, @function\n"
" .globl my_tramp2\n"
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 39c82908ff3a..38b3416bb979 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -225,7 +225,11 @@ fn main() {
ts.push("features", features);
ts.push("llvm-target", "x86_64-linux-gnu");
ts.push("supported-sanitizers", ["kcfi", "kernel-address"]);
- ts.push("target-pointer-width", "64");
+ if cfg.rustc_version_atleast(1, 91, 0) {
+ ts.push("target-pointer-width", 64);
+ } else {
+ ts.push("target-pointer-width", "64");
+ }
} else if cfg.has("X86_32") {
// This only works on UML, as i386 otherwise needs regparm support in rustc
if !cfg.has("UML") {
@@ -245,7 +249,11 @@ fn main() {
}
ts.push("features", features);
ts.push("llvm-target", "i386-unknown-linux-gnu");
- ts.push("target-pointer-width", "32");
+ if cfg.rustc_version_atleast(1, 91, 0) {
+ ts.push("target-pointer-width", 32);
+ } else {
+ ts.push("target-pointer-width", "32");
+ }
} else if cfg.has("LOONGARCH") {
panic!("loongarch uses the builtin rustc loongarch64-unknown-none-softfloat target");
} else {
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index ed565eb52275..342e056c8c66 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -77,7 +77,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN)
clean:
rm -f $(ALL_PROGRAMS)
- rm -f $(OUTPUT)include/linux/gpio.h
+ rm -rf $(OUTPUT)include
find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
install: $(ALL_PROGRAMS)
diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c
index 30c7da79e109..8b31d1d05f90 100644
--- a/tools/perf/tests/pe-file-parsing.c
+++ b/tools/perf/tests/pe-file-parsing.c
@@ -37,7 +37,7 @@ static int run_dir(const char *d)
size_t idx;
scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d);
- ret = filename__read_build_id(filename, &bid);
+ ret = filename__read_build_id(filename, &bid, /*block=*/true);
TEST_ASSERT_VAL("Failed to read build_id",
ret == sizeof(expect_build_id));
TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,
@@ -49,7 +49,7 @@ static int run_dir(const char *d)
!strcmp(debuglink, expect_debuglink));
scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink);
- ret = filename__read_build_id(debugfile, &bid);
+ ret = filename__read_build_id(debugfile, &bid, /*block=*/true);
TEST_ASSERT_VAL("Failed to read debug file build_id",
ret == sizeof(expect_build_id));
TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,
diff --git a/tools/perf/tests/shell/test_bpf_metadata.sh b/tools/perf/tests/shell/test_bpf_metadata.sh
index 69e3c2055134..be67d56e0f09 100755
--- a/tools/perf/tests/shell/test_bpf_metadata.sh
+++ b/tools/perf/tests/shell/test_bpf_metadata.sh
@@ -61,7 +61,7 @@ test_bpf_metadata() {
/perf_version/ {
if (entry) print $NF;
}
- ' | egrep "$VERS" > /dev/null
+ ' | grep -qF "$VERS"
then
echo "Basic BPF metadata test [Failed invalid output]"
err=1
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 5b6d3e899e11..2298cd396c42 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -657,9 +657,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
info_node->info_linear = info_linear;
info_node->metadata = NULL;
if (!perf_env__insert_bpf_prog_info(env, info_node)) {
- free(info_linear);
+ /*
+ * Insert failed, likely because of a duplicate event
+ * made by the sideband thread. Ignore synthesizing the
+ * metadata.
+ */
free(info_node);
+ goto out;
}
+ /* info_linear is now owned by info_node and shouldn't be freed below. */
info_linear = NULL;
/*
@@ -827,18 +833,18 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
return err;
}
-static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+static int perf_env__add_bpf_info(struct perf_env *env, u32 id)
{
struct bpf_prog_info_node *info_node;
struct perf_bpil *info_linear;
struct btf *btf = NULL;
u64 arrays;
u32 btf_id;
- int fd;
+ int fd, err = 0;
fd = bpf_prog_get_fd_by_id(id);
if (fd < 0)
- return;
+ return -EINVAL;
arrays = 1UL << PERF_BPIL_JITED_KSYMS;
arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS;
@@ -852,6 +858,7 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
info_linear = get_bpf_prog_info_linear(fd, arrays);
if (IS_ERR_OR_NULL(info_linear)) {
pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+ err = PTR_ERR(info_linear);
goto out;
}
@@ -862,38 +869,46 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
info_node->info_linear = info_linear;
info_node->metadata = bpf_metadata_create(&info_linear->info);
if (!perf_env__insert_bpf_prog_info(env, info_node)) {
+ pr_debug("%s: duplicate add bpf info request for id %u\n",
+ __func__, btf_id);
free(info_linear);
free(info_node);
+ goto out;
}
- } else
+ } else {
free(info_linear);
+ err = -ENOMEM;
+ goto out;
+ }
if (btf_id == 0)
goto out;
btf = btf__load_from_kernel_by_id(btf_id);
- if (libbpf_get_error(btf)) {
- pr_debug("%s: failed to get BTF of id %u, aborting\n",
- __func__, btf_id);
- goto out;
+ if (!btf) {
+ err = -errno;
+ pr_debug("%s: failed to get BTF of id %u %d\n", __func__, btf_id, err);
+ } else {
+ perf_env__fetch_btf(env, btf_id, btf);
}
- perf_env__fetch_btf(env, btf_id, btf);
out:
btf__free(btf);
close(fd);
+ return err;
}
static int bpf_event__sb_cb(union perf_event *event, void *data)
{
struct perf_env *env = data;
+ int ret = 0;
if (event->header.type != PERF_RECORD_BPF_EVENT)
return -1;
switch (event->bpf.type) {
case PERF_BPF_EVENT_PROG_LOAD:
- perf_env__add_bpf_info(env, event->bpf.id);
+ ret = perf_env__add_bpf_info(env, event->bpf.id);
case PERF_BPF_EVENT_PROG_UNLOAD:
/*
@@ -907,7 +922,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
break;
}
- return 0;
+ return ret;
}
int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index 80b1d2b3729b..5a66dc8594aa 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -20,7 +20,7 @@ struct bpil_array_desc {
*/
};
-static struct bpil_array_desc bpil_array_desc[] = {
+static const struct bpil_array_desc bpil_array_desc[] = {
[PERF_BPIL_JITED_INSNS] = {
offsetof(struct bpf_prog_info, jited_prog_insns),
offsetof(struct bpf_prog_info, jited_prog_len),
@@ -115,7 +115,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
__u32 info_len = sizeof(info);
__u32 data_len = 0;
int i, err;
- void *ptr;
+ __u8 *ptr;
if (arrays >> PERF_BPIL_LAST_ARRAY)
return ERR_PTR(-EINVAL);
@@ -126,15 +126,15 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
pr_debug("can't get prog info: %s", strerror(errno));
return ERR_PTR(-EFAULT);
}
+ if (info.type >= __MAX_BPF_PROG_TYPE)
+ pr_debug("%s:%d: unexpected program type %u\n", __func__, __LINE__, info.type);
/* step 2: calculate total size of all arrays */
for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
+ const struct bpil_array_desc *desc = &bpil_array_desc[i];
bool include_array = (arrays & (1UL << i)) > 0;
- struct bpil_array_desc *desc;
__u32 count, size;
- desc = bpil_array_desc + i;
-
/* kernel is too old to support this field */
if (info_len < desc->array_offset + sizeof(__u32) ||
info_len < desc->count_offset + sizeof(__u32) ||
@@ -163,19 +163,20 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
ptr = info_linear->data;
for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
- struct bpil_array_desc *desc;
+ const struct bpil_array_desc *desc = &bpil_array_desc[i];
__u32 count, size;
if ((arrays & (1UL << i)) == 0)
continue;
- desc = bpil_array_desc + i;
count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
size = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
bpf_prog_info_set_offset_u32(&info_linear->info,
desc->count_offset, count);
bpf_prog_info_set_offset_u32(&info_linear->info,
desc->size_offset, size);
+ assert(ptr >= info_linear->data);
+ assert(ptr < &info_linear->data[data_len]);
bpf_prog_info_set_offset_u64(&info_linear->info,
desc->array_offset,
ptr_to_u64(ptr));
@@ -189,27 +190,45 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
free(info_linear);
return ERR_PTR(-EFAULT);
}
+ if (info_linear->info.type >= __MAX_BPF_PROG_TYPE) {
+ pr_debug("%s:%d: unexpected program type %u\n",
+ __func__, __LINE__, info_linear->info.type);
+ }
/* step 6: verify the data */
+ ptr = info_linear->data;
for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
- struct bpil_array_desc *desc;
- __u32 v1, v2;
+ const struct bpil_array_desc *desc = &bpil_array_desc[i];
+ __u32 count1, count2, size1, size2;
+ __u64 ptr2;
if ((arrays & (1UL << i)) == 0)
continue;
- desc = bpil_array_desc + i;
- v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
- v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ count1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+ count2 = bpf_prog_info_read_offset_u32(&info_linear->info,
desc->count_offset);
- if (v1 != v2)
- pr_warning("%s: mismatch in element count\n", __func__);
+ if (count1 != count2) {
+ pr_warning("%s: mismatch in element count %u vs %u\n", __func__, count1, count2);
+ free(info_linear);
+ return ERR_PTR(-ERANGE);
+ }
- v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
- v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+ size1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+ size2 = bpf_prog_info_read_offset_u32(&info_linear->info,
desc->size_offset);
- if (v1 != v2)
- pr_warning("%s: mismatch in rec size\n", __func__);
+ if (size1 != size2) {
+ pr_warning("%s: mismatch in rec size %u vs %u\n", __func__, size1, size2);
+ free(info_linear);
+ return ERR_PTR(-ERANGE);
+ }
+ ptr2 = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset);
+ if (ptr_to_u64(ptr) != ptr2) {
+ pr_warning("%s: mismatch in array %p vs %llx\n", __func__, ptr, ptr2);
+ free(info_linear);
+ return ERR_PTR(-ERANGE);
+ }
+ ptr += roundup(count1 * size1, sizeof(__u64));
}
/* step 7: update info_len and data_len */
@@ -224,13 +243,12 @@ void bpil_addr_to_offs(struct perf_bpil *info_linear)
int i;
for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
- struct bpil_array_desc *desc;
+ const struct bpil_array_desc *desc = &bpil_array_desc[i];
__u64 addr, offs;
if ((info_linear->arrays & (1UL << i)) == 0)
continue;
- desc = bpil_array_desc + i;
addr = bpf_prog_info_read_offset_u64(&info_linear->info,
desc->array_offset);
offs = addr - ptr_to_u64(info_linear->data);
@@ -244,13 +262,12 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear)
int i;
for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
- struct bpil_array_desc *desc;
+ const struct bpil_array_desc *desc = &bpil_array_desc[i];
__u64 addr, offs;
if ((info_linear->arrays & (1UL << i)) == 0)
continue;
- desc = bpil_array_desc + i;
offs = bpf_prog_info_read_offset_u64(&info_linear->info,
desc->array_offset);
addr = offs + ptr_to_u64(info_linear->data);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 033c79231a54..1346fd180653 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -873,13 +873,17 @@ out:
#ifdef HAVE_LIBBFD_BUILDID_SUPPORT
-static int read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid, bool block)
{
size_t size = sizeof(bid->data);
- int err = -1;
+ int err = -1, fd;
bfd *abfd;
- abfd = bfd_openr(filename, NULL);
+ fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
+ if (fd < 0)
+ return -1;
+
+ abfd = bfd_fdopenr(filename, /*target=*/NULL, fd);
if (!abfd)
return -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
index b7b77a6b2979..0de8facca4c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/free_timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -124,6 +124,10 @@ void test_free_timer(void)
int err;
skel = free_timer__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "open_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index d66687f1ee6a..56f660ca567b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -86,6 +86,10 @@ void serial_test_timer(void)
int err;
timer_skel = timer__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
struct timer_crash *skel;
skel = timer_crash__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
return;
skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
index 1a2f99596916..eb303fa1e09a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -59,6 +59,10 @@ void test_timer_lockup(void)
}
skel = timer_lockup__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
goto cleanup;
timer_skel = timer_mim__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
index d67466c1ff77..f90531cf3ee5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
+++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
@@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val
* barriers.
*/
if (val & _Q_LOCKED_MASK)
- smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+ (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
/*
* take ownership and clear the pending bit.
@@ -380,7 +380,7 @@ queue:
/* Link @node into the waitqueue. */
WRITE_ONCE(prev->next, node);
- arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+ (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
/*
* While waiting for the MCS lock, the next pointer may have
diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
index 645be6cddf36..dfd8a258f14a 100644
--- a/tools/testing/selftests/bpf/progs/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -14,7 +14,7 @@ unsigned char key[256] = {};
u16 udp_test_port = 7777;
u32 authsize, key_len;
char algo[128] = {};
-char dst[16] = {};
+char dst[16] = {}, dst_bad[8] = {};
int status;
static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc)
@@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx)
.authsize = authsize,
};
struct bpf_crypto_ctx *cctx;
- int err = 0;
+ int err;
status = 0;
-
if (key_len > 256) {
status = -EINVAL;
return 0;
@@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx)
__builtin_memcpy(&params.algo, algo, sizeof(algo));
__builtin_memcpy(&params.key, key, sizeof(key));
- cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+ cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
if (!cctx) {
status = err;
return 0;
@@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx)
err = crypto_ctx_insert(cctx);
if (err && err != -EEXIST)
status = err;
-
return 0;
}
@@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb)
struct bpf_dynptr psrc, pdst;
int err;
+ status = 0;
err = skb_dynptr_validate(skb, &psrc);
if (err < 0) {
status = err;
@@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- /* dst is a global variable to make testing part easier to check. In real
- * production code, a percpu map should be used to store the result.
+ /* Check also bad case where the dst buffer is smaller than the
+ * skb's linear section.
+ */
+ bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+ status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+ if (!status)
+ status = -EIO;
+ if (status != -EINVAL)
+ goto err;
+
+ /* dst is a global variable to make testing part easier to check.
+ * In real production code, a percpu map should be used to store
+ * the result.
*/
bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
-
+err:
return TC_ACT_SHOT;
}
@@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb)
int err;
status = 0;
-
err = skb_dynptr_validate(skb, &psrc);
if (err < 0) {
status = err;
@@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb)
return TC_ACT_SHOT;
}
- /* dst is a global variable to make testing part easier to check. In real
- * production code, a percpu map should be used to store the result.
+ /* Check also bad case where the dst buffer is smaller than the
+ * skb's linear section.
+ */
+ bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+ status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+ if (!status)
+ status = -EIO;
+ if (status != -EINVAL)
+ goto err;
+
+ /* dst is a global variable to make testing part easier to check.
+ * In real production code, a percpu map should be used to store
+ * the result.
*/
bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
-
+err:
return TC_ACT_SHOT;
}
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index 6438982b928b..ddd26d1a083f 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx)
SEC("?tc")
int obj_new_no_struct(void *ctx)
{
-
- bpf_obj_new(union { int data; unsigned udata; });
+ (void)bpf_obj_new(union { int data; unsigned udata; });
return 0;
}
@@ -252,7 +251,7 @@ int new_null_ret(void *ctx)
SEC("?tc")
int obj_new_acq(void *ctx)
{
- bpf_obj_new(struct foo);
+ (void)bpf_obj_new(struct foo);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
index 46697f381878..a47690174e0e 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
__test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
__test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
__test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
-__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); }
-__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); }
+__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); }
+__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); }
+__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); }
__test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 63ce708d93ed..e4b7c2b457ee 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -2,6 +2,13 @@
// Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
#define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
#include <fcntl.h>
#include <sched.h>
#include <stdio.h>
@@ -10,20 +17,12 @@
#include <sys/mount.h>
#include <unistd.h>
#include <sys/syscall.h>
+#include <sys/fanotify.h>
#include "../../kselftest_harness.h"
#include "../statmount/statmount.h"
#include "../utils.h"
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
static const int mark_cmds[] = {
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
index 090a5ca65004..9f57ca46e3af 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
@@ -2,6 +2,13 @@
// Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
#define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
#include <fcntl.h>
#include <sched.h>
#include <stdio.h>
@@ -10,21 +17,12 @@
#include <sys/mount.h>
#include <unistd.h>
#include <sys/syscall.h>
+#include <sys/fanotify.h>
#include "../../kselftest_harness.h"
-#include "../../pidfd/pidfd.h"
#include "../statmount/statmount.h"
#include "../utils.h"
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
- int val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
static const int mark_types[] = {
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c7e03e1d6f63..2b31d4a93ad7 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -116,6 +116,7 @@ TEST_PROGS += skf_net_off.sh
TEST_GEN_FILES += skf_net_off
TEST_GEN_FILES += tfo
TEST_PROGS += tfo_passive.sh
+TEST_PROGS += broadcast_ether_dst.sh
TEST_PROGS += broadcast_pmtu.sh
TEST_PROGS += ipv6_force_forwarding.sh
diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh
new file mode 100755
index 000000000000..334a7eca8a80
--- /dev/null
+++ b/tools/testing/selftests/net/broadcast_ether_dst.sh
@@ -0,0 +1,83 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Author: Brett A C Sheffield <bacs@librecast.net>
+# Author: Oscar Maes <oscmaes92@gmail.com>
+#
+# Ensure destination ethernet field is correctly set for
+# broadcast packets
+
+source lib.sh
+
+CLIENT_IP4="192.168.0.1"
+GW_IP4="192.168.0.2"
+
+setup() {
+ setup_ns CLIENT_NS SERVER_NS
+
+ ip -net "${SERVER_NS}" link add link1 type veth \
+ peer name link0 netns "${CLIENT_NS}"
+
+ ip -net "${CLIENT_NS}" link set link0 up
+ ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0
+
+ ip -net "${SERVER_NS}" link set link1 up
+
+ ip -net "${CLIENT_NS}" route add default via "${GW_IP4}"
+ ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55
+}
+
+cleanup() {
+ rm -f "${CAPFILE}" "${OUTPUT}"
+ ip -net "${SERVER_NS}" link del link1
+ cleanup_ns "${CLIENT_NS}" "${SERVER_NS}"
+}
+
+test_broadcast_ether_dst() {
+ local rc=0
+ CAPFILE=$(mktemp -u cap.XXXXXXXXXX)
+ OUTPUT=$(mktemp -u out.XXXXXXXXXX)
+
+ echo "Testing ethernet broadcast destination"
+
+ # start tcpdump listening for icmp
+ # tcpdump will exit after receiving a single packet
+ # timeout will kill tcpdump if it is still running after 2s
+ timeout 2s ip netns exec "${CLIENT_NS}" \
+ tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" &
+ pid=$!
+ slowwait 1 grep -qs "listening" "${OUTPUT}"
+
+ # send broadcast ping
+ ip netns exec "${CLIENT_NS}" \
+ ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null
+
+ # wait for tcpdump for exit after receiving packet
+ wait "${pid}"
+
+ # compare ethernet destination field to ff:ff:ff:ff:ff:ff
+ ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \
+ awk '{sub(/,/,"",$3); print $3}')
+ if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then
+ echo "[ OK ]"
+ rc="${ksft_pass}"
+ else
+ echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \
+ "got ${ether_dst}"
+ rc="${ksft_fail}"
+ fi
+
+ return "${rc}"
+}
+
+if [ ! -x "$(command -v tcpdump)" ]; then
+ echo "SKIP: Could not run test without tcpdump tool"
+ exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+setup
+test_broadcast_ether_dst
+
+exit $?
diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config
new file mode 100644
index 000000000000..188f79796670
--- /dev/null
+++ b/tools/testing/selftests/net/can/config
@@ -0,0 +1,3 @@
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VCAN=m
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 7a3cb4c09e45..d847ff1737c3 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -28,7 +28,7 @@ flush_pids()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 5e3c56253274..c2ab9f7f0d21 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -134,7 +134,7 @@ ns4=""
TEST_GROUP=""
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "$cin_disconnect"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 82cae37d9c20..7fd555b123b9 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,7 +8,7 @@
# ShellCheck incorrectly believes that most of the code here is unreachable
# because it's invoked by variable name, see how the "tests" array is used
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
. "$(dirname "${0}")/mptcp_lib.sh"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 418a903c3a4d..f01989be6e9b 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -95,7 +95,7 @@ init()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}"
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index ac7ec6f94023..ec6a87588191 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -32,7 +32,7 @@ ns1=""
err=$(mktemp)
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "${err}"
@@ -70,8 +70,9 @@ format_endpoints() {
mptcp_lib_pm_nl_format_endpoints "${@}"
}
+# This function is invoked indirectly
+#shellcheck disable=SC2317,SC2329
get_endpoint() {
- # shellcheck disable=SC2317 # invoked indirectly
mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}"
}
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 2329c2f8519b..1903e8e84a31 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -35,7 +35,7 @@ usage() {
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
rm -f "$cout" "$sout"
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 333064b0b5ac..970c329735ff 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -94,7 +94,7 @@ test_fail()
}
# This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
cleanup()
{
print_title "Cleanup"