diff --git a/.mailmap b/.mailmap index b78aa092b4bb..eec4a740f7ca 100644 --- a/.mailmap +++ b/.mailmap @@ -682,6 +682,7 @@ Peter A Jonsson Peter Hilber Peter Oruba Peter Oruba +Peter Rosin Pierre-Louis Bossart Pratyush Anand Pratyush Yadav diff --git a/Documentation/ABI/obsolete/sysfs-selinux-user b/Documentation/ABI/removed/sysfs-selinux-user similarity index 100% rename from Documentation/ABI/obsolete/sysfs-selinux-user rename to Documentation/ABI/removed/sysfs-selinux-user diff --git a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml index c4cc8af18280..7b59b60b62e5 100644 --- a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml @@ -16,10 +16,15 @@ allOf: properties: compatible: - enum: - - amlogic,meson6-i2c # Meson6, Meson8 and compatible SoCs - - amlogic,meson-gxbb-i2c # GXBB and compatible SoCs - - amlogic,meson-axg-i2c # AXG and compatible SoCs + oneOf: + - items: + - enum: + - amlogic,t7-i2c + - const: amlogic,meson-axg-i2c + - enum: + - amlogic,meson6-i2c # Meson6, Meson8 and compatible SoCs + - amlogic,meson-gxbb-i2c # GXBB and compatible SoCs + - amlogic,meson-axg-i2c # AXG and compatible SoCs reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml index 500a965bdb7a..9e59200ad37b 100644 --- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -22,7 +22,9 @@ properties: compatible: oneOf: - items: - - const: apple,t6020-i2c + - enum: + - apple,t6020-i2c + - apple,t8122-i2c - const: apple,t8103-i2c - items: - enum: diff --git a/Documentation/hwmon/yogafan.rst b/Documentation/hwmon/yogafan.rst index c553a381f772..68761947a1a8 100644 --- a/Documentation/hwmon/yogafan.rst +++ b/Documentation/hwmon/yogafan.rst @@ -135,4 +135,4 @@ References 4. **Lenovo IdeaPad Laptop Driver:** Reference for DMI-based hardware feature gating in Lenovo laptops. - https://github.com/torvalds/linux/blob/master/drivers/platform/x86/ideapad-laptop.c + https://github.com/torvalds/linux/blob/master/drivers/platform/x86/lenovo/ideapad-laptop.c diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 57f59fe23e3f..4ea31e8fc4d1 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -69,6 +69,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags ] doc: diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 66fb8653a344..f9c44747729a 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -83,6 +83,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags, struct ] # Trim doc: diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index a1194d5d93fc..d3f3f3399ddf 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -55,6 +55,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags ] doc: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index dd98dda55bd0..4c436b59a34b 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -87,6 +87,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags, struct ] # Trim doc: diff --git a/Documentation/netlink/specs/net_shaper.yaml b/Documentation/netlink/specs/net_shaper.yaml index 3f2ad772b64b..de01f922040a 100644 --- a/Documentation/netlink/specs/net_shaper.yaml +++ b/Documentation/netlink/specs/net_shaper.yaml @@ -33,6 +33,11 @@ doc: | @cap-get operation. definitions: + - + type: const + name: max-handle-id + value: 0x3fffffe + scope: kernel - type: enum name: scope @@ -140,6 +145,8 @@ attribute-sets: - name: id type: u32 + checks: + max: max-handle-id doc: | Numeric identifier of a shaper. The id semantic depends on the scope. For @queue scope it's the queue id and for @node diff --git a/Documentation/userspace-api/rseq.rst b/Documentation/userspace-api/rseq.rst index 3cd27a3c7c7e..8549a6c61531 100644 --- a/Documentation/userspace-api/rseq.rst +++ b/Documentation/userspace-api/rseq.rst @@ -24,6 +24,97 @@ Quick access to CPU number, node ID Allows to implement per CPU data efficiently. Documentation is in code and selftests. :( +Optimized RSEQ V2 +----------------- + +On architectures which utilize the generic entry code and generic TIF bits +the kernel supports runtime optimizations for RSEQ, which also enable +enhanced features like scheduler time slice extensions. + +To enable them a task has to register the RSEQ region with at least the +length advertised by getauxval(AT_RSEQ_FEATURE_SIZE). + +If existing binaries register with RSEQ_ORIG_SIZE (32 bytes), the kernel +keeps the legacy low performance mode enabled to fulfil the expectations +of existing users regarding the original RSEQ implementation behaviour. + +The following table documents the ABI and behavioral guarantees of the +legacy and the optimized V2 mode. + +.. list-table:: RSEQ modes + :header-rows: 1 + + * - Nr + - What + + - Legacy + - Optimized V2 + + * - 1 + - The cpu_id_start, cpu_id, node_id and mm_cid fields (User mode read + only) + .. Legacy + - Updated by the kernel unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Updated by the kernel if and only if they change, i.e. if the task + is migrated or mm_cid changes + + * - 2 + - The rseq_cs critical section field + .. Legacy + - Evaluated and handled unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Evaluated and handled conditionally only when user space was + interrupted and was scheduled out or before delivering a signal in + the interrupted context. + + * - 3 + - Read only fields + .. Legacy + - No strict enforcement except in debug mode + .. Optimized V2 + - Strict enforcement + + * - 4 + - membarrier(...RSEQ) + .. Legacy + - All running threads of the process are interrupted and the ID fields + are rewritten and eventually active critical sections are aborted + before they return to user space. All threads which are scheduled + out whether voluntary or not are covered by #1/#2 above. + .. Optimized V2 + - All running threads of the process are interrupted and eventually + active critical sections are aborted before these threads return to + user space. The ID fields are only updated if changed as a + consequence of the interrupt. All threads which are scheduled out + whether voluntary or not are covered by #1/#2 above. + + * - 5 + - Time slice extensions + .. Legacy + - Not supported + .. Optimized V2 + - Supported + +The legacy mode is obviously less performant as it does unconditional +updates and critical section checks even if not strictly required by the +ABI contract. That can't be changed anymore as some users depend on that +observed behavior, which in turn enables them to violate the ABI and +overwrite the cpu_id_start field for their own purposes. This is obviously +discouraged as it renders RSEQ incompatible with the intended usage and +breaks the expectation of other libraries in the same application. + +The ABI compliant optimized v2 mode, which respects the read only fields, +does not require unconditional updates and therefore is way more +performant. The kernel validates the read only fields for compliance. If +user space modifies them, the process is killed. Compliant usage allows +multiple libraries in the same application to benefit from the RSEQ +functionality without disturbing each other. The ABI compliant optimized v2 +mode also enables extended RSEQ features like time slice extensions. + + Scheduler time slice extensions ------------------------------- @@ -37,7 +128,8 @@ The prerequisites for this functionality are: * Enabled at boot time (default is enabled) - * A rseq userspace pointer has been registered for the thread + * A rseq userspace pointer has been registered for the thread in + optimized V2 mode The thread has to enable the functionality via prctl(2):: diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index b2395dd4769d..bd04a908a8db 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -656,8 +656,8 @@ References See [white-paper]_, [api-spec]_, [amd-apm]_, [kvm-forum]_, and [snp-fw-abi]_ for more info. -.. [white-paper] https://developer.amd.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf -.. [api-spec] https://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf -.. [amd-apm] https://support.amd.com/TechDocs/24593.pdf (section 15.34) +.. [white-paper] https://docs.amd.com/v/u/en-US/memory-encryption-white-paper +.. [api-spec] https://docs.amd.com/v/u/en-US/55766_PUB_3.24_SEV_API +.. [amd-apm] https://docs.amd.com/v/u/en-US/24593_3.44_APM_Vol2 (section 15.34) .. [kvm-forum] https://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf -.. [snp-fw-abi] https://www.amd.com/system/files/TechDocs/56860.pdf +.. [snp-fw-abi] https://www.amd.com/content/dam/amd/en/documents/developer/56860.pdf diff --git a/MAINTAINERS b/MAINTAINERS index 5bbbbde6b907..edd161f2c62d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -68,6 +68,12 @@ Maintainers List first. When adding to this list, please keep the entries in alphabetical order. +3C509 NETWORK DRIVER +M: "Maciej W. Rozycki" +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/3com/3c509.c + 3C59X NETWORK DRIVER M: Steffen Klassert L: netdev@vger.kernel.org @@ -2015,7 +2021,7 @@ F: Documentation/hwmon/aquacomputer_d5next.rst F: drivers/hwmon/aquacomputer_d5next.c AQUANTIA ETHERNET DRIVER (atlantic) -M: Igor Russkikh +M: Sukhdeep Singh L: netdev@vger.kernel.org S: Maintained W: https://www.marvell.com/ @@ -2024,7 +2030,7 @@ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst F: drivers/net/ethernet/aquantia/atlantic/ AQUANTIA ETHERNET DRIVER PTP SUBSYSTEM -M: Egor Pomozov +M: Sukhdeep Singh L: netdev@vger.kernel.org S: Maintained W: http://www.aquantia.com @@ -4181,8 +4187,8 @@ F: include/uapi/linux/sonet.h F: net/atm/ ATMEL MACB ETHERNET DRIVER -M: Nicolas Ferre -M: Claudiu Beznea +M: Théo Lebrun +R: Conor Dooley S: Maintained F: drivers/net/ethernet/cadence/ @@ -4299,18 +4305,16 @@ F: Documentation/devicetree/bindings/leds/backlight/awinic,aw99706.yaml F: drivers/video/backlight/aw99706.c AXENTIA ARM DEVICES -M: Peter Rosin L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: arch/arm/boot/dts/microchip/at91-linea.dtsi F: arch/arm/boot/dts/microchip/at91-natte.dtsi F: arch/arm/boot/dts/microchip/at91-nattis-2-natte-2.dts F: arch/arm/boot/dts/microchip/at91-tse850-3.dts AXENTIA ASOC DRIVERS -M: Peter Rosin L: linux-sound@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/sound/axentia,* F: sound/soc/atmel/tse850-pcm5142.c @@ -6358,6 +6362,7 @@ F: include/uapi/linux/comedi.h COMMON CLK FRAMEWORK M: Michael Turquette M: Stephen Boyd +R: Brian Masney L: linux-clk@vger.kernel.org S: Maintained Q: http://patchwork.kernel.org/project/linux-clk/list/ @@ -8199,10 +8204,9 @@ F: include/uapi/drm/nouveau_drm.h CORE DRIVER FOR NVIDIA GPUS [RUST] M: Danilo Krummrich M: Alexandre Courbot -L: nouveau@lists.freedesktop.org +L: nova-gpu@lists.linux.dev S: Supported W: https://rust-for-linux.com/nova-gpu-driver -Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next @@ -8211,10 +8215,9 @@ F: drivers/gpu/nova-core/ DRM DRIVER FOR NVIDIA GPUS [RUST] M: Danilo Krummrich -L: nouveau@lists.freedesktop.org +L: nova-gpu@lists.linux.dev S: Supported W: https://rust-for-linux.com/nova-gpu-driver -Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau T: git https://gitlab.freedesktop.org/drm/rust/kernel.git drm-rust-next @@ -12052,7 +12055,7 @@ F: Documentation/i2c/busses/i2c-nvidia-gpu.rst F: drivers/i2c/busses/i2c-nvidia-gpu.c I2C MUXES -M: Peter Rosin +M: Peter Rosin L: linux-i2c@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/i2c/i2c-arb* @@ -12453,7 +12456,7 @@ F: drivers/iio/industrialio-backend.c F: include/linux/iio/backend.h IIO DIGITAL POTENTIOMETER DAC -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-dac-dpot-dac @@ -12461,7 +12464,7 @@ F: Documentation/devicetree/bindings/iio/dac/dpot-dac.yaml F: drivers/iio/dac/dpot-dac.c IIO ENVELOPE DETECTOR -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector @@ -12477,7 +12480,7 @@ F: include/linux/iio/iio-gts-helper.h F: drivers/iio/test/iio-test-gts.c IIO MULTIPLEXER -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.yaml @@ -12508,7 +12511,7 @@ F: include/linux/iio/ F: tools/iio/ IIO UNIT CONVERTER -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/afe/current-sense-amplifier.yaml @@ -14058,6 +14061,7 @@ KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier M: Oliver Upton R: Joey Gouly +R: Steffen Eiden R: Suzuki K Poulose R: Zenghui Yu L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -15724,7 +15728,7 @@ F: Documentation/devicetree/bindings/media/i2c/maxim,max96717.yaml F: drivers/media/i2c/max96717.c MAX9860 MONO AUDIO VOICE CODEC DRIVER -M: Peter Rosin +M: Peter Rosin L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/max9860.txt @@ -15939,7 +15943,7 @@ F: Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml F: drivers/net/can/spi/mcp251xfd/ MCP4018 AND MCP4531 MICROCHIP DIGITAL POTENTIOMETER DRIVERS -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531 @@ -18244,7 +18248,7 @@ F: include/linux/mmc/ F: include/uapi/linux/mmc/ MULTIPLEXER SUBSYSTEM -M: Peter Rosin +M: Peter Rosin S: Odd Fixes F: Documentation/ABI/testing/sysfs-class-mux* F: Documentation/devicetree/bindings/mux/ @@ -19353,7 +19357,7 @@ F: include/dt-bindings/display/tda998x.h K: "nxp,tda998x" NXP TFA9879 DRIVER -M: Peter Rosin +M: Peter Rosin L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/trivial-codec.yaml @@ -20354,13 +20358,14 @@ F: Documentation/devicetree/bindings/pci/marvell,armada8k-pcie.yaml F: drivers/pci/controller/dwc/pcie-armada8k.c PCI DRIVER FOR CADENCE PCIE IP +R: Aksh Garg L: linux-pci@vger.kernel.org S: Orphan F: Documentation/devicetree/bindings/pci/cdns,* -F: drivers/pci/controller/cadence/*cadence* +F: drivers/pci/controller/cadence/ PCI DRIVER FOR CIX Sky1 -M: Hans Zhang +M: Hans Zhang <18255117159@163.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/cix,sky1-pcie-*.yaml @@ -20472,7 +20477,7 @@ F: drivers/pci/controller/plda/pcie-plda-host.c F: drivers/pci/controller/plda/pcie-plda.h PCI DRIVER FOR RENESAS R-CAR -M: Marek Vasut +M: Marek Vasut M: Yoshihiro Shimoda L: linux-pci@vger.kernel.org L: linux-renesas-soc@vger.kernel.org diff --git a/Makefile b/Makefile index 9f88dcaae382..b7b80e84e1eb 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -486,6 +486,8 @@ export rust_common_flags := --edition=2021 \ -Wclippy::as_ptr_cast_mut \ -Wclippy::as_underscore \ -Wclippy::cast_lossless \ + -Aclippy::collapsible_if \ + -Aclippy::collapsible_match \ -Wclippy::ignored_unit_patterns \ -Aclippy::incompatible_msrv \ -Wclippy::mut_mut \ diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 091544e6af44..dc2957662ff2 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -23,6 +23,7 @@ static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2) static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) { return TCR_EPD1_MASK | /* disable TTBR1_EL1 */ + ((tcr & TCR_EL2_DS) ? TCR_DS : 0) | ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) | tcr_el2_ps_to_tcr_el1_ips(tcr) | (tcr & TCR_EL2_TG0_MASK) | diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 736561480f36..7aa08d59d494 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -844,7 +844,7 @@ #define INIT_SCTLR_EL2_MMU_ON \ (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | \ SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | \ - SCTLR_ELx_ITFSB | SCTLR_EL2_RES1) + SCTLR_ELx_ITFSB | SCTLR_ELx_EIS | SCTLR_ELx_EOS | SCTLR_EL2_RES1) #define INIT_SCTLR_EL2_MMU_OFF \ (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index ba5eab23fd90..4d08598e2891 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -983,8 +983,8 @@ static int sve_set_common(struct task_struct *target, } /* Always zero V regs, FPSR, and FPCR */ - memset(¤t->thread.uw.fpsimd_state, 0, - sizeof(current->thread.uw.fpsimd_state)); + memset(&target->thread.uw.fpsimd_state, 0, + sizeof(target->thread.uw.fpsimd_state)); /* Registers: FPSIMD-only case */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 8bb2c7422cc8..34c9950884d5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -4,6 +4,7 @@ * Author: Christoffer Dall */ +#include #include #include #include @@ -2638,6 +2639,22 @@ static int init_pkvm_host_sve_state(void) return 0; } +static int pkvm_check_sme_dvmsync_fw_call(void) +{ + struct arm_smccc_res res; + + if (!cpus_have_final_cap(ARM64_WORKAROUND_4193714)) + return 0; + + arm_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res); + if (res.a0) { + kvm_err("pKVM requires firmware support for C1-Pro erratum 4193714\n"); + return -ENODEV; + } + + return 0; +} + /* * Finalizes the initialization of hyp mode, once everything else is initialized * and the initialziation process cannot fail. @@ -2838,6 +2855,10 @@ static int __init init_hyp_mode(void) if (err) goto out_err; + err = pkvm_check_sme_dvmsync_fw_call(); + if (err) + goto out_err; + err = kvm_hyp_init_protection(hyp_va_bits); if (err) { kvm_err("Failed to init hyp memory protection\n"); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 98b2976837b1..bf0eb5e43427 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -245,7 +245,7 @@ static inline void __activate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) __activate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); } -#define __deactivate_fgt(htcxt, vcpu, reg) \ +#define __deactivate_fgt(hctxt, vcpu, reg) \ do { \ write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ SYS_ ## reg); \ diff --git a/arch/arm64/kvm/hyp/nvhe/clock.c b/arch/arm64/kvm/hyp/nvhe/clock.c index 32fc4313fe43..a7fc61976fd0 100644 --- a/arch/arm64/kvm/hyp/nvhe/clock.c +++ b/arch/arm64/kvm/hyp/nvhe/clock.c @@ -35,6 +35,9 @@ void trace_clock_update(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) struct clock_data *clock = &trace_clock_data; u64 bank = clock->cur ^ 1; + if (!mult || shift >= 64) + return; + clock->data[bank].mult = mult; clock->data[bank].shift = shift; clock->data[bank].epoch_ns = epoch_ns; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 28a471d1927c..25f04629014e 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -5,6 +5,7 @@ */ #include + #include #include #include @@ -14,6 +15,7 @@ #include +#include #include #include #include @@ -29,6 +31,19 @@ static struct hyp_pool host_s2_pool; static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm); #define current_vm (*this_cpu_ptr(&__current_vm)) +static void pkvm_sme_dvmsync_fw_call(void) +{ + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) { + struct arm_smccc_res res; + + /* + * Ignore the return value. Probing for the workaround + * availability took place in init_hyp_mode(). + */ + hyp_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res); + } +} + static void guest_lock_component(struct pkvm_hyp_vm *vm) { hyp_spin_lock(&vm->lock); @@ -574,8 +589,14 @@ static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size, ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt, addr, size, &host_s2_pool, KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation); - if (!ret) + if (!ret) { + /* + * After stage2 maintenance has happened, but before the page + * owner has changed. + */ + pkvm_sme_dvmsync_fw_call(); __host_update_page_state(addr, size, PKVM_NOPAGE); + } return ret; } @@ -1369,6 +1390,22 @@ int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm) return ret && ret != -EHWPOISON ? ret : 0; } +/* + * share/donate install at most one stage-2 leaf (PAGE_SIZE, or one + * KVM_PGTABLE_LAST_LEVEL - 1 block for share). kvm_mmu_cache_min_pages() + * bounds the worst-case allocation: exact for the PAGE_SIZE leaf, + * conservative by one for the block. + */ +static int __guest_check_pgtable_memcache(struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + if (vcpu->vcpu.arch.pkvm_memcache.nr_pages < kvm_mmu_cache_min_pages(vm->pgt.mmu)) + return -ENOMEM; + + return 0; +} + int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); @@ -1388,6 +1425,10 @@ int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu) if (ret) goto unlock; + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + meta = host_stage2_encode_gfn_meta(vm, gfn); WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE, PKVM_ID_GUEST, meta)); @@ -1453,6 +1494,10 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu } } + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + for_each_hyp_page(page, phys, size) { set_host_state(page, PKVM_PAGE_SHARED_OWNED); page->host_share_guest_count++; diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index e7496eb85628..eb1c10120f9f 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -752,16 +752,30 @@ static struct pkvm_hyp_vcpu selftest_vcpu = { struct pkvm_hyp_vcpu *init_selftest_vm(void *virt) { struct hyp_page *p = hyp_virt_to_page(virt); + unsigned long min_pages, seeded = 0; int i; selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt)); + /* + * Mirror pkvm_refill_memcache() for the share/donate pre-checks; + * the selftest invokes those functions directly and would + * otherwise see an empty memcache. + */ + min_pages = kvm_mmu_cache_min_pages(&selftest_vm.kvm.arch.mmu); + for (i = 0; i < pkvm_selftest_pages(); i++) { if (p[i].refcount) continue; p[i].refcount = 1; - hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + if (seeded < min_pages) { + push_hyp_memcache(&selftest_vcpu.vcpu.arch.pkvm_memcache, + hyp_page_to_virt(&p[i]), hyp_virt_to_phys); + seeded++; + } else { + hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + } } selftest_vm.kvm.arch.pkvm.handle = __pkvm_reserve_vm(); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 9db3f11a4754..1e8995add14f 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -663,7 +663,8 @@ static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par) host_ctxt = host_data_ptr(host_ctxt); vcpu = host_ctxt->__hyp_running_vcpu; - __deactivate_traps(vcpu); + if (vcpu) + __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n", diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d089c107d9b7..4da9281312eb 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1576,21 +1576,24 @@ struct kvm_s2_fault_desc { static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) { bool write_fault, exec_fault; + bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu); enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt; unsigned long mmu_seq; struct page *page; struct kvm *kvm = s2fd->vcpu->kvm; - void *memcache; + void *memcache = NULL; kvm_pfn_t pfn; gfn_t gfn; int ret; - memcache = get_mmu_memcache(s2fd->vcpu); - ret = topup_mmu_memcache(s2fd->vcpu, memcache); - if (ret) - return ret; + if (!perm_fault) { + memcache = get_mmu_memcache(s2fd->vcpu); + ret = topup_mmu_memcache(s2fd->vcpu, memcache); + if (ret) + return ret; + } if (s2fd->nested) gfn = kvm_s2_trans_output(s2fd->nested) >> PAGE_SHIFT; @@ -1631,9 +1634,19 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) goto out_unlock; } - ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE, - __pfn_to_phys(pfn), prot, - memcache, flags); + if (perm_fault) { + /* + * Drop the SW bits in favour of those stored in the + * PTE, which will be preserved. + */ + prot &= ~KVM_NV_GUEST_MAP_SZ; + ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, s2fd->fault_ipa, + prot, flags); + } else { + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE, + __pfn_to_phys(pfn), prot, + memcache, flags); + } out_unlock: kvm_release_faultin_page(kvm, page, !!ret, prot & KVM_PGTABLE_PROT_W); diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index 69ef3dc31c4b..7a515390646b 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -76,7 +76,6 @@ CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_RADEON=y CONFIG_FB_3DFX=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index b799c95480ae..66eae5b7e16c 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -76,7 +76,6 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_NVRAM=y # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 04bbb37f5978..e9996711b362 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -121,7 +121,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_AGP=m CONFIG_AGP_UNINORTH=m CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_OF=y CONFIG_FB_NVIDIA=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 8bbf51b38480..89bcbeb05067 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -98,7 +98,6 @@ CONFIG_SENSORS_LM85=y CONFIG_SENSORS_LM90=y CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_VGA16=y CONFIG_FB_NVIDIA=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index cc9802420237..5d32c2767a65 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -196,7 +196,6 @@ CONFIG_I2C_CHARDEV=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_AST=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=m CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 3bf518e3a573..6316ca4df25d 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -249,7 +249,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_I2C_PASEMI=y CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 0fd49f67331f..20cc17dce94d 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -118,7 +118,6 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index ff1bed4b6d2c..005536ee75bb 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -214,7 +214,6 @@ CONFIG_SENSORS_IBMPOWERNV=m CONFIG_DRM=m CONFIG_DRM_AST=m CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 8834dfe9d727..368759f81708 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -62,6 +62,12 @@ CC32FLAGSREMOVE += -fno-stack-clash-protection # 32-bit one. clang validates the values passed to these arguments during # parsing, even when -fno-stack-protector is passed afterwards. CC32FLAGSREMOVE += -mstack-protector-guard% +# ftrace is disabled for the vdso but arch/powerpc/Makefile adds this define to +# KBUILD_CPPFLAGS, which enables use of the 'patchable_function_entry' +# attribute in the 'inline' define via 'notrace'. This attribute is not +# supported for the powerpcle target, resulting in many instances of +# -Wunknown-attributes. +CC32FLAGSREMOVE += -DCC_USING_PATCHABLE_FUNCTION_ENTRY endif LD32FLAGS := -Wl,-soname=linux-vdso32.so.1 AS32FLAGS := -D__VDSO32__ diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile index 470eb0453e17..ec7a0eed75dc 100644 --- a/arch/powerpc/kexec/Makefile +++ b/arch/powerpc/kexec/Makefile @@ -16,4 +16,4 @@ GCOV_PROFILE_core_$(BITS).o := n KCOV_INSTRUMENT_core_$(BITS).o := n UBSAN_SANITIZE_core_$(BITS).o := n KASAN_SANITIZE_core.o := n -KASAN_SANITIZE_core_$(BITS) := n +KASAN_SANITIZE_core_$(BITS).o := n diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 554b248002b4..57e897b60db8 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -52,7 +52,14 @@ int exit_vmx_usercopy(void) } EXPORT_SYMBOL(exit_vmx_usercopy); -int enter_vmx_ops(void) +/* + * Can be called from kexec copy_page() path with MMU off. The kexec + * code sets preempt_count to HARDIRQ_OFFSET so we return early here. + * Since in_interrupt() is always inline, __no_sanitize_address on this + * function is sufficient to avoid KASAN shadow memory accesses in real + * mode. + */ +int __no_sanitize_address enter_vmx_ops(void) { if (in_interrupt()) return 0; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8b0081441f85..2e6adf5b95c4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2242,6 +2242,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, const u64 last_period = event->hw.last_period; s64 prev, delta, left; int record = 0; + int mark_event = regs->dsisr & MMCRA_SAMPLE_ENABLE; if (event->hw.state & PERF_HES_STOPPED) { write_pmc(event->hw.idx, 0); @@ -2304,9 +2305,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * In ISA v3.0 and before values "0" and "7" are considered reserved. * In ISA v3.1, value "7" has been used to indicate "larx/stcx". * Drop the sample if "type" has reserved values for this field with a - * ISA version check. + * ISA version check for marked events. */ - if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC && + if (mark_event && event->attr.sample_type & PERF_SAMPLE_DATA_SRC && ppmu->get_mem_data_src) { val = (regs->dar & SIER_TYPE_MASK) >> SIER_TYPE_SHIFT; if (val == 0 || (val == 7 && !cpu_has_feature(CPU_FTR_ARCH_31))) { diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 7433be7d66ee..f00734f0590c 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -477,7 +477,7 @@ int cpm1_gpiochip_add16(struct device *dev) struct device_node *np = dev->of_node; struct cpm1_gpio16_chip *cpm1_gc; struct gpio_chip *gc; - u16 mask; + u32 mask; cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) @@ -485,7 +485,7 @@ int cpm1_gpiochip_add16(struct device *dev) spin_lock_init(&cpm1_gc->lock); - if (!of_property_read_u16(np, "fsl,cpm1-gpio-irq-mask", &mask)) { + if (!of_property_read_u32(np, "fsl,cpm1-gpio-irq-mask", &mask)) { int i, j; for (i = 0, j = 0; i < 16; i++) diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index 60f990a336c4..2df955274652 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -272,13 +272,12 @@ void __init pas_pci_init(void) { struct device_node *root = of_find_node_by_path("/"); struct device_node *np; - int res; pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS); np = of_find_compatible_node(root, NULL, "pasemi,rootbus"); if (np) { - res = pas_add_bridge(np); + pas_add_bridge(np); of_node_put(np); } of_node_put(root); diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index 12c473768c39..9109c218a060 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -950,8 +950,6 @@ static int __init ps3_start_probe_thread(enum ps3_bus_type bus_type) static int __init ps3_register_devices(void) { - int result; - if (!firmware_has_feature(FW_FEATURE_PS3_LV1)) return -ENODEV; @@ -959,7 +957,7 @@ static int __init ps3_register_devices(void) /* ps3_repository_dump_bus_info(); */ - result = ps3_start_probe_thread(PS3_BUS_TYPE_STORAGE); + ps3_start_probe_thread(PS3_BUS_TYPE_STORAGE); ps3_register_vuart_devices(); diff --git a/arch/powerpc/platforms/pseries/htmdump.c b/arch/powerpc/platforms/pseries/htmdump.c index 742ec52c9d4d..489a80e87082 100644 --- a/arch/powerpc/platforms/pseries/htmdump.c +++ b/arch/powerpc/platforms/pseries/htmdump.c @@ -16,6 +16,7 @@ static void *htm_buf; static void *htm_status_buf; static void *htm_info_buf; static void *htm_caps_buf; +static void *htm_mem_buf; static u32 nodeindex; static u32 nodalchipindex; static u32 coreindexonchip; @@ -86,7 +87,7 @@ static ssize_t htm_return_check(long rc) static ssize_t htmdump_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_buf = filp->private_data; + void *htm_buf_data = filp->private_data; unsigned long page, read_size, available; loff_t offset; long rc, ret; @@ -100,7 +101,7 @@ static ssize_t htmdump_read(struct file *filp, char __user *ubuf, * - last three values are address, size and offset */ rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf), + htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf_data), PAGE_SIZE, page); ret = htm_return_check(rc); @@ -112,7 +113,61 @@ static ssize_t htmdump_read(struct file *filp, char __user *ubuf, available = PAGE_SIZE; read_size = min(count, available); *ppos += read_size; - return simple_read_from_buffer(ubuf, count, &offset, htm_buf, available); + return simple_read_from_buffer(ubuf, count, &offset, htm_buf_data, available); +} + +static ssize_t htmsystem_mem_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + void *htm_mem_data = filp->private_data; + long rc, ret; + u64 *num_entries; + u64 to_copy = 0; + loff_t offset = 0; + u64 mem_offset = 0; + + /* + * Invoke H_HTM call with: + * - operation as htm status (H_HTM_OP_STATUS) + * - last three values as addr, size and offset. "offset" + * is value from output buffer header that points to next + * entry to dump. 0 is the first entry to dump. next entry + * is read from the output bufferbyte offset 0x8. + * + * When first time hcall is invoked, mem_offset should be + * zero because zero is the first entry. + * In the next hcall, offset of next entry to read from is + * picked from output buffer header itself. So don't fill + * mem_offset for first read. + * + * If there is no further data to read in next iteration, + * offset value from output buffer header will point to -1. + */ + if (*ppos) { + mem_offset = *(u64 *)(htm_mem_data + 0x8); + if (mem_offset == -1) + return 0; + } + rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, + htmtype, H_HTM_OP_DUMP_SYSMEM_CONF, virt_to_phys(htm_mem_data), + PAGE_SIZE, be64_to_cpu(mem_offset)); + ret = htm_return_check(rc); + if (ret <= 0) { + pr_debug("H_HTM hcall returned for op: H_HTM_OP_DUMP_SYSMEM_CONF with hcall returning %ld\n", ret); + return ret; + } + + /* + * HTM system mem buffer, start of buffer + 0x10 gives the + * number of HTM entries in the buffer. + * So total count to copy is: + * 32 bytes (for first 5 fields) + (number of HTM entries * entry size) + */ + num_entries = htm_mem_data + 0x10; + to_copy = 32 + (be64_to_cpu(*num_entries) * 32); + + *ppos += to_copy; + return simple_read_from_buffer(ubuf, count, &offset, htm_mem_data, to_copy); } static const struct file_operations htmdump_fops = { @@ -121,6 +176,12 @@ static const struct file_operations htmdump_fops = { .open = simple_open, }; +static const struct file_operations htmsystem_mem_fops = { + .llseek = NULL, + .read = htmsystem_mem_read, + .open = simple_open, +}; + static int htmconfigure_set(void *data, u64 val) { long rc, ret; @@ -226,20 +287,31 @@ static int htmstart_get(void *data, u64 *val) static ssize_t htmstatus_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_status_buf = filp->private_data; + void *htm_status_data = filp->private_data; long rc, ret; u64 *num_entries; u64 to_copy; int htmstatus_flag; + loff_t offset = 0; + u64 status_offset = 0; /* * Invoke H_HTM call with: * - operation as htm status (H_HTM_OP_STATUS) - * - last three values as addr, size and offset + * - last three values as addr, size and offset. + * "offset" is value from output buffer header + * that points to next entry to dump. 0 is the first + * entry to dump. next entry is read from the output + * bufferbyte offset 0x8. */ + if (*ppos) { + status_offset = *(u64 *)(htm_status_data + 0x8); + if (status_offset == -1) + return 0; + } rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_buf), - PAGE_SIZE, 0); + htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_data), + PAGE_SIZE, be64_to_cpu(status_offset)); ret = htm_return_check(rc); if (ret <= 0) { @@ -255,13 +327,15 @@ static ssize_t htmstatus_read(struct file *filp, char __user *ubuf, * So total count to copy is: * 32 bytes (for first 7 fields) + (number of HTM entries * entry size) */ - num_entries = htm_status_buf + 0x10; + num_entries = htm_status_data + 0x10; if (htmtype == 0x2) htmstatus_flag = 0x8; else htmstatus_flag = 0x6; to_copy = 32 + (be64_to_cpu(*num_entries) * htmstatus_flag); - return simple_read_from_buffer(ubuf, count, ppos, htm_status_buf, to_copy); + *ppos += to_copy; + + return simple_read_from_buffer(ubuf, count, &offset, htm_status_data, to_copy); } static const struct file_operations htmstatus_fops = { @@ -273,19 +347,30 @@ static const struct file_operations htmstatus_fops = { static ssize_t htminfo_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_info_buf = filp->private_data; + void *htm_info_data = filp->private_data; long rc, ret; u64 *num_entries; u64 to_copy; + loff_t offset = 0; + u64 info_offset = 0; /* * Invoke H_HTM call with: * - operation as htm status (H_HTM_OP_STATUS) * - last three values as addr, size and offset + * "offset" is value from output buffer header + * that points to next entry to dump. 0 is the first + * entry to dump. next entry is read from the output + * bufferbyte offset 0x8. */ + if (*ppos) { + info_offset = *(u64 *)(htm_info_data + 0x8); + if (info_offset == -1) + return 0; + } rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_buf), - PAGE_SIZE, 0); + htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_data), + PAGE_SIZE, be64_to_cpu(info_offset)); ret = htm_return_check(rc); if (ret <= 0) { @@ -301,15 +386,17 @@ static ssize_t htminfo_read(struct file *filp, char __user *ubuf, * So total count to copy is: * 32 bytes (for first 5 fields) + (number of HTM entries * entry size) */ - num_entries = htm_info_buf + 0x10; + num_entries = htm_info_data + 0x10; to_copy = 32 + (be64_to_cpu(*num_entries) * 16); - return simple_read_from_buffer(ubuf, count, ppos, htm_info_buf, to_copy); + + *ppos += to_copy; + return simple_read_from_buffer(ubuf, count, &offset, htm_info_data, to_copy); } static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_caps_buf = filp->private_data; + void *htm_caps_data = filp->private_data; long rc, ret; /* @@ -319,7 +406,7 @@ static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, * and zero */ rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_buf), + htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_data), 0x80, 0); ret = htm_return_check(rc); @@ -328,7 +415,7 @@ static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, return ret; } - return simple_read_from_buffer(ubuf, count, ppos, htm_caps_buf, 0x80); + return simple_read_from_buffer(ubuf, count, ppos, htm_caps_data, 0x80); } static const struct file_operations htminfo_fops = { @@ -457,9 +544,17 @@ static int htmdump_init_debugfs(void) return -ENOMEM; } + /* Memory to present HTM system memory configuration */ + htm_mem_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!htm_mem_buf) { + pr_err("Failed to allocate htm mem buf\n"); + return -ENOMEM; + } + debugfs_create_file("htmstatus", 0400, htmdump_debugfs_dir, htm_status_buf, &htmstatus_fops); debugfs_create_file("htminfo", 0400, htmdump_debugfs_dir, htm_info_buf, &htminfo_fops); debugfs_create_file("htmcaps", 0400, htmdump_debugfs_dir, htm_caps_buf, &htmcaps_fops); + debugfs_create_file("htmsystem_mem", 0400, htmdump_debugfs_dir, htm_mem_buf, &htmsystem_mem_fops); return 0; } @@ -482,6 +577,10 @@ static void __exit htmdump_exit(void) { debugfs_remove_recursive(htmdump_debugfs_dir); kfree(htm_buf); + kfree(htm_status_buf); + kfree(htm_info_buf); + kfree(htm_caps_buf); + kfree(htm_mem_buf); } module_init(htmdump_init); diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index 14ae480d060a..0c40bdde45e2 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -190,33 +190,34 @@ static int hvpipe_rtas_recv_msg(char __user *buf, int size) return -ENOMEM; } - ret = rtas_ibm_receive_hvpipe_msg(work_area, &srcID, - &bytes_written); - if (!ret) { - /* - * Recv HVPIPE RTAS is successful. - * When releasing FD or no one is waiting on the - * specific source, issue recv HVPIPE RTAS call - * so that pipe is not blocked - this func is called - * with NULL buf. - */ - if (buf) { - if (size < bytes_written) { - pr_err("Received the payload size = %d, but the buffer size = %d\n", - bytes_written, size); - bytes_written = size; - } - ret = copy_to_user(buf, - rtas_work_area_raw_buf(work_area), - bytes_written); - if (!ret) - ret = bytes_written; - } - } else { - pr_err("ibm,receive-hvpipe-msg failed with %d\n", - ret); + /* + * Recv HVPIPE RTAS is successful. + * When releasing FD or no one is waiting on the + * specific source, issue recv HVPIPE RTAS call + * so that pipe is not blocked - this func is called + * with NULL buf. + */ + ret = rtas_ibm_receive_hvpipe_msg(work_area, &srcID, &bytes_written); + if (ret) { + pr_err("ibm,receive-hvpipe-msg failed with %d\n", ret); + goto out; } + if (!buf) + goto out; + + if (size < bytes_written) { + pr_err("Received the payload size = %d, but the buffer size = %d\n", + bytes_written, size); + bytes_written = size; + } + + if (copy_to_user(buf, rtas_work_area_raw_buf(work_area), bytes_written)) + ret = -EFAULT; + else + ret = bytes_written; + +out: rtas_work_area_free(work_area); return ret; } @@ -327,8 +328,8 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, { struct hvpipe_source_info *src_info = file->private_data; - struct papr_hvpipe_hdr hdr; - long ret; + struct papr_hvpipe_hdr hdr = {}; + ssize_t ret = 0; /* * Return -ENXIO during migration @@ -376,7 +377,7 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, ret = copy_to_user(buf, &hdr, HVPIPE_HDR_LEN); if (ret) - return ret; + return -EFAULT; /* * Message event has payload, so get the payload with @@ -385,19 +386,23 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, if (hdr.flags & HVPIPE_MSG_AVAILABLE) { ret = hvpipe_rtas_recv_msg(buf + HVPIPE_HDR_LEN, size - HVPIPE_HDR_LEN); - if (ret > 0) { + /* + * Always clear MSG_AVAILABLE once the RTAS call has drained + * the message, regardless of whether copy_to_user succeeded. + */ + if (ret >= 0 || ret == -EFAULT) src_info->hvpipe_status &= ~HVPIPE_MSG_AVAILABLE; - ret += HVPIPE_HDR_LEN; - } } else if (hdr.flags & HVPIPE_LOST_CONNECTION) { /* * Hypervisor is closing the pipe for the specific * source. So notify user space. */ src_info->hvpipe_status &= ~HVPIPE_LOST_CONNECTION; - ret = HVPIPE_HDR_LEN; } + if (ret >= 0) + ret += HVPIPE_HDR_LEN; + return ret; } @@ -444,16 +449,18 @@ static int papr_hvpipe_handle_release(struct inode *inode, struct file *file) { struct hvpipe_source_info *src_info; + unsigned long flags; /* * Hold the lock, remove source from src_list, reset the * hvpipe status and release the lock to prevent any race * with message event IRQ. */ - spin_lock(&hvpipe_src_list_lock); + spin_lock_irqsave(&hvpipe_src_list_lock, flags); src_info = file->private_data; list_del(&src_info->list); file->private_data = NULL; + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); /* * If the pipe for this specific source has any pending * payload, issue recv HVPIPE RTAS so that pipe will not @@ -461,10 +468,8 @@ static int papr_hvpipe_handle_release(struct inode *inode, */ if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) { src_info->hvpipe_status = 0; - spin_unlock(&hvpipe_src_list_lock); hvpipe_rtas_recv_msg(NULL, 0); - } else - spin_unlock(&hvpipe_src_list_lock); + } kfree(src_info); return 0; @@ -479,50 +484,53 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { - struct hvpipe_source_info *src_info __free(kfree) = NULL; - - spin_lock(&hvpipe_src_list_lock); - /* - * Do not allow more than one process communicates with - * each source. - */ - src_info = hvpipe_find_source(srcID); - if (src_info) { - spin_unlock(&hvpipe_src_list_lock); - pr_err("pid(%d) is already using the source(%d)\n", - src_info->tsk->pid, srcID); - return -EALREADY; - } - spin_unlock(&hvpipe_src_list_lock); + struct hvpipe_source_info *src_info; + int fd; + unsigned long flags; src_info = kzalloc_obj(*src_info, GFP_KERNEL_ACCOUNT); if (!src_info) return -ENOMEM; src_info->srcID = srcID; - src_info->tsk = current; init_waitqueue_head(&src_info->recv_wqh); - FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC, - anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, - (void *)src_info, O_RDWR)); - if (fdf.err) - return fdf.err; - - retain_and_null_ptr(src_info); - spin_lock(&hvpipe_src_list_lock); /* - * If two processes are executing ioctl() for the same - * source ID concurrently, prevent the second process to - * acquire FD. + * Do not allow more than one process communicates with + * each source. */ + spin_lock_irqsave(&hvpipe_src_list_lock, flags); if (hvpipe_find_source(srcID)) { - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + pr_err("pid(%s:%d) could not get the source(%d)\n", + current->comm, task_pid_nr(current), srcID); + kfree(src_info); return -EALREADY; } list_add(&src_info->list, &hvpipe_src_list); - spin_unlock(&hvpipe_src_list_lock); - return fd_publish(fdf); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + + fd = FD_ADD(O_RDONLY | O_CLOEXEC, + anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, + (void *)src_info, O_RDWR)); + if (fd < 0) { + spin_lock_irqsave(&hvpipe_src_list_lock, flags); + list_del(&src_info->list); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + /* + * if we fail to add FD, that means no userspace program is + * polling. In that case if there is a msg pending because the + * interrupt was fired after the src_info was added to the + * global list, then let's consume it here, to unblock the + * hvpipe + */ + if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) + hvpipe_rtas_recv_msg(NULL, 0); + kfree(src_info); + return fd; + } + + return fd; } /* @@ -685,20 +693,19 @@ static int __init enable_hvpipe_IRQ(void) struct device_node *np; hvpipe_check_exception_token = rtas_function_token(RTAS_FN_CHECK_EXCEPTION); - if (hvpipe_check_exception_token == RTAS_UNKNOWN_SERVICE) + if (hvpipe_check_exception_token == RTAS_UNKNOWN_SERVICE) return -ENODEV; /* hvpipe events */ np = of_find_node_by_path("/event-sources/ibm,hvpipe-msg-events"); - if (np != NULL) { - request_event_sources_irqs(np, hvpipe_event_interrupt, - "HPIPE_EVENT"); - of_node_put(np); - } else { - pr_err("Can not enable hvpipe event IRQ\n"); + if (!np) { + pr_err("No device node found, could not enable hvpipe event IRQ\n"); return -ENODEV; } + request_event_sources_irqs(np, hvpipe_event_interrupt, "HPIPE_EVENT"); + of_node_put(np); + return 0; } @@ -775,23 +782,29 @@ static int __init papr_hvpipe_init(void) } ret = enable_hvpipe_IRQ(); - if (!ret) { - ret = set_hvpipe_sys_param(1); - if (!ret) - ret = misc_register(&papr_hvpipe_dev); - } + if (ret) + goto out_wq; - if (!ret) { - pr_info("hvpipe feature is enabled\n"); - hvpipe_feature = true; - return 0; - } + ret = misc_register(&papr_hvpipe_dev); + if (ret) + goto out_wq; - pr_err("hvpipe feature is not enabled %d\n", ret); + ret = set_hvpipe_sys_param(1); + if (ret) + goto out_misc; + + pr_info("hvpipe feature is enabled\n"); + hvpipe_feature = true; + return 0; + +out_misc: + misc_deregister(&papr_hvpipe_dev); +out_wq: destroy_workqueue(papr_hvpipe_wq); out: kfree(papr_hvpipe_work); papr_hvpipe_work = NULL; + pr_err("hvpipe feature is not enabled %d\n", ret); return ret; } machine_device_initcall(pseries, papr_hvpipe_init); diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.h b/arch/powerpc/platforms/pseries/papr-hvpipe.h index c343f4230865..4bdf7bb2fc4d 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.h +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.h @@ -21,7 +21,6 @@ struct hvpipe_source_info { u32 srcID; u32 hvpipe_status; wait_queue_head_t recv_wqh; /* wake up poll() waitq */ - struct task_struct *tsk; }; /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 07f59c3b9a7b..3bcdbbbb6891 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3310,8 +3310,7 @@ static void aen_host_forward(unsigned long si) struct zpci_gaite *gaite; struct kvm *kvm; - gaite = (struct zpci_gaite *)aift->gait + - (si * sizeof(struct zpci_gaite)); + gaite = aift->gait + si; if (gaite->count == 0) return; if (gaite->aisb != 0) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 86d93e8dddae..5b075c38998e 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -166,7 +166,7 @@ static int kvm_zpci_set_airq(struct zpci_dev *zdev) fib.fmt0.noi = airq_iv_end(zdev->aibv); fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector); fib.fmt0.aibvo = 0; - fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib.fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8; fib.fmt0.aisbo = zdev->aisb & 63; fib.gd = zdev->gisa; @@ -290,8 +290,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, phys_to_virt(fib->fmt0.aibv)); spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; /* If assist not requested, host will get all alerts */ if (assist) @@ -309,7 +308,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, /* Update guest FIB for re-issue */ fib->fmt0.aisbo = zdev->aisb & 63; - fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib->fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8; fib->fmt0.isc = gisc; /* Save some guest fib values in the host for later use */ @@ -357,8 +356,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) if (zdev->kzdev->fib.fmt0.aibv == 0) goto out; spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; isc = gaite->gisc; gaite->count--; if (gaite->count == 0) { diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 810ab21ffd99..4b9e105309c6 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1294,13 +1294,16 @@ int x86_perf_rdpmc_index(struct perf_event *event) return event->hw.event_base_rdpmc; } -static inline int match_prev_assignment(struct hw_perf_event *hwc, +static inline int match_prev_assignment(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { + struct hw_perf_event *hwc = &event->hw; + return hwc->idx == cpuc->assign[i] && - hwc->last_cpu == smp_processor_id() && - hwc->last_tag == cpuc->tags[i]; + hwc->last_cpu == smp_processor_id() && + hwc->last_tag == cpuc->tags[i] && + !is_acr_event_group(event); } static void x86_pmu_start(struct perf_event *event, int flags); @@ -1346,7 +1349,7 @@ static void x86_pmu_enable(struct pmu *pmu) * - no other event has used the counter since */ if (hwc->idx == -1 || - match_prev_assignment(hwc, cpuc, i)) + match_prev_assignment(event, cpuc, i)) continue; /* @@ -1367,7 +1370,7 @@ static void x86_pmu_enable(struct pmu *pmu) event = cpuc->event_list[i]; hwc = &event->hw; - if (!match_prev_assignment(hwc, cpuc, i)) + if (!match_prev_assignment(event, cpuc, i)) x86_assign_hw_event(event, cpuc, i); else if (i < n_running) continue; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d9488ade0f8e..dd1e3aa75ee9 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3118,11 +3118,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) intel_set_masks(event, idx); /* - * Enable IRQ generation (0x8), if not PEBS, - * and enable ring-3 counting (0x2) and ring-0 counting (0x1) - * if requested: + * Enable IRQ generation (0x8), if not PEBS or self-reloaded + * ACR event, and enable ring-3 counting (0x2) and ring-0 + * counting (0x1) if requested: */ - if (!event->attr.precise_ip) + if (!event->attr.precise_ip && !is_acr_self_reload_event(event)) bits |= INTEL_FIXED_0_ENABLE_PMI; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= INTEL_FIXED_0_USER; @@ -3306,6 +3306,15 @@ static void intel_pmu_enable_event(struct perf_event *event) intel_set_masks(event, idx); static_call_cond(intel_pmu_enable_acr_event)(event); static_call_cond(intel_pmu_enable_event_ext)(event); + /* + * For self-reloaded ACR event, don't enable PMI since + * HW won't set overflow bit in GLOBAL_STATUS. Otherwise, + * the PMI would be recognized as a suspicious NMI. + */ + if (is_acr_self_reload_event(event)) + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + else if (!event->attr.precise_ip) + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: @@ -3332,23 +3341,41 @@ static void intel_pmu_enable_event(struct perf_event *event) static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc) { struct perf_event *event, *leader; - int i, j, idx; + int i, j, k, bit, idx; + /* + * FIXME: ACR mask parsing relies on cpuc->event_list[] (active events only). + * Disabling an ACR event causes bit-shifting errors in the acr_mask of + * remaining group members. As ACR sampling requires all events to be active, + * this limitation is acceptable for now. Revisit if independent event toggling + * is required. + */ for (i = 0; i < cpuc->n_events; i++) { leader = cpuc->event_list[i]; if (!is_acr_event_group(leader)) continue; - /* The ACR events must be contiguous. */ + /* Find the last event of the ACR group. */ for (j = i; j < cpuc->n_events; j++) { event = cpuc->event_list[j]; if (event->group_leader != leader->group_leader) break; - for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) { - if (i + idx >= cpuc->n_events || - !is_acr_event_group(cpuc->event_list[i + idx])) - return; - __set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1); + } + + /* + * Translate the user-space ACR mask (attr.config2) into the physical + * counter bitmask (hw.config1) for each ACR event in the group. + * NOTE: ACR event contiguity is guaranteed by intel_pmu_hw_config(). + */ + for (k = i; k < j; k++) { + event = cpuc->event_list[k]; + event->hw.config1 = 0; + for_each_set_bit(bit, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) { + idx = i + bit; + /* Event index of ACR group must locate in [i, j). */ + if (idx >= j || !is_acr_event_group(cpuc->event_list[idx])) + continue; + __set_bit(cpuc->assign[idx], (unsigned long *)&event->hw.config1); } } i = j - 1; @@ -7504,6 +7531,7 @@ static __always_inline void intel_pmu_init_pnc(struct pmu *pmu) hybrid(pmu, event_constraints) = intel_pnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_pnc_pebs_event_constraints; hybrid(pmu, extra_regs) = intel_pnc_extra_regs; + static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr); } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fad87d3c8b2c..524668dcf4cc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -137,6 +137,16 @@ static inline bool is_acr_event_group(struct perf_event *event) return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR); } +static inline bool is_acr_self_reload_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < 0) + return false; + + return test_bit(hwc->idx, (unsigned long *)&hwc->config1); +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a14a0f43e04a..86554de9a3f5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -803,9 +803,10 @@ #define MSR_AMD64_LBR_SELECT 0xc000010e /* Zen4 */ -#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG 0xc001102e #define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 /* Fam 19h MSRs */ #define MSR_F19H_UMC_PERF_CTL 0xc0010800 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2d9ae6ab1701..2f8e8ff2d000 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -989,6 +989,9 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) /* Correct misconfigured CPUID on some clients. */ clear_cpu_cap(c, X86_FEATURE_INVLPGB); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN2_BP_CFG_BUG_FIX_BIT); } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2a9992758933..eb72537bc0b1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -450,6 +450,10 @@ __init static int append_e820_table(struct boot_e820_entry *entries, u32 nr_entr { struct boot_e820_entry *entry = entries; + /* If there aren't any entries, we'll want to fall back to another source: */ + if (!nr_entries) + return -ENOENT; + while (nr_entries) { u64 start = entry->addr; u64 size = entry->size; @@ -458,7 +462,7 @@ __init static int append_e820_table(struct boot_e820_entry *entries, u32 nr_entr /* Ignore the remaining entries on 64-bit overflow: */ if (start > end && likely(size)) - return -1; + return -EINVAL; e820__range_add(start, size, type); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c8c6cc0406d6..8013dccb3110 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4481,7 +4481,7 @@ static const struct opcode opcode_map_0f_38[256] = { X16(N), X16(N), /* 0x20 - 0x2f */ X8(N), - X2(N), GP(SrcReg | DstMem | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, + X2(N), GP(SrcMem | DstReg | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, /* 0x30 - 0x7f */ X16(N), X16(N), X16(N), X16(N), X16(N), /* 0x80 - 0xef */ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 892246204435..f0144ae8d891 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2526,6 +2526,23 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) __shadow_walk_next(iterator, *iterator->sptep); } +/* + * Note: while normally KVM uses a "bool flush" return value to let + * the caller batch flushes, __link_shadow_page() flushes immediately + * before populating the parent PTE with the new shadow page. The + * typical callers, direct_map() and FNAME(fetch)(), are not going + * to zap more than one huge SPTE anyway. + * + * The only exception, where @flush can be false, is when a huge SPTE + * is replaced with a shadow page SPTE with a fully populated page table, + * which can happen from shadow_mmu_split_huge_page(). In this case, + * no memory is unmapped across the change to the page tables and no + * immediate flush is needed for correctness. + * + * Even in that case, calls to kvm_mmu_commit_zap_page() are not + * batched. Doing so would require adding an invalid_list argument + * all the way down to __walk_slot_rmaps(). + */ static void __link_shadow_page(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, u64 *sptep, struct kvm_mmu_page *sp, bool flush) @@ -2541,8 +2558,10 @@ static void __link_shadow_page(struct kvm *kvm, parent_sp = sptep_to_sp(sptep); WARN_ON_ONCE(parent_sp->role.level == PG_LEVEL_4K); - mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list); - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, true); + if (mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list)) + kvm_mmu_commit_zap_page(kvm, &invalid_list); + else if (flush) + kvm_flush_remote_tlbs_sptep(kvm, sptep); } spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp)); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 961804df5f45..b340dc9991ad 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -160,6 +160,16 @@ void nested_vmcb02_recalc_intercepts(struct vcpu_svm *svm) if (!intercept_smi) vmcb_clr_intercept(&vmcb02->control, INTERCEPT_SMI); + /* + * Intercept PAUSE if and only if L1 wants to. KVM intercepts PAUSE so + * that a vCPU that may be spinning waiting for a lock can be scheduled + * out in favor of the vCPU that holds said lock. KVM doesn't support + * yielding across L2 vCPUs, as KVM has limited visilibity into which + * L2 vCPUs are in the same L2 VM, i.e. may be contending for locks. + */ + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) + vmcb_clr_intercept(&vmcb02->control, INTERCEPT_PAUSE); + if (nested_vmcb_needs_vls_intercept(svm)) { /* * If the virtual VMLOAD/VMSAVE is not enabled for the L2, @@ -819,7 +829,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; struct vmcb *vmcb01 = svm->vmcb01.ptr; struct kvm_vcpu *vcpu = &svm->vcpu; - u32 pause_count12, pause_thresh12; nested_svm_transition_tlb_flush(vcpu); @@ -947,31 +956,13 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) vmcb02->control.misc_ctl2 |= SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; if (guest_cpu_cap_has(vcpu, X86_FEATURE_PAUSEFILTER)) - pause_count12 = vmcb12_ctrl->pause_filter_count; + vmcb02->control.pause_filter_count = vmcb12_ctrl->pause_filter_count; else - pause_count12 = 0; + vmcb02->control.pause_filter_count = 0; if (guest_cpu_cap_has(vcpu, X86_FEATURE_PFTHRESHOLD)) - pause_thresh12 = vmcb12_ctrl->pause_filter_thresh; + vmcb02->control.pause_filter_thresh = vmcb12_ctrl->pause_filter_thresh; else - pause_thresh12 = 0; - if (kvm_pause_in_guest(svm->vcpu.kvm)) { - /* use guest values since host doesn't intercept PAUSE */ - vmcb02->control.pause_filter_count = pause_count12; - vmcb02->control.pause_filter_thresh = pause_thresh12; - - } else { - /* start from host values otherwise */ - vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count; - vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh; - - /* ... but ensure filtering is disabled if so requested. */ - if (vmcb12_is_intercept(vmcb12_ctrl, INTERCEPT_PAUSE)) { - if (!pause_count12) - vmcb02->control.pause_filter_count = 0; - if (!pause_thresh12) - vmcb02->control.pause_filter_thresh = 0; - } - } + vmcb02->control.pause_filter_thresh = 0; /* * Take ALLOW_LARGER_RAP from vmcb12 even though it should be safe to @@ -1298,12 +1289,6 @@ void nested_svm_vmexit(struct vcpu_svm *svm) /* in case we halted in L2 */ kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); - if (!kvm_pause_in_guest(vcpu->kvm)) { - vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; - vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); - - } - /* * Invalidate last_bus_lock_rip unless KVM is still waiting for the * guest to make forward progress before re-enabling bus lock detection. diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e7fdd7a9c280..e02a38da5296 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -913,7 +913,15 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm)) + /* Adjusting pause_filter_count makes no sense if PLE is disabled. */ + WARN_ON_ONCE(kvm_pause_in_guest(vcpu->kvm)); + + /* + * While running L2, KVM should intercept PAUSE if and only if L1 wants + * to intercept PAUSE, and L1's intercept should take priority, i.e. + * KVM should never handle a PAUSE intercept from L2. + */ + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return; control->pause_filter_count = __grow_ple_window(old, @@ -934,7 +942,10 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm)) + /* Adjusting pause_filter_count makes no sense if PLE is disabled. */ + WARN_ON_ONCE(kvm_pause_in_guest(vcpu->kvm)); + + if (is_guest_mode(vcpu)) return; control->pause_filter_count = diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index e7fdbe9efc90..0db25bba17f6 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -154,7 +154,7 @@ TRACE_EVENT(kvm_xen_hypercall, __entry->a2 = a2; __entry->a3 = a3; __entry->a4 = a4; - __entry->a4 = a5; + __entry->a5 = a5; ), TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 56cacc06225e..31568274d8bb 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -14,6 +14,7 @@ extern bool __read_mostly flexpriority_enabled; extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; +extern bool __read_mostly enable_cet; extern bool __read_mostly enable_pml; extern int __read_mostly pt_mode; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5c2c33a5f7dc..49feecb286b2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -108,6 +108,9 @@ module_param_named(unrestricted_guest, bool __read_mostly enable_ept_ad_bits = 1; module_param_named(eptad, enable_ept_ad_bits, bool, 0444); +bool __read_mostly enable_cet = 1; +module_param_named(cet, enable_cet, bool, 0444); + static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, 0444); @@ -4476,7 +4479,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter * 3 and 4 for details. */ - if (cpu_has_load_cet_ctrl()) { + if (enable_cet) { vmcs_writel(HOST_S_CET, kvm_host.s_cet); vmcs_writel(HOST_SSP, 0); vmcs_writel(HOST_INTR_SSP_TABLE, 0); @@ -4532,6 +4535,10 @@ static u32 vmx_get_initial_vmentry_ctrl(void) if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); + + if (!enable_cet) + vmentry_ctrl &= ~VM_ENTRY_LOAD_CET_STATE; + /* * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. */ @@ -4546,6 +4553,9 @@ static u32 vmx_get_initial_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + if (!enable_cet) + vmexit_ctrl &= ~VM_EXIT_LOAD_CET_STATE; + /* * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for * nested virtualization and thus allowed to be set in vmcs12. @@ -8155,7 +8165,7 @@ static __init void vmx_set_cpu_caps(void) * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code * fails, so disable CET in this case too. */ - if (!cpu_has_load_cet_ctrl() || !enable_unrestricted_guest || + if (!enable_cet || !enable_unrestricted_guest || !cpu_has_vmx_basic_no_hw_errcode_cc()) { kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); @@ -8630,6 +8640,9 @@ __init int vmx_hardware_setup(void) !cpu_has_vmx_invept_global()) enable_ept = 0; + if (!cpu_has_load_cet_ctrl()) + enable_cet = 0; + /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { pr_err_ratelimited("NX (Execute Disable) not supported\n"); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ac8021c3a997..bb95a05259b8 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -695,17 +695,22 @@ static void __init xen_e820_resolve_conflicts(phys_addr_t start, return; end = start + size; - entry = xen_e820_table.entries; + mapcnt = 0; - for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + while (mapcnt < xen_e820_table.nr_entries) { + entry = xen_e820_table.entries + mapcnt; if (entry->addr >= end) return; if (entry->addr + entry->size > start && - entry->type == E820_TYPE_NVS) + entry->type == E820_TYPE_NVS) { xen_e820_swap_entry_with_ram(entry); + /* E820 map has been changed, restart loop! */ + mapcnt = 0; + continue; + } - entry++; + mapcnt++; } } diff --git a/block/ioctl.c b/block/ioctl.c index fc3be0549aa7..ab2c9ed79946 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -857,6 +857,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) #endif struct blk_iou_cmd { + u64 start; + u64 len; int res; bool nowait; }; @@ -946,23 +948,27 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); - const struct io_uring_sqe *sqe = cmd->sqe; u32 cmd_op = cmd->cmd_op; - uint64_t start, len; - if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || - sqe->rw_flags || sqe->file_index)) - return -EINVAL; + /* Read what we need from the SQE on the first issue */ + if (!(issue_flags & IORING_URING_CMD_REISSUE)) { + const struct io_uring_sqe *sqe = cmd->sqe; + + if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || + sqe->rw_flags || sqe->file_index)) + return -EINVAL; + + bic->start = READ_ONCE(sqe->addr); + bic->len = READ_ONCE(sqe->addr3); + } bic->res = 0; bic->nowait = issue_flags & IO_URING_F_NONBLOCK; - start = READ_ONCE(sqe->addr); - len = READ_ONCE(sqe->addr3); - switch (cmd_op) { case BLOCK_URING_CMD_DISCARD: - return blkdev_cmd_discard(cmd, bdev, start, len, bic->nowait); + return blkdev_cmd_discard(cmd, bdev, bic->start, bic->len, + bic->nowait); } return -EINVAL; } diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 2801378e3e19..3b7b008bccfe 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -537,6 +537,26 @@ static const struct file_operations ivpu_fops = { #endif }; +static int ivpu_gem_prime_handle_to_fd(struct drm_device *dev, struct drm_file *file_priv, + u32 handle, u32 flags, int *prime_fd) +{ + struct drm_gem_object *obj; + + obj = drm_gem_object_lookup(file_priv, handle); + if (!obj) + return -ENOENT; + + if (drm_gem_is_imported(obj)) { + /* Do not allow re-exporting */ + drm_gem_object_put(obj); + return -EOPNOTSUPP; + } + + drm_gem_object_put(obj); + + return drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd); +} + static const struct drm_driver driver = { .driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL, @@ -545,6 +565,7 @@ static const struct drm_driver driver = { .gem_create_object = ivpu_gem_create_object, .gem_prime_import = ivpu_gem_prime_import, + .prime_handle_to_fd = ivpu_gem_prime_handle_to_fd, .ioctls = ivpu_drm_ioctls, .num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls), diff --git a/drivers/accel/qaic/qaic_ras.c b/drivers/accel/qaic/qaic_ras.c index cc0b75461e1a..6791af366cba 100644 --- a/drivers/accel/qaic/qaic_ras.c +++ b/drivers/accel/qaic/qaic_ras.c @@ -497,11 +497,11 @@ static void decode_ras_msg(struct qaic_device *qdev, struct ras_data *msg) qdev->ce_count++; break; case UE: - if (qdev->ce_count != UINT_MAX) + if (qdev->ue_count != UINT_MAX) qdev->ue_count++; break; case UE_NF: - if (qdev->ce_count != UINT_MAX) + if (qdev->ue_nf_count != UINT_MAX) qdev->ue_nf_count++; break; default: diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs index ada1d1b4302e..081d19b09d4b 100644 --- a/drivers/android/binder/range_alloc/array.rs +++ b/drivers/android/binder/range_alloc/array.rs @@ -204,7 +204,6 @@ pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result // caller will mark them as unused, which means that they can be freed if the system comes // under memory pressure. let mut freed_range = FreedRange::interior_pages(offset, size); - #[expect(clippy::collapsible_if)] // reads better like this if offset % PAGE_SIZE != 0 { if i == 0 || self.ranges[i - 1].endpoint() <= (offset & PAGE_MASK) { freed_range.start_page_idx -= 1; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 8e5f3738c203..6d13f1481de0 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -900,6 +900,20 @@ static int ublk_validate_params(const struct ublk_device *ub) if (p->logical_bs_shift > PAGE_SHIFT || p->logical_bs_shift < 9) return -EINVAL; + /* + * 256M is a reasonable upper bound for physical block size, + * io_min and io_opt; it aligns with the maximum physical + * block size possible in NVMe. + */ + if (p->physical_bs_shift > ilog2(SZ_256M)) + return -EINVAL; + + if (p->io_min_shift > ilog2(SZ_256M)) + return -EINVAL; + + if (p->io_opt_shift > ilog2(SZ_256M)) + return -EINVAL; + if (p->logical_bs_shift > p->physical_bs_shift) return -EINVAL; @@ -2397,8 +2411,14 @@ static void ublk_reset_ch_dev(struct ublk_device *ub) { int i; - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_queue_reinit(ub, ublk_get_queue(ub, i)); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + + /* Sync with ublk_cancel_cmd() */ + spin_lock(&ubq->cancel_lock); + ublk_queue_reinit(ub, ubq); + spin_unlock(&ubq->cancel_lock); + } /* set to NULL, otherwise new tasks cannot mmap io_cmd_buf */ ub->mm = NULL; @@ -2739,6 +2759,7 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag, { struct ublk_io *io = &ubq->ios[tag]; struct ublk_device *ub = ubq->dev; + struct io_uring_cmd *cmd = NULL; struct request *req; bool done; @@ -2761,12 +2782,15 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag, spin_lock(&ubq->cancel_lock); done = !!(io->flags & UBLK_IO_FLAG_CANCELED); - if (!done) + if (!done) { io->flags |= UBLK_IO_FLAG_CANCELED; + cmd = io->cmd; + io->cmd = NULL; + } spin_unlock(&ubq->cancel_lock); - if (!done) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, issue_flags); + if (!done && cmd) + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, issue_flags); } /* @@ -3496,8 +3520,10 @@ static void ublk_ch_uring_cmd_cb(struct io_tw_req tw_req, io_tw_token_t tw) { unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS; struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req); - int ret = ublk_ch_uring_cmd_local(cmd, issue_flags); + int ret = -ECANCELED; + if (!tw.cancel) + ret = ublk_ch_uring_cmd_local(cmd, issue_flags); if (ret != -EIOCBQUEUED) io_uring_cmd_done(cmd, ret, issue_flags); } @@ -4990,13 +5016,15 @@ static int ublk_ctrl_set_params(struct ublk_device *ub, */ ret = -EACCES; } else if (copy_from_user(&ub->params, argp, ph.len)) { + /* zero out partial copy so no stale params survive */ + memset(&ub->params, 0, sizeof(ub->params)); ret = -EFAULT; } else { /* clear all we don't support yet */ ub->params.types &= UBLK_PARAM_TYPE_ALL; ret = ublk_validate_params(ub); if (ret) - ub->params.types = 0; + memset(&ub->params, 0, sizeof(ub->params)); } mutex_unlock(&ub->mutex); diff --git a/drivers/clk/clk-eyeq.c b/drivers/clk/clk-eyeq.c index c1dccedf8d5b..d9303c2c7aa5 100644 --- a/drivers/clk/clk-eyeq.c +++ b/drivers/clk/clk-eyeq.c @@ -110,6 +110,7 @@ struct eqc_match_data { const char *reset_auxdev_name; const char *pinctrl_auxdev_name; + const char *eth_phy_auxdev_name; unsigned int early_clk_count; }; @@ -321,38 +322,18 @@ static void eqc_probe_init_fixed_factors(struct device *dev, } } -static void eqc_auxdev_release(struct device *dev) -{ - struct auxiliary_device *adev = to_auxiliary_dev(dev); - - kfree(adev); -} - -static int eqc_auxdev_create(struct device *dev, void __iomem *base, - const char *name, u32 id) +static void eqc_auxdev_create_optional(struct device *dev, void __iomem *base, + const char *name) { struct auxiliary_device *adev; - int ret; - adev = kzalloc_obj(*adev); - if (!adev) - return -ENOMEM; - - adev->name = name; - adev->dev.parent = dev; - adev->dev.platform_data = (void __force *)base; - adev->dev.release = eqc_auxdev_release; - adev->id = id; - - ret = auxiliary_device_init(adev); - if (ret) - return ret; - - ret = auxiliary_device_add(adev); - if (ret) - auxiliary_device_uninit(adev); - - return ret; + if (name) { + adev = devm_auxiliary_device_create(dev, name, + (void __force *)base); + if (!adev) + dev_warn(dev, "failed creating auxiliary device %s.%s\n", + KBUILD_MODNAME, name); + } } static int eqc_probe(struct platform_device *pdev) @@ -364,7 +345,6 @@ static int eqc_probe(struct platform_device *pdev) unsigned int i, clk_count; struct resource *res; void __iomem *base; - int ret; data = device_get_match_data(dev); if (!data) @@ -378,21 +358,10 @@ static int eqc_probe(struct platform_device *pdev) if (!base) return -ENOMEM; - /* Init optional reset auxiliary device. */ - if (data->reset_auxdev_name) { - ret = eqc_auxdev_create(dev, base, data->reset_auxdev_name, 0); - if (ret) - dev_warn(dev, "failed creating auxiliary device %s.%s: %d\n", - KBUILD_MODNAME, data->reset_auxdev_name, ret); - } - - /* Init optional pinctrl auxiliary device. */ - if (data->pinctrl_auxdev_name) { - ret = eqc_auxdev_create(dev, base, data->pinctrl_auxdev_name, 0); - if (ret) - dev_warn(dev, "failed creating auxiliary device %s.%s: %d\n", - KBUILD_MODNAME, data->pinctrl_auxdev_name, ret); - } + /* Init optional auxiliary devices. */ + eqc_auxdev_create_optional(dev, base, data->reset_auxdev_name); + eqc_auxdev_create_optional(dev, base, data->pinctrl_auxdev_name); + eqc_auxdev_create_optional(dev, base, data->eth_phy_auxdev_name); if (data->pll_count + data->div_count + data->fixed_factor_count == 0) return 0; /* Zero clocks, we are done. */ @@ -553,6 +522,7 @@ static const struct eqc_match_data eqc_eyeq5_match_data = { .reset_auxdev_name = "reset", .pinctrl_auxdev_name = "pinctrl", + .eth_phy_auxdev_name = "phy", .early_clk_count = ARRAY_SIZE(eqc_eyeq5_early_plls) + ARRAY_SIZE(eqc_eyeq5_early_fixed_factors), diff --git a/drivers/clk/clk-rk808.c b/drivers/clk/clk-rk808.c index f7412b137e5e..5a75b5c91555 100644 --- a/drivers/clk/clk-rk808.c +++ b/drivers/clk/clk-rk808.c @@ -153,7 +153,7 @@ static int rk808_clkout_probe(struct platform_device *pdev) struct rk808_clkout *rk808_clkout; int ret; - dev->of_node = pdev->dev.parent->of_node; + device_set_of_node_from_dev(dev, dev->parent); rk808_clkout = devm_kzalloc(dev, sizeof(*rk808_clkout), GFP_KERNEL); diff --git a/drivers/clk/spacemit/ccu-k3.c b/drivers/clk/spacemit/ccu-k3.c index e98afd59f05c..bb8b75bdbdb3 100644 --- a/drivers/clk/spacemit/ccu-k3.c +++ b/drivers/clk/spacemit/ccu-k3.c @@ -846,7 +846,7 @@ static const struct clk_parent_data top_parents[] = { CCU_PARENT_HW(pll6_d3), }; CCU_MUX_DIV_GATE_FC_DEFINE(top_dclk, top_parents, APMU_TOP_DCLK_CTRL, 5, 3, - BIT(8), 2, 3, BIT(1), 0); + BIT(8), 2, 3, BIT(1), CLK_IS_CRITICAL); static const struct clk_parent_data ucie_parents[] = { CCU_PARENT_HW(pll1_d8_307p2), diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index ec1315582414..97ec05d68bbb 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -777,9 +777,9 @@ static int init_one_mc(struct mc_priv *priv, struct platform_device *pdev, int i u32 num_chans, rank, dwidth, config; struct edac_mc_layer layers[2]; struct mem_ctl_info *mci; + char name[MC_NAME_LEN]; struct device *dev; enum dev_type dt; - char *name; int rc; config = priv->adec[CONF + i * ADEC_NUM]; @@ -813,13 +813,9 @@ static int init_one_mc(struct mc_priv *priv, struct platform_device *pdev, int i layers[1].is_virt_csrow = false; rc = -ENOMEM; - name = kzalloc(MC_NAME_LEN, GFP_KERNEL); - if (!name) - return rc; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) - goto err_name_free; + return rc; mci = edac_mc_alloc(i, ARRAY_SIZE(layers), layers, sizeof(struct mc_priv)); if (!mci) { @@ -858,8 +854,6 @@ static int init_one_mc(struct mc_priv *priv, struct platform_device *pdev, int i edac_mc_free(mci); err_dev_free: kfree(dev); -err_name_free: - kfree(name); return rc; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 46aae3fad4bf..60debd543e44 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -3149,11 +3149,7 @@ static int __init amdgpu_init(void) r = amdgpu_sync_init(); if (r) - goto error_sync; - - r = amdgpu_userq_fence_slab_init(); - if (r) - goto error_fence; + return r; amdgpu_register_atpx_handler(); amdgpu_acpi_detect(); @@ -3161,7 +3157,7 @@ static int __init amdgpu_init(void) /* Ignore KFD init failures when CONFIG_HSA_AMD is not set. */ r = amdgpu_amdkfd_init(); if (r && r != -ENOENT) - goto error_fence; + goto error_fini_sync; if (amdgpu_pp_feature_mask & PP_OVERDRIVE_MASK) { add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); @@ -3172,10 +3168,8 @@ static int __init amdgpu_init(void) /* let modprobe override vga console setting */ return pci_register_driver(&amdgpu_kms_pci_driver); -error_fence: +error_fini_sync: amdgpu_sync_fini(); - -error_sync: return r; } @@ -3186,7 +3180,6 @@ static void __exit amdgpu_exit(void) amdgpu_unregister_atpx_handler(); amdgpu_acpi_release(); amdgpu_sync_fini(); - amdgpu_userq_fence_slab_fini(); mmu_notifier_synchronize(); amdgpu_xcp_drv_release(); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index bc772ca3dab7..b6f849d51c2e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -262,12 +262,19 @@ void amdgpu_gart_table_ram_free(struct amdgpu_device *adev) */ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev) { + int r; + if (adev->gart.bo != NULL) return 0; - return amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, - NULL, (void *)&adev->gart.ptr); + r = amdgpu_bo_create_kernel(adev, adev->gart.table_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, &adev->gart.bo, + NULL, (void *)&adev->gart.ptr); + if (r) + return r; + + memset_io(adev->gart.ptr, adev->gart.gart_pte_flags, adev->gart.table_size); + return 0; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index da39ac862f37..e2d5f04296e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -32,29 +32,9 @@ #include "amdgpu.h" #include "amdgpu_userq_fence.h" -static const struct dma_fence_ops amdgpu_userq_fence_ops; -static struct kmem_cache *amdgpu_userq_fence_slab; - #define AMDGPU_USERQ_MAX_HANDLES (1U << 16) -int amdgpu_userq_fence_slab_init(void) -{ - amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence", - sizeof(struct amdgpu_userq_fence), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!amdgpu_userq_fence_slab) - return -ENOMEM; - - return 0; -} - -void amdgpu_userq_fence_slab_fini(void) -{ - rcu_barrier(); - kmem_cache_destroy(amdgpu_userq_fence_slab); -} +static const struct dma_fence_ops amdgpu_userq_fence_ops; static inline struct amdgpu_userq_fence *to_amdgpu_userq_fence(struct dma_fence *f) { @@ -231,7 +211,7 @@ void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv) static int amdgpu_userq_fence_alloc(struct amdgpu_userq_fence **userq_fence) { - *userq_fence = kmem_cache_alloc(amdgpu_userq_fence_slab, GFP_ATOMIC); + *userq_fence = kmalloc(sizeof(**userq_fence), GFP_KERNEL); return *userq_fence ? 0 : -ENOMEM; } @@ -342,7 +322,7 @@ static void amdgpu_userq_fence_free(struct rcu_head *rcu) amdgpu_userq_fence_driver_put(fence_drv); kvfree(userq_fence->fence_drv_array); - kmem_cache_free(amdgpu_userq_fence_slab, userq_fence); + kfree(userq_fence); } static void amdgpu_userq_fence_release(struct dma_fence *f) @@ -545,7 +525,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, r = amdgpu_userq_fence_create(queue, userq_fence, wptr, &fence); if (r) { mutex_unlock(&userq_mgr->userq_mutex); - kmem_cache_free(amdgpu_userq_fence_slab, userq_fence); + kfree(userq_fence); goto put_gobj_write; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h index d56246ad8c26..d355a0eecc07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h @@ -58,9 +58,6 @@ struct amdgpu_userq_fence_driver { char timeline_name[TASK_COMM_LEN]; }; -int amdgpu_userq_fence_slab_init(void); -void amdgpu_userq_fence_slab_fini(void); - void amdgpu_userq_fence_driver_get(struct amdgpu_userq_fence_driver *fence_drv); void amdgpu_userq_fence_driver_put(struct amdgpu_userq_fence_driver *fence_drv); int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 95be105671ec..86c7c2a429b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -5660,9 +5660,6 @@ static void gfx_v9_0_ring_emit_fence_kiq(struct amdgpu_ring *ring, u64 addr, { struct amdgpu_device *adev = ring->adev; - /* we only allocate 32bit for each seq wb address */ - BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - /* write fence seq to the "addr" */ amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) | diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index 2fc39a6938f6..5b4121ddc78c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -30,34 +30,6 @@ #define AMDGPU_USERQ_PROC_CTX_SZ PAGE_SIZE #define AMDGPU_USERQ_GANG_CTX_SZ PAGE_SIZE -static int -mes_userq_map_gtt_bo_to_gart(struct amdgpu_bo *bo) -{ - int ret; - - ret = amdgpu_bo_reserve(bo, true); - if (ret) { - DRM_ERROR("Failed to reserve bo. ret %d\n", ret); - goto err_reserve_bo_failed; - } - - ret = amdgpu_ttm_alloc_gart(&bo->tbo); - if (ret) { - DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret); - goto err_map_bo_gart_failed; - } - - amdgpu_bo_unreserve(bo); - bo = amdgpu_bo_ref(bo); - - return 0; - -err_map_bo_gart_failed: - amdgpu_bo_unreserve(bo); -err_reserve_bo_failed: - return ret; -} - static int mes_userq_create_wptr_mapping(struct amdgpu_device *adev, struct amdgpu_userq_mgr *uq_mgr, @@ -65,55 +37,62 @@ mes_userq_create_wptr_mapping(struct amdgpu_device *adev, uint64_t wptr) { struct amdgpu_bo_va_mapping *wptr_mapping; - struct amdgpu_vm *wptr_vm; struct amdgpu_userq_obj *wptr_obj = &queue->wptr_obj; + struct amdgpu_bo *obj; + struct amdgpu_vm *vm = queue->vm; + struct drm_exec exec; int ret; - wptr_vm = queue->vm; - ret = amdgpu_bo_reserve(wptr_vm->root.bo, false); - if (ret) - return ret; - wptr &= AMDGPU_GMC_HOLE_MASK; - wptr_mapping = amdgpu_vm_bo_lookup_mapping(wptr_vm, wptr >> PAGE_SHIFT); - amdgpu_bo_unreserve(wptr_vm->root.bo); - if (!wptr_mapping) { - DRM_ERROR("Failed to lookup wptr bo\n"); - return -EINVAL; + + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 2); + drm_exec_until_all_locked(&exec) { + ret = amdgpu_vm_lock_pd(vm, &exec, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto fail_lock; + + wptr_mapping = amdgpu_vm_bo_lookup_mapping(vm, wptr >> PAGE_SHIFT); + if (!wptr_mapping) { + ret = -EINVAL; + goto fail_lock; + } + + obj = wptr_mapping->bo_va->base.bo; + ret = drm_exec_lock_obj(&exec, &obj->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto fail_lock; } - wptr_obj->obj = wptr_mapping->bo_va->base.bo; + wptr_obj->obj = amdgpu_bo_ref(wptr_mapping->bo_va->base.bo); if (wptr_obj->obj->tbo.base.size > PAGE_SIZE) { - DRM_ERROR("Requested GART mapping for wptr bo larger than one page\n"); - return -EINVAL; - } - - ret = mes_userq_map_gtt_bo_to_gart(wptr_obj->obj); - if (ret) { - DRM_ERROR("Failed to map wptr bo to GART\n"); - return ret; - } - - ret = amdgpu_bo_reserve(wptr_obj->obj, true); - if (ret) { - DRM_ERROR("Failed to reserve wptr bo\n"); - return ret; + ret = -EINVAL; + goto fail_map; } /* TODO use eviction fence instead of pinning. */ ret = amdgpu_bo_pin(wptr_obj->obj, AMDGPU_GEM_DOMAIN_GTT); if (ret) { - drm_file_err(uq_mgr->file, "[Usermode queues] Failed to pin wptr bo\n"); - goto unresv_bo; + DRM_ERROR("Failed to pin wptr bo. ret %d\n", ret); + goto fail_map; + } + + ret = amdgpu_ttm_alloc_gart(&wptr_obj->obj->tbo); + if (ret) { + DRM_ERROR("Failed to bind bo to GART. ret %d\n", ret); + goto fail_map; } queue->wptr_obj.gpu_addr = amdgpu_bo_gpu_offset(wptr_obj->obj); - amdgpu_bo_unreserve(wptr_obj->obj); + drm_exec_fini(&exec); return 0; -unresv_bo: - amdgpu_bo_unreserve(wptr_obj->obj); +fail_map: + amdgpu_bo_unref(&wptr_obj->obj); +fail_lock: + drm_exec_fini(&exec); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 44f0f23e1148..e64f2f6df9a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -889,7 +889,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /* write the fence */ amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, lower_32_bits(seq)); @@ -899,7 +899,7 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se addr += 4; amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_FENCE)); /* zero in first two bits */ - BUG_ON(addr & 0x3); + WARN_ON(addr & 0x3); amdgpu_ring_write(ring, lower_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(addr)); amdgpu_ring_write(ring, upper_32_bits(seq)); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f829d65a79b4..f95bf6d95534 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1360,7 +1360,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); if (WARN_ON_ONCE(!peer_pdd)) continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(peer_pdd); } kfree(devices_arr); @@ -1455,7 +1455,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, if (WARN_ON_ONCE(!peer_pdd)) continue; if (flush_tlb) - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(peer_pdd); /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 8ff97bf7d95a..b7f8f7ff8198 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1737,37 +1737,6 @@ bool kgd2kfd_vmfault_fast_path(struct amdgpu_device *adev, struct amdgpu_iv_entr return false; } -/* check if there is kfd process still uses adev */ -static bool kgd2kfd_check_device_idle(struct amdgpu_device *adev) -{ - struct kfd_process *p; - struct hlist_node *p_temp; - unsigned int temp; - struct kfd_node *dev; - - mutex_lock(&kfd_processes_mutex); - - if (hash_empty(kfd_processes_table)) { - mutex_unlock(&kfd_processes_mutex); - return true; - } - - /* check if there is device still use adev */ - hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) { - for (int i = 0; i < p->n_pdds; i++) { - dev = p->pdds[i]->dev; - if (dev->adev == adev) { - mutex_unlock(&kfd_processes_mutex); - return false; - } - } - } - - mutex_unlock(&kfd_processes_mutex); - - return true; -} - /** kgd2kfd_teardown_processes - gracefully tear down existing * kfd processes that use adev * @@ -1800,7 +1769,7 @@ void kgd2kfd_teardown_processes(struct amdgpu_device *adev) mutex_unlock(&kfd_processes_mutex); /* wait all kfd processes use adev terminate */ - while (!kgd2kfd_check_device_idle(adev)) + while (!!atomic_read(&adev->kfd.dev->kfd_processes_count)) cond_resched(); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ab3b2e7be9bd..9185ebe4c079 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -572,7 +572,7 @@ static int allocate_vmid(struct device_queue_manager *dqm, qpd->vmid, qpd->page_table_base); /* invalidate the VM context after pasid and vmid mapping is set up */ - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); if (dqm->dev->kfd2kgd->set_scratch_backing_va) dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->adev, @@ -610,7 +610,7 @@ static void deallocate_vmid(struct device_queue_manager *dqm, if (flush_texture_cache_nocpsch(q->device, qpd)) dev_err(dev, "Failed to flush TC\n"); - kfd_flush_tlb(qpd_to_pdd(qpd), TLB_FLUSH_LEGACY); + kfd_flush_tlb(qpd_to_pdd(qpd)); /* Release the vmid mapping */ set_pasid_vmid_mapping(dqm, 0, qpd->vmid); @@ -1284,7 +1284,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, dqm->dev->adev, qpd->vmid, qpd->page_table_base); - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } /* Take a safe reference to the mm_struct, which may otherwise diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 163d665a6074..7b5b12206919 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1554,13 +1554,13 @@ void kfd_signal_reset_event(struct kfd_node *dev); void kfd_signal_poison_consumed_event(struct kfd_node *dev, u32 pasid); void kfd_signal_process_terminate_event(struct kfd_process *p); -static inline void kfd_flush_tlb(struct kfd_process_device *pdd, - enum TLB_FLUSH_TYPE type) +static inline void kfd_flush_tlb(struct kfd_process_device *pdd) { struct amdgpu_device *adev = pdd->dev->adev; struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv); - amdgpu_vm_flush_compute_tlb(adev, vm, type, pdd->dev->xcc_mask); + amdgpu_vm_flush_compute_tlb(adev, vm, TLB_FLUSH_HEAVYWEIGHT, + pdd->dev->xcc_mask); } static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 38085a0a0f58..35ec67d9739b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1424,7 +1424,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start, if (r) break; } - kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT); + kfd_flush_tlb(pdd); } return r; @@ -1571,7 +1571,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset, } } - kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY); + kfd_flush_tlb(pdd); } return r; diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index 731355bdb9bc..3650e7beeb67 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -1333,12 +1333,13 @@ static int ci_populate_all_memory_levels(struct pp_hwmgr *hwmgr) dev_id = adev->pdev->device; - if ((dpm_table->mclk_table.count >= 2) - && ((dev_id == 0x67B0) || (dev_id == 0x67B1))) { - smu_data->smc_state_table.MemoryLevel[1].MinVddci = - smu_data->smc_state_table.MemoryLevel[0].MinVddci; - smu_data->smc_state_table.MemoryLevel[1].MinMvdd = - smu_data->smc_state_table.MemoryLevel[0].MinMvdd; + if ((dpm_table->mclk_table.count >= 2) && + ((dev_id == 0x67B0) || (dev_id == 0x67B1)) && + (adev->pdev->revision == 0)) { + smu_data->smc_state_table.MemoryLevel[1].MinVddc = + smu_data->smc_state_table.MemoryLevel[0].MinVddc; + smu_data->smc_state_table.MemoryLevel[1].MinVddcPhases = + smu_data->smc_state_table.MemoryLevel[0].MinVddcPhases; } smu_data->smc_state_table.MemoryLevel[0].ActivityLevel = 0x1F; CONVERT_FROM_HOST_TO_SMC_US(smu_data->smc_state_table.MemoryLevel[0].ActivityLevel); diff --git a/drivers/gpu/drm/bridge/tda998x_drv.c b/drivers/gpu/drm/bridge/tda998x_drv.c index d9b388165de1..6c427bc75896 100644 --- a/drivers/gpu/drm/bridge/tda998x_drv.c +++ b/drivers/gpu/drm/bridge/tda998x_drv.c @@ -1293,7 +1293,7 @@ static const struct drm_edid *tda998x_edid_read(struct tda998x_priv *priv, * can't handle signals gracefully. */ if (tda998x_edid_delay_wait(priv)) - return 0; + return NULL; if (priv->rev == TDA19988) reg_clear(priv, REG_TX4, TX4_PD_RAM); @@ -1762,7 +1762,7 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = { static int tda998x_get_audio_ports(struct tda998x_priv *priv, struct device_node *np) { - const u32 *port_data; + const __be32 *port_data; u32 size; int i; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index a80a335f4148..1541fc8a9ac2 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -490,7 +490,7 @@ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, * the number of horizontal pixels that need an update. */ off_t bit_off = (off % line_length) * 8; - off_t bit_end = (end % line_length) * 8; + off_t bit_end = bit_off + len * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index d6424267260b..51a887cc7fd7 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1019,7 +1019,7 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_change_handle *args = data; - struct drm_gem_object *obj; + struct drm_gem_object *obj, *idrobj; int handle, ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) @@ -1042,8 +1042,29 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, mutex_lock(&file_priv->prime.lock); spin_lock(&file_priv->table_lock); + + /* When create_tail allocs an obj idr, it needs to first alloc as NULL, + * then later replace with the correct object. This is not necessary + * here, because the only operations that could race are drm_prime + * bookkeeping, and we hold the prime lock. + */ ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1, GFP_NOWAIT); + + if (ret < 0) { + spin_unlock(&file_priv->table_lock); + goto out_unlock; + } + + idrobj = idr_replace(&file_priv->object_idr, NULL, handle); + if (idrobj != obj) { + idr_replace(&file_priv->object_idr, idrobj, handle); + idr_remove(&file_priv->object_idr, args->new_handle); + spin_unlock(&file_priv->table_lock); + ret = -ENOENT; + goto out_unlock; + } + spin_unlock(&file_priv->table_lock); if (ret < 0) @@ -1055,6 +1076,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, if (ret < 0) { spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, handle); + idrobj = idr_replace(&file_priv->object_idr, obj, handle); + WARN_ON(idrobj != NULL); spin_unlock(&file_priv->table_lock); goto out_unlock; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index df4232d7e135..3cc50d697c89 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -116,16 +116,18 @@ int etnaviv_sched_push_job(struct etnaviv_gem_submit *submit) */ mutex_lock(&gpu->sched_lock); + ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id, + NULL, xa_limit_32b, &gpu->next_user_fence, + GFP_KERNEL); + if (ret < 0) + goto out_unlock; + drm_sched_job_arm(&submit->sched_job); submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished); - ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id, - submit->out_fence, xa_limit_32b, - &gpu->next_user_fence, GFP_KERNEL); - if (ret < 0) { - drm_sched_job_cleanup(&submit->sched_job); - goto out_unlock; - } + + xa_store(&gpu->user_fences, submit->out_fence_id, + submit->out_fence, GFP_KERNEL); /* the scheduler holds on to the job now */ kref_get(&submit->refcount); diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 29a8366513fa..e68c954ec3e6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -423,7 +423,9 @@ static int exynos_mic_probe(struct platform_device *pdev) mic->bridge.of_node = dev->of_node; - drm_bridge_add(&mic->bridge); + ret = devm_drm_bridge_add(dev, &mic->bridge); + if (ret) + goto err; pm_runtime_enable(dev); @@ -443,12 +445,8 @@ static int exynos_mic_probe(struct platform_device *pdev) static void exynos_mic_remove(struct platform_device *pdev) { - struct exynos_mic *mic = platform_get_drvdata(pdev); - component_del(&pdev->dev, &exynos_mic_component_ops); pm_runtime_disable(&pdev->dev); - - drm_bridge_remove(&mic->bridge); } static const struct of_device_id exynos_mic_of_match[] = { diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 385a634c3ed0..d9be7a5a239c 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -750,9 +750,8 @@ static bool has_auxccs(struct drm_device *drm) { struct drm_i915_private *i915 = to_i915(drm); - return IS_GRAPHICS_VER(i915, 9, 12) || - IS_ALDERLAKE_P(i915) || - IS_METEORLAKE(i915); + return IS_GRAPHICS_VER(i915, 9, 12) && + !HAS_FLAT_CCS(i915); } static bool has_fenced_regions(struct drm_device *drm) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 72848ed80df7..b101e14f841e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2513,6 +2513,7 @@ static const struct nvkm_device_chip nv170_chipset = { .name = "GA100", .bar = { 0x00000001, tu102_bar_new }, + .bios = { 0x00000001, nvkm_bios_new }, .devinit = { 0x00000001, ga100_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, .fb = { 0x00000001, ga100_fb_new }, @@ -2529,7 +2530,6 @@ nv170_chipset = { .vfn = { 0x00000001, ga100_vfn_new }, .ce = { 0x000003ff, ga100_ce_new }, .fifo = { 0x00000001, ga100_fifo_new }, - .sec2 = { 0x00000001, tu102_sec2_new }, }; static const struct nvkm_device_chip @@ -3341,7 +3341,6 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x166: device->chip = &nv166_chipset; break; case 0x167: device->chip = &nv167_chipset; break; case 0x168: device->chip = &nv168_chipset; break; - case 0x170: device->chip = &nv170_chipset; break; case 0x172: device->chip = &nv172_chipset; break; case 0x173: device->chip = &nv173_chipset; break; case 0x174: device->chip = &nv174_chipset; break; @@ -3361,6 +3360,14 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x1b6: device->chip = &nv1b6_chipset; break; case 0x1b7: device->chip = &nv1b7_chipset; break; default: + if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) { + switch (device->chipset) { + case 0x170: device->chip = &nv170_chipset; break; + default: + break; + } + } + if (!device->chip) { nvdev_error(device, "unknown chipset (%08x)\n", boot0); ret = -ENODEV; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c index fdd820eeef81..27a13aeccd3c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c @@ -41,11 +41,15 @@ ga100_gsp_flcn = { static const struct nvkm_gsp_func ga100_gsp = { .flcn = &ga100_gsp_flcn, + .fwsec = &tu102_gsp_fwsec, .sig_section = ".fwsignature_ga100", .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c index dd82c76b8b9a..19cb269e7a26 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c @@ -318,13 +318,8 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp) if (ret) return ret; - /* - * Calculate FB layout. FRTS is a memory region created by the FWSEC-FRTS firmware. - * FWSEC comes from VBIOS. So on systems with no VBIOS (e.g. GA100), the FRTS does - * not exist. Therefore, use the existence of VBIOS to determine whether to reserve - * an FRTS region. - */ - gsp->fb.wpr2.frts.size = device->bios ? 0x100000 : 0; + /* Calculate FB layout. */ + gsp->fb.wpr2.frts.size = 0x100000; gsp->fb.wpr2.frts.addr = ALIGN_DOWN(gsp->fb.bios.addr, 0x20000) - gsp->fb.wpr2.frts.size; gsp->fb.wpr2.boot.size = gsp->boot.fw.size; @@ -348,12 +343,9 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp) if (ret) return ret; - /* Only boot FWSEC-FRTS if it actually exists */ - if (gsp->fb.wpr2.frts.size) { - ret = nvkm_gsp_fwsec_frts(gsp); - if (WARN_ON(ret)) - return ret; - } + ret = nvkm_gsp_fwsec_frts(gsp); + if (WARN_ON(ret)) + return ret; /* Reset GSP into RISC-V mode. */ ret = gsp->func->reset(gsp); diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index d6863b28ddc5..d592f4f4b939 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -208,6 +208,7 @@ config DRM_PANEL_HIMAX_HX83121A depends on OF depends on DRM_MIPI_DSI depends on BACKLIGHT_CLASS_DEVICE + select DRM_DISPLAY_DSC_HELPER select DRM_KMS_HELPER help Say Y here if you want to enable support for Himax HX83121A-based diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index d5fe105bdbdd..658ce64c71eb 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1324,6 +1324,8 @@ static int boe_panel_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&ctx); + boe->dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&ctx, 150); return ctx.accum_err; diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c index 4f8d6d8c07e4..dbdb7e3cb7b6 100644 --- a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c +++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c @@ -98,9 +98,7 @@ static int feiyang_enable(struct drm_panel *panel) /* T12 (video & logic signal rise + backlight rise) T12 >= 200ms */ msleep(200); - mipi_dsi_dcs_set_display_on(ctx->dsi); - - return 0; + return mipi_dsi_dcs_set_display_on(ctx->dsi); } static int feiyang_disable(struct drm_panel *panel) diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 8b2a68ee851e..a5e5c9ea7a73 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -937,6 +937,8 @@ static int hx83102_disable(struct drm_panel *panel) mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx); + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + mipi_dsi_msleep(&dsi_ctx, 150); return dsi_ctx.accum_err; diff --git a/drivers/gpu/drm/panel/panel-himax-hx83121a.c b/drivers/gpu/drm/panel/panel-himax-hx83121a.c index ebe643ba4184..bed79aa06f46 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83121a.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83121a.c @@ -596,8 +596,8 @@ static int himax_probe(struct mipi_dsi_device *dsi) ctx = devm_drm_panel_alloc(dev, struct himax, panel, &himax_panel_funcs, DRM_MODE_CONNECTOR_DSI); - if (!ctx) - return -ENOMEM; + if (IS_ERR(ctx)) + return PTR_ERR(ctx); ret = devm_regulator_bulk_get_const(&dsi->dev, ARRAY_SIZE(himax_supplies), diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index 2bbb1168a3ff..1e6a2392d7c6 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -118,12 +118,13 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Complete initialization. */ ret = drm_dev_register(&qdev->ddev, ent->driver_data); if (ret) - goto modeset_cleanup; + goto poll_fini; drm_client_setup(&qdev->ddev, NULL); return 0; -modeset_cleanup: +poll_fini: + drm_kms_helper_poll_fini(&qdev->ddev); qxl_modeset_fini(qdev); unload: qxl_device_fini(qdev); @@ -154,6 +155,7 @@ qxl_pci_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + drm_kms_helper_poll_fini(dev); drm_dev_unregister(dev); drm_atomic_helper_shutdown(dev); if (pci_is_vga(pdev) && pdev->revision < 5) diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 22321eb95b7d..703848fac189 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -2461,7 +2461,8 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { if ((memory_clock > 100000) && (memory_clock <= 125000)) { tmp2 = (((0x31 * engine_clock) / 125000) - 1) & 0xff; *dram_timimg2 &= ~0x00ff0000; @@ -3304,7 +3305,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev) pi->smc_state_table.MemoryLevel[0].EnabledForActivity = 1; if ((dpm_table->mclk_table.count >= 2) && - ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1))) { + ((rdev->pdev->device == 0x67B0) || (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { pi->smc_state_table.MemoryLevel[1].MinVddc = pi->smc_state_table.MemoryLevel[0].MinVddc; pi->smc_state_table.MemoryLevel[1].MinVddcPhases = @@ -4493,7 +4495,8 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev, if (patch && ((rdev->pdev->device == 0x67B0) || - (rdev->pdev->device == 0x67B1))) { + (rdev->pdev->device == 0x67B1)) && + (rdev->pdev->revision == 0)) { for (i = 0; i < table->last; i++) { if (table->last >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE) return -EINVAL; diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index b7397827889c..360a88ca8f0c 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -741,6 +741,7 @@ static int sti_hda_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct sti_hda *hda; struct resource *res; + int ret; DRM_INFO("%s\n", __func__); @@ -779,7 +780,9 @@ static int sti_hda_probe(struct platform_device *pdev) return PTR_ERR(hda->clk_hddac); } - drm_bridge_add(&hda->bridge); + ret = devm_drm_bridge_add(dev, &hda->bridge); + if (ret) + return ret; platform_set_drvdata(pdev, hda); @@ -788,10 +791,7 @@ static int sti_hda_probe(struct platform_device *pdev) static void sti_hda_remove(struct platform_device *pdev) { - struct sti_hda *hda = platform_get_drvdata(pdev); - component_del(&pdev->dev, &sti_hda_ops); - drm_bridge_remove(&hda->bridge); } static const struct of_device_id hda_of_match[] = { diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 222e4ae1abbd..5d8dc5efec77 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -761,25 +761,21 @@ static int bochs_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent ret = pcim_enable_device(pdev); if (ret) - goto err_free_dev; + return ret; pci_set_drvdata(pdev, dev); ret = bochs_load(bochs); if (ret) - goto err_free_dev; + return ret; ret = drm_dev_register(dev, 0); if (ret) - goto err_free_dev; + return ret; drm_client_setup(dev, NULL); return ret; - -err_free_dev: - drm_dev_put(dev); - return ret; } static void bochs_pci_remove(struct pci_dev *pdev) diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 26a3689e5fd9..278bbe7a11ad 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -206,6 +206,14 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, return NULL; } +static void __free_pages_gpu_account(struct page *p, unsigned int order, + bool reclaim) +{ + mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, + -(1 << order)); + __free_pages(p, order); +} + /* Reset the caching and pages of size 1 << order */ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order, struct page *p, bool reclaim) @@ -223,9 +231,7 @@ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching, #endif if (!pool || !ttm_pool_uses_dma_alloc(pool)) { - mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, - -(1 << order)); - __free_pages(p, order); + __free_pages_gpu_account(p, order, reclaim); return; } @@ -606,7 +612,7 @@ static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore, */ ttm_pool_split_for_swap(restore->pool, p); copy_highpage(restore->alloced_page + i, p); - __free_pages(p, 0); + __free_pages_gpu_account(p, 0, false); } restore->restored_pages++; @@ -1068,7 +1074,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, if (flags->purge) { shrunken += num_pages; page->private = 0; - __free_pages(page, order); + __free_pages_gpu_account(page, order, false); memset(tt->pages + i, 0, num_pages * sizeof(*tt->pages)); } @@ -1109,7 +1115,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, } handle = shandle; tt->pages[i] = ttm_backup_handle_to_page_ptr(handle); - put_page(page); + __free_pages_gpu_account(page, 0, false); shrunken++; } diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c index 29c72aa4b0d2..33494b86205d 100644 --- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c +++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c @@ -37,9 +37,17 @@ static bool intel_hdcp_gsc_check_status(struct drm_device *drm) struct xe_device *xe = to_xe_device(drm); struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_gt *gt = tile->media_gt; - struct xe_gsc *gsc = >->uc.gsc; + struct xe_gsc *gsc; - if (!gsc || !xe_uc_fw_is_available(&gsc->fw)) { + if (!gt) { + drm_dbg_kms(&xe->drm, + "not checking GSC status for HDCP2.x: media GT not present or disabled\n"); + return false; + } + + gsc = >->uc.gsc; + + if (!xe_uc_fw_is_available(&gsc->fw)) { drm_dbg_kms(&xe->drm, "GSC Components not ready for HDCP2.x\n"); return false; diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c index 87a164efcc33..01fe03b9efe8 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c @@ -385,10 +385,10 @@ static int pf_migration_mmio_save(struct xe_gt *gt, unsigned int vfid, void *buf if (xe_gt_is_media_type(gt)) for (n = 0; n < MED_VF_SW_FLAG_COUNT; n++) - regs[n] = xe_mmio_read32(>->mmio, MED_VF_SW_FLAG(n)); + regs[n] = xe_mmio_read32(&mmio, MED_VF_SW_FLAG(n)); else for (n = 0; n < VF_SW_FLAG_COUNT; n++) - regs[n] = xe_mmio_read32(>->mmio, VF_SW_FLAG(n)); + regs[n] = xe_mmio_read32(&mmio, VF_SW_FLAG(n)); return 0; } @@ -407,10 +407,10 @@ static int pf_migration_mmio_restore(struct xe_gt *gt, unsigned int vfid, if (xe_gt_is_media_type(gt)) for (n = 0; n < MED_VF_SW_FLAG_COUNT; n++) - xe_mmio_write32(>->mmio, MED_VF_SW_FLAG(n), regs[n]); + xe_mmio_write32(&mmio, MED_VF_SW_FLAG(n), regs[n]); else for (n = 0; n < VF_SW_FLAG_COUNT; n++) - xe_mmio_write32(>->mmio, VF_SW_FLAG(n), regs[n]); + xe_mmio_write32(&mmio, VF_SW_FLAG(n), regs[n]); return 0; } diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index 81b5f01b1f65..2b835d48b565 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -512,12 +512,9 @@ static void guc_golden_lrc_init(struct xe_guc_ads *ads) * that starts after the execlists LRC registers. This is * required to allow the GuC to restore just the engine state * when a watchdog reset occurs. - * We calculate the engine state size by removing the size of - * what comes before it in the context image (which is identical - * on all engines). */ ads_blob_write(ads, ads.eng_state_size[guc_class], - real_size - xe_lrc_skip_size(xe)); + xe_lrc_engine_state_size(gt, class)); ads_blob_write(ads, ads.golden_context_lrca[guc_class], addr_ggtt); diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index c725cde4508d..4af9f0d7c6f3 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -746,9 +746,16 @@ size_t xe_lrc_reg_size(struct xe_device *xe) return 80 * sizeof(u32); } -size_t xe_lrc_skip_size(struct xe_device *xe) +/** + * xe_lrc_engine_state_size() - Get size of the engine state within LRC + * @gt: the &xe_gt struct instance + * @class: Hardware engine class + * + * Returns: Size of the engine state + */ +size_t xe_lrc_engine_state_size(struct xe_gt *gt, enum xe_engine_class class) { - return LRC_PPHWSP_SIZE + xe_lrc_reg_size(xe); + return xe_gt_lrc_hang_replay_size(gt, class) - xe_lrc_reg_size(gt_to_xe(gt)); } static inline u32 __xe_lrc_seqno_offset(struct xe_lrc *lrc) diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index e7c975f9e2d9..5440663183f6 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -130,7 +130,7 @@ u32 xe_lrc_parallel_ggtt_addr(struct xe_lrc *lrc); struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc); size_t xe_lrc_reg_size(struct xe_device *xe); -size_t xe_lrc_skip_size(struct xe_device *xe); +size_t xe_lrc_engine_state_size(struct xe_gt *gt, enum xe_engine_class class); void xe_lrc_dump_default(struct drm_printer *p, struct xe_gt *gt, diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c index 6c4b16409cc9..150a241110fb 100644 --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c @@ -149,10 +149,11 @@ pf_migration_consume(struct xe_device *xe, unsigned int vfid) for_each_gt(gt, xe, gt_id) { data = xe_gt_sriov_pf_migration_save_consume(gt, vfid); - if (data && PTR_ERR(data) != EAGAIN) + if (!data) + continue; + if (!IS_ERR(data) || PTR_ERR(data) != -EAGAIN) return data; - if (PTR_ERR(data) == -EAGAIN) - more_data = true; + more_data = true; } if (!more_data) diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 4788996aa137..982ee2c6f9de 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -201,7 +201,6 @@ obj-$(CONFIG_SENSORS_PWM_FAN) += pwm-fan.o obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON) += qnap-mcu-hwmon.o obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON) += raspberrypi-hwmon.o obj-$(CONFIG_SENSORS_SBTSI) += sbtsi_temp.o -obj-$(CONFIG_SENSORS_SBRMI) += sbrmi.o obj-$(CONFIG_SENSORS_SCH56XX_COMMON)+= sch56xx-common.o obj-$(CONFIG_SENSORS_SCH5627) += sch5627.o obj-$(CONFIG_SENSORS_SCH5636) += sch5636.o diff --git a/drivers/hwmon/ads7871.c b/drivers/hwmon/ads7871.c index 9bfdf9e6bcd7..9ee3ce01f130 100644 --- a/drivers/hwmon/ads7871.c +++ b/drivers/hwmon/ads7871.c @@ -77,9 +77,13 @@ static int ads7871_read_reg8(struct spi_device *spi, int reg) static int ads7871_read_reg16(struct spi_device *spi, int reg) { int ret; + reg = reg | INST_READ_BM | INST_16BIT_BM; ret = spi_w8r16(spi, reg); - return ret; + if (ret < 0) + return ret; + + return le16_to_cpu((__force __le16)ret); } static int ads7871_write_reg8(struct spi_device *spi, int reg, u8 val) diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index dddbd2463f8d..76f3e1da68d0 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -796,13 +796,13 @@ static int corsairpsu_probe(struct hid_device *hdev, const struct hid_device_id ret = corsairpsu_init(priv); if (ret < 0) { dev_err(&hdev->dev, "unable to initialize device (%d)\n", ret); - goto fail_and_stop; + goto fail_and_close; } ret = corsairpsu_fwinfo(priv); if (ret < 0) { dev_err(&hdev->dev, "unable to query firmware (%d)\n", ret); - goto fail_and_stop; + goto fail_and_close; } corsairpsu_get_criticals(priv); diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c index 035176a98ce9..30500b4d2221 100644 --- a/drivers/hwmon/lm63.c +++ b/drivers/hwmon/lm63.c @@ -333,7 +333,13 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *devattr, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); - return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan[attr->index])); + int fan; + + mutex_lock(&data->update_lock); + fan = FAN_FROM_REG(data->fan[attr->index]); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", fan); } static ssize_t set_fan(struct device *dev, struct device_attribute *dummy, @@ -366,12 +372,14 @@ static ssize_t show_pwm1(struct device *dev, struct device_attribute *devattr, int nr = attr->index; int pwm; + mutex_lock(&data->update_lock); if (data->pwm_highres) pwm = data->pwm1[nr]; else pwm = data->pwm1[nr] >= 2 * data->pwm1_freq ? 255 : (data->pwm1[nr] * 255 + data->pwm1_freq) / (2 * data->pwm1_freq); + mutex_unlock(&data->update_lock); return sprintf(buf, "%d\n", pwm); } @@ -529,6 +537,7 @@ static ssize_t show_temp11(struct device *dev, struct device_attribute *devattr, int nr = attr->index; int temp; + mutex_lock(&data->update_lock); if (!nr) { /* * Use unsigned temperature unless its value is zero. @@ -544,7 +553,10 @@ static ssize_t show_temp11(struct device *dev, struct device_attribute *devattr, else temp = TEMP11_FROM_REG(data->temp11[nr]); } - return sprintf(buf, "%d\n", temp + data->temp2_offset); + temp += data->temp2_offset; + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr, @@ -592,9 +604,14 @@ static ssize_t temp2_crit_hyst_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm63_data *data = lm63_update_device(dev); - return sprintf(buf, "%d\n", temp8_from_reg(data, 2) - + data->temp2_offset - - TEMP8_FROM_REG(data->temp2_crit_hyst)); + int temp; + + mutex_lock(&data->update_lock); + temp = temp8_from_reg(data, 2) + data->temp2_offset + - TEMP8_FROM_REG(data->temp2_crit_hyst); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } static ssize_t show_lut_temp_hyst(struct device *dev, @@ -602,10 +619,14 @@ static ssize_t show_lut_temp_hyst(struct device *dev, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); + int temp; - return sprintf(buf, "%d\n", lut_temp_from_reg(data, attr->index) - + data->temp2_offset - - TEMP8_FROM_REG(data->lut_temp_hyst)); + mutex_lock(&data->update_lock); + temp = lut_temp_from_reg(data, attr->index) + data->temp2_offset + - TEMP8_FROM_REG(data->lut_temp_hyst); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } /* @@ -616,7 +637,7 @@ static ssize_t temp2_crit_hyst_store(struct device *dev, struct device_attribute *dummy, const char *buf, size_t count) { - struct lm63_data *data = dev_get_drvdata(dev); + struct lm63_data *data = lm63_update_device(dev); struct i2c_client *client = data->client; long val; int err; diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c index f1a1e5b888f6..c283443e363b 100644 --- a/drivers/hwmon/lm75.c +++ b/drivers/hwmon/lm75.c @@ -137,7 +137,7 @@ static const struct lm75_params device_params[] = { }, [as6200] = { .config_reg_16bits = true, - .set_mask = 0x94C0, /* 8 sample/s, 4 CF, positive polarity */ + .set_mask = 0xC010, /* 8 sample/s, 4 CF */ .default_resolution = 12, .default_sample_time = 125, .num_sample_times = 4, @@ -286,8 +286,8 @@ static const struct lm75_params device_params[] = { }, [tmp112] = { .config_reg_16bits = true, - .set_mask = 0x60C0, /* 12-bit mode, 8 samples / second */ - .clr_mask = 1 << 15, /* no one-shot mode*/ + .set_mask = 0xC060, /* 12-bit mode, 8 samples / second */ + .clr_mask = 1 << 7, /* no one-shot mode*/ .default_resolution = 12, .default_sample_time = 125, .num_sample_times = 4, @@ -353,7 +353,7 @@ static inline int lm75_write_config(struct lm75_data *data, u16 set_mask, u16 clr_mask) { return regmap_update_bits(data->regmap, LM75_REG_CONF, - clr_mask | LM75_SHUTDOWN, set_mask); + clr_mask | set_mask | LM75_SHUTDOWN, set_mask); } static irqreturn_t lm75_alarm_handler(int irq, void *private) @@ -416,7 +416,7 @@ static int lm75_read(struct device *dev, enum hwmon_sensor_types type, switch (data->kind) { case as6200: case tmp112: - *val = (regval >> 13) & 0x1; + *val = !!(regval & BIT(13)) == !!(regval & BIT(2)); break; default: return -EINVAL; diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 1fcd320d6161..2617c4538af9 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -431,10 +431,16 @@ static int ltc2992_get_voltage(struct ltc2992_state *st, u32 reg, u32 scale, lon static int ltc2992_set_voltage(struct ltc2992_state *st, u32 reg, u32 scale, long val) { - val = DIV_ROUND_CLOSEST(val * 1000, scale); - val = val << 4; + u32 reg_val; + long vmax; - return ltc2992_write_reg(st, reg, 2, val); + vmax = DIV_ROUND_CLOSEST_ULL(0xFFFULL * scale, 1000); + val = max(val, 0L); + val = min(val, vmax); + reg_val = min(DIV_ROUND_CLOSEST_ULL((u64)val * 1000, scale), + 0xFFFULL) << 4; + + return ltc2992_write_reg(st, reg, 2, reg_val); } static int ltc2992_read_gpio_alarm(struct ltc2992_state *st, int nr_gpio, u32 attr, long *val) @@ -559,9 +565,15 @@ static int ltc2992_get_current(struct ltc2992_state *st, u32 reg, u32 channel, l static int ltc2992_set_current(struct ltc2992_state *st, u32 reg, u32 channel, long val) { u32 reg_val; + long cmax; - reg_val = DIV_ROUND_CLOSEST(val * st->r_sense_uohm[channel], LTC2992_IADC_NANOV_LSB); - reg_val = reg_val << 4; + cmax = DIV_ROUND_CLOSEST_ULL(0xFFFULL * LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); + val = max(val, 0L); + val = min(val, cmax); + reg_val = min(DIV_ROUND_CLOSEST_ULL((u64)val * st->r_sense_uohm[channel], + LTC2992_IADC_NANOV_LSB), + 0xFFFULL) << 4; return ltc2992_write_reg(st, reg, 2, reg_val); } @@ -625,8 +637,10 @@ static int ltc2992_get_power(struct ltc2992_state *st, u32 reg, u32 channel, lon if (reg_val < 0) return reg_val; - *val = mul_u64_u32_div(reg_val, LTC2992_VADC_UV_LSB * LTC2992_IADC_NANOV_LSB, - st->r_sense_uohm[channel] * 1000); + *val = mul_u64_u32_div(reg_val, + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); return 0; } @@ -634,9 +648,18 @@ static int ltc2992_get_power(struct ltc2992_state *st, u32 reg, u32 channel, lon static int ltc2992_set_power(struct ltc2992_state *st, u32 reg, u32 channel, long val) { u32 reg_val; + u64 pmax, uval; - reg_val = mul_u64_u32_div(val, st->r_sense_uohm[channel] * 1000, - LTC2992_VADC_UV_LSB * LTC2992_IADC_NANOV_LSB); + uval = max(val, 0L); + pmax = mul_u64_u32_div(0xFFFFFFULL, + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); + uval = min(uval, pmax); + reg_val = min(mul_u64_u32_div(uval, st->r_sense_uohm[channel], + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB), + 0xFFFFFFULL); return ltc2992_write_reg(st, reg, 3, reg_val); } diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 70cb5822bf17..53d9df70ebe4 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -895,8 +895,6 @@ static void stm32f7_i2c_xfer_msg(struct stm32f7_i2c_dev *i2c_dev, f7_msg->result = 0; f7_msg->stop = (i2c_dev->msg_id >= i2c_dev->msg_num - 1); - reinit_completion(&i2c_dev->complete); - cr1 = readl_relaxed(base + STM32F7_I2C_CR1); cr2 = readl_relaxed(base + STM32F7_I2C_CR2); @@ -1728,6 +1726,8 @@ static int stm32f7_i2c_xfer_core(struct i2c_adapter *i2c_adap, if (ret) goto pm_free; + reinit_completion(&i2c_dev->complete); + stm32f7_i2c_xfer_msg(i2c_dev, msgs); if (!i2c_dev->atomic) @@ -2253,7 +2253,7 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) snprintf(adap->name, sizeof(adap->name), "STM32F7 I2C(%pa)", &res->start); adap->owner = THIS_MODULE; - adap->timeout = 2 * HZ; + adap->timeout = 8 * HZ; adap->retries = 3; adap->algo = &stm32f7_i2c_algo; adap->dev.parent = &pdev->dev; diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 2cbd31f77667..28c0e4884a7f 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -371,6 +371,7 @@ static const struct acpi_device_id i2c_acpi_force_100khz_device_ids[] = { * a 400KHz frequency. The root cause of the issue is not known. */ { "DLL0945", 0 }, + { "ELAN0678", 0 }, { "ELAN06FA", 0 }, {} }; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 9c46147e3506..a2132d70fb36 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -445,8 +445,7 @@ static int i2c_init_recovery(struct i2c_adapter *adap) bri->set_scl = set_scl_gpio_value; if (bri->sda_gpiod) { bri->get_sda = get_sda_gpio_value; - /* FIXME: add proper flag instead of '0' once available */ - if (gpiod_get_direction(bri->sda_gpiod) == 0) + if (gpiod_get_direction(bri->sda_gpiod) == GPIO_LINE_DIRECTION_OUT) bri->set_sda = set_sda_gpio_value; } } else if (bri->recover_bus == i2c_generic_scl_recovery) { diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 71eb1ef56f0c..ad6acb5ebadc 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -566,6 +566,18 @@ s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, if (res) return res; + /* Reject invalid caller-supplied block lengths before any + * tracepoint or native smbus_xfer callback runs. + */ + if (data && + (protocol == I2C_SMBUS_I2C_BLOCK_DATA || + protocol == I2C_SMBUS_BLOCK_PROC_CALL || + (protocol == I2C_SMBUS_BLOCK_DATA && + read_write == I2C_SMBUS_WRITE)) && + (data->block[0] == 0 || + data->block[0] > I2C_SMBUS_BLOCK_MAX)) + return -EINVAL; + /* If enabled, the following two tracepoints are conditional on * read_write and protocol. */ diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 7bbe0263411e..ccaac5e29f90 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -487,12 +487,13 @@ static long i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) client->adapter->retries = arg; break; case I2C_TIMEOUT: - if (arg > INT_MAX) + /* + * For historical reasons, user-space sets the timeout value in + * units of 10 ms. + */ + if (arg > INT_MAX / 10) return -EINVAL; - /* For historical reasons, user-space sets the timeout - * value in units of 10 ms. - */ client->adapter->timeout = msecs_to_jiffies(arg * 10); break; default: diff --git a/drivers/i2c/i2c-slave-testunit.c b/drivers/i2c/i2c-slave-testunit.c index 6de4307050dd..871c58461ebc 100644 --- a/drivers/i2c/i2c-slave-testunit.c +++ b/drivers/i2c/i2c-slave-testunit.c @@ -15,7 +15,7 @@ #include #include #include -#include /* FIXME: is system_long_wq the best choice? */ +#include #define TU_VERSION_MAX_LENGTH 128 @@ -124,7 +124,7 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, case I2C_SLAVE_STOP: if (tu->reg_idx == TU_NUM_REGS) { set_bit(TU_FLAG_IN_PROCESS, &tu->flags); - queue_delayed_work(system_long_wq, &tu->worker, + queue_delayed_work(system_dfl_long_wq, &tu->worker, msecs_to_jiffies(10 * tu->regs[TU_REG_DELAY])); } diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c index fbb0db41b10e..04314e3ed24c 100644 --- a/drivers/i2c/i2c-stub.c +++ b/drivers/i2c/i2c-stub.c @@ -214,6 +214,11 @@ static s32 stub_xfer(struct i2c_adapter *adap, u16 addr, unsigned short flags, * We ignore banks here, because banked chips don't use I2C * block transfers */ + if (data->block[0] == 0 || + data->block[0] > I2C_SMBUS_BLOCK_MAX) { + ret = -EINVAL; + break; + } if (data->block[0] > 256 - command) /* Avoid overrun */ data->block[0] = 256 - command; len = data->block[0]; diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 1342e764a548..834d8fabfba3 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -11,6 +11,9 @@ #include "amd_iommu_types.h" +extern int amd_iommu_evtlog_size; +extern int amd_iommu_pprlog_size; + irqreturn_t amd_iommu_int_thread(int irq, void *data); irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index c685d3771436..f9f718087893 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -141,7 +142,6 @@ #define MMIO_STATUS_GALOG_INT_MASK BIT(10) /* event logging constants */ -#define EVENT_ENTRY_SIZE 0x10 #define EVENT_TYPE_SHIFT 28 #define EVENT_TYPE_MASK 0xf #define EVENT_TYPE_ILL_DEV 0x1 @@ -259,15 +259,20 @@ #define MMIO_CMD_BUFFER_TAIL(x) FIELD_GET(MMIO_CMD_TAIL_MASK, (x)) /* constants for event buffer handling */ -#define EVT_BUFFER_SIZE 8192 /* 512 entries */ -#define EVT_LEN_MASK (0x9ULL << 56) +#define EVTLOG_ENTRY_SIZE 0x10 +#define EVTLOG_SIZE_SHIFT 56 +#define EVTLOG_SIZE_DEF SZ_8K /* 512 entries */ +#define EVTLOG_LEN_MASK_DEF (0x9ULL << EVTLOG_SIZE_SHIFT) +#define EVTLOG_SIZE_MAX SZ_512K /* 32K entries */ +#define EVTLOG_LEN_MASK_MAX (0xFULL << EVTLOG_SIZE_SHIFT) /* Constants for PPR Log handling */ -#define PPR_LOG_ENTRIES 512 -#define PPR_LOG_SIZE_SHIFT 56 -#define PPR_LOG_SIZE_512 (0x9ULL << PPR_LOG_SIZE_SHIFT) -#define PPR_ENTRY_SIZE 16 -#define PPR_LOG_SIZE (PPR_ENTRY_SIZE * PPR_LOG_ENTRIES) +#define PPRLOG_ENTRY_SIZE 0x10 +#define PPRLOG_SIZE_SHIFT 56 +#define PPRLOG_SIZE_DEF SZ_8K /* 512 entries */ +#define PPRLOG_LEN_MASK_DEF (0x9ULL << PPRLOG_SIZE_SHIFT) +#define PPRLOG_SIZE_MAX SZ_512K /* 32K entries */ +#define PPRLOG_LEN_MASK_MAX (0xFULL << PPRLOG_SIZE_SHIFT) /* PAGE_SERVICE_REQUEST PPR Log Buffer Entry flags */ #define PPR_FLAG_EXEC 0x002 /* Execute permission requested */ diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 56ad020df494..3bdb380d23e9 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -132,6 +132,9 @@ struct ivhd_entry { u8 uid; } __attribute__((packed)); +int amd_iommu_evtlog_size = EVTLOG_SIZE_DEF; +int amd_iommu_pprlog_size = PPRLOG_SIZE_DEF; + /* * An AMD IOMMU memory definition structure. It defines things like exclusion * ranges for devices and regions that should be unity mapped. @@ -865,35 +868,47 @@ void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp, } /* allocates the memory where the IOMMU will log its events to */ -static int __init alloc_event_buffer(struct amd_iommu *iommu) +static int __init alloc_event_buffer(void) { - iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL, - EVT_BUFFER_SIZE); + struct amd_iommu *iommu; - return iommu->evt_buf ? 0 : -ENOMEM; -} - -static void iommu_enable_event_buffer(struct amd_iommu *iommu) -{ - u64 entry; - - BUG_ON(iommu->evt_buf == NULL); - - if (!is_kdump_kernel()) { - /* - * Event buffer is re-used for kdump kernel and setting - * of MMIO register is not required. - */ - entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK; - memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, - &entry, sizeof(entry)); + for_each_iommu(iommu) { + iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL, + amd_iommu_evtlog_size); + if (!iommu->evt_buf) + return -ENOMEM; } - /* set head and tail to zero manually */ - writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); - writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + return 0; +} - iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); +static void iommu_enable_event_buffer(void) +{ + struct amd_iommu *iommu; + u64 entry; + + for_each_iommu(iommu) { + BUG_ON(iommu->evt_buf == NULL); + + if (!is_kdump_kernel()) { + /* + * Event buffer is re-used for kdump kernel and setting + * of MMIO register is not required. + */ + entry = iommu_virt_to_phys(iommu->evt_buf); + entry |= (amd_iommu_evtlog_size == EVTLOG_SIZE_DEF) ? + EVTLOG_LEN_MASK_DEF : EVTLOG_LEN_MASK_MAX; + + memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET, + &entry, sizeof(entry)); + } + + /* set head and tail to zero manually */ + writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET); + + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); + } } /* @@ -984,15 +999,20 @@ static int __init alloc_cwwb_sem(struct amd_iommu *iommu) return 0; } -static int __init remap_event_buffer(struct amd_iommu *iommu) +static int __init remap_event_buffer(void) { + struct amd_iommu *iommu; u64 paddr; pr_info_once("Re-using event buffer from the previous kernel\n"); - paddr = readq(iommu->mmio_base + MMIO_EVT_BUF_OFFSET) & PM_ADDR_MASK; - iommu->evt_buf = iommu_memremap(paddr, EVT_BUFFER_SIZE); + for_each_iommu(iommu) { + paddr = readq(iommu->mmio_base + MMIO_EVT_BUF_OFFSET) & PM_ADDR_MASK; + iommu->evt_buf = iommu_memremap(paddr, amd_iommu_evtlog_size); + if (!iommu->evt_buf) + return -ENOMEM; + } - return iommu->evt_buf ? 0 : -ENOMEM; + return 0; } static int __init remap_command_buffer(struct amd_iommu *iommu) @@ -1044,10 +1064,6 @@ static int __init alloc_iommu_buffers(struct amd_iommu *iommu) ret = remap_command_buffer(iommu); if (ret) return ret; - - ret = remap_event_buffer(iommu); - if (ret) - return ret; } else { ret = alloc_cwwb_sem(iommu); if (ret) @@ -1056,10 +1072,6 @@ static int __init alloc_iommu_buffers(struct amd_iommu *iommu) ret = alloc_command_buffer(iommu); if (ret) return ret; - - ret = alloc_event_buffer(iommu); - if (ret) - return ret; } return 0; @@ -2893,7 +2905,6 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); - iommu_enable_event_buffer(iommu); iommu_set_exclusion_range(iommu); iommu_enable_gt(iommu); iommu_enable_ga(iommu); @@ -2957,7 +2968,6 @@ static void early_enable_iommus(void) iommu_disable_event_buffer(iommu); iommu_disable_irtcachedis(iommu); iommu_enable_command_buffer(iommu); - iommu_enable_event_buffer(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); iommu_enable_irtcachedis(iommu); @@ -3070,6 +3080,7 @@ static void amd_iommu_resume(void *data) for_each_iommu(iommu) early_enable_iommu(iommu); + iommu_enable_event_buffer(); amd_iommu_enable_interrupts(); } @@ -3399,6 +3410,33 @@ static __init void iommu_snp_enable(void) #endif } +static void amd_iommu_apply_erratum_snp(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + if (!amd_iommu_snp_en) + return; + + /* Errata fix for Family 0x19 */ + if (boot_cpu_data.x86 != 0x19) + return; + + /* Set event log buffer size to max */ + amd_iommu_evtlog_size = EVTLOG_SIZE_MAX; + pr_info("Applying erratum: Increase Event log size to 0x%x\n", + amd_iommu_evtlog_size); + + /* + * Set PPR log buffer size to max. + * (Family 0x19, model < 0x10 doesn't support PPR when SNP is enabled). + */ + if (boot_cpu_data.x86_model >= 0x10) { + amd_iommu_pprlog_size = PPRLOG_SIZE_MAX; + pr_info("Applying erratum: Increase PPR log size to 0x%x\n", + amd_iommu_pprlog_size); + } +#endif +} + /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -3435,6 +3473,21 @@ static int __init state_next(void) case IOMMU_ENABLED: register_syscore(&amd_iommu_syscore); iommu_snp_enable(); + + amd_iommu_apply_erratum_snp(); + + /* Allocate/enable event log buffer */ + if (is_kdump_kernel()) + ret = remap_event_buffer(); + else + ret = alloc_event_buffer(); + + if (ret) { + init_state = IOMMU_INIT_ERROR; + break; + } + iommu_enable_event_buffer(); + ret = amd_iommu_init_pci(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; break; @@ -4037,11 +4090,11 @@ int amd_iommu_snp_disable(void) return 0; for_each_iommu(iommu) { - ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE); + ret = iommu_make_shared(iommu->evt_buf, amd_iommu_evtlog_size); if (ret) return ret; - ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE); + ret = iommu_make_shared(iommu->ppr_log, amd_iommu_pprlog_size); if (ret) return ret; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 01171361f9bc..f78e23f03938 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1010,7 +1010,7 @@ static void iommu_poll_events(struct amd_iommu *iommu) iommu_print_event(iommu, iommu->evt_buf + head); /* Update head pointer of hardware ring-buffer */ - head = (head + EVENT_ENTRY_SIZE) % EVT_BUFFER_SIZE; + head = (head + EVTLOG_ENTRY_SIZE) % amd_iommu_evtlog_size; writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET); } @@ -2149,7 +2149,8 @@ static void set_dte_passthrough(struct iommu_dev_data *dev_data, new->data[0] |= DTE_FLAG_TV | DTE_FLAG_IR | DTE_FLAG_IW; new->data[1] |= FIELD_PREP(DTE_DOMID_MASK, domain->id) | - (dev_data->ats_enabled) ? DTE_FLAG_IOTLB : 0; + (dev_data->ats_enabled ? DTE_FLAG_IOTLB : 0); + } static void set_dte_entry(struct amd_iommu *iommu, diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index e6767c057d01..1f8d2823bea4 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -20,7 +20,7 @@ int __init amd_iommu_alloc_ppr_log(struct amd_iommu *iommu) { iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, - PPR_LOG_SIZE); + amd_iommu_pprlog_size); return iommu->ppr_log ? 0 : -ENOMEM; } @@ -33,7 +33,9 @@ void amd_iommu_enable_ppr_log(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_PPR_EN); - entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512; + entry = iommu_virt_to_phys(iommu->ppr_log); + entry |= (amd_iommu_pprlog_size == PPRLOG_SIZE_DEF) ? + PPRLOG_LEN_MASK_DEF : PPRLOG_LEN_MASK_MAX; memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET, &entry, sizeof(entry)); @@ -201,7 +203,7 @@ void amd_iommu_poll_ppr_log(struct amd_iommu *iommu) raw[0] = raw[1] = 0UL; /* Update head pointer of hardware ring-buffer */ - head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE; + head = (head + PPRLOG_ENTRY_SIZE) % amd_iommu_pprlog_size; writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET); /* Handle PPR entry */ diff --git a/drivers/iommu/iommu-pages.h b/drivers/iommu/iommu-pages.h index ae9da4f571f6..e9e605b5fa3a 100644 --- a/drivers/iommu/iommu-pages.h +++ b/drivers/iommu/iommu-pages.h @@ -137,7 +137,7 @@ static inline void iommu_pages_flush_incoherent(struct device *dma_dev, void *virt, size_t offset, size_t len) { - dma_sync_single_for_device(dma_dev, (uintptr_t)virt + offset, len, + dma_sync_single_for_device(dma_dev, virt_to_phys(virt) + offset, len, DMA_TO_DEVICE); } void iommu_pages_stop_incoherent_list(struct iommu_pages_list *list, diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index e67b592e5697..8c86789d867a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1782,20 +1782,23 @@ void ena_com_phc_destroy(struct ena_com_dev *ena_dev) int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp) { - volatile struct ena_admin_phc_resp *resp = ena_dev->phc.virt_addr; const ktime_t zero_system_time = ktime_set(0, 0); struct ena_com_phc_info *phc = &ena_dev->phc; + volatile struct ena_admin_phc_resp *resp; ktime_t expire_time; ktime_t block_time; unsigned long flags = 0; int ret = 0; + spin_lock_irqsave(&phc->lock, flags); + if (!phc->active) { + spin_unlock_irqrestore(&phc->lock, flags); netdev_err(ena_dev->net_device, "PHC feature is not active in the device\n"); return -EOPNOTSUPP; } - spin_lock_irqsave(&phc->lock, flags); + resp = ena_dev->phc.virt_addr; /* Check if PHC is in blocked state */ if (unlikely(ktime_compare(phc->system_time, zero_system_time))) { diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.c b/drivers/net/ethernet/amazon/ena/ena_phc.c index 7867e893fd15..c2a3ff1ef645 100644 --- a/drivers/net/ethernet/amazon/ena/ena_phc.c +++ b/drivers/net/ethernet/amazon/ena/ena_phc.c @@ -46,9 +46,12 @@ static int ena_phc_gettimex64(struct ptp_clock_info *clock_info, spin_unlock_irqrestore(&phc_info->lock, flags); + if (rc) + return rc; + *ts = ns_to_timespec64(timestamp_nsec); - return rc; + return 0; } static int ena_phc_settime64(struct ptp_clock_info *clock_info, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index b854b6b42d77..2926e1e59941 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -910,7 +910,9 @@ static int xgene_mdiobus_register(struct xgene_enet_pdata *pdata, return -ENXIO; } - return of_mdiobus_register(mdio, mdio_np); + ret = of_mdiobus_register(mdio, mdio_np); + of_node_put(mdio_np); + return ret; } /* Mask out all PHYs from auto probing. */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index e9e38af680c3..39e1b606a75a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -371,7 +371,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev) pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - pci_wake_from_d3(pdev, false); + pci_wake_from_d3(pdev, self->aq_hw->aq_nic_cfg->wol); pci_set_power_state(pdev, PCI_D3hot); } } diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 8ab4b899d0ca..fc8b1cb950a1 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -944,7 +944,6 @@ static const struct net_device_ops net_ops = { static void __init reset_chip(struct net_device *dev) { -#if !defined(CONFIG_MACH_MX31ADS) struct net_local *lp = netdev_priv(dev); unsigned long reset_start_time; @@ -971,7 +970,6 @@ static void __init reset_chip(struct net_device *dev) while ((readreg(dev, PP_SelfST) & INIT_DONE) == 0 && time_before(jiffies, reset_start_time + 2)) ; -#endif /* !CONFIG_MACH_MX31ADS */ } /* This is the real probe routine. diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 065cbbf52686..4c762229ce42 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -122,6 +122,9 @@ struct gemini_ethernet_port { struct napi_struct napi; struct hrtimer rx_coalesce_timer; unsigned int rx_coalesce_nsecs; + struct sk_buff *rx_skb; + unsigned int rx_frag_nr; + unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; unsigned int txq_order; @@ -1442,10 +1445,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short m = (1 << port->rxq_order) - 1; struct gemini_ethernet *geth = port->geth; void __iomem *ptr_reg = port->rxq_rwptr; + unsigned int frag_nr = port->rx_frag_nr; + struct sk_buff *skb = port->rx_skb; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; - static struct sk_buff *skb; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1455,7 +1459,6 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short r, w; union dma_rwptr rw; dma_addr_t mapping; - int frag_nr = 0; spin_lock_irqsave(&geth->irq_lock, flags); rw.bits32 = readl(ptr_reg); @@ -1491,10 +1494,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); + port->stats.rx_dropped++; if (skb) { napi_free_frags(&port->napi); - port->stats.rx_dropped++; skb = NULL; + frag_nr = 0; } continue; } @@ -1504,6 +1508,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (skb) { napi_free_frags(&port->napi); port->stats.rx_dropped++; + skb = NULL; + frag_nr = 0; } skb = gmac_skb_if_good_frame(port, word0, frame_len); @@ -1538,6 +1544,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (word3.bits32 & EOF_BIT) { napi_gro_frags(&port->napi); skb = NULL; + frag_nr = 0; --budget; } continue; @@ -1546,6 +1553,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (skb) { napi_free_frags(&port->napi); skb = NULL; + frag_nr = 0; } if (mapping) @@ -1554,6 +1562,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) port->stats.rx_dropped++; } + port->rx_skb = skb; + port->rx_frag_nr = frag_nr; writew(r, ptr_reg); return budget; } @@ -1881,6 +1891,8 @@ static int gmac_stop(struct net_device *netdev) gmac_disable_tx_rx(netdev); gmac_stop_dma(port); napi_disable(&port->napi); + port->rx_skb = NULL; + port->rx_frag_nr = 0; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index dcb50c2e1aa2..83e780919ac9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1318,6 +1318,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +void i40e_ptp_free_pins(struct i40e_pf *pf); int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); int i40e_get_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 93faada2d328..a04683004a56 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16111,9 +16111,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Unwind what we've done if something failed in the setup */ err_vsis: set_bit(__I40E_DOWN, pf->state); + i40e_ptp_stop(pf); i40e_clear_interrupt_scheme(pf); kfree(pf->vsi); err_switch_setup: + i40e_ptp_free_pins(pf); i40e_reset_interrupt_capability(pf); timer_shutdown_sync(&pf->service_timer); err_mac_addr: diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 7bcea7d9720f..ff62b5f2c815 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -937,12 +937,13 @@ int i40e_ptp_hwtstamp_get(struct net_device *netdev, * * Release memory allocated for PTP pins. **/ -static void i40e_ptp_free_pins(struct i40e_pf *pf) +void i40e_ptp_free_pins(struct i40e_pf *pf) { if (i40e_is_ptp_pin_dev(&pf->hw)) { kfree(pf->ptp_pins); kfree(pf->ptp_caps.pin_config); pf->ptp_pins = NULL; + pf->ptp_caps.pin_config = NULL; } } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 16aa25535152..0bc6dd375687 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -537,14 +537,14 @@ void ice_dcb_rebuild(struct ice_pf *pf) struct ice_dcbx_cfg *err_cfg; int ret; + mutex_lock(&pf->tc_mutex); + ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); goto dcb_error; } - mutex_lock(&pf->tc_mutex); - if (!pf->hw.port_info->qos_cfg.is_sw_lldp) ice_cfg_etsrec_defaults(pf->hw.port_info); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index a00da99dd19f..b9c7df50123d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -2523,6 +2523,8 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, if (hw_idx < 0) goto unlock; hw_idx -= pf->dplls.base_rclk_idx; + if (hw_idx >= ICE_DPLL_RCLK_NUM_MAX) + goto unlock; if ((enable && p->state[hw_idx] == DPLL_PIN_STATE_CONNECTED) || (!enable && p->state[hw_idx] == DPLL_PIN_STATE_DISCONNECTED)) { @@ -2586,6 +2588,9 @@ ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv, hw_idx = ice_dpll_pin_get_parent_idx(p, parent_pin); if (hw_idx < 0) goto unlock; + hw_idx -= pf->dplls.base_rclk_idx; + if (hw_idx >= ICE_DPLL_RCLK_NUM_MAX) + goto unlock; ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_RCLK_INPUT, extack); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index ae42cdea0ee1..8678575359b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -8,6 +8,22 @@ #define ICE_DPLL_RCLK_NUM_MAX 4 +#define ICE_CGU_R10 0x28 +#define ICE_CGU_R10_SYNCE_CLKO_SEL GENMASK(8, 5) +#define ICE_CGU_R10_SYNCE_CLKODIV_M1 GENMASK(13, 9) +#define ICE_CGU_R10_SYNCE_CLKODIV_LOAD BIT(14) +#define ICE_CGU_R10_SYNCE_DCK_RST BIT(15) +#define ICE_CGU_R10_SYNCE_ETHCLKO_SEL GENMASK(18, 16) +#define ICE_CGU_R10_SYNCE_ETHDIV_M1 GENMASK(23, 19) +#define ICE_CGU_R10_SYNCE_ETHDIV_LOAD BIT(24) +#define ICE_CGU_R10_SYNCE_DCK2_RST BIT(25) +#define ICE_CGU_R10_SYNCE_S_REF_CLK GENMASK(31, 27) + +#define ICE_CGU_R11 0x2C +#define ICE_CGU_R11_SYNCE_S_BYP_CLK GENMASK(6, 1) + +#define ICE_CGU_BYPASS_MUX_OFFSET_E825C 3 + /** * enum ice_dpll_pin_sw - enumerate ice software pin indices: * @ICE_DPLL_PIN_SW_1_IDX: index of first SW pin @@ -157,19 +173,3 @@ static inline void ice_dpll_deinit(struct ice_pf *pf) { } #endif #endif - -#define ICE_CGU_R10 0x28 -#define ICE_CGU_R10_SYNCE_CLKO_SEL GENMASK(8, 5) -#define ICE_CGU_R10_SYNCE_CLKODIV_M1 GENMASK(13, 9) -#define ICE_CGU_R10_SYNCE_CLKODIV_LOAD BIT(14) -#define ICE_CGU_R10_SYNCE_DCK_RST BIT(15) -#define ICE_CGU_R10_SYNCE_ETHCLKO_SEL GENMASK(18, 16) -#define ICE_CGU_R10_SYNCE_ETHDIV_M1 GENMASK(23, 19) -#define ICE_CGU_R10_SYNCE_ETHDIV_LOAD BIT(24) -#define ICE_CGU_R10_SYNCE_DCK2_RST BIT(25) -#define ICE_CGU_R10_SYNCE_S_REF_CLK GENMASK(31, 27) - -#define ICE_CGU_R11 0x2C -#define ICE_CGU_R11_SYNCE_S_BYP_CLK GENMASK(6, 1) - -#define ICE_CGU_BYPASS_MUX_OFFSET_E825C 3 diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1d1947a7fe11..c52c465280f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8046,7 +8046,7 @@ int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc) ctx->info.q_opt_rss |= FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc); ctx->info.q_opt_tc = vsi->info.q_opt_tc; - ctx->info.q_opt_flags = vsi->info.q_opt_rss; + ctx->info.q_opt_flags = vsi->info.q_opt_flags; err = ice_update_vsi(hw, vsi->idx, ctx, NULL); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 7e4f4ac92653..b7d6b08fc89e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -90,7 +90,10 @@ static int idpf_plug_vport_aux_dev(struct iidc_rdma_core_dev_info *cdev_info, return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + vdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: @@ -228,7 +231,10 @@ static int idpf_plug_core_aux_dev(struct iidc_rdma_core_dev_info *cdev_info) return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + cdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index eec91c4f0a75..4a51d2727547 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -952,6 +952,8 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto free_ptp; } + spin_lock_init(&adapter->ptp->read_dev_clk_lock); + err = idpf_ptp_create_clock(adapter); if (err) goto free_ptp; @@ -977,8 +979,6 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto remove_clock; } - spin_lock_init(&adapter->ptp->read_dev_clk_lock); - pci_dbg(adapter->pdev, "PTP init successful\n"); return 0; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 47752d3fde0b..1179a6e127c5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -749,11 +749,10 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) for (p = 0; p < lan966x->num_phys_ports; p++) { port = lan966x->ports[p]; - if (!port) + if (!port || !port->dev) continue; - if (port->dev) - unregister_netdev(port->dev); + unregister_netdev(port->dev); lan966x_xdp_port_deinit(port); if (lan966x->fdma && lan966x->fdma_ndev == port->dev) @@ -873,6 +872,9 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, err = register_netdev(dev); if (err) { dev_err(lan966x->dev, "register_netdev failed\n"); + phylink_destroy(phylink); + port->phylink = NULL; + port->dev = NULL; return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 42c6dcfb1f0f..dd75c47758e1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -5103,6 +5103,13 @@ static int qed_init_wfq_param(struct qed_hwfn *p_hwfn, return -EINVAL; } + /* All vports are already or become configured, nothing to distribute */ + if (non_requested_count == 0) { + p_hwfn->qm_info.wfq_data[vport_id].min_speed = req_rate; + p_hwfn->qm_info.wfq_data[vport_id].configured = true; + return 0; + } + total_left_rate = min_pf_rate - total_req_min_rate; left_rate_per_vp = total_left_rate / non_requested_count; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 1dbfadb2a881..5f88733094d0 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1108,9 +1108,12 @@ static int ravb_stop_dma(struct net_device *ndev) /* Request for transmission suspension */ ravb_modify(ndev, CCC, CCC_DTSR, CCC_DTSR); - error = ravb_wait(ndev, CSR, CSR_DTS, CSR_DTS); - if (error) - netdev_err(ndev, "failed to stop AXI BUS\n"); + /* Access to URAM will not be suspended if WoL is enabled. */ + if (!priv->wol_enabled) { + error = ravb_wait(ndev, CSR, CSR_DTS, CSR_DTS); + if (error) + netdev_err(ndev, "failed to stop AXI BUS\n"); + } /* Stop AVB-DMAC process */ return ravb_set_opmode(ndev, CCC_OPC_CONFIG); diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.c b/drivers/net/ethernet/ti/icssm/icssm_prueth.c index 53bbd9290904..b7e94244355a 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_prueth.c +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.c @@ -1825,6 +1825,7 @@ static int icssm_prueth_probe(struct platform_device *pdev) dev_err(dev, "%pOF error reading port_id %d\n", eth_node, ret); of_node_put(eth_node); + of_node_put(eth_ports_node); return ret; } diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 064fa484f797..9bfecc87d6b2 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -984,7 +984,7 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) case FZA_STATE_UNINITIALIZED: netif_carrier_off(dev); - timer_delete_sync(&fp->reset_timer); + timer_delete_sync_try(&fp->reset_timer); fp->ring_cmd_index = 0; fp->ring_uns_index = 0; fp->ring_rmc_tx_index = 0; @@ -1018,7 +1018,9 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) fp->queue_active = 0; netif_stop_queue(dev); pr_debug("%s: queue stopped\n", fp->name); - timer_delete_sync(&fp->reset_timer); + + spin_lock(&fp->lock); + timer_delete(&fp->reset_timer); pr_warn("%s: halted, reason: %x\n", fp->name, FZA_STATUS_GET_HALT(status)); fza_regs_dump(fp); @@ -1027,6 +1029,8 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) fp->timer_state = 0; fp->reset_timer.expires = jiffies + 45 * HZ; add_timer(&fp->reset_timer); + spin_unlock(&fp->lock); + break; default: @@ -1046,7 +1050,9 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) static void fza_reset_timer(struct timer_list *t) { struct fza_private *fp = timer_container_of(fp, t, reset_timer); + unsigned long flags; + spin_lock_irqsave(&fp->lock, flags); if (!fp->timer_state) { pr_err("%s: RESET timed out!\n", fp->name); pr_info("%s: trying harder...\n", fp->name); @@ -1069,6 +1075,7 @@ static void fza_reset_timer(struct timer_list *t) fp->reset_timer.expires = jiffies + 45 * HZ; } add_timer(&fp->reset_timer); + spin_unlock_irqrestore(&fp->lock, flags); } static int fza_set_mac_address(struct net_device *dev, void *addr) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 6147ee8b1d78..f904f4d16b45 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -26,6 +26,8 @@ #include +static struct workqueue_struct *macsec_wq; + /* SecTAG length = macsec_eth_header without the optional SCI */ #define MACSEC_TAG_LEN 6 @@ -174,9 +176,10 @@ static void macsec_rxsc_put(struct macsec_rx_sc *sc) call_rcu(&sc->rcu_head, free_rx_sc_rcu); } -static void free_rxsa(struct rcu_head *head) +static void free_rxsa_work(struct work_struct *work) { - struct macsec_rx_sa *sa = container_of(head, struct macsec_rx_sa, rcu); + struct macsec_rx_sa *sa = + container_of(to_rcu_work(work), struct macsec_rx_sa, destroy_work); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); @@ -186,7 +189,7 @@ static void free_rxsa(struct rcu_head *head) static void macsec_rxsa_put(struct macsec_rx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) - call_rcu(&sa->rcu, free_rxsa); + queue_rcu_work(macsec_wq, &sa->destroy_work); } static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) @@ -202,9 +205,10 @@ static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) return sa; } -static void free_txsa(struct rcu_head *head) +static void free_txsa_work(struct work_struct *work) { - struct macsec_tx_sa *sa = container_of(head, struct macsec_tx_sa, rcu); + struct macsec_tx_sa *sa = + container_of(to_rcu_work(work), struct macsec_tx_sa, destroy_work); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); @@ -214,7 +218,7 @@ static void free_txsa(struct rcu_head *head) static void macsec_txsa_put(struct macsec_tx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) - call_rcu(&sa->rcu, free_txsa); + queue_rcu_work(macsec_wq, &sa->destroy_work); } static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) @@ -1407,6 +1411,7 @@ static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, rx_sa->next_pn = 1; refcount_set(&rx_sa->refcnt, 1); spin_lock_init(&rx_sa->lock); + INIT_RCU_WORK(&rx_sa->destroy_work, free_rxsa_work); return 0; } @@ -1506,6 +1511,7 @@ static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, tx_sa->active = false; refcount_set(&tx_sa->refcnt, 1); spin_lock_init(&tx_sa->lock); + INIT_RCU_WORK(&tx_sa->destroy_work, free_txsa_work); return 0; } @@ -4505,25 +4511,35 @@ static int __init macsec_init(void) { int err; + macsec_wq = alloc_workqueue("macsec", WQ_UNBOUND, 0); + if (!macsec_wq) + return -ENOMEM; + pr_info("MACsec IEEE 802.1AE\n"); err = register_netdevice_notifier(&macsec_notifier); if (err) - return err; + goto err_destroy_wq; err = rtnl_link_register(&macsec_link_ops); if (err) - goto notifier; + goto err_notifier; err = genl_register_family(&macsec_fam); if (err) - goto rtnl; + goto err_rtnl; return 0; -rtnl: +err_rtnl: rtnl_link_unregister(&macsec_link_ops); -notifier: +err_notifier: unregister_netdevice_notifier(&macsec_notifier); +err_destroy_wq: + /* Precautionary, mirrors macsec_exit() to stay safe if work + * ever becomes queueable before this point in the future. + */ + rcu_barrier(); + destroy_workqueue(macsec_wq); return err; } @@ -4533,6 +4549,7 @@ static void __exit macsec_exit(void) rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); rcu_barrier(); + destroy_workqueue(macsec_wq); } module_init(macsec_init); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index d0361aaf25ef..3f7d31033bae 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -502,7 +502,7 @@ static int net_failover_slave_register(struct net_device *slave_dev, /* Align MTU of slave with failover dev */ orig_mtu = slave_dev->mtu; - err = dev_set_mtu(slave_dev, failover_dev->mtu); + err = netif_set_mtu(slave_dev, failover_dev->mtu); if (err) { netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n", slave_dev->name, failover_dev->mtu); @@ -512,11 +512,11 @@ static int net_failover_slave_register(struct net_device *slave_dev, dev_hold(slave_dev); if (netif_running(failover_dev)) { - err = dev_open(slave_dev, NULL); + err = netif_open(slave_dev, NULL); if (err && (err != -EBUSY)) { netdev_err(failover_dev, "Opening slave %s failed err:%d\n", slave_dev->name, err); - goto err_dev_open; + goto err_netif_open; } } @@ -562,10 +562,10 @@ static int net_failover_slave_register(struct net_device *slave_dev, err_vlan_add: dev_uc_unsync(slave_dev, failover_dev); dev_mc_unsync(slave_dev, failover_dev); - dev_close(slave_dev); -err_dev_open: + netif_close(slave_dev); +err_netif_open: dev_put(slave_dev); - dev_set_mtu(slave_dev, orig_mtu); + netif_set_mtu(slave_dev, orig_mtu); done: return err; } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index e480c2a07450..252fb12b3e68 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -393,6 +393,7 @@ static struct phy_driver dp83811_driver[] = { .config_init = dp83811_config_init, .config_aneg = dp83811_config_aneg, .soft_reset = dp83811_phy_reset, + .get_features = genphy_c45_pma_read_ext_abilities, .get_wol = dp83811_get_wol, .set_wol = dp83811_set_wol, .config_intr = dp83811_config_intr, diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 15bfb78381d4..809f21fb93f5 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -740,6 +740,8 @@ static int uhdlc_open(struct net_device *dev) static void uhdlc_memclean(struct ucc_hdlc_private *priv) { + int i; + qe_muram_free(ioread16be(&priv->ucc_pram->riptr)); qe_muram_free(ioread16be(&priv->ucc_pram->tiptr)); @@ -770,6 +772,11 @@ static void uhdlc_memclean(struct ucc_hdlc_private *priv) kfree(priv->rx_skbuff); priv->rx_skbuff = NULL; + for (i = 0; i < TX_BD_RING_LEN; i++) { + dev_kfree_skb(priv->tx_skbuff[i]); + priv->tx_skbuff[i] = NULL; + } + kfree(priv->tx_skbuff); priv->tx_skbuff = NULL; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d10ece0889f0..e3f59001785a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -179,6 +179,11 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, return NULL; } +static void _pci_free_device(struct device *dev) +{ + kfree(to_pci_dev(dev)); +} + /** * new_id_store - sysfs frontend to pci_add_dynid() * @driver: target device driver @@ -214,11 +219,13 @@ static ssize_t new_id_store(struct device_driver *driver, const char *buf, pdev->subsystem_vendor = subvendor; pdev->subsystem_device = subdevice; pdev->class = class; + pdev->dev.release = _pci_free_device; + device_initialize(&pdev->dev); if (pci_match_device(pdrv, pdev)) retval = -EEXIST; - kfree(pdev); + put_device(&pdev->dev); if (retval) return retval; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8f7cfcc00090..d34266651ad0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5607,13 +5607,14 @@ static int pci_try_reset_bus(struct pci_bus *bus) * reset for affected devices * * This function will first try to reset the slots on this bus if the method is - * available. If slot reset fails or is not available, this will fall back to a + * available. If slot reset is not available, this will fall back to a * secondary bus reset. */ static int pci_reset_bridge(struct pci_dev *bridge, bool restore) { struct pci_bus *bus = bridge->subordinate; struct pci_slot *slot; + int ret = 0; if (!bus) return -ENOTTY; @@ -5627,19 +5628,17 @@ static int pci_reset_bridge(struct pci_dev *bridge, bool restore) goto bus_reset; list_for_each_entry(slot, &bus->slots, list) { - int ret; - if (restore) ret = pci_try_reset_slot(slot); else ret = pci_slot_reset(slot, PCI_RESET_DO_RESET); if (ret) - goto bus_reset; + break; } mutex_unlock(&pci_slot_mutex); - return 0; + return ret; bus_reset: mutex_unlock(&pci_slot_mutex); diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index fbc05cda96ee..991d3ed543f5 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -102,6 +102,7 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno) } pci_write_config_dword(dev, reg, new); + dev->saved_config_space[reg / 4] = new; pci_read_config_dword(dev, reg, &check); if ((new ^ check) & mask) { @@ -112,6 +113,7 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno) if (res->flags & IORESOURCE_MEM_64) { new = region.start >> 16 >> 16; pci_write_config_dword(dev, reg + 4, new); + dev->saved_config_space[(reg + 4) / 4] = new; pci_read_config_dword(dev, reg + 4, &check); if (check != new) { pci_err(dev, "%s: error updating (high %#010x != %#010x)\n", diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 6e4cb2871fca..0dcb50bf5c35 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -1512,7 +1512,7 @@ static const struct rpmh_vreg_init_data pmh0101_vreg_data[] = { RPMH_VREG("ldo13", LDO, 13, &pmic5_pldo530_mvp150, "vdd-l2-l13-l14"), RPMH_VREG("ldo14", LDO, 14, &pmic5_pldo530_mvp150, "vdd-l2-l13-l14"), RPMH_VREG("ldo15", LDO, 15, &pmic5_nldo530, "vdd-l15"), - RPMH_VREG("ldo16", LDO, 15, &pmic5_pldo530_mvp600, "vdd-l5-l16"), + RPMH_VREG("ldo16", LDO, 16, &pmic5_pldo530_mvp600, "vdd-l5-l16"), RPMH_VREG("ldo17", LDO, 17, &pmic5_pldo515_mv, "vdd-l17"), RPMH_VREG("ldo18", LDO, 18, &pmic5_nldo530, "vdd-l18"), RPMH_VREG("bob1", BOB, 1, &pmic5_bob, "vdd-bob1"), diff --git a/drivers/reset/reset-eyeq.c b/drivers/reset/reset-eyeq.c index 791b7283111e..1a3857983897 100644 --- a/drivers/reset/reset-eyeq.c +++ b/drivers/reset/reset-eyeq.c @@ -422,13 +422,6 @@ static int eqr_of_xlate_twocells(struct reset_controller_dev *rcdev, return eqr_of_xlate_internal(rcdev, reset_spec->args[0], reset_spec->args[1]); } -static void eqr_of_node_put(void *_dev) -{ - struct device *dev = _dev; - - of_node_put(dev->of_node); -} - static int eqr_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { @@ -439,21 +432,8 @@ static int eqr_probe(struct auxiliary_device *adev, int ret; /* - * We are an auxiliary device of clk-eyeq. We do not have an OF node by - * default; let's reuse our parent's OF node. - */ - WARN_ON(dev->of_node); - device_set_of_node_from_dev(dev, dev->parent); - if (!dev->of_node) - return -ENODEV; - - ret = devm_add_action_or_reset(dev, eqr_of_node_put, dev); - if (ret) - return ret; - - /* - * Using our newfound OF node, we can get match data. We cannot use - * device_get_match_data() because it does not match reused OF nodes. + * Get match data. We cannot use device_get_match_data() because it does + * not accept reused OF nodes; see device_set_of_node_from_dev(). */ match = of_match_node(dev->driver->of_match_table, dev->of_node); if (!match || !match->data) diff --git a/drivers/spi/spi-ch341.c b/drivers/spi/spi-ch341.c index 3eaa8f176f63..6448a44a8b67 100644 --- a/drivers/spi/spi-ch341.c +++ b/drivers/spi/spi-ch341.c @@ -250,5 +250,5 @@ static struct usb_driver ch341a_usb_driver = { module_usb_driver(ch341a_usb_driver); MODULE_AUTHOR("Johannes Thumshirn "); -MODULE_DESCRIPTION("QiHeng Electronics ch341 USB2SPI"); +MODULE_DESCRIPTION("Nanjing Qinheng Microelectronics CH341 USB2SPI driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index e5c907c45b87..480d1e8b281f 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1382,9 +1382,7 @@ static int spi_imx_setupxfer(struct spi_device *spi, spi_imx->target_burst = t->len; } - spi_imx->devtype_data->prepare_transfer(spi_imx, spi, t); - - return 0; + return spi_imx->devtype_data->prepare_transfer(spi_imx, spi, t); } static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx) @@ -1709,6 +1707,7 @@ static int spi_imx_dma_data_prepare(struct spi_imx_data *spi_imx, kfree(spi_imx->dma_data[0].dma_tx_buf); kfree(spi_imx->dma_data[0].dma_rx_buf); kfree(spi_imx->dma_data); + return ret; } } @@ -1836,7 +1835,7 @@ static void spi_imx_dma_max_wml_find(struct spi_imx_data *spi_imx, unsigned int i; for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) { - if (!dma_data->dma_len % (i * bytes_per_word)) + if (!(dma_data->dma_len % (i * bytes_per_word))) break; } /* Use 1 as wml in case no available burst length got */ diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index eab059fb0bc2..4dee0fea1df8 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -74,6 +74,13 @@ #define STATUS_FLAGSX4 BIT(8) #define STATUS_MASK GENMASK(8, 0) +/* + * QSPI Direct Access register defines + */ +#define DIRECT_ACCESS_EN_SSEL BIT(0) +#define DIRECT_ACCESS_OP_SSEL BIT(1) +#define DIRECT_ACCESS_OP_SSEL_SHIFT 1 + #define BYTESUPPER_MASK GENMASK(31, 16) #define BYTESLOWER_MASK GENMASK(15, 0) @@ -158,7 +165,39 @@ static int mchp_coreqspi_set_mode(struct mchp_coreqspi *qspi, const struct spi_m return 0; } -static inline void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_set_cs(struct spi_device *spi, bool enable) +{ + struct mchp_coreqspi *qspi = spi_controller_get_devdata(spi->controller); + u32 val; + + val = readl(qspi->regs + REG_DIRECT_ACCESS); + + val &= ~DIRECT_ACCESS_OP_SSEL; + val |= !enable << DIRECT_ACCESS_OP_SSEL_SHIFT; + + writel(val, qspi->regs + REG_DIRECT_ACCESS); +} + +static int mchp_coreqspi_setup(struct spi_device *spi) +{ + struct mchp_coreqspi *qspi = spi_controller_get_devdata(spi->controller); + u32 val; + + /* + * Active low devices need to be specifically set to their inactive + * states during probe. + */ + if (spi->mode & SPI_CS_HIGH) + return 0; + + val = readl(qspi->regs + REG_DIRECT_ACCESS); + val |= DIRECT_ACCESS_OP_SSEL; + writel(val, qspi->regs + REG_DIRECT_ACCESS); + + return 0; +} + +static void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -194,7 +233,7 @@ static inline void mchp_coreqspi_read_op(struct mchp_coreqspi *qspi) } } -static inline void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -222,7 +261,7 @@ static inline void mchp_coreqspi_write_op(struct mchp_coreqspi *qspi) } } -static inline void mchp_coreqspi_write_read_op(struct mchp_coreqspi *qspi) +static void mchp_coreqspi_write_read_op(struct mchp_coreqspi *qspi) { u32 control, data; @@ -380,20 +419,7 @@ static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_devi return 0; } -static int mchp_coreqspi_setup_op(struct spi_device *spi_dev) -{ - struct spi_controller *ctlr = spi_dev->controller; - struct mchp_coreqspi *qspi = spi_controller_get_devdata(ctlr); - u32 control = readl_relaxed(qspi->regs + REG_CONTROL); - - control |= (CONTROL_MASTER | CONTROL_ENABLE); - control &= ~CONTROL_CLKIDLE; - writel_relaxed(control, qspi->regs + REG_CONTROL); - - return 0; -} - -static inline void mchp_coreqspi_config_op(struct mchp_coreqspi *qspi, const struct spi_mem_op *op) +static void mchp_coreqspi_config_op(struct mchp_coreqspi *qspi, const struct spi_mem_op *op) { u32 idle_cycles = 0; int total_bytes, cmd_bytes, frames, ctrl; @@ -483,6 +509,7 @@ static int mchp_coreqspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *o reinit_completion(&qspi->data_completion); mchp_coreqspi_config_op(qspi, op); + mchp_coreqspi_set_cs(mem->spi, true); if (op->cmd.opcode) { qspi->txbuf = &opcode; qspi->rxbuf = NULL; @@ -523,6 +550,7 @@ static int mchp_coreqspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *o err = -ETIMEDOUT; error: + mchp_coreqspi_set_cs(mem->spi, false); mutex_unlock(&qspi->op_lock); mchp_coreqspi_disable_ints(qspi); @@ -662,18 +690,28 @@ static int mchp_coreqspi_transfer_one(struct spi_controller *ctlr, struct spi_de struct spi_transfer *t) { struct mchp_coreqspi *qspi = spi_controller_get_devdata(ctlr); + bool dual_quad = false; qspi->tx_len = t->len; + if (t->tx_nbits == SPI_NBITS_QUAD || t->rx_nbits == SPI_NBITS_QUAD || + t->tx_nbits == SPI_NBITS_DUAL || + t->rx_nbits == SPI_NBITS_DUAL) + dual_quad = true; + if (t->tx_buf) qspi->txbuf = (u8 *)t->tx_buf; if (!t->rx_buf) { mchp_coreqspi_write_op(qspi); - } else { + } else if (!dual_quad) { qspi->rxbuf = (u8 *)t->rx_buf; qspi->rx_len = t->len; mchp_coreqspi_write_read_op(qspi); + } else { + qspi->rxbuf = (u8 *)t->rx_buf; + qspi->rx_len = t->len; + mchp_coreqspi_read_op(qspi); } return 0; @@ -686,6 +724,7 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; int ret; + u32 num_cs, val; ctlr = devm_spi_alloc_host(&pdev->dev, sizeof(*qspi)); if (!ctlr) @@ -718,10 +757,18 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) return ret; } + /* + * The IP core only has a single CS, any more have to be provided via + * gpios + */ + if (of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs)) + num_cs = 1; + + ctlr->num_chipselect = num_cs; + ctlr->bits_per_word_mask = SPI_BPW_MASK(8); ctlr->mem_ops = &mchp_coreqspi_mem_ops; ctlr->mem_caps = &mchp_coreqspi_mem_caps; - ctlr->setup = mchp_coreqspi_setup_op; ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD; ctlr->dev.of_node = np; @@ -729,9 +776,21 @@ static int mchp_coreqspi_probe(struct platform_device *pdev) ctlr->prepare_message = mchp_coreqspi_prepare_message; ctlr->unprepare_message = mchp_coreqspi_unprepare_message; ctlr->transfer_one = mchp_coreqspi_transfer_one; - ctlr->num_chipselect = 2; + ctlr->setup = mchp_coreqspi_setup; + ctlr->set_cs = mchp_coreqspi_set_cs; ctlr->use_gpio_descriptors = true; + val = readl_relaxed(qspi->regs + REG_CONTROL); + val |= (CONTROL_MASTER | CONTROL_ENABLE); + writel_relaxed(val, qspi->regs + REG_CONTROL); + + /* + * Put cs into software controlled mode + */ + val = readl_relaxed(qspi->regs + REG_DIRECT_ACCESS); + val |= DIRECT_ACCESS_EN_SSEL; + writel(val, qspi->regs + REG_DIRECT_ACCESS); + ret = spi_register_controller(ctlr); if (ret) return dev_err_probe(&pdev->dev, ret, diff --git a/drivers/staging/rtl8723bs/os_dep/osdep_service.c b/drivers/staging/rtl8723bs/os_dep/osdep_service.c index 7959daeabc6f..4cfdf7c62344 100644 --- a/drivers/staging/rtl8723bs/os_dep/osdep_service.c +++ b/drivers/staging/rtl8723bs/os_dep/osdep_service.c @@ -194,7 +194,8 @@ struct rtw_cbuf *rtw_cbuf_alloc(u32 size) struct rtw_cbuf *cbuf; cbuf = kzalloc_flex(*cbuf, bufs, size); - cbuf->size = size; + if (cbuf) + cbuf->size = size; return cbuf; } diff --git a/drivers/staging/vme_user/vme_fake.c b/drivers/staging/vme_user/vme_fake.c index be4ad47ed526..8abaa3165fbb 100644 --- a/drivers/staging/vme_user/vme_fake.c +++ b/drivers/staging/vme_user/vme_fake.c @@ -1230,6 +1230,8 @@ static int __init fake_init(void) err_driver: kfree(fake_bridge); err_struct: + root_device_unregister(vme_root); + return retval; } diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 669b9e6879bf..746414763da5 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -1178,7 +1178,7 @@ static int usblp_probe(struct usb_interface *intf, } /* Allocate buffer for printer status */ - usblp->statusbuf = kmalloc(STATUS_BUF_SIZE, GFP_KERNEL); + usblp->statusbuf = kzalloc(STATUS_BUF_SIZE, GFP_KERNEL); if (!usblp->statusbuf) { retval = -ENOMEM; goto abort; @@ -1377,6 +1377,7 @@ static int usblp_cache_device_id_string(struct usblp *usblp) { int err, length; + memset(usblp->device_id_string, 0, USBLP_DEVICE_ID_SIZE); err = usblp_get_id(usblp, 0, usblp->device_id_string, USBLP_DEVICE_ID_SIZE - 1); if (err < 0) { dev_dbg(&usblp->intf->dev, diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index b34fb65813c4..9b69148128e5 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -286,12 +286,15 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) ACPI_COMPANION_SET(&ulpi->dev, ACPI_COMPANION(dev)); ret = ulpi_of_register(ulpi); - if (ret) + if (ret) { + kfree(ulpi); return ret; + } ret = ulpi_read_id(ulpi); if (ret) { of_node_put(ulpi->dev.of_node); + kfree(ulpi); return ret; } diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 58899b1fa96d..65213896de99 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1359,12 +1359,6 @@ int dwc3_core_init(struct dwc3 *dwc) hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - /* - * Write Linux Version Code to our GUID register so it's easy to figure - * out which kernel version a bug was found. - */ - dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); - ret = dwc3_phy_setup(dwc); if (ret) return ret; @@ -1398,6 +1392,12 @@ int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err_exit_phy; + /* + * Write Linux Version Code to our GUID register so it's easy to figure + * out which kernel version a bug was found. + */ + dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); + dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index 91139ae668f4..f3ca79cece1b 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -733,8 +733,6 @@ static void dma_channel_claim(struct omap_ep *ep, unsigned channel) if (status == 0) { omap_writew(reg, UDC_TXDMA_CFG); /* EMIFF or SDRC */ - omap_set_dma_src_burst_mode(ep->lch, - OMAP_DMA_DATA_BURST_4); omap_set_dma_src_data_pack(ep->lch, 1); /* TIPB */ omap_set_dma_dest_params(ep->lch, @@ -756,8 +754,6 @@ static void dma_channel_claim(struct omap_ep *ep, unsigned channel) UDC_DATA_DMA, 0, 0); /* EMIFF or SDRC */ - omap_set_dma_dest_burst_mode(ep->lch, - OMAP_DMA_DATA_BURST_4); omap_set_dma_dest_data_pack(ep->lch, 1); } } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index c71461893d20..42e4cecd28ac 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1513,7 +1513,11 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x1250, 0xff, 0x00, 0x00) }, /* Telit LE910Cx (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1251, 0xff) }, /* Telit LE910Cx (RNDIS) */ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1252, 0xff) }, /* Telit LE910Cx (MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1253, 0xff) }, /* Telit LE910Cx (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1254, 0xff) }, /* Telit LE910Cx */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1255, 0xff) }, /* Telit LE910Cx */ { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index dfbb94ddc98a..55fee96d3342 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -732,9 +732,14 @@ static const char * const pd_rev[] = { (tcpm_cc_is_source((port)->cc2) && \ !tcpm_cc_is_source((port)->cc1))) +#define tcpm_port_is_debug_source(port) \ + (tcpm_cc_is_source((port)->cc1) && tcpm_cc_is_source((port)->cc2)) + +#define tcpm_port_is_debug_sink(port) \ + (tcpm_cc_is_sink((port)->cc1) && tcpm_cc_is_sink((port)->cc2)) + #define tcpm_port_is_debug(port) \ - ((tcpm_cc_is_source((port)->cc1) && tcpm_cc_is_source((port)->cc2)) || \ - (tcpm_cc_is_sink((port)->cc1) && tcpm_cc_is_sink((port)->cc2))) + (tcpm_port_is_debug_source(port) || tcpm_port_is_debug_sink(port)) #define tcpm_port_is_audio(port) \ (tcpm_cc_is_audio((port)->cc1) && tcpm_cc_is_audio((port)->cc2)) @@ -5176,7 +5181,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SNK_UNATTACHED, PD_T_DRP_SNK); break; case SRC_ATTACH_WAIT: - if (tcpm_port_is_debug(port)) + if (tcpm_port_is_debug_source(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, port->timings.cc_debounce_time); else if (tcpm_port_is_audio(port)) @@ -5434,7 +5439,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SRC_UNATTACHED, PD_T_DRP_SRC); break; case SNK_ATTACH_WAIT: - if (tcpm_port_is_debug(port)) + if (tcpm_port_is_debug_sink(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, PD_T_CC_DEBOUNCE); else if (tcpm_port_is_audio(port)) @@ -5454,7 +5459,7 @@ static void run_state_machine(struct tcpm_port *port) if (tcpm_port_is_disconnected(port)) tcpm_set_state(port, SNK_UNATTACHED, PD_T_PD_DEBOUNCE); - else if (tcpm_port_is_debug(port)) + else if (tcpm_port_is_debug_sink(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, PD_T_CC_DEBOUNCE); else if (tcpm_port_is_audio(port)) @@ -5935,6 +5940,8 @@ static void run_state_machine(struct tcpm_port *port) /* remove existing capabilities */ tcpm_partner_source_caps_reset(port); tcpm_pd_send_control(port, PD_CTRL_ACCEPT, TCPC_TX_SOP); + port->vdm_sm_running = false; + port->explicit_contract = false; tcpm_ams_finish(port); if (port->pwr_role == TYPEC_SOURCE) { port->upcoming_state = SRC_SEND_CAPABILITIES; @@ -6360,10 +6367,10 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, switch (port->state) { case TOGGLING: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_source(port) || tcpm_port_is_audio(port) || tcpm_port_is_source(port)) tcpm_set_state(port, SRC_ATTACH_WAIT, 0); - else if (tcpm_port_is_sink(port)) + else if (tcpm_port_is_debug_sink(port) || tcpm_port_is_sink(port)) tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; case CHECK_CONTAMINANT: @@ -6371,9 +6378,11 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, break; case SRC_UNATTACHED: case ACC_UNATTACHED: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_source(port) || tcpm_port_is_audio(port) || tcpm_port_is_source(port)) tcpm_set_state(port, SRC_ATTACH_WAIT, 0); + else if (tcpm_port_is_debug_sink(port)) + tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; case SRC_ATTACH_WAIT: if (tcpm_port_is_disconnected(port) || @@ -6395,7 +6404,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, } break; case SNK_UNATTACHED: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_sink(port) || tcpm_port_is_audio(port) || tcpm_port_is_sink(port)) tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 7b86a6bac644..b41f4788e4f0 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -1354,7 +1354,7 @@ int ovl_ensure_verity_loaded(const struct path *datapath) struct inode *inode = d_inode(datapath->dentry); struct file *filp; - if (!fsverity_active(inode) && IS_VERITY(inode)) { + if (IS_VERITY(inode) && fsverity_get_info(inode) == NULL) { /* * If this inode was not yet opened, the verity info hasn't been * loaded yet, so we need to do that here to force it into memory. diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 02791ec3c5a1..88d5e9a32f28 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -286,6 +286,14 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto oshr_free; + + if (oplock != SMB2_OPLOCK_LEVEL_II) { + rc = -EINVAL; + cifs_dbg(FYI, "%s: Oplock level %d not suitable for cached directory\n", + __func__, oplock); + goto oshr_free; + } + smb2_set_next_command(tcon, &rqst[0]); memset(&qi_iov, 0, sizeof(qi_iov)); diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index ec5d47779304..786dbbc43c5b 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1264,6 +1264,17 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl) return 0; } +static bool dacl_offset_valid(unsigned int acl_len, __u32 dacloffset) +{ + if (acl_len < sizeof(struct smb_acl)) + return false; + + if (dacloffset < sizeof(struct smb_ntsd)) + return false; + + return dacloffset <= acl_len - sizeof(struct smb_acl); +} + /* Convert CIFS ACL to POSIX form */ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, @@ -1284,7 +1295,6 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, group_sid_ptr = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->gsidoffset)); dacloffset = le32_to_cpu(pntsd->dacloffset); - dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); cifs_dbg(NOISY, "revision %d type 0x%x ooffset 0x%x goffset 0x%x sacloffset 0x%x dacloffset 0x%x\n", pntsd->revision, pntsd->type, le32_to_cpu(pntsd->osidoffset), le32_to_cpu(pntsd->gsidoffset), @@ -1315,11 +1325,18 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, return rc; } - if (dacloffset) + if (dacloffset) { + if (!dacl_offset_valid(acl_len, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + return -EINVAL; + } + + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); parse_dacl(dacl_ptr, end_of_acl, owner_sid_ptr, group_sid_ptr, fattr, get_mode_from_special_sid); - else + } else { cifs_dbg(FYI, "no ACL\n"); /* BB grant all or default perms? */ + } return rc; } @@ -1342,6 +1359,11 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, dacloffset = le32_to_cpu(pntsd->dacloffset); if (dacloffset) { + if (!dacl_offset_valid(secdesclen, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + return -EINVAL; + } + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); rc = validate_dacl(dacl_ptr, end_of_acl); if (rc) @@ -1710,6 +1732,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, nsecdesclen = sizeof(struct smb_ntsd) + (sizeof(struct smb_sid) * 2); dacloffset = le32_to_cpu(pntsd->dacloffset); if (dacloffset) { + if (!dacl_offset_valid(secdesclen, dacloffset)) { + cifs_dbg(VFS, "Server returned illegal DACL offset\n"); + rc = -EINVAL; + goto id_mode_to_cifs_acl_exit; + } + dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset); rc = validate_dacl(dacl_ptr, (char *)pntsd + secdesclen); if (rc) { @@ -1732,7 +1760,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, * descriptor parameters, and security descriptor itself */ nsecdesclen = max_t(u32, nsecdesclen, DEFAULT_SEC_DESC_LEN); - pnntsd = kmalloc(nsecdesclen, GFP_KERNEL); + pnntsd = kzalloc(nsecdesclen, GFP_KERNEL); if (!pnntsd) { kfree(pntsd); cifs_put_tlink(tlink); @@ -1752,6 +1780,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, rc = ops->set_acl(pnntsd, nsecdesclen, inode, path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } +id_mode_to_cifs_acl_exit: cifs_put_tlink(tlink); kfree(pnntsd); diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 9afab3237e54..17408bb8ab65 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -296,7 +296,7 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug break; case SMB2_ENCRYPTION_AES256_CCM: case SMB2_ENCRYPTION_AES256_GCM: - out.session_key_length = CIFS_SESS_KEY_SIZE; + out.session_key_length = ses->auth_key.len; out.server_in_key_length = out.server_out_key_length = SMB3_GCM256_CRYPTKEY_SIZE; break; default: diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 286912616c73..6c9c229b91f6 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -111,7 +111,7 @@ static int check_wsl_eas(struct kvec *rsp_iov) u32 outlen, next; u16 vlen; u8 nlen; - u8 *end; + u8 *ea_end, *iov_end; outlen = le32_to_cpu(rsp->OutputBufferLength); if (outlen < SMB2_WSL_MIN_QUERY_EA_RESP_SIZE || @@ -120,15 +120,19 @@ static int check_wsl_eas(struct kvec *rsp_iov) ea = (void *)((u8 *)rsp_iov->iov_base + le16_to_cpu(rsp->OutputBufferOffset)); - end = (u8 *)rsp_iov->iov_base + rsp_iov->iov_len; + ea_end = (u8 *)ea + outlen; + iov_end = (u8 *)rsp_iov->iov_base + rsp_iov->iov_len; + if (ea_end > iov_end) + return -EINVAL; + for (;;) { - if ((u8 *)ea > end - sizeof(*ea)) + if ((u8 *)ea > ea_end - sizeof(*ea)) return -EINVAL; nlen = ea->ea_name_length; vlen = le16_to_cpu(ea->ea_value_length); if (nlen != SMB2_WSL_XATTR_NAME_LEN || - (u8 *)ea->ea_data + nlen + 1 + vlen > end) + (u8 *)ea->ea_data + nlen + 1 + vlen > ea_end) return -EINVAL; switch (vlen) { diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 973fce3c959c..2a7355ce1a07 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -241,7 +241,8 @@ smb2_check_message(char *buf, unsigned int pdu_len, unsigned int len, if (len != calc_len) { /* create failed on symlink */ if (command == SMB2_CREATE_HE && - shdr->Status == STATUS_STOPPED_ON_SYMLINK) + shdr->Status == STATUS_STOPPED_ON_SYMLINK && + len > calc_len) return 0; /* Windows 7 server returns 24 bytes more */ if (calc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index cb61051f9af3..995fcdd30681 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1713,17 +1713,30 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) is_binding = (ses->ses_status == SES_GOOD); spin_unlock(&ses->ses_lock); + /* + * Per MS-SMB2 3.2.5.3, Session.SessionKey is the first 16 bytes of the + * GSS cryptographic key, right-padded with zero bytes if shorter. + * Allocate at least SMB2_NTLMV2_SESSKEY_SIZE bytes (zeroed) so the KDF + * input buffer is always valid for HMAC-SHA256 even with deprecated + * Kerberos enctypes that return a short session key. + */ + if (unlikely(msg->sesskey_len < SMB2_NTLMV2_SESSKEY_SIZE)) + cifs_dbg(VFS, + "short GSS session key (%u bytes); zero-padding per MS-SMB2 3.2.5.3\n", + msg->sesskey_len); + kfree_sensitive(ses->auth_key.response); - ses->auth_key.response = kmemdup(msg->data, - msg->sesskey_len, - GFP_KERNEL); + ses->auth_key.len = max_t(unsigned int, msg->sesskey_len, + SMB2_NTLMV2_SESSKEY_SIZE); + ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL); if (!ses->auth_key.response) { cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n", - __func__, msg->sesskey_len); + __func__, ses->auth_key.len); + ses->auth_key.len = 0; rc = -ENOMEM; goto out_put_spnego_key; } - ses->auth_key.len = msg->sesskey_len; + memcpy(ses->auth_key.response, msg->data, msg->sesskey_len); sess_data->iov[1].iov_base = msg->data + msg->sesskey_len; sess_data->iov[1].iov_len = msg->secblob_len; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 41009039b4cb..e8eeff9e50d6 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -251,7 +251,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) } static void generate_key(struct cifs_ses *ses, struct kvec label, - struct kvec context, __u8 *key, unsigned int key_size) + struct kvec context, __u8 *key, unsigned int key_size, + unsigned int full_key_size) { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; @@ -265,7 +266,7 @@ static void generate_key(struct cifs_ses *ses, struct kvec label, memset(key, 0x0, key_size); hmac_sha256_init_usingrawkey(&hmac_ctx, ses->auth_key.response, - SMB2_NTLMV2_SESSKEY_SIZE); + full_key_size); hmac_sha256_update(&hmac_ctx, i, 4); hmac_sha256_update(&hmac_ctx, label.iov_base, label.iov_len); hmac_sha256_update(&hmac_ctx, &zero, 1); @@ -298,6 +299,7 @@ generate_smb3signingkey(struct cifs_ses *ses, struct TCP_Server_Info *server, const struct derivation_triplet *ptriplet) { + unsigned int full_key_size = SMB2_NTLMV2_SESSKEY_SIZE; bool is_binding = false; int chan_index = 0; @@ -330,12 +332,24 @@ generate_smb3signingkey(struct cifs_ses *ses, if (is_binding) { generate_key(ses, ptriplet->signing.label, ptriplet->signing.context, - ses->chans[chan_index].signkey, - SMB3_SIGN_KEY_SIZE); + ses->chans[chan_index].signkey, SMB3_SIGN_KEY_SIZE, + SMB2_NTLMV2_SESSKEY_SIZE); } else { generate_key(ses, ptriplet->signing.label, - ptriplet->signing.context, - ses->smb3signingkey, SMB3_SIGN_KEY_SIZE); + ptriplet->signing.context, ses->smb3signingkey, + SMB3_SIGN_KEY_SIZE, SMB2_NTLMV2_SESSKEY_SIZE); + + /* + * Per MS-SMB2 3.2.5.3.1, signing key always uses Session.SessionKey + * (first 16 bytes). Encryption/decryption keys use + * Session.FullSessionKey when dialect is 3.1.1 and cipher is + * AES-256-CCM or AES-256-GCM, otherwise Session.SessionKey. + */ + + if (server->dialect == SMB311_PROT_ID && + (server->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) + full_key_size = ses->auth_key.len; /* safe to access primary channel, since it will never go away */ spin_lock(&ses->chan_lock); @@ -345,10 +359,13 @@ generate_smb3signingkey(struct cifs_ses *ses, generate_key(ses, ptriplet->encryption.label, ptriplet->encryption.context, - ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); + ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE, + full_key_size); + generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, - ses->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE); + ses->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE, + full_key_size); } #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS @@ -361,7 +378,7 @@ generate_smb3signingkey(struct cifs_ses *ses, &ses->Suid); cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type); cifs_dbg(VFS, "Session Key %*ph\n", - SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + (int)ses->auth_key.len, ses->auth_key.response); cifs_dbg(VFS, "Signing Key %*ph\n", SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h index 060eab094e5a..5290a2b2e15a 100644 --- a/include/asm-generic/kprobes.h +++ b/include/asm-generic/kprobes.h @@ -14,7 +14,7 @@ static unsigned long __used \ _kbl_addr_##fname = (unsigned long)fname; # define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) /* Use this to forbid a kprobes attach on very low level functions */ -# define __kprobes __section(".kprobes.text") +# define __kprobes notrace __section(".kprobes.text") # define nokprobe_inline __always_inline #else # define NOKPROBE_SYMBOL(fname) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 50b47eba7d01..e7195750d21b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -105,6 +105,12 @@ ARM_SMCCC_SMC_32, \ 0, 0x3fff) +/* C1-Pro erratum 4193714: SME DVMSync early acknowledgement */ +#define ARM_SMCCC_CPU_WORKAROUND_4193714 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_CPU, 0x10) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4b703c90ca9..01e203964892 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3725,6 +3725,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 0a3bcd1718f3..be1b38c981d4 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -94,6 +94,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); int unregister_fprobe(struct fprobe *fp); +int unregister_fprobe_async(struct fprobe *fp); bool fprobe_is_registered(struct fprobe *fp); int fprobe_count_ips_from_filter(const char *filter, const char *notfilter); #else @@ -113,6 +114,10 @@ static inline int unregister_fprobe(struct fprobe *fp) { return -EOPNOTSUPP; } +static inline int unregister_fprobe_async(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} static inline bool fprobe_is_registered(struct fprobe *fp) { return false; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index a81b46af5118..5a1c5c336fa4 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -305,9 +305,11 @@ struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, + const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); -void *xt_unregister_table(struct xt_table *table); +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name); +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index a40aaf645fa4..05631a25e622 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); -void arpt_unregister_table_pre_exit(struct net *net, const char *name); extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 132b0e4a6d4d..13593391d605 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -26,7 +26,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops); -void ipt_unregister_table_pre_exit(struct net *net, const char *name); void ipt_unregister_table_exit(struct net *net, const char *name); /* Standard entry. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8b8885a73c76..c6d5b927830d 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -27,7 +27,6 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *); int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops); -void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/rseq.h b/include/linux/rseq.h index b9d62fc2140d..7ef79b25e714 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -9,6 +9,11 @@ void __rseq_handle_slowpath(struct pt_regs *regs); +static __always_inline bool rseq_v2(struct task_struct *t) +{ + return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.has_rseq > 1); +} + /* Invoked from resume_user_mode_work() */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { @@ -16,8 +21,7 @@ static inline void rseq_handle_slowpath(struct pt_regs *regs) if (current->rseq.event.slowpath) __rseq_handle_slowpath(regs); } else { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + if (current->rseq.event.sched_switch && current->rseq.event.has_rseq) __rseq_handle_slowpath(regs); } } @@ -30,9 +34,9 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs); */ static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + if (rseq_v2(current)) { + /* has_rseq is implied in rseq_v2() */ + if (current->rseq.event.user_irq) __rseq_signal_deliver(ksig->sig, regs); } else { if (current->rseq.event.has_rseq) @@ -50,15 +54,22 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) { struct rseq_event *ev = &t->rseq.event; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Only apply the user_irq optimization for RSEQ ABI V2 registrations. + * Legacy users like TCMalloc rely on the original ABI V1 behaviour + * which updates IDs on every context swtich. + */ + if (rseq_v2(t)) { /* - * Avoid a boat load of conditionals by using simple logic - * to determine whether NOTIFY_RESUME needs to be raised. + * Avoid a boat load of conditionals by using simple logic to + * determine whether TIF_NOTIFY_RESUME or TIF_RSEQ needs to be + * raised. * - * It's required when the CPU or MM CID has changed or - * the entry was from user space. + * It's required when the CPU or MM CID has changed or the entry + * was via interrupt from user space. ev->has_rseq does not have + * to be evaluated here because rseq_v2() implies has_rseq. */ - bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + bool raise = ev->user_irq | ev->ids_changed; if (raise) { ev->sched_switch = true; @@ -66,6 +77,7 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) } } else { if (ev->has_rseq) { + t->rseq.event.ids_changed = true; t->rseq.event.sched_switch = true; rseq_raise_notify_resume(t); } @@ -119,6 +131,8 @@ static inline void rseq_virt_userspace_exit(void) static inline void rseq_reset(struct task_struct *t) { + /* Protect against preemption and membarrier IPI */ + guard(irqsave)(); memset(&t->rseq, 0, sizeof(t->rseq)); t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } @@ -159,6 +173,7 @@ static inline unsigned int rseq_alloc_align(void) } #else /* CONFIG_RSEQ */ +static inline bool rseq_v2(struct task_struct *t) { return false; } static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_sched_switch_event(struct task_struct *t) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index f11ebd34f8b9..2d0295df5107 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -111,6 +111,20 @@ static __always_inline void rseq_slice_clear_grant(struct task_struct *t) t->rseq.slice.state.granted = false; } +/* + * Open coded, so it can be invoked within a user access region. + * + * This clears the user space state of the time slice extensions field only when + * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations, + * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be + * overwritten by an unconditional write. + */ +#define rseq_slice_clear_user(rseq, efault) \ +do { \ + if (rseq_slice_extension_enabled()) \ + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); \ +} while (0) + static __always_inline bool __rseq_grant_slice_extension(bool work_pending) { struct task_struct *curr = current; @@ -230,10 +244,10 @@ static __always_inline bool rseq_slice_extension_enabled(void) { return false; } static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; } +#define rseq_slice_clear_user(rseq, efault) do { } while (0) #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); -bool rseq_debug_validate_ids(struct task_struct *t); static __always_inline void rseq_note_user_irq_entry(void) { @@ -353,43 +367,6 @@ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, return false; } -/* - * On debug kernels validate that user space did not mess with it if the - * debug branch is enabled. - */ -bool rseq_debug_validate_ids(struct task_struct *t) -{ - struct rseq __user *rseq = t->rseq.usrptr; - u32 cpu_id, uval, node_id; - - /* - * On the first exit after registering the rseq region CPU ID is - * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! - */ - node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? - cpu_to_node(t->rseq.ids.cpu_id) : 0; - - scoped_user_read_access(rseq, efault) { - unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); - if (cpu_id != t->rseq.ids.cpu_id) - goto die; - unsafe_get_user(uval, &rseq->cpu_id, efault); - if (uval != cpu_id) - goto die; - unsafe_get_user(uval, &rseq->node_id, efault); - if (uval != node_id) - goto die; - unsafe_get_user(uval, &rseq->mm_cid, efault); - if (uval != t->rseq.ids.mm_cid) - goto die; - } - return true; -die: - t->rseq.event.fatal = true; -efault: - return false; -} - #endif /* RSEQ_BUILD_SLOW_PATH */ /* @@ -499,37 +476,50 @@ rseq_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long c * faults in task context are fatal too. */ static rseq_inline -bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, - u32 node_id, u64 *csaddr) +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, u64 *csaddr) { struct rseq __user *rseq = t->rseq.usrptr; - if (static_branch_unlikely(&rseq_debug_enabled)) { - if (!rseq_debug_validate_ids(t)) - return false; - } - scoped_user_rw_access(rseq, efault) { + /* Validate the R/O fields for debug and optimized mode */ + if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) { + u32 cpu_id, uval; + + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != t->rseq.ids.node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); - unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->node_id, &rseq->node_id, efault); unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); if (csaddr) unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); /* Cache the new values */ - t->rseq.ids.cpu_cid = ids->cpu_cid; + t->rseq.ids = *ids; rseq_stat_inc(rseq_stats.ids); rseq_trace_update(t, ids); return true; + +die: + t->rseq.event.fatal = true; efault: return false; } @@ -539,11 +529,11 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, * is in a critical section. */ static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, - struct rseq_ids *ids, u32 node_id) + struct rseq_ids *ids) { u64 csaddr; - if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + if (!rseq_set_ids_get_csaddr(t, ids, &csaddr)) return false; /* @@ -612,6 +602,14 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t * interrupts disabled */ guard(pagefault)(); + /* + * This optimization is only valid when the task registered for the + * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original + * RSEQ implementation behaviour which unconditionally updated the IDs. + * rseq_sched_switch_event() ensures that legacy registrations always + * have both sched_switch and ids_changed set, which is compatible with + * the historical TIF_NOTIFY_RESUME behaviour. + */ if (likely(!t->rseq.event.ids_changed)) { struct rseq __user *rseq = t->rseq.usrptr; /* @@ -623,11 +621,9 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t scoped_user_rw_access(rseq, efault) { unsafe_get_user(csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); @@ -640,12 +636,12 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t } struct rseq_ids ids = { - .cpu_id = task_cpu(t), - .mm_cid = task_mm_cid(t), + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + .node_id = cpu_to_node(ids.cpu_id), }; - u32 node_id = cpu_to_node(ids.cpu_id); - return rseq_update_usr(t, regs, &ids, node_id); + return rseq_update_usr(t, regs, &ids); efault: return false; } diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index 0b42045988db..85739a63e85e 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -9,6 +9,12 @@ #ifdef CONFIG_RSEQ struct rseq; +/* + * rseq_event::has_rseq contains the ABI version number so preserving it + * in AND operations requires a mask. + */ +#define RSEQ_HAS_RSEQ_VERSION_MASK 0xff + /** * struct rseq_event - Storage for rseq related event management * @all: Compound to initialize and clear the data efficiently @@ -17,7 +23,8 @@ struct rseq; * exit to user * @ids_changed: Indicator that IDs need to be updated * @user_irq: True on interrupt entry from user mode - * @has_rseq: True if the task has a rseq pointer installed + * @has_rseq: Greater than 0 if the task has a rseq pointer installed. + * Contains the RSEQ version number * @error: Compound error code for the slow path to analyze * @fatal: User space data corrupted or invalid * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME @@ -59,8 +66,9 @@ struct rseq_event { * compiler emit a single compare on 64-bit * @cpu_id: The CPU ID which was written last to user space * @mm_cid: The MM CID which was written last to user space + * @node_id: The node ID which was written last to user space * - * @cpu_id and @mm_cid are updated when the data is written to user space. + * @cpu_id, @mm_cid and @node_id are updated when the data is written to user space. */ struct rseq_ids { union { @@ -70,6 +78,7 @@ struct rseq_ids { u32 mm_cid; }; }; + u32 node_id; }; /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 368c7b4d7cb5..ee06cba5c6f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1002,6 +1002,9 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif + /* Save user-dumpable when mm goes away */ + unsigned user_dumpable:1; + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1198138cb839..273538200a44 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -33,6 +33,15 @@ struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); extern void dl_clear_root_domain_cpu(int cpu); +/* + * Return whether moving DL task @p to @new_mask requires moving DL + * bandwidth accounting between root domains. This helper is specific to + * DL bandwidth move accounting semantics and is shared by + * cpuset_can_attach() and set_cpus_allowed_dl() so both paths use the + * same source root-domain test. + */ +extern bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask); extern u64 dl_cookie; extern bool dl_bw_visited(int cpu, u64 cookie); diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index adb9a4de068a..2129e18ada58 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -101,24 +101,27 @@ enum scx_ent_flags { SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ - SCX_TASK_OFF_TASKS = 1 << 6, /* removed from scx_tasks by sched_ext_dead() */ /* - * Bits 8 and 9 are used to carry task state: + * Bits 8 to 10 are used to carry task state: * * NONE ops.init_task() not called yet + * INIT_BEGIN ops.init_task() in flight; see sched_ext_dead() * INIT ops.init_task() succeeded, but task can be cancelled * READY fully initialized, but not in sched_ext * ENABLED fully initialized and in sched_ext + * DEAD terminal state set by sched_ext_dead() */ - SCX_TASK_STATE_SHIFT = 8, /* bits 8 and 9 are used to carry task state */ - SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_SHIFT = 8, + SCX_TASK_STATE_BITS = 3, SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, SCX_TASK_NONE = 0 << SCX_TASK_STATE_SHIFT, - SCX_TASK_INIT = 1 << SCX_TASK_STATE_SHIFT, - SCX_TASK_READY = 2 << SCX_TASK_STATE_SHIFT, - SCX_TASK_ENABLED = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT_BEGIN = 1 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT = 2 << SCX_TASK_STATE_SHIFT, + SCX_TASK_READY = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_ENABLED = 4 << SCX_TASK_STATE_SHIFT, + SCX_TASK_DEAD = 5 << SCX_TASK_STATE_SHIFT, /* * Bits 12 and 13 are used to carry reenqueue reason. In addition to diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 7b84f2cef8b1..d70510ac31ab 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -489,8 +489,10 @@ genlmsg_multicast_netns_filtered(const struct genl_family *family, netlink_filter_fn filter, void *filter_data) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + nlmsg_free(skb); return -EINVAL; + } group = family->mcgrp_offset + group; return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group, flags, filter, filter_data); diff --git a/include/net/macsec.h b/include/net/macsec.h index bc7de5b53e54..d962093ee923 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -9,6 +9,7 @@ #include #include +#include #include #include @@ -123,6 +124,7 @@ struct macsec_dev_stats { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_rx_sa { struct macsec_key key; @@ -136,7 +138,7 @@ struct macsec_rx_sa { bool active; struct macsec_rx_sa_stats __percpu *stats; struct macsec_rx_sc *sc; - struct rcu_head rcu; + struct rcu_work destroy_work; }; struct pcpu_rx_sc_stats { @@ -174,6 +176,7 @@ struct macsec_rx_sc { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_tx_sa { struct macsec_key key; @@ -186,7 +189,7 @@ struct macsec_tx_sa { refcount_t refcnt; bool active; struct macsec_tx_sa_stats __percpu *stats; - struct rcu_head rcu; + struct rcu_work destroy_work; }; /** diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index e9a8350e7ccf..80f50fd0f7ad 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -45,9 +45,12 @@ struct nf_conntrack_expect { void (*expectfn)(struct nf_conn *new, struct nf_conntrack_expect *this); - /* Helper to assign to new connection */ + /* Helper that created this expectation */ struct nf_conntrack_helper __rcu *helper; + /* Helper to assign to new connection */ + struct nf_conntrack_helper __rcu *assign_helper; + /* The conntrack of the master connection */ struct nf_conn *master; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 499e4288170f..875916d60bfe 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -119,6 +119,7 @@ struct netns_ipv6 { struct fib_notifier_ops *notifier_ops; struct fib_notifier_ops *ip6mr_notifier_ops; atomic_t ipmr_seq; + int flowlabel_count; struct { struct hlist_head head; spinlock_t lock; diff --git a/include/net/nsh.h b/include/net/nsh.h index 16a751093896..15a26c590815 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -247,10 +247,10 @@ struct nshhdr { #define NSH_M_TYPE1_LEN 24 /* NSH header maximum Length. */ -#define NSH_HDR_MAX_LEN 256 +#define NSH_HDR_MAX_LEN ((NSH_LEN_MASK >> NSH_LEN_SHIFT) * 4) /* NSH context headers maximum Length. */ -#define NSH_CTX_HDRS_MAX_LEN 248 +#define NSH_CTX_HDRS_MAX_LEN (NSH_HDR_MAX_LEN - NSH_BASE_HDR_LEN) static inline struct nshhdr *nsh_hdr(struct sk_buff *skb) { diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index f69344fe6c08..ca6fe1f9d05e 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -28,7 +28,7 @@ enum rseq_cs_flags_bit { RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, - /* (3) Intentional gap to put new bits into a separate byte */ + /* (3) Intentional gap to keep new bits separate */ /* User read only feature flags */ RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT = 4, @@ -161,6 +161,9 @@ struct rseq { * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE + * + * It is now used for feature status advertisement by the kernel. + * See: enum rseq_cs_flags_bit for further information. */ __u32 flags; diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index 3da028500f76..d656cc2a0b9b 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -43,6 +43,7 @@ static void io_eventfd_do_signal(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + atomic_andnot(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops); eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); io_eventfd_put(ev_fd); } diff --git a/io_uring/napi.c b/io_uring/napi.c index 8d68366a4b90..bfc771445912 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -38,7 +38,8 @@ static inline ktime_t net_to_ktime(unsigned long t) return ns_to_ktime(t << 10); } -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode) { struct hlist_head *hash_list; struct io_napi_entry *e; @@ -69,6 +70,11 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) * kfree() */ spin_lock(&ctx->napi_lock); + if (unlikely(READ_ONCE(ctx->napi_track_mode) != mode)) { + spin_unlock(&ctx->napi_lock); + kfree(e); + return -EINVAL; + } if (unlikely(io_napi_hash_find(hash_list, napi_id))) { spin_unlock(&ctx->napi_lock); kfree(e); @@ -196,9 +202,14 @@ __io_napi_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { - if (READ_ONCE(ctx->napi_track_mode) == IO_URING_NAPI_TRACKING_STATIC) + switch (READ_ONCE(ctx->napi_track_mode)) { + case IO_URING_NAPI_TRACKING_STATIC: return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); - return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + case IO_URING_NAPI_TRACKING_DYNAMIC: + return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + default: + return false; + } } static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, @@ -273,13 +284,13 @@ static int io_napi_register_napi(struct io_ring_ctx *ctx, default: return -EINVAL; } - /* clean the napi list for new settings */ + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); io_napi_free(ctx); - WRITE_ONCE(ctx->napi_track_mode, napi->op_param); /* cap NAPI at 10 msec of spin time */ napi->busy_poll_to = min(10000, napi->busy_poll_to); WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll); + WRITE_ONCE(ctx->napi_track_mode, napi->op_param); return 0; } @@ -315,7 +326,8 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) case IO_URING_NAPI_STATIC_ADD_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; - return __io_napi_add_id(ctx, napi.op_param); + return __io_napi_add_id(ctx, napi.op_param, + IO_URING_NAPI_TRACKING_STATIC); case IO_URING_NAPI_STATIC_DEL_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; @@ -343,9 +355,10 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); WRITE_ONCE(ctx->napi_busy_poll_dt, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); - WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); + io_napi_free(ctx); return 0; } diff --git a/io_uring/napi.h b/io_uring/napi.h index fa742f42e09b..e0aecccc5065 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -15,7 +15,8 @@ void io_napi_free(struct io_ring_ctx *ctx); int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id); +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode); void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq); int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx); @@ -43,13 +44,14 @@ static inline void io_napi_add(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct socket *sock; + unsigned int mode = IO_URING_NAPI_TRACKING_DYNAMIC; - if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC) + if (READ_ONCE(ctx->napi_track_mode) != mode) return; sock = sock_from_file(req->file); if (sock && sock->sk) - __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id)); + __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id), mode); } #else diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 4cfdfc519770..e2595cae2b07 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -3,6 +3,7 @@ #include #include #include +#include #include @@ -35,6 +36,22 @@ struct io_timeout_rem { bool ltimeout; }; +static clockid_t io_flags_to_clock(unsigned flags) +{ + switch (flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) { struct timespec64 ts; @@ -43,7 +60,7 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) *time = ns_to_ktime(arg); if (*time < 0) return -EINVAL; - return 0; + goto out; } if (get_timespec64(&ts, u64_to_user_ptr(arg))) @@ -51,6 +68,9 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) if (ts.tv_sec < 0 || ts.tv_nsec < 0) return -EINVAL; *time = timespec64_to_ktime(ts); +out: + if (flags & IORING_TIMEOUT_ABS) + *time = timens_ktime_to_host(io_flags_to_clock(flags), *time); return 0; } @@ -399,18 +419,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) static clockid_t io_timeout_get_clock(struct io_timeout_data *data) { - switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { - case IORING_TIMEOUT_BOOTTIME: - return CLOCK_BOOTTIME; - case IORING_TIMEOUT_REALTIME: - return CLOCK_REALTIME; - default: - /* can't happen, vetted at prep time */ - WARN_ON_ONCE(1); - fallthrough; - case 0: - return CLOCK_MONOTONIC; - } + return io_flags_to_clock(data->flags); } static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, diff --git a/io_uring/wait.c b/io_uring/wait.c index 91df86ce0d18..ec01e78a216d 100644 --- a/io_uring/wait.c +++ b/io_uring/wait.c @@ -5,6 +5,7 @@ #include #include #include +#include #include @@ -229,7 +230,10 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, if (ext_arg->ts_set) { iowq.timeout = timespec64_to_ktime(ext_arg->ts); - if (!(flags & IORING_ENTER_ABS_TIMER)) + if (flags & IORING_ENTER_ABS_TIMER) + iowq.timeout = timens_ktime_to_host(ctx->clockid, + iowq.timeout); + else iowq.timeout = ktime_add(iowq.timeout, start_time); } diff --git a/kernel/audit.c b/kernel/audit.c index e1d489bc2dff..34dc7cb246ff 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1468,6 +1468,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); @@ -1480,6 +1482,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, size_t msglen = data_len; char *old, *new; + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ab54fccba215..abdf8da3be93 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2786,7 +2786,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; - context->capset.cap.inheritable = new->cap_effective; + context->capset.cap.inheritable = new->cap_inheritable; context->capset.cap.permitted = new->cap_permitted; context->capset.cap.ambient = new->cap_ambient; context->type = AUDIT_CAPSET; diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 802656c6fd3c..49a8f7b1beef 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -511,7 +511,7 @@ static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 { struct bpf_arena *arena = container_of(map, struct bpf_arena, map); - if ((u64)off > arena->user_vm_end - arena->user_vm_start) + if ((u64)off >= arena->user_vm_end - arena->user_vm_start) return -ERANGE; *imm = (unsigned long)arena->user_vm_start; return 0; diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c index 332e6e003f27..58197d73b120 100644 --- a/kernel/bpf/liveness.c +++ b/kernel/bpf/liveness.c @@ -1914,26 +1914,15 @@ int bpf_compute_subprog_arg_access(struct bpf_verifier_env *env) return -ENOMEM; } - instance = call_instance(env, NULL, 0, 0); - if (IS_ERR(instance)) { - err = PTR_ERR(instance); - goto out; - } - err = analyze_subprog(env, NULL, info, instance, callsites); - if (err) - goto out; - /* - * Subprogs and callbacks that don't receive FP-derived arguments - * cannot access ancestor stack frames, so they were skipped during - * the recursive walk above. Async callbacks (timer, workqueue) are - * also not reachable from the main program's call graph. Analyze - * all unvisited subprogs as independent roots at depth 0. + * Analyze every subprog in reverse topological order (callers + * before callees) so that each subprog is analyzed before its + * callees, allowing the recursive walk inside analyze_subprog() + * to naturally reach callees that receive FP-derived args. * - * Use reverse topological order (callers before callees) so that - * each subprog is analyzed before its callees, allowing the - * recursive walk inside analyze_subprog() to naturally - * reach nested callees that also lack FP-derived args. + * Subprogs and callbacks that don't receive FP-derived arguments + * cannot access ancestor stack frames are analyzed independently. + * Async callbacks (timer, workqueue) are handled the same way. */ for (k = env->subprog_cnt - 1; k >= 0; k--) { int sub = env->subprog_topo_order[k]; diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index bb4e692bea30..f7aaf01f7cd5 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -167,6 +167,7 @@ struct cpuset { */ int nr_deadline_tasks; int nr_migrate_dl_tasks; + /* DL bandwidth that needs destination reservation for this attach. */ u64 sum_migrate_dl_bw; /* * CPU used for temporary DL bandwidth allocation during attach; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e3a081a07c6d..5c33ab20cc20 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1718,7 +1718,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, */ if (is_partition_valid(parent)) adding = cpumask_and(tmp->addmask, - xcpus, parent->effective_xcpus); + cs->effective_xcpus, + parent->effective_xcpus); if (old_prs > 0) new_prs = -old_prs; @@ -2993,7 +2994,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) struct cpuset *cs, *oldcs; struct task_struct *task; bool setsched_check; - int ret; + int cpu, ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); @@ -3038,39 +3039,42 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) } if (dl_task(task)) { + /* + * Count all migrating DL tasks for cpuset task accounting. + * Only tasks that need a root-domain bandwidth move + * contribute to sum_migrate_dl_bw. + */ cs->nr_migrate_dl_tasks++; - cs->sum_migrate_dl_bw += task->dl.dl_bw; + if (dl_task_needs_bw_move(task, cs->effective_cpus)) + cs->sum_migrate_dl_bw += task->dl.dl_bw; } } - if (!cs->nr_migrate_dl_tasks) + if (!cs->sum_migrate_dl_bw) goto out_success; - if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) { - reset_migrate_dl_data(cs); - ret = -EINVAL; - goto out_unlock; - } - - ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); - if (ret) { - reset_migrate_dl_data(cs); - goto out_unlock; - } - - cs->dl_bw_cpu = cpu; + cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + if (unlikely(cpu >= nr_cpu_ids)) { + ret = -EINVAL; + goto out_unlock; } + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) + goto out_unlock; + + cs->dl_bw_cpu = cpu; + out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; + out_unlock: + if (ret) + reset_migrate_dl_data(cs); mutex_unlock(&cpuset_mutex); return ret; } @@ -4176,11 +4180,11 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. - * Otherwise, no. + * If the current task is PF_EXITING, yes. Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset - * unless the task has been OOM killed. + * unless the task has been OOM killed or is exiting. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * @@ -4194,7 +4198,9 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless - * in interrupt, of course). + * in interrupt, of course). The PF_EXITING check must therefore + * come before the __GFP_HARDWALL check, otherwise a dying task + * would be blocked on the fast path. * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() @@ -4204,6 +4210,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok + * PF_EXITING - any node ok (let dying task exit quickly) * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ @@ -4223,11 +4230,10 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask) */ if (unlikely(tsk_is_oom_victim(current))) return true; - if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ - return false; - if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; + if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ + return false; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index 1ab1fb47f271..4753a67d0f0f 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -602,6 +602,7 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = NULL; continue; } + pool = ERR_PTR(-ENOMEM); } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6d1f8bad7e1c..7935d5663944 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7006,6 +7006,7 @@ static void perf_mmap_open(struct vm_area_struct *vma) } static void perf_pmu_output_stop(struct perf_event *event); +static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb); /* * A buffer can be mmap()ed multiple times; either directly through the same @@ -7021,8 +7022,6 @@ static void perf_mmap_close(struct vm_area_struct *vma) mapped_f unmapped = get_mapped(event, event_unmapped); struct perf_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; - int mmap_locked = rb->mmap_locked; - unsigned long size = perf_data_size(rb); bool detach_rest = false; /* FIXIES vs perf_pmu_unregister() */ @@ -7117,11 +7116,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) * Aside from that, this buffer is 'fully' detached and unmapped, * undo the VM accounting. */ - - atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked, - &mmap_user->locked_vm); - atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm); - free_uid(mmap_user); + perf_mmap_unaccount(vma, rb); out_put: ring_buffer_put(rb); /* could be last */ @@ -7261,6 +7256,15 @@ static void perf_mmap_account(struct vm_area_struct *vma, long user_extra, long atomic64_add(extra, &vma->vm_mm->pinned_vm); } +static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb) +{ + struct user_struct *user = rb->mmap_user; + + atomic_long_sub((perf_data_size(rb) >> PAGE_SHIFT) + 1 - rb->mmap_locked, + &user->locked_vm); + atomic64_sub(rb->mmap_locked, &vma->vm_mm->pinned_vm); +} + static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, unsigned long nr_pages) { @@ -7323,8 +7327,6 @@ static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, if (!rb) return -ENOMEM; - refcount_set(&rb->mmap_count, 1); - rb->mmap_user = get_current_user(); rb->mmap_locked = extra; ring_buffer_attach(event, rb); @@ -7474,16 +7476,54 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) mapped(event, vma->vm_mm); /* - * Try to map it into the page table. On fail, invoke - * perf_mmap_close() to undo the above, as the callsite expects - * full cleanup in this case and therefore does not invoke - * vmops::close(). + * Try to map it into the page table. On fail undo the above, + * as the callsite expects full cleanup in this case and + * therefore does not invoke vmops::close(). */ ret = map_range(event->rb, vma); - if (ret) - perf_mmap_close(vma); + if (likely(!ret)) + return 0; + + /* Error path */ + + /* + * If this is the first mmap(), then event->mmap_count should + * be stable at 1. It is only modified by: + * perf_mmap_{open,close}() and perf_mmap(). + * + * The former are not possible because this mmap() hasn't been + * successful yet, and the latter is serialized by + * event->mmap_mutex which we still hold (note that mmap_lock + * is not strictly sufficient here, because the event fd can + * be passed to another process through trivial means like + * fork(), leading to concurrent mmap() from different mm). + * + * Make sure to remove event->rb before releasing + * event->mmap_mutex, such that any concurrent mmap() will not + * attempt use this failed buffer. + */ + if (refcount_read(&event->mmap_count) == 1) { + /* + * Minimal perf_mmap_close(); there can't be AUX or + * other events on account of this being the first. + */ + mapped = get_mapped(event, event_unmapped); + if (mapped) + mapped(event, vma->vm_mm); + perf_mmap_unaccount(vma, event->rb); + ring_buffer_attach(event, NULL); /* drops last rb->refcount */ + refcount_set(&event->mmap_count, 0); + return ret; + } + + /* + * Otherwise this is an already existing buffer, and there is + * no race vs first exposure, so fall-through and call + * perf_mmap_close(). + */ } + perf_mmap_close(vma); return ret; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index d9cc57083091..c03c4f2eea57 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -67,6 +67,7 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head) struct perf_buffer *rb; rb = container_of(rcu_head, struct perf_buffer, rcu_head); + free_uid(rb->mmap_user); rb_free(rb); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 3e7de2661417..9fe92161715e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -340,6 +340,8 @@ ring_buffer_init(struct perf_buffer *rb, long watermark, int flags) rb->paused = 1; mutex_init(&rb->aux_mutex); + rb->mmap_user = get_current_user(); + refcount_set(&rb->mmap_count, 1); } void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags) diff --git a/kernel/exit.c b/kernel/exit.c index 25e9cb6de7e7..f50d73c272d6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -571,6 +571,7 @@ static void exit_mm(void) */ smp_mb__after_spinlock(); local_irq_disable(); + current->user_dumpable = (get_dumpable(mm) == SUID_DUMP_USER); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); @@ -1073,6 +1074,7 @@ void __noreturn make_task_dead(int signr) futex_exit_recursive(tsk); tsk->exit_state = EXIT_DEAD; refcount_inc(&tsk->rcu_users); + preempt_disable(); do_task_dead(); } diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 18509d8082ea..2592f7ca16e2 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -1707,7 +1707,7 @@ int kho_fill_kimage(struct kimage *image) int err = 0; struct kexec_buf scratch; - if (!kho_enable) + if (!kho_enable || image->type == KEXEC_TYPE_CRASH) return 0; image->kho.fdt = virt_to_phys(kho_out.fdt); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 68c17daef8d4..130043bfc209 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -272,11 +272,24 @@ static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) return ns_capable(ns, CAP_SYS_PTRACE); } +static bool task_still_dumpable(struct task_struct *task, unsigned int mode) +{ + struct mm_struct *mm = task->mm; + if (mm) { + if (get_dumpable(mm) == SUID_DUMP_USER) + return true; + return ptrace_has_cap(mm->user_ns, mode); + } + + if (task->user_dumpable) + return true; + return ptrace_has_cap(&init_user_ns, mode); +} + /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; - struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; @@ -337,11 +350,8 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) * Pairs with a write barrier in commit_creds(). */ smp_rmb(); - mm = task->mm; - if (mm && - ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) - return -EPERM; + if (!task_still_dumpable(task, mode)) + return -EPERM; return security_ptrace_access_check(task, mode); } diff --git a/kernel/rseq.c b/kernel/rseq.c index 38d3ef540760..e75e3a5e312c 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -236,11 +236,6 @@ static int __init rseq_debugfs_init(void) } __initcall(rseq_debugfs_init); -static bool rseq_set_ids(struct task_struct *t, struct rseq_ids *ids, u32 node_id) -{ - return rseq_set_ids_get_csaddr(t, ids, node_id, NULL); -} - static bool rseq_handle_cs(struct task_struct *t, struct pt_regs *regs) { struct rseq __user *urseq = t->rseq.usrptr; @@ -258,14 +253,16 @@ static bool rseq_handle_cs(struct task_struct *t, struct pt_regs *regs) static void rseq_slowpath_update_usr(struct pt_regs *regs) { /* - * Preserve rseq state and user_irq state. The generic entry code - * clears user_irq on the way out, the non-generic entry - * architectures are not having user_irq. + * Preserve has_rseq and user_irq state. The generic entry code clears + * user_irq on the way out, the non-generic entry architectures are not + * setting user_irq. */ - const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, }; + const struct rseq_event evt_mask = { + .has_rseq = RSEQ_HAS_RSEQ_VERSION_MASK, + .user_irq = true, + }; struct task_struct *t = current; struct rseq_ids ids; - u32 node_id; bool event; if (unlikely(t->flags & PF_EXITING)) @@ -301,9 +298,9 @@ static void rseq_slowpath_update_usr(struct pt_regs *regs) if (!event) return; - node_id = cpu_to_node(ids.cpu_id); + ids.node_id = cpu_to_node(ids.cpu_id); - if (unlikely(!rseq_update_usr(t, regs, &ids, node_id))) { + if (unlikely(!rseq_update_usr(t, regs, &ids))) { /* * Clear the errors just in case this might survive magically, but * leave the rest intact. @@ -335,8 +332,9 @@ void __rseq_handle_slowpath(struct pt_regs *regs) void __rseq_signal_deliver(int sig, struct pt_regs *regs) { rseq_stat_inc(rseq_stats.signal); + /* - * Don't update IDs, they are handled on exit to user if + * Don't update IDs yet, they are handled on exit to user if * necessary. The important thing is to abort a critical section of * the interrupted context as after this point the instruction * pointer in @regs points to the signal handler. @@ -349,6 +347,13 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs) current->rseq.event.error = 0; force_sigsegv(sig); } + + /* + * In legacy mode, force the update of IDs before returning to user + * space to stay compatible. + */ + if (!rseq_v2(current)) + rseq_force_update(); } /* @@ -384,19 +389,22 @@ void rseq_syscall(struct pt_regs *regs) static bool rseq_reset_ids(void) { - struct rseq_ids ids = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, - .mm_cid = 0, - }; + struct rseq __user *rseq = current->rseq.usrptr; /* * If this fails, terminate it because this leaves the kernel in * stupid state as exit to user space will try to fixup the ids * again. */ - if (rseq_set_ids(current, &ids, 0)) - return true; + scoped_user_rw_access(rseq, efault) { + unsafe_put_user(0, &rseq->cpu_id_start, efault); + unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); + unsafe_put_user(0, &rseq->node_id, efault); + unsafe_put_user(0, &rseq->mm_cid, efault); + } + return true; +efault: force_sig(SIGSEGV); return false; } @@ -404,70 +412,29 @@ static bool rseq_reset_ids(void) /* The original rseq structure size (including padding) is 32 bytes. */ #define ORIG_RSEQ_SIZE 32 -/* - * sys_rseq - setup restartable sequences for caller thread. - */ -SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +static long rseq_register(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) { u32 rseqfl = 0; + u8 version = 1; - if (flags & RSEQ_FLAG_UNREGISTER) { - if (flags & ~RSEQ_FLAG_UNREGISTER) - return -EINVAL; - /* Unregister rseq for current thread. */ - if (current->rseq.usrptr != rseq || !current->rseq.usrptr) - return -EINVAL; - if (rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - if (!rseq_reset_ids()) - return -EFAULT; - rseq_reset(current); - return 0; - } - - if (unlikely(flags & ~(RSEQ_FLAG_SLICE_EXT_DEFAULT_ON))) - return -EINVAL; - - if (current->rseq.usrptr) { - /* - * If rseq is already registered, check whether - * the provided address differs from the prior - * one. - */ - if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - /* Already registered. */ - return -EBUSY; - } - - /* - * If there was no rseq previously registered, ensure the provided rseq - * is properly aligned, as communcated to user-space through the ELF - * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq - * size, the required alignment is the original struct rseq alignment. - * - * The rseq_len is required to be greater or equal to the original rseq - * size. In order to be valid, rseq_len is either the original rseq size, - * or large enough to contain all supported fields, as communicated to - * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. - */ - if (rseq_len < ORIG_RSEQ_SIZE || - (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || - rseq_len < offsetof(struct rseq, end)))) - return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; - if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { - rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; - if (rseq_slice_extension_enabled() && - (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON)) - rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; + /* + * Architectures, which use the generic IRQ entry code (at least) enable + * registrations with a size greater than the original v1 fixed sized + * @rseq_len, which has been validated already to utilize the optimized + * v2 ABI mode which also enables extended RSEQ features beyond MMCID. + */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_len > ORIG_RSEQ_SIZE) + version = 2; + + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && version > 1) { + if (rseq_slice_extension_enabled()) { + rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; + if (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) + rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; + } } scoped_user_write_access(rseq, efault) { @@ -485,7 +452,15 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); unsafe_put_user(0U, &rseq->node_id, efault); unsafe_put_user(0U, &rseq->mm_cid, efault); - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + + /* + * All fields past mm_cid are only valid for non-legacy v2 + * registrations. + */ + if (version > 1) { + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + } } /* @@ -501,11 +476,10 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 #endif /* - * If rseq was previously inactive, and has just been - * registered, ensure the cpu_id_start and cpu_id fields - * are updated before returning to user-space. + * Ensure the cpu_id_start and cpu_id fields are updated before + * returning to user-space. */ - current->rseq.event.has_rseq = true; + current->rseq.event.has_rseq = version; rseq_force_update(); return 0; @@ -513,6 +487,80 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 return -EFAULT; } +static long rseq_unregister(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) +{ + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; + if (current->rseq.usrptr != rseq || !current->rseq.usrptr) + return -EINVAL; + if (rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + if (!rseq_reset_ids()) + return -EFAULT; + rseq_reset(current); + return 0; +} + +static long rseq_reregister(struct rseq __user * rseq, u32 rseq_len, u32 sig) +{ + /* + * If rseq is already registered, check whether the provided address + * differs from the prior one. + */ + if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + /* Already registered. */ + return -EBUSY; +} + +static bool rseq_length_valid(struct rseq __user *rseq, unsigned int rseq_len) +{ + /* + * Ensure the provided rseq is properly aligned, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_ALIGN. If + * rseq_len is the original rseq size, the required alignment is the + * original struct rseq alignment. + * + * In order to be valid, rseq_len is either the original rseq size, or + * large enough to contain all supported fields, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. + */ + if (rseq_len < ORIG_RSEQ_SIZE) + return false; + + if (rseq_len == ORIG_RSEQ_SIZE) + return IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE); + + return IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) && + rseq_len >= offsetof(struct rseq, end); +} + +#define RSEQ_FLAGS_SUPPORTED (RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) + +/* + * sys_rseq - Register or unregister restartable sequences for the caller thread. + */ +SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +{ + if (flags & RSEQ_FLAG_UNREGISTER) + return rseq_unregister(rseq, rseq_len, flags, sig); + + if (unlikely(flags & ~RSEQ_FLAGS_SUPPORTED)) + return -EINVAL; + + if (current->rseq.usrptr) + return rseq_reregister(rseq, rseq_len, sig); + + if (!rseq_length_valid(rseq, rseq_len)) + return -EINVAL; + + return rseq_register(rseq, rseq_len, flags, sig); +} + #ifdef CONFIG_RSEQ_SLICE_EXTENSION struct slice_timer { struct hrtimer timer; @@ -713,6 +761,8 @@ int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3) return -ENOTSUPP; if (!current->rseq.usrptr) return -ENXIO; + if (!rseq_v2(current)) + return -ENOTSUPP; /* No change? */ if (enable == !!current->rseq.slice.state.enabled) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index edca7849b165..7db4c87df83b 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3107,20 +3107,18 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) static void set_cpus_allowed_dl(struct task_struct *p, struct affinity_context *ctx) { - struct root_domain *src_rd; struct rq *rq; WARN_ON_ONCE(!dl_task(p)); rq = task_rq(p); - src_rd = rq->rd; /* * Migrating a SCHED_DEADLINE task between exclusive * cpusets (different root_domains) entails a bandwidth * update. We already made space for us in the destination * domain (see cpuset_can_attach()). */ - if (!cpumask_intersects(src_rd->span, ctx->new_mask)) { + if (dl_task_needs_bw_move(p, ctx->new_mask)) { struct dl_bw *src_dl_b; src_dl_b = dl_bw_of(cpu_of(rq)); @@ -3137,6 +3135,15 @@ static void set_cpus_allowed_dl(struct task_struct *p, set_cpus_allowed_common(p, ctx); } +bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask) +{ + if (!dl_task(p)) + return false; + + return !cpumask_intersects(task_rq(p)->rd->span, new_mask); +} + /* Assumes rq->lock is held */ static void rq_online_dl(struct rq *rq) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 38d90baf78cf..d3ce708991c3 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -297,7 +297,6 @@ static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) #else /* CONFIG_EXT_SUB_SCHED */ static struct scx_sched *scx_parent(struct scx_sched *sch) { return NULL; } static struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos, struct scx_sched *root) { return pos ? NULL : root; } -static struct scx_sched *scx_find_sub_sched(u64 cgroup_id) { return NULL; } static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) {} #endif /* CONFIG_EXT_SUB_SCHED */ @@ -712,6 +711,51 @@ struct bpf_iter_scx_dsq { } __attribute__((aligned(8))); +static u32 scx_get_task_state(const struct task_struct *p) +{ + return p->scx.flags & SCX_TASK_STATE_MASK; +} + +static void scx_set_task_state(struct task_struct *p, u32 state) +{ + u32 prev_state = scx_get_task_state(p); + bool warn = false; + + switch (state) { + case SCX_TASK_NONE: + warn = prev_state == SCX_TASK_DEAD; + break; + case SCX_TASK_INIT_BEGIN: + warn = prev_state != SCX_TASK_NONE; + break; + case SCX_TASK_INIT: + warn = prev_state != SCX_TASK_INIT_BEGIN; + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; + break; + case SCX_TASK_READY: + warn = !(prev_state == SCX_TASK_INIT || + prev_state == SCX_TASK_ENABLED); + break; + case SCX_TASK_ENABLED: + warn = prev_state != SCX_TASK_READY; + break; + case SCX_TASK_DEAD: + warn = !(prev_state == SCX_TASK_NONE || + prev_state == SCX_TASK_INIT_BEGIN); + break; + default: + WARN_ONCE(1, "sched_ext: Invalid task state %d -> %d for %s[%d]", + prev_state, state, p->comm, p->pid); + return; + } + + WARN_ONCE(warn, "sched_ext: Invalid task state transition 0x%x -> 0x%x for %s[%d]", + prev_state, state, p->comm, p->pid); + + p->scx.flags &= ~SCX_TASK_STATE_MASK; + p->scx.flags |= state; +} + /* * SCX task iterator. */ @@ -937,11 +981,11 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) /* * cgroup_task_dead() removes the dead tasks from cset->tasks * after sched_ext_dead() and cgroup iteration may see tasks - * which already finished sched_ext_dead(). %SCX_TASK_OFF_TASKS - * is set by sched_ext_dead() under @p's rq lock. Test it to + * which already finished sched_ext_dead(). %SCX_TASK_DEAD is + * set by sched_ext_dead() under @p's rq lock. Test it to * avoid visiting tasks which are already dead from SCX POV. */ - if (p->scx.flags & SCX_TASK_OFF_TASKS) { + if (scx_get_task_state(p) == SCX_TASK_DEAD) { __scx_task_iter_rq_unlock(iter); continue; } @@ -3500,41 +3544,6 @@ static struct cgroup *tg_cgrp(struct task_group *tg) #endif /* CONFIG_EXT_GROUP_SCHED */ -static u32 scx_get_task_state(const struct task_struct *p) -{ - return p->scx.flags & SCX_TASK_STATE_MASK; -} - -static void scx_set_task_state(struct task_struct *p, u32 state) -{ - u32 prev_state = scx_get_task_state(p); - bool warn = false; - - switch (state) { - case SCX_TASK_NONE: - break; - case SCX_TASK_INIT: - warn = prev_state != SCX_TASK_NONE; - break; - case SCX_TASK_READY: - warn = prev_state == SCX_TASK_NONE; - break; - case SCX_TASK_ENABLED: - warn = prev_state != SCX_TASK_READY; - break; - default: - WARN_ONCE(1, "sched_ext: Invalid task state %d -> %d for %s[%d]", - prev_state, state, p->comm, p->pid); - return; - } - - WARN_ONCE(warn, "sched_ext: Invalid task state transition 0x%x -> 0x%x for %s[%d]", - prev_state, state, p->comm, p->pid); - - p->scx.flags &= ~SCX_TASK_STATE_MASK; - p->scx.flags |= state; -} - static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fork) { int ret; @@ -3586,22 +3595,6 @@ static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fo return 0; } -static int scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fork) -{ - int ret; - - ret = __scx_init_task(sch, p, fork); - if (!ret) { - /* - * While @p's rq is not locked. @p is not visible to the rest of - * SCX yet and it's safe to update the flags and state. - */ - p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; - scx_set_task_state(p, SCX_TASK_INIT); - } - return ret; -} - static void __scx_enable_task(struct scx_sched *sch, struct task_struct *p) { struct rq *rq = task_rq(p); @@ -3716,7 +3709,8 @@ static void scx_disable_and_exit_task(struct scx_sched *sch, * If set, @p exited between __scx_init_task() and scx_enable_task() in * scx_sub_enable() and is initialized for both the associated sched and * its parent. Exit for the child too - scx_enable_task() never ran for - * it, so undo only init_task. + * it, so undo only init_task. The flag is only set on the sub-enable + * path, so it's always clear when @p arrives here in %SCX_TASK_NONE. */ if (p->scx.flags & SCX_TASK_SUB_INIT) { if (!WARN_ON_ONCE(!scx_enabling_sub_sched)) @@ -3764,10 +3758,14 @@ int scx_fork(struct task_struct *p, struct kernel_clone_args *kargs) #else struct scx_sched *sch = scx_root; #endif - ret = scx_init_task(sch, p, true); - if (!ret) - scx_set_task_sched(p, sch); - return ret; + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); + ret = __scx_init_task(sch, p, true); + if (unlikely(ret)) { + scx_set_task_state(p, SCX_TASK_NONE); + return ret; + } + scx_set_task_state(p, SCX_TASK_INIT); + scx_set_task_sched(p, sch); } return 0; @@ -3862,18 +3860,23 @@ void sched_ext_dead(struct task_struct *p) * @p is off scx_tasks and wholly ours. scx_root_enable()'s READY -> * ENABLED transitions can't race us. Disable ops for @p. * - * %SCX_TASK_OFF_TASKS synchronizes against cgroup task iteration - see + * %SCX_TASK_DEAD synchronizes against cgroup task iteration - see * scx_task_iter_next_locked(). NONE tasks need no marking: cgroup * iteration is only used from sub-sched paths, which require root * enabled. Root enable transitions every live task to at least READY. + * + * %INIT_BEGIN means ops.init_task() is running for @p. Don't call + * into ops; transition to %DEAD so the post-init recheck unwinds + * via scx_sub_init_cancel_task(). */ if (scx_get_task_state(p) != SCX_TASK_NONE) { struct rq_flags rf; struct rq *rq; rq = task_rq_lock(p, &rf); - scx_disable_and_exit_task(scx_task_sched(p), p); - p->scx.flags |= SCX_TASK_OFF_TASKS; + if (scx_get_task_state(p) != SCX_TASK_INIT_BEGIN) + scx_disable_and_exit_task(scx_task_sched(p), p); + scx_set_task_state(p, SCX_TASK_DEAD); task_rq_unlock(rq, p, &rf); } } @@ -3919,6 +3922,16 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p) if (task_dead_and_done(p)) return; + /* + * %NONE means SCX is no longer tracking @p at the task level (e.g. + * scx_fail_parent() handed @p back to the parent at NONE pending the + * parent's own teardown). There is nothing to disable; calling + * scx_disable_task() would WARN on the non-%ENABLED state and trigger a + * NONE -> READY validation failure. + */ + if (scx_get_task_state(p) == SCX_TASK_NONE) + return; + scx_disable_task(scx_task_sched(p), p); } @@ -4808,6 +4821,8 @@ static void scx_sched_free_rcu_work(struct work_struct *work) kfree(sch->cgrp_path); if (sch_cgroup(sch)) cgroup_put(sch_cgroup(sch)); + if (sch->sub_kset) + kobject_put(&sch->sub_kset->kobj); #endif /* CONFIG_EXT_SUB_SCHED */ for_each_possible_cpu(cpu) { @@ -5585,10 +5600,12 @@ static void refresh_watchdog(void) static s32 scx_link_sched(struct scx_sched *sch) { + const char *err_msg = ""; + s32 ret = 0; + scoped_guard(raw_spinlock_irq, &scx_sched_lock) { #ifdef CONFIG_EXT_SUB_SCHED struct scx_sched *parent = scx_parent(sch); - s32 ret; if (parent) { /* @@ -5598,15 +5615,16 @@ static s32 scx_link_sched(struct scx_sched *sch) * parent can shoot us down. */ if (atomic_read(&parent->exit_kind) != SCX_EXIT_NONE) { - scx_error(sch, "parent disabled"); - return -ENOENT; + err_msg = "parent disabled"; + ret = -ENOENT; + break; } ret = rhashtable_lookup_insert_fast(&scx_sched_hash, &sch->hash_node, scx_sched_hash_params); if (ret) { - scx_error(sch, "failed to insert into scx_sched_hash (%d)", ret); - return ret; + err_msg = "failed to insert into scx_sched_hash"; + break; } list_add_tail(&sch->sibling, &parent->children); @@ -5616,6 +5634,15 @@ static s32 scx_link_sched(struct scx_sched *sch) list_add_tail_rcu(&sch->all, &scx_sched_all); } + /* + * scx_error() takes scx_sched_lock via scx_claim_exit(), so it must run after + * the guard above is released. + */ + if (ret) { + scx_error(sch, "%s (%d)", err_msg, ret); + return ret; + } + refresh_watchdog(); return 0; } @@ -5685,7 +5712,7 @@ static void scx_fail_parent(struct scx_sched *sch, scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) { scx_disable_and_exit_task(sch, p); - rcu_assign_pointer(p->scx.sched, parent); + scx_set_task_sched(p, parent); } } scx_task_iter_stop(&sti); @@ -5763,6 +5790,21 @@ static void scx_sub_disable(struct scx_sched *sch) } rq = task_rq_lock(p, &rf); + + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() raced us between __scx_init_task() + * and this rq lock and ran exit_task() on @sch (the + * sched @p was on at that point), not on $parent. + * $parent's just-completed init is owed an exit_task() + * and we issue it here. + */ + scx_sub_init_cancel_task(parent, p); + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + continue; + } + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) { /* * $p is initialized for $parent and still attached to @@ -5771,13 +5813,14 @@ static void scx_sub_disable(struct scx_sched *sch) * $p having already been initialized, and then enable. */ scx_disable_and_exit_task(sch, p); + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_set_task_state(p, SCX_TASK_INIT); - rcu_assign_pointer(p->scx.sched, parent); + scx_set_task_sched(p, parent); scx_set_task_state(p, SCX_TASK_READY); scx_enable_task(parent, p); } - task_rq_unlock(rq, p, &rf); + task_rq_unlock(rq, p, &rf); put_task_struct(p); } scx_task_iter_stop(&sti); @@ -5820,7 +5863,7 @@ static void scx_sub_disable(struct scx_sched *sch) if (sch->ops.exit) SCX_CALL_OP(sch, exit, NULL, sch->exit_info); if (sch->sub_kset) - kset_unregister(sch->sub_kset); + kobject_del(&sch->sub_kset->kobj); kobject_del(&sch->kobj); } #else /* CONFIG_EXT_SUB_SCHED */ @@ -5954,7 +5997,7 @@ static void scx_root_disable(struct scx_sched *sch) */ #ifdef CONFIG_EXT_SUB_SCHED if (sch->sub_kset) - kset_unregister(sch->sub_kset); + kobject_del(&sch->sub_kset->kobj); #endif kobject_del(&sch->kobj); @@ -6578,7 +6621,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, sch->slice_dfl = SCX_SLICE_DFL; atomic_set(&sch->exit_kind, SCX_EXIT_NONE); - init_irq_work(&sch->disable_irq_work, scx_disable_irq_workfn); + sch->disable_irq_work = IRQ_WORK_INIT_HARD(scx_disable_irq_workfn); kthread_init_work(&sch->disable_work, scx_disable_workfn); timer_setup(&sch->bypass_lb_timer, scx_bypass_lb_timerfn, 0); @@ -6594,6 +6637,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, rcu_assign_pointer(ops->priv, sch); sch->kobj.kset = scx_kset; + INIT_LIST_HEAD(&sch->all); #ifdef CONFIG_EXT_SUB_SCHED char *buf = kzalloc(PATH_MAX, GFP_KERNEL); @@ -6621,6 +6665,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); if (ret < 0) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(ret); } @@ -6628,6 +6673,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, if (ops->sub_attach) { sch->sub_kset = kset_create_and_add("sub", NULL, &sch->kobj); if (!sch->sub_kset) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(-ENOMEM); } @@ -6635,14 +6681,18 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, #else /* CONFIG_EXT_SUB_SCHED */ ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); if (ret < 0) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(ret); } #endif /* CONFIG_EXT_SUB_SCHED */ return sch; +#ifdef CONFIG_EXT_SUB_SCHED err_free_lb_resched: + RCU_INIT_POINTER(ops->priv, NULL); free_cpumask_var(sch->bypass_lb_resched_cpumask); +#endif err_free_lb_cpumask: free_cpumask_var(sch->bypass_lb_donee_cpumask); err_stop_helper: @@ -6752,6 +6802,19 @@ static void scx_root_enable_workfn(struct kthread_work *work) goto err_unlock; } + /* + * @ops->priv binds @ops to its scx_sched instance. It is set here by + * scx_alloc_and_add_sched() and cleared at the tail of bpf_scx_unreg(), + * which runs after scx_root_disable() has dropped scx_enable_mutex. If + * it's still non-NULL here, a previous attachment on @ops has not + * finished tearing down; proceeding would let the in-flight unreg's + * RCU_INIT_POINTER(NULL) clobber the @ops->priv we are about to assign. + */ + if (rcu_access_pointer(ops->priv)) { + ret = -EBUSY; + goto err_unlock; + } + ret = alloc_kick_syncs(); if (ret) goto err_unlock; @@ -6874,6 +6937,9 @@ static void scx_root_enable_workfn(struct kthread_work *work) scx_task_iter_start(&sti, NULL); while ((p = scx_task_iter_next_locked(&sti))) { + struct rq_flags rf; + struct rq *rq; + /* * @p may already be dead, have lost all its usages counts and * be waiting for RCU grace period before being freed. @p can't @@ -6882,20 +6948,47 @@ static void scx_root_enable_workfn(struct kthread_work *work) if (!tryget_task_struct(p)) continue; + /* + * Set %INIT_BEGIN under the iter's rq lock so that a concurrent + * sched_ext_dead() does not call ops.exit_task() on @p while + * ops.init_task() is running. If sched_ext_dead() runs before + * this store, it has already removed @p from scx_tasks and the + * iter won't visit @p; if it runs after, it observes + * %INIT_BEGIN and transitions to %DEAD without calling ops, + * leaving the post-init recheck below to unwind. + */ + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_task_iter_unlock(&sti); - ret = scx_init_task(sch, p, false); - if (ret) { - put_task_struct(p); + ret = __scx_init_task(sch, p, false); + + rq = task_rq_lock(p, &rf); + + if (unlikely(ret)) { + if (scx_get_task_state(p) != SCX_TASK_DEAD) + scx_set_task_state(p, SCX_TASK_NONE); + task_rq_unlock(rq, p, &rf); scx_task_iter_stop(&sti); scx_error(sch, "ops.init_task() failed (%d) for %s[%d]", ret, p->comm, p->pid); + put_task_struct(p); goto err_disable_unlock_all; } - scx_set_task_sched(p, sch); - scx_set_task_state(p, SCX_TASK_READY); + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() observed %INIT_BEGIN and set %DEAD. + * ops.exit_task() is owed to the sched __scx_init_task() + * ran against; call it now. + */ + scx_sub_init_cancel_task(sch, p); + } else { + scx_set_task_state(p, SCX_TASK_INIT); + scx_set_task_sched(p, sch); + scx_set_task_state(p, SCX_TASK_READY); + } + task_rq_unlock(rq, p, &rf); put_task_struct(p); } scx_task_iter_stop(&sti); @@ -7039,6 +7132,12 @@ static void scx_sub_enable_workfn(struct kthread_work *work) goto out_unlock; } + /* See scx_root_enable_workfn() for the @ops->priv check. */ + if (rcu_access_pointer(ops->priv)) { + ret = -EBUSY; + goto out_unlock; + } + cgrp = cgroup_get_from_id(ops->sub_cgroup_id); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); @@ -7165,6 +7264,21 @@ static void scx_sub_enable_workfn(struct kthread_work *work) goto abort; rq = task_rq_lock(p, &rf); + + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() raced us between __scx_init_task() + * and this rq lock and ran exit_task() on $parent (the + * sched @p was on at that point), not on @sch. @sch's + * just-completed init is owed an exit_task() and we + * issue it here. + */ + scx_sub_init_cancel_task(sch, p); + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + continue; + } + p->scx.flags |= SCX_TASK_SUB_INIT; task_rq_unlock(rq, p, &rf); @@ -7199,7 +7313,7 @@ static void scx_sub_enable_workfn(struct kthread_work *work) * $p is now only initialized for @sch and READY, which * is what we want. Assign it to @sch and enable. */ - rcu_assign_pointer(p->scx.sched, sch); + scx_set_task_sched(p, sch); scx_enable_task(sch, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; @@ -7301,8 +7415,7 @@ static s32 scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) static DEFINE_MUTEX(helper_mutex); struct scx_enable_cmd cmd; - if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), - cpu_possible_mask)) { + if (housekeeping_enabled(HK_TYPE_DOMAIN_BOOT)) { pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); return -EINVAL; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 728965851842..3ebec186f982 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -882,11 +882,11 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) * * lag_i >= 0 -> V >= v_i * - * \Sum (v_i - v)*w_i - * V = ------------------ + v + * \Sum (v_i - v0)*w_i + * V = ------------------- + v0 * \Sum w_i * - * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i) + * lag_i >= 0 -> \Sum (v_i - v0)*w_i >= (v_i - v0)*(\Sum w_i) * * Note: using 'avg_vruntime() > se->vruntime' is inaccurate due * to the loss in precision caused by the division. @@ -894,7 +894,7 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) { struct sched_entity *curr = cfs_rq->curr; - s64 avg = cfs_rq->sum_w_vruntime; + s64 key, avg = cfs_rq->sum_w_vruntime; long load = cfs_rq->sum_weight; if (curr && curr->on_rq) { @@ -904,7 +904,36 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) load += weight; } - return avg >= vruntime_op(vruntime, "-", cfs_rq->zero_vruntime) * load; + key = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime); + + /* + * The worst case term for @key includes 'NSEC_TICK * NICE_0_LOAD' + * and @load obviously includes NICE_0_LOAD. NSEC_TICK is around 24 + * bits, while NICE_0_LOAD is 20 on 64bit and 10 otherwise. + * + * This gives that on 64bit the product will be at least 64bit which + * overflows s64, while on 32bit it will only be 44bits and should fit + * comfortably. + */ +#ifdef CONFIG_64BIT +#ifdef CONFIG_ARCH_SUPPORTS_INT128 + /* This often results in simpler code than __builtin_mul_overflow(). */ + return avg >= (__int128)key * load; +#else + s64 rhs; + /* + * On overflow, the sign of key tells us the correct answer: a large + * positive key means vruntime >> V, so not eligible; a large negative + * key means vruntime << V, so eligible. + */ + if (check_mul_overflow(key, load, &rhs)) + return key <= 0; + + return avg >= rhs; +#endif +#else /* 32bit */ + return avg >= key * load; +#endif } int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -9145,9 +9174,10 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f /* * Because p is enqueued, nse being null can only mean that we - * dequeued a delayed task. + * dequeued a delayed task. If there are still entities queued in + * cfs, check if the next one will be p. */ - if (!nse) + if (!nse && cfs_rq->nr_queued) goto pick; if (sched_feat(RUN_TO_PARITY)) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 623445603725..226a6329f3e9 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -199,7 +199,16 @@ static void ipi_rseq(void *info) * is negligible. */ smp_mb(); - rseq_sched_switch_event(current); + /* + * Legacy mode requires that IDs are written and the critical section is + * evaluated. V2 optimized mode handles the critical section and IDs are + * only updated if they change as a consequence of preemption after + * return from this IPI. + */ + if (rseq_v2(current)) + rseq_sched_switch_event(current); + else + rseq_force_update(); } static void ipi_sync_rq_state(void *info) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 155eeaea4113..1d0d3a4058d5 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1860,19 +1860,37 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, * child to the new parents. So tmigr_active_up() activates the * new parents while walking up from the old root to the new. * - * * It is ensured that @start is active, as this setup path is - * executed in hotplug prepare callback. This is executed by an - * already connected and !idle CPU. Even if all other CPUs go idle, - * the CPU executing the setup will be responsible up to current top - * level group. And the next time it goes inactive, it will release - * the new childmask and parent to subsequent walkers through this - * @child. Therefore propagate active state unconditionally. + * * It is ensured that @start is active, (or on the way to be activated + * by another CPU that woke up before the current one) as this setup path + * is executed in hotplug prepare callback. This is executed by an already + * connected and !idle CPU in the hierarchy. + * + * * The below RmW atomic operation ensures that: + * + * 1) If the old root has been completely activated, the latest state is + * acquired (the below implicit acquire pairs with the implicit release + * from cmpxchg() in tmigr_active_up()). + * + * 2) If the old root is still on the way to be activated, the lagging behind + * CPU performing the activation will acquire the links up to the new root. + * (The below implicit release pairs with the implicit acquire from cmpxchg() + * in tmigr_active_up()). + * + * 3) Every subsequent CPU below the old root will acquire the new links while + * walking through the old root (The below implicit release pairs with the + * implicit acquire from cmpxchg() in either tmigr_active_up()) or + * tmigr_inactive_up(). */ - state.state = atomic_read(&start->migr_state); - WARN_ON_ONCE(!state.active); + state.state = atomic_fetch_or(0, &start->migr_state); WARN_ON_ONCE(!start->parent); - data.childmask = start->groupmask; - __walk_groups_from(tmigr_active_up, &data, start, start->parent); + /* + * If the state of the old root is inactive, another CPU is on its way to activate + * it and propagate to the new root. + */ + if (state.active) { + data.childmask = start->groupmask; + __walk_groups_from(tmigr_active_up, &data, start, start->parent); + } } /* Root update */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index af7079aa0f36..a02bd258677e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2384,7 +2384,8 @@ static void bpf_kprobe_multi_link_release(struct bpf_link *link) struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); - unregister_fprobe(&kmulti_link->fp); + /* Don't wait for RCU GP here. */ + unregister_fprobe_async(&kmulti_link->fp); kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt); } diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index cc49ebd2a773..f378613ad120 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -1093,14 +1093,15 @@ static int unregister_fprobe_nolock(struct fprobe *fp) } /** - * unregister_fprobe() - Unregister fprobe. + * unregister_fprobe_async() - Unregister fprobe without RCU GP wait * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will NOT wait until the fprobe is no longer used. * * Return 0 if @fp is unregistered successfully, -errno if not. */ -int unregister_fprobe(struct fprobe *fp) +int unregister_fprobe_async(struct fprobe *fp) { guard(mutex)(&fprobe_mutex); if (!fp || !fprobe_registered(fp)) @@ -1108,6 +1109,24 @@ int unregister_fprobe(struct fprobe *fp) return unregister_fprobe_nolock(fp); } + +/** + * unregister_fprobe() - Unregister fprobe with RCU GP wait + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will block until the fprobe is no longer used. + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + int ret = unregister_fprobe_async(fp); + + if (!ret) + synchronize_rcu(); + return ret; +} EXPORT_SYMBOL_GPL(unregister_fprobe); static int __init fprobe_initcall(void) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3d2e3b2ec528..33b721a9af02 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2296,6 +2296,18 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { + struct work_offq_data offqd; + + /* + * State on entry: PENDING is set, work is off-queue (no + * insert_work() has run). + * + * Returning without clearing PENDING would leave the work + * in a weird state (PENDING=1, PWQ=0, entry empty) + */ + work_offqd_unpack(&offqd, *work_data_bits(work)); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); return; } rcu_read_lock(); @@ -5642,7 +5654,9 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } - return ret; + if (ret) + goto enomem; + return 0; enomem: if (wq->cpu_pwq) { diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 498cc51e493d..94ff8e4089bf 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -16,8 +16,9 @@ menuconfig KUNIT if KUNIT config KUNIT_DEBUGFS - bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" if !KUNIT_ALL_TESTS - default KUNIT_ALL_TESTS + bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" + depends on DEBUG_FS + default y help Enable debugfs representation for kunit. Currently this consists of /sys/kernel/debug/kunit//results files for each diff --git a/lib/tests/test_kprobes.c b/lib/tests/test_kprobes.c index b7582010125c..06e729e4de05 100644 --- a/lib/tests/test_kprobes.c +++ b/lib/tests/test_kprobes.c @@ -12,6 +12,12 @@ #define div_factor 3 +#define KP_CLEAR(_kp) \ +do { \ + (_kp).addr = NULL; \ + (_kp).flags = 0; \ +} while (0) + static u32 rand1, preh_val, posth_val; static u32 (*target)(u32 value); static u32 (*recursed_target)(u32 value); @@ -125,10 +131,6 @@ static void test_kprobes(struct kunit *test) current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - kp.addr = NULL; - kp.flags = 0; - KUNIT_EXPECT_EQ(test, 0, register_kprobes(kps, 2)); preh_val = 0; posth_val = 0; @@ -226,9 +228,6 @@ static void test_kretprobes(struct kunit *test) struct kretprobe *rps[2] = {&rp, &rp2}; current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - rp.kp.addr = NULL; - rp.kp.flags = 0; KUNIT_EXPECT_EQ(test, 0, register_kretprobes(rps, 2)); krph_val = 0; @@ -290,8 +289,6 @@ static void test_stacktrace_on_kretprobe(struct kunit *test) unsigned long myretaddr = (unsigned long)__builtin_return_address(0); current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; /* * Run the stacktrace_driver() to record correct return address in @@ -352,8 +349,6 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) struct kretprobe *rps[2] = {&rp3, &rp4}; current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; //KUNIT_ASSERT_NE(test, myretaddr, stacktrace_driver()); @@ -367,6 +362,18 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) static int kprobes_test_init(struct kunit *test) { + KP_CLEAR(kp); + KP_CLEAR(kp2); + KP_CLEAR(kp_missed); +#ifdef CONFIG_KRETPROBES + KP_CLEAR(rp.kp); + KP_CLEAR(rp2.kp); +#ifdef CONFIG_ARCH_CORRECT_STACKTRACE_ON_KRETPROBE + KP_CLEAR(rp3.kp); + KP_CLEAR(rp4.kp); +#endif +#endif + target = kprobe_target; target2 = kprobe_target2; recursed_target = kprobe_recursed_target; diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index b02b503c750d..59de210bee5f 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -50,6 +50,11 @@ * memfds are always opened with ``O_RDWR`` and ``O_LARGEFILE``. This property * is maintained. * + * Seals + * File seals set on the memfd are preserved and re-applied on restore. + * Only seals known to this LUO version (see ``MEMFD_LUO_ALL_SEALS``) may + * be present; preservation fails with ``-EOPNOTSUPP`` otherwise. + * * Non-Preserved Properties * ======================== * @@ -61,10 +66,6 @@ * A memfd can be created with the ``MFD_CLOEXEC`` flag that sets the * ``FD_CLOEXEC`` on the file. This flag is not preserved and must be set * again after restore via ``fcntl()``. - * - * Seals - * File seals are not preserved. The file is unsealed on restore and if - * needed, must be sealed again via ``fcntl()``. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -259,7 +260,7 @@ static int memfd_luo_preserve(struct liveupdate_file_op_args *args) struct inode *inode = file_inode(args->file); struct memfd_luo_folio_ser *folios_ser; struct memfd_luo_ser *ser; - u64 nr_folios; + u64 nr_folios, inode_size; int err = 0, seals; inode_lock(inode); @@ -285,7 +286,18 @@ static int memfd_luo_preserve(struct liveupdate_file_op_args *args) } ser->pos = args->file->f_pos; - ser->size = i_size_read(inode); + inode_size = i_size_read(inode); + + /* + * memfd_pin_folios() caps at UINT_MAX folios; refuse larger + * files to avoid silently preserving only a prefix. + */ + if (DIV_ROUND_UP_ULL(inode_size, PAGE_SIZE) > UINT_MAX) { + err = -EFBIG; + goto err_free_ser; + } + + ser->size = inode_size; ser->seals = seals; err = memfd_luo_preserve_folios(args->file, &ser->folios, @@ -427,6 +439,7 @@ static int memfd_luo_retrieve_folios(struct file *file, if (!folio) { pr_err("Unable to restore folio at physical address: %llx\n", phys); + err = -EIO; goto put_folios; } index = pfolio->index; diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 358fbe5e4d1d..b991d937205a 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -179,6 +179,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) break; default: pr_alert("bad message type %d\n", (int)msg->type); + dev_kfree_skb(skb); /* Paired with find_get_vcc(msg->vcc) above */ sock_put(sk); return -EINVAL; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f28e9cbf8ad5..74ef7dc2b2f9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -173,19 +173,12 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, - struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh) + struct batadv_orig_node *orig_node) { struct batadv_neigh_node *neigh_node; neigh_node = batadv_neigh_node_get_or_create(orig_node, hard_iface, neigh_addr); - if (!neigh_node) - goto out; - - neigh_node->orig_node = orig_neigh; - -out: return neigh_node; } @@ -335,7 +328,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); const char *fwd_str; u8 packet_num; - s16 buff_pos; + int buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; struct sk_buff *skb; u8 *packet_pos; @@ -906,6 +899,31 @@ static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node, return sum; } +/** + * batadv_iv_ogm_neigh_ifinfo_sum() - Get bcast_own sum for a last-hop neighbor + * @bat_priv: the bat priv with all the mesh interface information + * @neigh_node: last-hop neighbor of an originator + * + * Return: Number of replied (rebroadcasted) OGMs for the originator currently + * announced by the neighbor. Returns 0 if the neighbor's originator entry is + * not available anymore. + */ +static u8 batadv_iv_ogm_neigh_ifinfo_sum(struct batadv_priv *bat_priv, + const struct batadv_neigh_node *neigh_node) +{ + struct batadv_orig_node *orig_neigh; + u8 sum; + + orig_neigh = batadv_orig_hash_find(bat_priv, neigh_node->addr); + if (!orig_neigh) + return 0; + + sum = batadv_iv_orig_ifinfo_sum(orig_neigh, neigh_node->if_incoming); + batadv_orig_node_put(orig_neigh); + + return sum; +} + /** * batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an * originator @@ -975,17 +993,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, } if (!neigh_node) { - struct batadv_orig_node *orig_tmp; - - orig_tmp = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); - if (!orig_tmp) - goto unlock; - neigh_node = batadv_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, - orig_node, orig_tmp); - - batadv_orig_node_put(orig_tmp); + orig_node); if (!neigh_node) goto unlock; } else { @@ -1037,10 +1047,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, */ if (router_ifinfo && neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { - sum_orig = batadv_iv_orig_ifinfo_sum(router->orig_node, - router->if_incoming); - sum_neigh = batadv_iv_orig_ifinfo_sum(neigh_node->orig_node, - neigh_node->if_incoming); + sum_orig = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, router); + sum_neigh = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, + neigh_node); if (sum_orig >= sum_neigh) goto out; } @@ -1106,7 +1115,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, if (!neigh_node) neigh_node = batadv_iv_ogm_neigh_new(if_incoming, orig_neigh_node->orig, - orig_neigh_node, orig_neigh_node); if (!neigh_node) @@ -1302,6 +1310,32 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, return ret; } +/** + * batadv_orig_to_direct_router() - get direct next hop neighbor to an orig address + * @bat_priv: the bat priv with all the mesh interface information + * @orig_addr: the originator MAC address to search the best next hop router for + * @if_outgoing: the interface where the OGM should be sent to + * + * Return: A neighbor node which is the best router towards the given originator + * address. Bonding candidates are ignored. + */ +static struct batadv_neigh_node * +batadv_orig_to_direct_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_orig_node *orig_node; + + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + if (!orig_node) + return NULL; + + neigh_node = batadv_orig_router_get(orig_node, if_outgoing); + batadv_orig_node_put(orig_node); + + return neigh_node; +} + /** * batadv_iv_ogm_process_per_outif() - process a batman iv OGM for an outgoing * interface @@ -1372,8 +1406,9 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { - router_router = batadv_orig_router_get(router->orig_node, - if_outgoing); + router_router = batadv_orig_to_direct_router(bat_priv, + router->addr, + if_outgoing); router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 51fe028b9088..cec11f1251d6 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -318,8 +318,8 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) if (claim->backbone_gw != backbone_gw) continue; - batadv_claim_put(claim); hlist_del_rcu(&claim->hash_entry); + batadv_claim_put(claim); } spin_unlock_bh(list_lock); } @@ -723,6 +723,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, if (unlikely(hash_added != 0)) { /* only local changes happened. */ + batadv_backbone_gw_put(backbone_gw); kfree(claim); return; } @@ -1288,6 +1289,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + /* only purge claims not currently in the process of being released. + * Such claims could otherwise have a NULL-ptr backbone_gw set because + * they already went through batadv_claim_release() + */ + if (!kref_get_unless_zero(&claim->refcount)) + continue; + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; @@ -1313,6 +1321,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, claim->addr, claim->vid); skip: batadv_backbone_gw_put(backbone_gw); + batadv_claim_put(claim); } rcu_read_unlock(); } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3a35aadd8b41..a4d33ee0fda5 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -249,6 +249,7 @@ void batadv_mesh_free(struct net_device *mesh_iface) atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); batadv_purge_outstanding_packets(bat_priv, NULL); + batadv_tp_stop_all(bat_priv); batadv_gw_node_free(bat_priv); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 2e42f6b348c8..066c76113fc4 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -365,23 +366,38 @@ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars) } /** - * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer - * @bat_priv: the bat priv with all the mesh interface information - * @tp_vars: the private data of the current TP meter session to cleanup + * batadv_tp_list_detach() - remove tp session from mesh session list once + * @tp_vars: the private data of the current TP meter session */ -static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv, - struct batadv_tp_vars *tp_vars) +static void batadv_tp_list_detach(struct batadv_tp_vars *tp_vars) { - cancel_delayed_work(&tp_vars->finish_work); + bool detached = false; spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); + if (!hlist_unhashed(&tp_vars->list)) { + hlist_del_init_rcu(&tp_vars->list); + detached = true; + } spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); + if (!detached) + return; + + atomic_dec(&tp_vars->bat_priv->tp_num); + /* drop list reference */ batadv_tp_vars_put(tp_vars); +} - atomic_dec(&tp_vars->bat_priv->tp_num); +/** + * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer + * @tp_vars: the private data of the current TP meter session to cleanup + */ +static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) +{ + cancel_delayed_work_sync(&tp_vars->finish_work); + + batadv_tp_list_detach(tp_vars); /* kill the timer and remove its reference */ timer_delete_sync(&tp_vars->timer); @@ -886,7 +902,8 @@ static int batadv_tp_send(void *arg) batadv_orig_node_put(orig_node); batadv_tp_sender_end(bat_priv, tp_vars); - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); batadv_tp_vars_put(tp_vars); @@ -918,7 +935,8 @@ static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars) batadv_tp_vars_put(tp_vars); /* cleanup of failed tp meter variables */ - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); return; } @@ -947,6 +965,13 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, /* look for an already existing test towards this node */ spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) { + spin_unlock_bh(&bat_priv->tp_list_lock); + batadv_tp_batctl_error_notify(BATADV_TP_REASON_DST_UNREACHABLE, + dst, bat_priv, session_cookie); + return; + } + tp_vars = batadv_tp_list_find(bat_priv, dst); if (tp_vars) { spin_unlock_bh(&bat_priv->tp_list_lock); @@ -969,6 +994,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC); if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); spin_unlock_bh(&bat_priv->tp_list_lock); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: %s cannot allocate list elements\n", @@ -1017,6 +1043,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars->start_time = jiffies; init_waitqueue_head(&tp_vars->more_bytes); + init_completion(&tp_vars->finished); spin_lock_init(&tp_vars->unacked_lock); INIT_LIST_HEAD(&tp_vars->unacked_list); @@ -1119,14 +1146,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) "Shutting down for inactivity (more than %dms) from %pM\n", BATADV_TP_RECV_TIMEOUT, tp_vars->other_end); - spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); - spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); - - /* drop list reference */ - batadv_tp_vars_put(tp_vars); - - atomic_dec(&bat_priv->tp_num); + batadv_tp_list_detach(tp_vars); spin_lock_bh(&tp_vars->unacked_lock); list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { @@ -1329,9 +1349,12 @@ static struct batadv_tp_vars * batadv_tp_init_recv(struct batadv_priv *bat_priv, const struct batadv_icmp_tp_packet *icmp) { - struct batadv_tp_vars *tp_vars; + struct batadv_tp_vars *tp_vars = NULL; spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out_unlock; + tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, icmp->session); if (tp_vars) @@ -1344,8 +1367,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, } tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC); - if (!tp_vars) + if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); goto out_unlock; + } ether_addr_copy(tp_vars->other_end, icmp->orig); tp_vars->role = BATADV_TP_RECEIVER; @@ -1464,6 +1489,9 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_icmp_tp_packet *icmp; + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out; + icmp = (struct batadv_icmp_tp_packet *)skb->data; switch (icmp->subtype) { @@ -1478,9 +1506,57 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) "Received unknown TP Metric packet type %u\n", icmp->subtype); } + +out: consume_skb(skb); } +/** + * batadv_tp_stop_all() - stop all currently running tp meter sessions + * @bat_priv: the bat priv with all the mesh interface information + */ +void batadv_tp_stop_all(struct batadv_priv *bat_priv) +{ + struct batadv_tp_vars *tp_vars[BATADV_TP_MAX_NUM]; + struct batadv_tp_vars *tp_var; + size_t count = 0; + size_t i; + + spin_lock_bh(&bat_priv->tp_list_lock); + hlist_for_each_entry(tp_var, &bat_priv->tp_list, list) { + if (WARN_ON_ONCE(count >= BATADV_TP_MAX_NUM)) + break; + + if (!kref_get_unless_zero(&tp_var->refcount)) + continue; + + tp_vars[count++] = tp_var; + } + spin_unlock_bh(&bat_priv->tp_list_lock); + + for (i = 0; i < count; i++) { + tp_var = tp_vars[i]; + + switch (tp_var->role) { + case BATADV_TP_SENDER: + batadv_tp_sender_shutdown(tp_var, + BATADV_TP_REASON_CANCEL); + wake_up(&tp_var->more_bytes); + wait_for_completion(&tp_var->finished); + break; + case BATADV_TP_RECEIVER: + batadv_tp_list_detach(tp_var); + if (timer_shutdown_sync(&tp_var->timer)) + batadv_tp_vars_put(tp_var); + break; + } + + batadv_tp_vars_put(tp_var); + } + + synchronize_net(); +} + /** * batadv_tp_meter_init() - initialize global tp_meter structures */ diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index f0046d366eac..4e97cd10cd02 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -17,6 +17,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, u32 test_length, u32 *cookie); void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, u8 return_value); +void batadv_tp_stop_all(struct batadv_priv *bat_priv); void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb); #endif /* _NET_BATMAN_ADV_TP_METER_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 8fc5fe0e9b05..daa06f421154 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -1328,6 +1329,9 @@ struct batadv_tp_vars { /** @finish_work: work item for the finishing procedure */ struct delayed_work finish_work; + /** @finished: completion signaled when a sender thread exits */ + struct completion finished; + /** @test_length: test length in milliseconds */ u32 test_length; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 741360219552..f05c79f215ea 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -112,24 +112,22 @@ static struct pernet_operations broute_net_ops = { static int __init ebtable_broute_init(void) { - int ret = ebt_register_template(&broute_table, broute_table_init); + int ret = register_pernet_subsys(&broute_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&broute_net_ops); - if (ret) { - ebt_unregister_template(&broute_table); - return ret; - } + ret = ebt_register_template(&broute_table, broute_table_init); + if (ret) + unregister_pernet_subsys(&broute_net_ops); - return 0; + return ret; } static void __exit ebtable_broute_fini(void) { - unregister_pernet_subsys(&broute_net_ops); ebt_unregister_template(&broute_table); + unregister_pernet_subsys(&broute_net_ops); } module_init(ebtable_broute_init); diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index dacd81b12e62..0fc03b07e62a 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,24 +93,22 @@ static struct pernet_operations frame_filter_net_ops = { static int __init ebtable_filter_init(void) { - int ret = ebt_register_template(&frame_filter, frame_filter_table_init); + int ret = register_pernet_subsys(&frame_filter_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_filter_net_ops); - if (ret) { - ebt_unregister_template(&frame_filter); - return ret; - } + ret = ebt_register_template(&frame_filter, frame_filter_table_init); + if (ret) + unregister_pernet_subsys(&frame_filter_net_ops); - return 0; + return ret; } static void __exit ebtable_filter_fini(void) { - unregister_pernet_subsys(&frame_filter_net_ops); ebt_unregister_template(&frame_filter); + unregister_pernet_subsys(&frame_filter_net_ops); } module_init(ebtable_filter_init); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 0f2a8c6118d4..8a10375d8909 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,24 +93,22 @@ static struct pernet_operations frame_nat_net_ops = { static int __init ebtable_nat_init(void) { - int ret = ebt_register_template(&frame_nat, frame_nat_table_init); + int ret = register_pernet_subsys(&frame_nat_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_nat_net_ops); - if (ret) { - ebt_unregister_template(&frame_nat); - return ret; - } + ret = ebt_register_template(&frame_nat, frame_nat_table_init); + if (ret) + unregister_pernet_subsys(&frame_nat_net_ops); return ret; } static void __exit ebtable_nat_fini(void) { - unregister_pernet_subsys(&frame_nat_net_ops); ebt_unregister_template(&frame_nat); + unregister_pernet_subsys(&frame_nat_net_ops); } module_init(ebtable_nat_init); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index aea3e19875c6..b9f4daac09af 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -42,6 +42,7 @@ struct ebt_pernet { struct list_head tables; + struct list_head dead_tables; }; struct ebt_template { @@ -1162,11 +1163,6 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) static void __ebt_unregister_table(struct net *net, struct ebt_table *table) { - mutex_lock(&ebt_mutex); - list_del(&table->list); - mutex_unlock(&ebt_mutex); - audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size, ebt_cleanup_entry, net, NULL); if (table->private->nentries) @@ -1267,13 +1263,15 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, for (i = 0; i < num_ops; i++) ops[i].priv = table; - list_add(&table->list, &ebt_net->tables); - mutex_unlock(&ebt_mutex); - table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); - if (ret) + if (ret) { + synchronize_rcu(); __ebt_unregister_table(net, table); + } else { + list_add(&table->list, &ebt_net->tables); + } + mutex_unlock(&ebt_mutex); audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries, AUDIT_XT_OP_REGISTER, GFP_KERNEL); @@ -1339,7 +1337,7 @@ void ebt_unregister_template(const struct ebt_table *t) } EXPORT_SYMBOL(ebt_unregister_template); -static struct ebt_table *__ebt_find_table(struct net *net, const char *name) +void ebt_unregister_table_pre_exit(struct net *net, const char *name) { struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); struct ebt_table *t; @@ -1348,30 +1346,36 @@ static struct ebt_table *__ebt_find_table(struct net *net, const char *name) list_for_each_entry(t, &ebt_net->tables, list) { if (strcmp(t->name, name) == 0) { + list_move(&t->list, &ebt_net->dead_tables); mutex_unlock(&ebt_mutex); - return t; + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; } } mutex_unlock(&ebt_mutex); - return NULL; -} - -void ebt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct ebt_table *table = __ebt_find_table(net, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } EXPORT_SYMBOL(ebt_unregister_table_pre_exit); void ebt_unregister_table(struct net *net, const char *name) { - struct ebt_table *table = __ebt_find_table(net, name); + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + struct ebt_table *t; - if (table) - __ebt_unregister_table(net, table); + mutex_lock(&ebt_mutex); + + list_for_each_entry(t, &ebt_net->dead_tables, list) { + if (strcmp(t->name, name) == 0) { + list_del(&t->list); + audit_log_nfcfg(t->name, AF_BRIDGE, t->private->nentries, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + __ebt_unregister_table(net, t); + mutex_unlock(&ebt_mutex); + return; + } + } + + mutex_unlock(&ebt_mutex); } /* userspace just supplied us with counters */ @@ -2556,11 +2560,21 @@ static int __net_init ebt_pernet_init(struct net *net) struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); INIT_LIST_HEAD(&ebt_net->tables); + INIT_LIST_HEAD(&ebt_net->dead_tables); return 0; } +static void __net_exit ebt_pernet_exit(struct net *net) +{ + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + + WARN_ON_ONCE(!list_empty(&ebt_net->tables)); + WARN_ON_ONCE(!list_empty(&ebt_net->dead_tables)); +} + static struct pernet_operations ebt_net_ops = { .init = ebt_pernet_init, + .exit = ebt_pernet_exit, .id = &ebt_pernet_id, .size = sizeof(struct ebt_pernet), }; @@ -2569,19 +2583,20 @@ static int __init ebtables_init(void) { int ret; - ret = xt_register_target(&ebt_standard_target); + ret = register_pernet_subsys(&ebt_net_ops); if (ret < 0) return ret; - ret = nf_register_sockopt(&ebt_sockopts); + + ret = xt_register_target(&ebt_standard_target); if (ret < 0) { - xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } - ret = register_pernet_subsys(&ebt_net_ops); + ret = nf_register_sockopt(&ebt_sockopts); if (ret < 0) { - nf_unregister_sockopt(&ebt_sockopts); xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 14eb7812bda4..ecd659f79fd4 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -172,7 +172,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); - if (!(smap->map.map_flags & BPF_F_CLONE)) + if (!smap || !(smap->map.map_flags & BPF_F_CLONE)) continue; /* Note that for lockless listeners adding new element @@ -531,10 +531,10 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); -static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) +static int diag_get(struct bpf_local_storage_map *smap, + struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; - struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); @@ -543,7 +543,6 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) if (!nla_stg) return -EMSGSIZE; - smap = rcu_dereference(sdata->smap); if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) goto errout; @@ -558,6 +557,7 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) sdata->data, true); else copy_map_value(&smap->map, nla_data(nla_value), sdata->data); + check_and_init_map_value(&smap->map, nla_data(nla_value)); nla_nest_end(skb, nla_stg); return 0; @@ -596,9 +596,11 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, saved_len = skb->len; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { smap = rcu_dereference(SDATA(selem)->smap); + if (!smap) + continue; diag_size += nla_value_size(smap->map.value_size); - if (nla_stgs && diag_get(SDATA(selem), skb)) + if (nla_stgs && diag_get(smap, SDATA(selem), skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } @@ -665,7 +667,7 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, diag_size += nla_value_size(diag->maps[i]->value_size); - if (nla_stgs && diag_get(sdata, skb)) + if (nla_stgs && diag_get((struct bpf_local_storage_map *)diag->maps[i], sdata, skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } diff --git a/net/core/dev.c b/net/core/dev.c index b0691e03dd6b..267cf3854395 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6862,9 +6862,9 @@ static void skb_defer_free_flush(void) #if defined(CONFIG_NET_RX_BUSY_POLL) -static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) +static void __busy_poll_stop(struct napi_struct *napi, unsigned long timeout) { - if (!skip_schedule) { + if (!timeout) { gro_normal_list(&napi->gro); __napi_schedule(napi); return; @@ -6874,6 +6874,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) gro_flush_normal(&napi->gro, HZ >= 1000); clear_bit(NAPI_STATE_SCHED, &napi->state); + hrtimer_start(&napi->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); } enum { @@ -6885,8 +6887,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; - bool skip_schedule = false; - unsigned long timeout; + unsigned long timeout = 0; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6906,10 +6907,12 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); - timeout = napi_get_gro_flush_timeout(napi); - if (napi->defer_hard_irqs_count && timeout) { - hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); - skip_schedule = true; + if (napi->defer_hard_irqs_count) { + /* A short enough gro flush timeout and long enough + * poll can result in timer firing too early. + * Timer will be armed later if necessary. + */ + timeout = napi_get_gro_flush_timeout(napi); } } @@ -6924,7 +6927,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) - __busy_poll_stop(napi, skip_schedule); + __busy_poll_stop(napi, timeout); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } diff --git a/net/core/failover.c b/net/core/failover.c index 11bb183c7a1b..e43c59cd6868 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -12,6 +12,7 @@ #include #include #include +#include #include static LIST_HEAD(failover_list); @@ -221,8 +222,11 @@ failover_existing_slave_register(struct net_device *failover_dev) for_each_netdev(net, dev) { if (netif_is_failover(dev)) continue; - if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) + if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) { + netdev_lock_ops(dev); failover_slave_register(dev); + netdev_unlock_ops(dev); + } } rtnl_unlock(); } diff --git a/net/core/filter.c b/net/core/filter.c index 80a3b702a2d4..9590877b0714 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1654,15 +1654,24 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) return err; } +static void sk_reuseport_prog_free_rcu(struct rcu_head *rcu) +{ + struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); + struct bpf_prog *prog = aux->prog; + + bpf_release_orig_filter(prog); + bpf_prog_free(prog); +} + void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; - if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - bpf_prog_put(prog); + if (bpf_prog_was_classic(prog)) + call_rcu(&prog->aux->rcu, sk_reuseport_prog_free_rcu); else - bpf_prog_destroy(prog); + bpf_prog_put(prog); } static inline int __bpf_try_make_writable(struct sk_buff *skb, @@ -5481,7 +5490,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { - if (sk->sk_protocol != IPPROTO_TCP) + if (!sk_is_tcp(sk)) return -EINVAL; switch (optname) { @@ -5688,6 +5697,30 @@ const struct bpf_func_proto bpf_sk_getsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_sk_setsockopt_nodelay, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + /* + * TCP_NODELAY triggers tcp_push_pending_frames() and re-enters + * CA_EVENT_TX_START in bpf_tcp_cc. + */ + if (level == SOL_TCP && optname == TCP_NODELAY) + return -EOPNOTSUPP; + + return _bpf_setsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto = { + .func = bpf_sk_setsockopt_nodelay, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg5_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { @@ -5833,6 +5866,12 @@ BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; + /* TCP_NODELAY triggers tcp_push_pending_frames() and re-enters these callbacks. */ + if ((bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB || + bpf_sock->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB) && + level == SOL_TCP && optname == TCP_NODELAY) + return -EOPNOTSUPP; + return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -6443,6 +6482,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); + if (unlikely(!dev)) + return -ENODEV; if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; @@ -7443,7 +7484,7 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + if (sk_fullsock(sk) && sk_is_tcp(sk)) return (unsigned long)sk; return (unsigned long)NULL; @@ -11915,7 +11956,7 @@ BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && - sk->sk_family == AF_INET6) + sk->sk_type == SOCK_STREAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; @@ -11931,7 +11972,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { - if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + if (sk && sk_fullsock(sk) && sk_is_tcp(sk)) return (unsigned long)sk; return (unsigned long)NULL; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 02a68be3002a..99e3789492a0 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1630,18 +1630,23 @@ void sock_map_unhash(struct sock *sk) void (*saved_unhash)(struct sock *sk); struct sk_psock *psock; +retry: rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_unhash = READ_ONCE(sk->sk_prot)->unhash; + if (unlikely(saved_unhash == sock_map_unhash)) + goto retry; } else { saved_unhash = psock->saved_unhash; sock_map_remove_links(sk, psock); rcu_read_unlock(); + + if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) + return; } - if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) - return; + if (saved_unhash) saved_unhash(sk); } @@ -1652,20 +1657,25 @@ void sock_map_destroy(struct sock *sk) void (*saved_destroy)(struct sock *sk); struct sk_psock *psock; +retry: rcu_read_lock(); psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_destroy = READ_ONCE(sk->sk_prot)->destroy; + if (unlikely(saved_destroy == sock_map_destroy)) + goto retry; } else { saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); sk_psock_put(sk, psock); + + if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) + return; } - if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) - return; + if (saved_destroy) saved_destroy(sk); } @@ -1676,32 +1686,33 @@ void sock_map_close(struct sock *sk, long timeout) void (*saved_close)(struct sock *sk, long timeout); struct sk_psock *psock; +retry: lock_sock(sk); rcu_read_lock(); - psock = sk_psock(sk); + psock = sk_psock_get(sk); if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); - psock = sk_psock_get(sk); - if (unlikely(!psock)) - goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); + + /* Make sure we do not recurse. This is a bug. + * Leak the socket instead of crashing on a stack overflow. + */ + if (WARN_ON_ONCE(saved_close == sock_map_close)) + return; } else { saved_close = READ_ONCE(sk->sk_prot)->close; -no_psock: rcu_read_unlock(); release_sock(sk); + + if (unlikely(saved_close == sock_map_close)) + goto retry; } - /* Make sure we do not recurse. This is a bug. - * Leak the socket instead of crashing on a stack overflow. - */ - if (WARN_ON_ONCE(saved_close == sock_map_close)) - return; saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 8bb98d3ea3db..a3a2cc6480a0 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -92,7 +92,7 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, u32 mask; if (end <= start) - return true; + return false; if (start % 32) { mask = ethnl_upper_bits(start); @@ -105,11 +105,11 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, start_word++; } - if (!memchr_inv(map + start_word, '\0', - (end_word - start_word) * sizeof(u32))) + if (memchr_inv(map + start_word, '\0', + (end_word - start_word) * sizeof(u32))) return true; if (end % 32 == 0) - return true; + return false; return map[end_word] & ethnl_lower_bits(end); } diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c index d4e6887055ab..ddc6eab701ed 100644 --- a/net/ethtool/phy.c +++ b/net/ethtool/phy.c @@ -76,6 +76,7 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, struct nlattr **tb = info->attrs; struct phy_device_node *pdn; struct phy_device *phydev; + int ret; /* RTNL is held by the caller */ phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER, @@ -88,8 +89,19 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, return -EOPNOTSUPP; rep_data->phyindex = phydev->phyindex; + rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL); - rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->name) + return -ENOMEM; + + if (phydev->drv) { + rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->drvname) { + ret = -ENOMEM; + goto err_free_name; + } + } + rep_data->upstream_type = pdn->upstream_type; if (pdn->upstream_type == PHY_UPSTREAM_PHY) { @@ -97,15 +109,33 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, rep_data->upstream_index = upstream->phyindex; } - if (pdn->parent_sfp_bus) + if (pdn->parent_sfp_bus) { rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus), GFP_KERNEL); + if (!rep_data->upstream_sfp_name) { + ret = -ENOMEM; + goto err_free_drvname; + } + } - if (phydev->sfp_bus) + if (phydev->sfp_bus) { rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus), GFP_KERNEL); + if (!rep_data->downstream_sfp_name) { + ret = -ENOMEM; + goto err_free_upstream_sfp; + } + } return 0; + +err_free_upstream_sfp: + kfree(rep_data->upstream_sfp_name); +err_free_drvname: + kfree(rep_data->drvname); +err_free_name: + kfree(rep_data->name); + return ret; } static int phy_fill_reply(struct sk_buff *skb, diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index d09875b33588..124619920d38 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -889,7 +889,10 @@ int hsr_get_node_data(struct hsr_priv *hsr, if (node->addr_B_port != HSR_PT_NONE) { port = hsr_port_get_hsr(hsr, node->addr_B_port); - *addr_b_ifindex = port->dev->ifindex; + if (port) + *addr_b_ifindex = port->dev->ifindex; + else + *addr_b_ifindex = -1; } else { *addr_b_ifindex = -1; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 008edc7f6688..791e15063237 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -168,7 +168,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, */ if (prog_ops_moff(prog) != offsetof(struct tcp_congestion_ops, release)) - return &bpf_sk_setsockopt_proto; + return &bpf_sk_setsockopt_nodelay_proto; return NULL; case BPF_FUNC_getsockopt: /* Since get/setsockopt is usually expected to diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 928654c34156..dbcd37dfdc15 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1108,7 +1108,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ - __inet_csk_reqsk_queue_drop(sk_listener, nreq, true); + __inet_csk_reqsk_queue_drop(sk_listener, nreq, false); goto no_ownership; } @@ -1134,7 +1134,7 @@ static void reqsk_timer_handler(struct timer_list *t) } drop: - __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); + __inet_csk_reqsk_queue_drop(oreq->rsk_listener, oreq, true); reqsk_put(oreq); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 97ead883e4a1..ad2259678c78 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1501,13 +1501,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len static void __arpt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; + void *loc_cpu_entry; struct arpt_entry *iter; - private = xt_unregister_table(table); - /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) @@ -1515,6 +1513,7 @@ static void __arpt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int arpt_register_table(struct net *net, @@ -1522,13 +1521,11 @@ int arpt_register_table(struct net *net, const struct arpt_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1543,7 +1540,7 @@ int arpt_register_table(struct net *net, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct arpt_entry *iter; @@ -1553,46 +1550,12 @@ int arpt_register_table(struct net *net, return PTR_ERR(new_table); } - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - - return ret; - -out_free: - __arpt_unregister_table(net, new_table); return ret; } -void arpt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); -} -EXPORT_SYMBOL(arpt_unregister_table_pre_exit); - void arpt_unregister_table(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_ARP, name); if (table) __arpt_unregister_table(net, table); diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 78cd5ee24448..370b635e3523 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -43,7 +43,7 @@ static int arptable_filter_table_init(struct net *net) static void __net_exit arptable_filter_net_pre_exit(struct net *net) { - arpt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_ARP, "filter"); } static void __net_exit arptable_filter_net_exit(struct net *net) @@ -58,32 +58,33 @@ static struct pernet_operations arptable_filter_net_ops = { static int __init arptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - arptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table); - if (IS_ERR(arpfilter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(arpfilter_ops)) return PTR_ERR(arpfilter_ops); - } ret = register_pernet_subsys(&arptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + arptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(arpfilter_ops); - return ret; + unregister_pernet_subsys(&arptable_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(arpfilter_ops); return ret; } static void __exit arptable_filter_fini(void) { - unregister_pernet_subsys(&arptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&arptable_filter_net_ops); kfree(arpfilter_ops); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 23c8deff8095..5cbdb0815857 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1704,12 +1704,10 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ipt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ipt_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1718,19 +1716,18 @@ static void __ipt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1745,7 +1742,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ipt_entry *iter; @@ -1755,51 +1752,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table, return PTR_ERR(new_table); } - /* No template? No need to do anything. This is used by 'nat' table, it registers - * with the nat core instead of the netfilter core. - */ - if (!template_ops) - return 0; - - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - return ret; - -out_free: - __ipt_unregister_table(net, new_table); - return ret; -} - -void ipt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ipt_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); @@ -1887,7 +1845,6 @@ static void __exit ip_tables_fini(void) } EXPORT_SYMBOL(ipt_register_table); -EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 3ab908b74795..672d7da1071d 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -61,7 +61,7 @@ static int __net_init iptable_filter_net_init(struct net *net) static void __net_exit iptable_filter_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "filter"); } static void __net_exit iptable_filter_net_exit(struct net *net) @@ -77,32 +77,33 @@ static struct pernet_operations iptable_filter_net_ops = { static int __init iptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - iptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&iptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + iptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&iptable_filter_net_ops); + goto err_free; } return 0; +err_free: + kfree(filter_ops); + return ret; } static void __exit iptable_filter_fini(void) { - unregister_pernet_subsys(&iptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&iptable_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 385d945d8ebe..13d25d9a4610 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -96,7 +96,7 @@ static int iptable_mangle_table_init(struct net *net) static void __net_exit iptable_mangle_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "mangle"); } static void __net_exit iptable_mangle_net_exit(struct net *net) @@ -111,32 +111,33 @@ static struct pernet_operations iptable_mangle_net_ops = { static int __init iptable_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - iptable_mangle_table_init); - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); - ret = PTR_ERR(mangle_ops); - return ret; - } + if (IS_ERR(mangle_ops)) + return PTR_ERR(mangle_ops); ret = register_pernet_subsys(&iptable_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + iptable_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&iptable_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } static void __exit iptable_mangle_fini(void) { - unregister_pernet_subsys(&iptable_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&iptable_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 625a1ca13b1b..a0df72554025 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -119,8 +119,11 @@ static int iptable_nat_table_init(struct net *net) } ret = ipt_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); + synchronize_rcu(); ipt_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; @@ -129,6 +132,7 @@ static int iptable_nat_table_init(struct net *net) static void __net_exit iptable_nat_net_pre_exit(struct net *net) { ipt_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); } static void __net_exit iptable_nat_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 0e7f53964d0a..2745c22f4034 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -53,7 +53,7 @@ static int iptable_raw_table_init(struct net *net) static void __net_exit iptable_raw_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "raw"); } static void __net_exit iptable_raw_net_exit(struct net *net) @@ -77,32 +77,32 @@ static int __init iptable_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, - iptable_raw_table_init); - if (ret < 0) - return ret; - rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&iptable_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, + iptable_raw_table_init); if (ret < 0) { - xt_unregister_template(table); - kfree(rawtable_ops); - return ret; + unregister_pernet_subsys(&iptable_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } static void __exit iptable_raw_fini(void) { + xt_unregister_template(&packet_raw); unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); - xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index d885443cb267..491894511c54 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -50,7 +50,7 @@ static int iptable_security_table_init(struct net *net) static void __net_exit iptable_security_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "security"); } static void __net_exit iptable_security_net_exit(struct net *net) @@ -65,33 +65,34 @@ static struct pernet_operations iptable_security_net_ops = { static int __init iptable_security_init(void) { - int ret = xt_register_template(&security_table, - iptable_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&iptable_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + iptable_security_table_init); if (ret < 0) { - xt_unregister_template(&security_table); - kfree(sectbl_ops); - return ret; + unregister_pernet_subsys(&iptable_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } static void __exit iptable_security_fini(void) { + xt_unregister_template(&security_table); unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); - xt_unregister_template(&security_table); } module_init(iptable_security_init); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 36a64c1cd8c9..2f69bcecae78 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -219,7 +219,8 @@ struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, { struct tcp_ao_key *key; - hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) { + hlist_for_each_entry_rcu(key, &ao->head, node, + sk_fullsock(sk) && lockdep_sock_is_held(sk)) { if ((sndid >= 0 && key->sndid != sndid) || (rcvid >= 0 && key->rcvid != rcvid)) continue; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index c92f98c6f6ec..b1ccdf0dc646 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -36,11 +36,11 @@ /* FL hash table */ #define FL_MAX_PER_SOCK 32 -#define FL_MAX_SIZE 4096 +#define FL_MAX_SIZE 8192 #define FL_HASH_MASK 255 #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) -static atomic_t fl_size = ATOMIC_INIT(0); +static int fl_size; static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(struct timer_list *unused); @@ -162,8 +162,9 @@ static void ip6_fl_gc(struct timer_list *unused) ttd = fl->expires; if (time_after_eq(now, ttd)) { *flp = fl->next; + fl_size--; + fl->fl_net->ipv6.flowlabel_count--; fl_free(fl); - atomic_dec(&fl_size); continue; } if (!sched || time_before(ttd, sched)) @@ -172,7 +173,7 @@ static void ip6_fl_gc(struct timer_list *unused) flp = &fl->next; } } - if (!sched && atomic_read(&fl_size)) + if (!sched && fl_size) sched = now + FL_MAX_LINGER; if (sched) { mod_timer(&ip6_fl_gc_timer, sched); @@ -196,7 +197,8 @@ static void __net_exit ip6_fl_purge(struct net *net) atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); - atomic_dec(&fl_size); + fl_size--; + net->ipv6.flowlabel_count--; continue; } flp = &fl->next; @@ -210,10 +212,10 @@ static struct ip6_flowlabel *fl_intern(struct net *net, { struct ip6_flowlabel *lfl; + lockdep_assert_held(&ip6_fl_lock); + fl->label = label & IPV6_FLOWLABEL_MASK; - rcu_read_lock(); - spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { fl->label = htonl(get_random_u32())&IPV6_FLOWLABEL_MASK; @@ -235,8 +237,6 @@ static struct ip6_flowlabel *fl_intern(struct net *net, lfl = __fl_lookup(net, fl->label); if (lfl) { atomic_inc(&lfl->users); - spin_unlock_bh(&ip6_fl_lock); - rcu_read_unlock(); return lfl; } } @@ -244,9 +244,8 @@ static struct ip6_flowlabel *fl_intern(struct net *net, fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); - atomic_inc(&fl_size); - spin_unlock_bh(&ip6_fl_lock); - rcu_read_unlock(); + fl_size++; + net->ipv6.flowlabel_count++; return NULL; } @@ -464,10 +463,17 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, static int mem_check(struct sock *sk) { - int room = FL_MAX_SIZE - atomic_read(&fl_size); + const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4); + const int unpriv_user_limit = unpriv_total_limit / 2; + struct net *net = sock_net(sk); + int room; struct ipv6_fl_socklist *sfl; int count = 0; + lockdep_assert_held(&ip6_fl_lock); + + room = FL_MAX_SIZE - fl_size; + if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; @@ -478,7 +484,9 @@ static int mem_check(struct sock *sk) if (room <= 0 || ((count >= FL_MAX_PER_SOCK || - (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && + (count > 0 && room < FL_MAX_SIZE / 2) || + room < FL_MAX_SIZE / 4 || + net->ipv6.flowlabel_count >= unpriv_user_limit) && !capable(CAP_NET_ADMIN))) return -ENOBUFS; @@ -692,11 +700,19 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, if (!sfl1) goto done; + rcu_read_lock(); + spin_lock_bh(&ip6_fl_lock); err = mem_check(sk); + if (err == 0) + fl1 = fl_intern(net, fl, freq->flr_label); + else + fl1 = NULL; + spin_unlock_bh(&ip6_fl_lock); + rcu_read_unlock(); + if (err != 0) goto done; - fl1 = fl_intern(net, fl, freq->flr_label); if (fl1) goto recheck; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d585ac3c1113..9d9c3763f2f5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1713,12 +1713,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ip6t_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1727,19 +1725,18 @@ static void __ip6t_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1754,7 +1751,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; @@ -1764,48 +1761,12 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, return PTR_ERR(new_table); } - if (!template_ops) - return 0; - - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - return ret; - -out_free: - __ip6t_unregister_table(net, new_table); - return ret; -} - -void ip6t_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); @@ -1894,7 +1855,6 @@ static void __exit ip6_tables_fini(void) } EXPORT_SYMBOL(ip6t_register_table); -EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index e8992693e14a..b074fc477676 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -60,7 +60,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) static void __net_exit ip6table_filter_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "filter"); } static void __net_exit ip6table_filter_net_exit(struct net *net) @@ -76,32 +76,32 @@ static struct pernet_operations ip6table_filter_net_ops = { static int __init ip6table_filter_init(void) { - int ret = xt_register_template(&packet_filter, - ip6table_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&ip6table_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, ip6table_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&ip6table_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(filter_ops); return ret; } static void __exit ip6table_filter_fini(void) { - unregister_pernet_subsys(&ip6table_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&ip6table_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 8dd4cd0c47bd..e6ee036a9b2c 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -89,7 +89,7 @@ static int ip6table_mangle_table_init(struct net *net) static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "mangle"); } static void __net_exit ip6table_mangle_net_exit(struct net *net) @@ -104,32 +104,33 @@ static struct pernet_operations ip6table_mangle_net_ops = { static int __init ip6table_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - ip6table_mangle_table_init); - - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); + if (IS_ERR(mangle_ops)) return PTR_ERR(mangle_ops); - } ret = register_pernet_subsys(&ip6table_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&ip6table_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } static void __exit ip6table_mangle_fini(void) { - unregister_pernet_subsys(&ip6table_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&ip6table_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 5be723232df8..c2394e2c94b5 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -121,8 +121,11 @@ static int ip6table_nat_table_init(struct net *net) } ret = ip6t_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); + synchronize_rcu(); ip6t_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; @@ -131,6 +134,7 @@ static int ip6table_nat_table_init(struct net *net) static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index fc9f6754028f..3b161ee875bc 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -52,7 +52,7 @@ static int ip6table_raw_table_init(struct net *net) static void __net_exit ip6table_raw_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "raw"); } static void __net_exit ip6table_raw_net_exit(struct net *net) @@ -75,31 +75,31 @@ static int __init ip6table_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, ip6table_raw_table_init); - if (ret < 0) - return ret; - /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&ip6table_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, ip6table_raw_table_init); if (ret < 0) { - kfree(rawtable_ops); - xt_unregister_template(table); - return ret; + unregister_pernet_subsys(&ip6table_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } static void __exit ip6table_raw_fini(void) { - unregister_pernet_subsys(&ip6table_raw_net_ops); xt_unregister_template(&packet_raw); + unregister_pernet_subsys(&ip6table_raw_net_ops); kfree(rawtable_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 4df14a9bae78..4bd5d97b8ab6 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -49,7 +49,7 @@ static int ip6table_security_table_init(struct net *net) static void __net_exit ip6table_security_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "security"); } static void __net_exit ip6table_security_net_exit(struct net *net) @@ -64,32 +64,33 @@ static struct pernet_operations ip6table_security_net_ops = { static int __init ip6table_security_init(void) { - int ret = xt_register_template(&security_table, - ip6table_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&ip6table_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + ip6table_security_table_init); if (ret < 0) { - kfree(sectbl_ops); - xt_unregister_template(&security_table); - return ret; + unregister_pernet_subsys(&ip6table_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } static void __exit ip6table_security_fini(void) { - unregister_pernet_subsys(&ip6table_security_net_ops); xt_unregister_template(&security_table); + unregister_pernet_subsys(&ip6table_security_net_ops); kfree(sectbl_ops); } diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c index 8a16672b94e2..4cc16cbeb328 100644 --- a/net/mptcp/bpf.c +++ b/net/mptcp/bpf.c @@ -14,7 +14,7 @@ struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { - if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk)) + if (sk && sk_fullsock(sk) && sk_is_tcp(sk) && sk_is_mptcp(sk)) return mptcp_sk(mptcp_subflow_ctx(sk)->conn); return NULL; diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 4f39bf7c843f..75e53fde6b29 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -72,6 +72,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->flags = NF_CT_EXPECT_PERMANENT; exp->class = NF_CT_EXPECT_CLASS_DEFAULT; rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b08189226320..8ba5b22a1eef 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1811,14 +1811,17 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl)); if (exp) { + struct nf_conntrack_helper *assign_helper; + /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ ct->master = exp->master; - if (exp->helper) { + assign_helper = rcu_dereference(exp->assign_helper); + if (assign_helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) - rcu_assign_pointer(help->helper, exp->helper); + rcu_assign_pointer(help->helper, assign_helper); } #ifdef CONFIG_NF_CONNTRACK_MARK diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 24d0576d84b7..8e943efbdf0a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -344,6 +344,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, helper = rcu_dereference(help->helper); rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 3f5c50455b71..b2fe6554b9cf 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245); + rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nathook = rcu_dereference(nfct_h323_nat_hook); @@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_UDP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); @@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index a715304a53d8..b594cd244fe1 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -400,6 +400,11 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) this = rcu_dereference_protected(exp->helper, lockdep_is_held(&nf_conntrack_expect_lock)); + if (this == me) + return true; + + this = rcu_dereference_protected(exp->assign_helper, + lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index eda5fe4a75c8..befa7e83ee49 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2634,6 +2634,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); @@ -2860,6 +2861,7 @@ static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { + struct nf_conntrack_helper *assign_helper = NULL; struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_expect *exp; @@ -2870,13 +2872,26 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (err < 0) return err; + if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK]) + return -EINVAL; + err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + assign_helper = __nf_conntrack_helper_find(helpname, + nf_ct_l3num(ct), + tuple.dst.protonum); + if (!assign_helper) + return -EOPNOTSUPP; + } + exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, - &tuple, &mask); + assign_helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); @@ -3515,6 +3530,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { @@ -3568,6 +3584,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp->zone = ct->zone; #endif rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, assign_helper); exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; @@ -3623,7 +3640,7 @@ ctnetlink_create_expect(struct net *net, ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); - exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask); + exp = ctnetlink_alloc_expect(cda, ct, NULL, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 1eb55907d470..e69941f1a101 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1366,6 +1366,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, goto store_cseq; } + helper = rcu_dereference(nfct_help(ct)->helper); + if (!helper) + return NF_DROP; + exp = nf_ct_expect_alloc(ct); if (!exp) { nf_ct_helper_log(skb, ct, "cannot alloc expectation"); @@ -1376,14 +1380,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, if (sip_direct_signalling) saddr = &ct->tuplehash[!dir].tuple.src.u3; - helper = rcu_dereference(nfct_help(ct)->helper); - if (!helper) - return NF_DROP; - nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; - rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; hooks = rcu_dereference(nf_nat_sip_hooks); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 60ee8d932fcb..fa2cc556331c 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1334,6 +1334,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; + + nf_ct_expect_put(exp); } static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2c67c2e6b132..4e6708c23922 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -55,6 +55,9 @@ static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; + + /* stash area used during netns exit */ + struct list_head dead_tables[NFPROTO_NUMPROTO]; }; struct compat_delta { @@ -1472,11 +1475,9 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); -struct xt_table_info * -xt_replace_table(struct xt_table *table, - unsigned int num_counters, - struct xt_table_info *newinfo, - int *error) +static struct xt_table_info * +do_replace_table(struct xt_table *table, unsigned int num_counters, + struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; @@ -1531,30 +1532,54 @@ xt_replace_table(struct xt_table *table, } } - audit_log_nfcfg(table->name, table->af, private->number, - !private->number ? AUDIT_XT_OP_REGISTER : - AUDIT_XT_OP_REPLACE, - GFP_KERNEL); + return private; +} + +struct xt_table_info * +xt_replace_table(struct xt_table *table, unsigned int num_counters, + struct xt_table_info *newinfo, + int *error) +{ + struct xt_table_info *private; + + private = do_replace_table(table, num_counters, newinfo, error); + if (private) + audit_log_nfcfg(table->name, table->af, private->number, + AUDIT_XT_OP_REPLACE, + GFP_KERNEL); + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, + const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t, *table = NULL; + struct nf_hook_ops *ops = NULL; struct xt_table_info *private; - struct xt_table *t, *table; - int ret; + unsigned int num_ops; + int ret = -EINVAL; + + num_ops = hweight32(input_table->valid_hooks); + if (num_ops == 0) + goto out; + + ret = -ENOMEM; + if (template_ops) { + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); + if (!ops) + goto out; + } /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); - if (!table) { - ret = -ENOMEM; + if (!table) goto out; - } mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ @@ -1568,7 +1593,7 @@ struct xt_table *xt_register_table(struct net *net, /* Simplifies replace_table code. */ table->private = bootstrap; - if (!xt_replace_table(table, 0, newinfo, &ret)) + if (!do_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; @@ -1577,34 +1602,122 @@ struct xt_table *xt_register_table(struct net *net, /* save number of initial entries */ private->initial_entries = private->number; + if (ops) { + int i; + + for (i = 0; i < num_ops; i++) + ops[i].priv = table; + + ret = nf_register_net_hooks(net, ops, num_ops); + if (ret != 0) { + mutex_unlock(&xt[table->af].mutex); + /* nf_register_net_hooks() might have published a + * base chain before internal error unwind. + */ + synchronize_rcu(); + goto out; + } + + table->ops = ops; + } + + audit_log_nfcfg(table->name, table->af, private->number, + AUDIT_XT_OP_REGISTER, GFP_KERNEL); + list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); - kfree(table); out: + kfree(table); + kfree(ops); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); -void *xt_unregister_table(struct xt_table *table) +/** + * xt_unregister_table_pre_exit - pre-shutdown unregister of a table + * @net: network namespace + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Unregisters the specified netfilter table from the given network namespace + * and also unregisters the hooks from netfilter core: no new packets will be + * processed. + * + * This must be called prior to xt_unregister_table_exit() from the pernet + * .pre_exit callback. After this call, the table is no longer visible to + * the get/setsockopt path. In case of rmmod, module exit path must have + * called xt_unregister_template() prior to unregistering pernet ops to + * prevent re-instantiation of the table. + * + * See also: xt_unregister_table_exit() + */ +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) { - struct xt_table_info *private; + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t; - mutex_lock(&xt[table->af].mutex); - private = table->private; - list_del(&table->list); - mutex_unlock(&xt[table->af].mutex); - audit_log_nfcfg(table->name, table->af, private->number, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); - kfree(table->ops); - kfree(table); + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_net->tables[af], list) { + if (strcmp(t->name, name) == 0) { + list_move(&t->list, &xt_net->dead_tables[af]); + mutex_unlock(&xt[af].mutex); - return private; + if (t->ops) /* nat table registers with nat core, t->ops is NULL. */ + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; + } + } + mutex_unlock(&xt[af].mutex); } -EXPORT_SYMBOL_GPL(xt_unregister_table); +EXPORT_SYMBOL(xt_unregister_table_pre_exit); + +/** + * xt_unregister_table_exit - remove a table during namespace teardown + * @net: the network namespace from which to unregister the table + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Completes the unregister process for a table. This must be called from + * the pernet ops .exit callback. This is the second stage after + * xt_unregister_table_pre_exit(). + * + * pair with xt_unregister_table_pre_exit() during namespace shutdown. + * + * Return: the unregistered table or NULL if the table was never + * instantiated. The caller needs to kfree() the table after it + * has removed the family specific matches/targets. + */ +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name) +{ + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *table; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(table, &xt_net->dead_tables[af], list) { + struct nf_hook_ops *ops = NULL; + + if (strcmp(table->name, name) != 0) + continue; + + list_del(&table->list); + + audit_log_nfcfg(table->name, table->af, table->private->number, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + swap(table->ops, ops); + mutex_unlock(&xt[af].mutex); + + kfree(ops); + return table; + } + mutex_unlock(&xt[af].mutex); + + return NULL; +} +EXPORT_SYMBOL_GPL(xt_unregister_table_exit); #endif #ifdef CONFIG_PROC_FS @@ -2051,8 +2164,10 @@ static int __net_init xt_net_init(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { INIT_LIST_HEAD(&xt_net->tables[i]); + INIT_LIST_HEAD(&xt_net->dead_tables[i]); + } return 0; } @@ -2061,8 +2176,10 @@ static void __net_exit xt_net_exit(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); + WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i])); + } } static struct pernet_operations xt_net_ops = { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d251d894afd4..0da39eaed255 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1972,8 +1972,10 @@ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + kfree_skb(skb); return -EINVAL; + } group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group); @@ -1986,8 +1988,10 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + kfree_skb(skb); return; + } group = family->mcgrp_offset + group; nlmsg_notify(sk, skb, info->snd_portid, group, diff --git a/net/rds/message.c b/net/rds/message.c index 25fedcb3cd00..7feb0eb6537d 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -448,6 +448,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter * for (i = 0; i < rm->data.op_nents; i++) put_page(sg_page(&rm->data.op_sg[i])); + rm->data.op_nents = 0; mmp = &rm->data.op_mmp_znotifier->z_mmp; mm_unaccount_pinned_pages(mmp); ret = -EFAULT; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index fdd683261226..2b19b252225e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -334,7 +334,9 @@ bool rxrpc_input_call_event(struct rxrpc_call *call) if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.securityIndex != 0 && - skb_cloned(skb)) { + (skb_cloned(skb) || + skb_has_frag_list(skb) || + skb_has_shared_frag(skb))) { /* Unshare the packet so that it can be * modified by in-place decryption. */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index a2130d25aaa9..442414d90ba1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -245,7 +245,8 @@ static int rxrpc_verify_response(struct rxrpc_connection *conn, { int ret; - if (skb_cloned(skb)) { + if (skb_cloned(skb) || skb_has_frag_list(skb) || + skb_has_shared_frag(skb)) { /* Copy the packet if shared so that we can do in-place * decryption. */ diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 2cfa0fd92829..b952353ec2a5 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -243,6 +243,20 @@ static struct sk_buff *cbs_dequeue(struct Qdisc *sch) return q->dequeue(sch); } +static void cbs_reset(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + /* Nothing to do if we couldn't create the underlying qdisc */ + if (!q->qdisc) + return; + + qdisc_reset(q->qdisc); + qdisc_watchdog_cancel(&q->watchdog); + q->credits = 0; + q->last = 0; +} + static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, }; @@ -540,7 +554,7 @@ static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .dequeue = cbs_dequeue, .peek = qdisc_peek_dequeued, .init = cbs_init, - .reset = qdisc_reset_queue, + .reset = cbs_reset, .destroy = cbs_destroy, .change = cbs_change, .dump = cbs_dump, diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index c6416f09dddd..d4173fa52e48 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -938,6 +938,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, int err; sch->flags |= TCQ_F_DEQUEUE_DROPS; + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1), extack); @@ -950,8 +952,6 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, q->sch = sch; dualpi2_reset_default(sch); - hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED_SOFT); if (opt && nla_len(opt)) { err = dualpi2_change(sch, opt, extack); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 58d0d9747f0b..1d2568bb6bc2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1986,6 +1986,15 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); + + /* sctp_sendmsg_to_asoc() may have released the socket + * lock (sctp_wait_for_sndbuf), during which other + * associations on ep->asocs could have been peeled + * off or freed. @asoc itself is revalidated by the + * base.dead and base.sk checks in sctp_wait_for_sndbuf, + * so re-derive the cached cursor from it. + */ + tmp = list_next_entry(asoc, asocs); } goto out_unlock; diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 94bc9c7382ea..b1c65110f04d 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -21,6 +21,8 @@ #define NET_SHAPER_ID_UNSPEC NET_SHAPER_ID_MASK +static_assert(NET_SHAPER_ID_UNSPEC == NET_SHAPER_MAX_HANDLE_ID + 1); + struct net_shaper_hierarchy { struct xarray shapers; }; @@ -90,6 +92,12 @@ static int net_shaper_handle_size(void) nla_total_size(sizeof(u32))); } +static int net_shaper_group_reply_size(void) +{ + return nla_total_size(sizeof(u32)) + /* NET_SHAPER_A_IFINDEX */ + net_shaper_handle_size(); /* NET_SHAPER_A_HANDLE */ +} + static int net_shaper_fill_binding(struct sk_buff *msg, const struct net_shaper_binding *binding, u32 type) @@ -275,11 +283,13 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle, parent->id = 0; } -/* - * MARK_0 is already in use due to XA_FLAGS_ALLOC, can't reuse such flag as - * it's cleared by xa_store(). +/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on + * an entry only after the device-side configuration has completed + * successfully (see net_shaper_commit()). Lookups and dumps must filter on + * this mark to avoid exposing tentative entries inserted by + * net_shaper_pre_insert() while the driver call is still in flight. */ -#define NET_SHAPER_NOT_VALID XA_MARK_1 +#define NET_SHAPER_VALID XA_MARK_1 static struct net_shaper * net_shaper_lookup(struct net_shaper_binding *binding, @@ -289,10 +299,14 @@ net_shaper_lookup(struct net_shaper_binding *binding, struct net_shaper_hierarchy *hierarchy; hierarchy = net_shaper_hierarchy_rcu(binding); - if (!hierarchy || xa_get_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID)) + if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index, + NET_SHAPER_VALID)) return NULL; + /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is + * valid, its contents must be visible too. + */ + smp_rmb(); return xa_load(&hierarchy->shapers, index); } @@ -348,7 +362,7 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding, handle->id == NET_SHAPER_ID_UNSPEC) { u32 min, max; - handle->id = NET_SHAPER_ID_MASK - 1; + handle->id = NET_SHAPER_MAX_HANDLE_ID; max = net_shaper_handle_to_index(handle); handle->id = 0; min = net_shaper_handle_to_index(handle); @@ -370,13 +384,10 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding, goto free_id; } - /* Mark 'tentative' shaper inside the hierarchy container. - * xa_set_mark is a no-op if the previous store fails. + /* Insert as 'tentative' (no VALID mark). The mark will be set by + * net_shaper_commit() once the driver-side configuration succeeds. */ - xa_lock(&hierarchy->shapers); - prev = __xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_NOT_VALID); - xa_unlock(&hierarchy->shapers); + prev = xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); if (xa_err(prev)) { NL_SET_ERR_MSG(extack, "Can't insert shaper into device store"); kfree_rcu(cur, rcu); @@ -413,9 +424,9 @@ static void net_shaper_commit(struct net_shaper_binding *binding, /* Successful update: drop the tentative mark * and update the hierarchy container. */ - __xa_clear_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID); *cur = shapers[i]; + smp_wmb(); + __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); } xa_unlock(&hierarchy->shapers); } @@ -431,8 +442,9 @@ static void net_shaper_rollback(struct net_shaper_binding *binding) return; xa_lock(&hierarchy->shapers); - xa_for_each_marked(&hierarchy->shapers, index, cur, - NET_SHAPER_NOT_VALID) { + xa_for_each(&hierarchy->shapers, index, cur) { + if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID)) + continue; __xa_erase(&hierarchy->shapers, index); kfree(cur); } @@ -465,10 +477,21 @@ static int net_shaper_parse_handle(const struct nlattr *attr, * shaper (any other value). */ id_attr = tb[NET_SHAPER_A_HANDLE_ID]; - if (id_attr) + if (id_attr) { id = nla_get_u32(id_attr); - else if (handle->scope == NET_SHAPER_SCOPE_NODE) + } else if (handle->scope == NET_SHAPER_SCOPE_NODE) { id = NET_SHAPER_ID_UNSPEC; + } else if (handle->scope == NET_SHAPER_SCOPE_QUEUE) { + NL_SET_ERR_ATTR_MISS(info->extack, attr, + NET_SHAPER_A_HANDLE_ID); + return -EINVAL; + } + + if (id && handle->scope == NET_SHAPER_SCOPE_NETDEV) { + NL_SET_ERR_MSG_ATTR(info->extack, id_attr, + "Netdev scope is a singleton, must use ID 0"); + return -EINVAL; + } handle->id = id; return 0; @@ -836,7 +859,12 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, goto out_unlock; for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, - U32_MAX, XA_PRESENT)); ctx->start_index++) { + U32_MAX, NET_SHAPER_VALID)); + ctx->start_index++) { + /* Pairs with smp_wmb() in net_shaper_commit(): the entry + * is marked VALID, so its contents must be visible too. + */ + smp_rmb(); ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; @@ -932,6 +960,46 @@ static int net_shaper_handle_cmp(const struct net_shaper_handle *a, return memcmp(a, b, sizeof(*a)); } +static int net_shaper_parse_leaves(struct net_shaper_binding *binding, + struct genl_info *info, + const struct net_shaper *node, + struct net_shaper *leaves, + int leaves_count) +{ + struct nlattr *attr; + int i, j, ret, rem; + + i = 0; + nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (WARN_ON_ONCE(i >= leaves_count)) + return -EINVAL; + + ret = net_shaper_parse_leaf(binding, attr, info, + node, &leaves[i]); + if (ret) + return ret; + + /* Reject duplicates */ + for (j = 0; j < i; j++) { + if (net_shaper_handle_cmp(&leaves[i].handle, + &leaves[j].handle)) + continue; + + NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr, + "Duplicate leaf shaper %d:%d", + leaves[i].handle.scope, + leaves[i].handle.id); + return -EINVAL; + } + + i++; + } + + return 0; +} + static int net_shaper_parent_from_leaves(int leaves_count, const struct net_shaper *leaves, struct net_shaper *node, @@ -964,15 +1032,22 @@ static int __net_shaper_group(struct net_shaper_binding *binding, int i, ret; if (node->handle.scope == NET_SHAPER_SCOPE_NODE) { + struct net_shaper *cur = NULL; + new_node = node->handle.id == NET_SHAPER_ID_UNSPEC; - if (!new_node && !net_shaper_lookup(binding, &node->handle)) { - /* The related attribute is not available when - * reaching here from the delete() op. - */ - NL_SET_ERR_MSG_FMT(extack, "Node shaper %d:%d does not exists", - node->handle.scope, node->handle.id); - return -ENOENT; + if (!new_node) { + cur = net_shaper_lookup(binding, &node->handle); + if (!cur) { + /* The related attribute is not available + * when reaching here from the delete() op. + */ + NL_SET_ERR_MSG_FMT(extack, + "Node shaper %d:%d does not exist", + node->handle.scope, + node->handle.id); + return -ENOENT; + } } /* When unspecified, the node parent scope is inherited from @@ -986,6 +1061,15 @@ static int __net_shaper_group(struct net_shaper_binding *binding, return ret; } + if (cur && net_shaper_handle_cmp(&cur->parent, + &node->parent)) { + NL_SET_ERR_MSG_FMT(extack, + "Cannot reparent node shaper %d:%d", + node->handle.scope, + node->handle.id); + return -EOPNOTSUPP; + } + } else { net_shaper_default_parent(&node->handle, &node->parent); } @@ -1162,7 +1246,7 @@ static int net_shaper_group_send_reply(struct net_shaper_binding *binding, free_msg: /* Should never happen as msg is pre-allocated with enough space. */ WARN_ONCE(true, "calculated message payload length (%d)", - net_shaper_handle_size()); + net_shaper_group_reply_size()); nlmsg_free(msg); return -EMSGSIZE; } @@ -1172,10 +1256,9 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) struct net_shaper **old_nodes, *leaves, node = {}; struct net_shaper_hierarchy *hierarchy; struct net_shaper_binding *binding; - int i, ret, rem, leaves_count; + int i, ret, leaves_count; int old_nodes_count = 0; struct sk_buff *msg; - struct nlattr *attr; if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_LEAVES)) return -EINVAL; @@ -1203,26 +1286,19 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_leaves; - i = 0; - nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, - genlmsg_data(info->genlhdr), - genlmsg_len(info->genlhdr), rem) { - if (WARN_ON_ONCE(i >= leaves_count)) - goto free_leaves; - - ret = net_shaper_parse_leaf(binding, attr, info, - &node, &leaves[i]); - if (ret) - goto free_leaves; - i++; - } + ret = net_shaper_parse_leaves(binding, info, &node, + leaves, leaves_count); + if (ret) + goto free_leaves; /* Prepare the msg reply in advance, to avoid device operation * rollback on allocation failure. */ - msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL); - if (!msg) + msg = genlmsg_new(net_shaper_group_reply_size(), GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; goto free_leaves; + } hierarchy = net_shaper_hierarchy_setup(binding); if (!hierarchy) { diff --git a/net/shaper/shaper_nl_gen.c b/net/shaper/shaper_nl_gen.c index 9b29be3ef19a..76eff85ec66d 100644 --- a/net/shaper/shaper_nl_gen.c +++ b/net/shaper/shaper_nl_gen.c @@ -11,10 +11,15 @@ #include +/* Integer value ranges */ +static const struct netlink_range_validation net_shaper_a_handle_id_range = { + .max = NET_SHAPER_MAX_HANDLE_ID, +}; + /* Common nested types */ const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1] = { [NET_SHAPER_A_HANDLE_SCOPE] = NLA_POLICY_MAX(NLA_U32, 3), - [NET_SHAPER_A_HANDLE_ID] = { .type = NLA_U32, }, + [NET_SHAPER_A_HANDLE_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &net_shaper_a_handle_id_range), }; const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1] = { diff --git a/net/shaper/shaper_nl_gen.h b/net/shaper/shaper_nl_gen.h index 42c46c52c775..2406652a9014 100644 --- a/net/shaper/shaper_nl_gen.h +++ b/net/shaper/shaper_nl_gen.h @@ -12,6 +12,8 @@ #include +#define NET_SHAPER_MAX_HANDLE_ID 67108862 + /* Common nested types */ extern const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1]; extern const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1]; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 185dbed7de5d..dffbd529762d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1400,7 +1400,8 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc, int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { - if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { + if (ini->ism_dev[i] && + ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } @@ -3054,18 +3055,17 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname, smc = smc_sk(sk); + /* pre-fetch user data outside the lock */ + if (optname == SMC_LIMIT_HS) { + if (optlen < sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + } + lock_sock(sk); switch (optname) { case SMC_LIMIT_HS: - if (optlen < sizeof(int)) { - rc = -EINVAL; - break; - } - if (copy_from_sockptr(&val, optval, sizeof(int))) { - rc = -EFAULT; - break; - } - smc->limit_smc_hs = !!val; rc = 0; break; diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h index a9a6e3c1113a..53da84f57fd6 100644 --- a/net/smc/smc_tracepoint.h +++ b/net/smc/smc_tracepoint.h @@ -51,7 +51,7 @@ DECLARE_EVENT_CLASS(smc_msg_event, __field(const void *, smc) __field(u64, net_cookie) __field(size_t, len) - __string(name, smc->conn.lnk->ibname) + __string(name, smc->conn.lnk ? smc->conn.lnk->ibname : "") ), TP_fast_assign( diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2590e855f6a5..3bfdaf5e64f5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -789,23 +789,33 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); + /* msg_pl->sg.data is a ring; data[MAX+1] is reserved for the wrap + * link (frags won't use it). 'i' is now the last filled entry: + * + * i end start + * v v v [ rsv ] + * [ d ][ d ][ ][ ]...[ ][ d ][ d ][ d ][chain] + * ^ END v + * `-----------------------------------------' + * + * Note that SGL does not allow chain-after-chain, so for TLS 1.3, + * we must make sure we don't create the wrap entry and then chain + * link to content_type immediately at index 0. + */ + if (i < msg_pl->sg.start) + sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data), + msg_pl->sg.data); + rec->content_type = record_type; if (prot->version == TLS_1_3_VERSION) { /* Add content type to end of message. No padding added */ sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); sg_mark_end(&rec->sg_content_type); - sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, - &rec->sg_content_type); + sg_chain(msg_pl->sg.data, i + 2, &rec->sg_content_type); } else { sg_mark_end(sk_msg_elem(msg_pl, i)); } - if (msg_pl->sg.end < msg_pl->sg.start) { - sg_chain(&msg_pl->sg.data[msg_pl->sg.start], - MAX_SKB_FRAGS - msg_pl->sg.start + 1, - msg_pl->sg.data); - } - i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 9b8014516f4f..989cc252d3d3 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -136,27 +136,6 @@ static void virtio_transport_init_hdr(struct sk_buff *skb, hdr->fwd_cnt = cpu_to_le32(0); } -static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb, - void *dst, - size_t len) -{ - struct iov_iter iov_iter = { 0 }; - struct kvec kvec; - size_t to_copy; - - kvec.iov_base = dst; - kvec.iov_len = len; - - iov_iter.iter_type = ITER_KVEC; - iov_iter.kvec = &kvec; - iov_iter.nr_segs = 1; - - to_copy = min_t(size_t, len, skb->len); - - skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, - &iov_iter, to_copy); -} - /* Packet capture */ static struct sk_buff *virtio_transport_build_skb(void *opaque) { @@ -166,12 +145,12 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct sk_buff *skb; size_t payload_len; - /* A packet could be split to fit the RX buffer, so we can retrieve - * the payload length from the header and the buffer pointer taking - * care of the offset in the original packet. + /* A packet could be split to fit the RX buffer, so we use + * the payload length from the header, which has been updated + * by the sender to reflect the fragment size. */ pkt_hdr = virtio_vsock_hdr(pkt); - payload_len = pkt->len; + payload_len = le32_to_cpu(pkt_hdr->len); skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); @@ -214,12 +193,18 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { - if (skb_is_nonlinear(pkt)) { - void *data = skb_put(skb, payload_len); + struct iov_iter iov_iter; + struct kvec kvec; + void *data = skb_put(skb, payload_len); - virtio_transport_copy_nonlinear_skb(pkt, data, payload_len); - } else { - skb_put_data(skb, pkt->data, payload_len); + kvec.iov_base = data; + kvec.iov_len = payload_len; + iov_iter_kvec(&iov_iter, ITER_DEST, &kvec, 1, payload_len); + + if (skb_copy_datagram_iter(pkt, VIRTIO_VSOCK_SKB_CB(pkt)->offset, + &iov_iter, payload_len)) { + kfree_skb(skb); + return NULL; } } diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index afa457506274..3bff346308d0 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -184,6 +184,10 @@ static long xsk_map_update_elem(struct bpf_map *map, void *key, void *value, } xs = (struct xdp_sock *)sock->sk; + if (!READ_ONCE(xs->rx)) { + sockfd_put(sock); + return -ENOBUFS; + } map_entry = &m->xsk_map[i]; node = xsk_map_node_alloc(m, map_entry); diff --git a/rust/Makefile b/rust/Makefile index b361bfedfdf0..b9e9f512cec3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -403,6 +403,8 @@ BINDGEN_TARGET_x86 := x86_64-linux-gnu BINDGEN_TARGET_arm64 := aarch64-linux-gnu BINDGEN_TARGET_arm := arm-linux-gnueabi BINDGEN_TARGET_loongarch := loongarch64-linux-gnusf +# This is only for i386 UM builds, which need the 32-bit target not -m32 +BINDGEN_TARGET_i386 := i386-linux-gnu BINDGEN_TARGET_um := $(BINDGEN_TARGET_$(SUBARCH)) BINDGEN_TARGET := $(BINDGEN_TARGET_$(SRCARCH)) diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index adbafe8db54d..403fc35353c7 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -119,13 +119,20 @@ pub fn new(dev: &device::Device, data: impl PinInit) -> Result()); + // Use a temporary vtable without a `release` callback until `data` is initialized, so + // init failure can release the DRM device without dropping uninitialized fields. + let alloc_vtable = bindings::drm_driver { + release: None, + ..Self::VTABLE + }; + // SAFETY: - // - `VTABLE`, as a `const` is pinned to the read-only section of the compilation, + // - `alloc_vtable` reference remains valid until no longer used, // - `dev` is valid by its type invarants, let raw_drm: *mut Self = unsafe { bindings::__drm_dev_alloc( dev.as_raw(), - &Self::VTABLE, + &alloc_vtable, layout.size(), mem::offset_of!(Self, dev), ) @@ -133,6 +140,10 @@ pub fn new(dev: &device::Device, data: impl PinInit) -> Result) -> Result, size: usize, args: T::Args) -> Result` is always treated as pinned. let ptr = KBox::into_raw(unsafe { Pin::into_inner_unchecked(obj) }); diff --git a/rust/kernel/drm/gem/shmem.rs b/rust/kernel/drm/gem/shmem.rs index d025fb035195..e1b648920d2f 100644 --- a/rust/kernel/drm/gem/shmem.rs +++ b/rust/kernel/drm/gem/shmem.rs @@ -19,10 +19,8 @@ }, error::to_result, prelude::*, - types::{ - ARef, - Opaque, // - }, // + sync::aref::ARef, + types::Opaque, // }; use core::{ ops::{ diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index daa3f1c6466e..487ee0013faf 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -249,22 +249,6 @@ fn init_fields( }); // Again span for better diagnostics let write = quote_spanned!(ident.span()=> ::core::ptr::write); - // NOTE: the field accessor ensures that the initialized field is properly aligned. - // Unaligned fields will cause the compiler to emit E0793. We do not support - // unaligned fields since `Init::__init` requires an aligned pointer; the call to - // `ptr::write` below has the same requirement. - let accessor = if pinned { - let project_ident = format_ident!("__project_{ident}"); - quote! { - // SAFETY: TODO - unsafe { #data.#project_ident(&mut (*#slot).#ident) } - } - } else { - quote! { - // SAFETY: TODO - unsafe { &mut (*#slot).#ident } - } - }; quote! { #(#attrs)* { @@ -272,51 +256,31 @@ fn init_fields( // SAFETY: TODO unsafe { #write(&raw mut (*#slot).#ident, #value_ident) }; } - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; } } InitializerKind::Init { ident, value, .. } => { // Again span for better diagnostics let init = format_ident!("init", span = value.span()); - // NOTE: the field accessor ensures that the initialized field is properly aligned. - // Unaligned fields will cause the compiler to emit E0793. We do not support - // unaligned fields since `Init::__init` requires an aligned pointer; the call to - // `ptr::write` below has the same requirement. - let (value_init, accessor) = if pinned { - let project_ident = format_ident!("__project_{ident}"); - ( - quote! { - // SAFETY: - // - `slot` is valid, because we are inside of an initializer closure, we - // return when an error/panic occurs. - // - We also use `#data` to require the correct trait (`Init` or `PinInit`) - // for `#ident`. - unsafe { #data.#ident(&raw mut (*#slot).#ident, #init)? }; - }, - quote! { - // SAFETY: TODO - unsafe { #data.#project_ident(&mut (*#slot).#ident) } - }, - ) + let value_init = if pinned { + quote! { + // SAFETY: + // - `slot` is valid, because we are inside of an initializer closure, we + // return when an error/panic occurs. + // - We also use `#data` to require the correct trait (`Init` or `PinInit`) + // for `#ident`. + unsafe { #data.#ident(&raw mut (*#slot).#ident, #init)? }; + } } else { - ( - quote! { - // SAFETY: `slot` is valid, because we are inside of an initializer - // closure, we return when an error/panic occurs. - unsafe { - ::pin_init::Init::__init( - #init, - &raw mut (*#slot).#ident, - )? - }; - }, - quote! { - // SAFETY: TODO - unsafe { &mut (*#slot).#ident } - }, - ) + quote! { + // SAFETY: `slot` is valid, because we are inside of an initializer + // closure, we return when an error/panic occurs. + unsafe { + ::pin_init::Init::__init( + #init, + &raw mut (*#slot).#ident, + )? + }; + } }; quote! { #(#attrs)* @@ -324,9 +288,6 @@ fn init_fields( let #init = #value; #value_init } - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; } } InitializerKind::Code { block: value, .. } => quote! { @@ -339,18 +300,41 @@ fn init_fields( if let Some(ident) = kind.ident() { // `mixed_site` ensures that the guard is not accessible to the user-controlled code. let guard = format_ident!("__{ident}_guard", span = Span::mixed_site()); + + // NOTE: The reference is derived from the guard so that it only lives as long as the + // guard does and cannot escape the scope. If it's created via `&mut (*#slot).#ident` + // like the unaligned field guard, it will become effectively `'static`. + let accessor = if pinned { + let project_ident = format_ident!("__project_{ident}"); + quote! { + // SAFETY: the initialization is pinned. + unsafe { #data.#project_ident(#guard.let_binding()) } + } + } else { + quote! { + #guard.let_binding() + } + }; + res.extend(quote! { #(#cfgs)* - // Create the drop guard: + // Create the drop guard. // - // We rely on macro hygiene to make it impossible for users to access this local - // variable. - // SAFETY: We forget the guard later when initialization has succeeded. - let #guard = unsafe { + // SAFETY: + // - `&raw mut (*slot).#ident` is valid. + // - `make_field_check` checks that `&raw mut (*slot).#ident` is properly aligned. + // - `(*slot).#ident` has been initialized above. + // - We only need the ownership to the pointee back when initialization has + // succeeded, where we `forget` the guard. + let mut #guard = unsafe { ::pin_init::__internal::DropGuard::new( &raw mut (*slot).#ident ) }; + + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; }); guards.push(guard); guard_attrs.push(cfgs); @@ -367,49 +351,49 @@ fn init_fields( } } -/// Generate the check for ensuring that every field has been initialized. +/// Generate the check for ensuring that every field has been initialized and aligned. fn make_field_check( fields: &Punctuated, init_kind: InitKind, path: &Path, ) -> TokenStream { - let field_attrs = fields + let field_attrs: Vec<_> = fields .iter() - .filter_map(|f| f.kind.ident().map(|_| &f.attrs)); - let field_name = fields.iter().filter_map(|f| f.kind.ident()); - match init_kind { - InitKind::Normal => quote! { - // We use unreachable code to ensure that all fields have been mentioned exactly once, - // this struct initializer will still be type-checked and complain with a very natural - // error message if a field is forgotten/mentioned more than once. - #[allow(unreachable_code, clippy::diverging_sub_expression)] - // SAFETY: this code is never executed. - let _ = || unsafe { - ::core::ptr::write(slot, #path { - #( - #(#field_attrs)* - #field_name: ::core::panic!(), - )* - }) - }; - }, - InitKind::Zeroing => quote! { - // We use unreachable code to ensure that all fields have been mentioned at most once. - // Since the user specified `..Zeroable::zeroed()` at the end, all missing fields will - // be zeroed. This struct initializer will still be type-checked and complain with a - // very natural error message if a field is mentioned more than once, or doesn't exist. - #[allow(unreachable_code, clippy::diverging_sub_expression, unused_assignments)] - // SAFETY: this code is never executed. - let _ = || unsafe { - ::core::ptr::write(slot, #path { - #( - #(#field_attrs)* - #field_name: ::core::panic!(), - )* - ..::core::mem::zeroed() - }) - }; - }, + .filter_map(|f| f.kind.ident().map(|_| &f.attrs)) + .collect(); + let field_name: Vec<_> = fields.iter().filter_map(|f| f.kind.ident()).collect(); + let zeroing_trailer = match init_kind { + InitKind::Normal => None, + InitKind::Zeroing => Some(quote! { + ..::core::mem::zeroed() + }), + }; + quote! { + #[allow(unreachable_code, clippy::diverging_sub_expression)] + // We use unreachable code to perform field checks. They're still checked by the compiler. + // SAFETY: this code is never executed. + let _ = || unsafe { + // Create references to ensure that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` for value-initialization case has the same requirement. + #( + #(#field_attrs)* + let _ = &(*slot).#field_name; + )* + + // If the zeroing trailer is not present, this checks that all fields have been + // mentioned exactly once. If the zeroing trailer is present, all missing fields will be + // zeroed, so this checks that all fields have been mentioned at most once. The use of + // struct initializer will still generate very natural error messages for any misuse. + ::core::ptr::write(slot, #path { + #( + #(#field_attrs)* + #field_name: ::core::panic!(), + )* + #zeroing_trailer + }) + }; } } diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs index 90adbdc1893b..5720a621aed7 100644 --- a/rust/pin-init/src/__internal.rs +++ b/rust/pin-init/src/__internal.rs @@ -238,32 +238,42 @@ struct Foo { /// When a value of this type is dropped, it drops a `T`. /// /// Can be forgotten to prevent the drop. +/// +/// # Invariants +/// +/// - `ptr` is valid and properly aligned. +/// - `*ptr` is initialized and owned by this guard. pub struct DropGuard { ptr: *mut T, } impl DropGuard { - /// Creates a new [`DropGuard`]. It will [`ptr::drop_in_place`] `ptr` when it gets dropped. + /// Creates a drop guard and transfer the ownership of the pointer content. + /// + /// The ownership is only relinguished if the guard is forgotten via [`core::mem::forget`]. /// /// # Safety /// - /// `ptr` must be a valid pointer. - /// - /// It is the callers responsibility that `self` will only get dropped if the pointee of `ptr`: - /// - has not been dropped, - /// - is not accessible by any other means, - /// - will not be dropped by any other means. + /// - `ptr` is valid and properly aligned. + /// - `*ptr` is initialized, and the ownership is transferred to this guard. #[inline] pub unsafe fn new(ptr: *mut T) -> Self { + // INVARIANT: By safety requirement. Self { ptr } } + + /// Create a let binding for accessor use. + #[inline] + pub fn let_binding(&mut self) -> &mut T { + // SAFETY: Per type invariant. + unsafe { &mut *self.ptr } + } } impl Drop for DropGuard { #[inline] fn drop(&mut self) { - // SAFETY: A `DropGuard` can only be constructed using the unsafe `new` function - // ensuring that this operation is safe. + // SAFETY: `self.ptr` is valid, properly aligned and `*self.ptr` is owned by this guard. unsafe { ptr::drop_in_place(self.ptr) } } } diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index d1f16d7f684d..0babb8992181 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -312,8 +312,6 @@ int security_context_to_sid_default(const char *scontext, u32 scontext_len, int security_context_to_sid_force(const char *scontext, u32 scontext_len, u32 *sid); -int security_get_user_sids(u32 fromsid, const char *username, u32 **sids, u32 *nel); - int security_port_sid(u8 protocol, u16 port, u32 *out_sid); int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 83aa765a09f9..25ca7d714014 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -76,7 +76,6 @@ struct selinux_fs_info { int *bool_pending_values; struct dentry *class_dir; unsigned long last_class_ino; - bool policy_opened; unsigned long last_ino; struct super_block *sb; }; @@ -272,35 +271,13 @@ static ssize_t sel_write_disable(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *page; - ssize_t length; - int new_value; - - if (count >= PAGE_SIZE) - return -ENOMEM; - - /* No partial writes. */ - if (*ppos != 0) - return -EINVAL; - - page = memdup_user_nul(buf, count); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (sscanf(page, "%d", &new_value) != 1) { - length = -EINVAL; - goto out; - } - length = count; - - if (new_value) { - pr_err("SELinux: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable\n"); - pr_err("SELinux: Runtime disable is not supported, use selinux=0 on the kernel cmdline.\n"); - } - -out: - kfree(page); - return length; + /* + * Setting disable is no longer supported, see + * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable + */ + pr_err_once("SELinux: %s (%d) wrote to disable. This is no longer supported.\n", + current->comm, current->pid); + return count; } static const struct file_operations sel_disable_ops = { @@ -362,44 +339,31 @@ struct policy_load_memory { static int sel_open_policy(struct inode *inode, struct file *filp) { - struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = NULL; int rc; - BUG_ON(filp->private_data); - - mutex_lock(&selinux_state.policy_mutex); - rc = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL); if (rc) - goto err; + return rc; - rc = -EBUSY; - if (fsi->policy_opened) - goto err; - - rc = -ENOMEM; plm = kzalloc_obj(*plm); if (!plm) - goto err; + return -ENOMEM; + mutex_lock(&selinux_state.policy_mutex); rc = security_read_policy(&plm->data, &plm->len); if (rc) goto err; - if ((size_t)i_size_read(inode) != plm->len) { inode_lock(inode); i_size_write(inode, plm->len); inode_unlock(inode); } - - fsi->policy_opened = 1; + mutex_unlock(&selinux_state.policy_mutex); filp->private_data = plm; - mutex_unlock(&selinux_state.policy_mutex); - return 0; err: mutex_unlock(&selinux_state.policy_mutex); @@ -412,13 +376,8 @@ static int sel_open_policy(struct inode *inode, struct file *filp) static int sel_release_policy(struct inode *inode, struct file *filp) { - struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = filp->private_data; - BUG_ON(!plm); - - fsi->policy_opened = 0; - vfree(plm->data); kfree(plm); @@ -594,34 +553,31 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, if (!count) return -EINVAL; - mutex_lock(&selinux_state.policy_mutex); - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__LOAD_POLICY, NULL); if (length) - goto out; + return length; data = vmalloc(count); - if (!data) { - length = -ENOMEM; - goto out; - } + if (!data) + return -ENOMEM; if (copy_from_user(data, buf, count) != 0) { length = -EFAULT; goto out; } + mutex_lock(&selinux_state.policy_mutex); length = security_load_policy(data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); - goto out; + goto out_unlock; } fsi = file_inode(file)->i_sb->s_fs_info; length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n"); selinux_policy_cancel(&load_state); - goto out; + goto out_unlock; } selinux_policy_commit(&load_state); @@ -631,8 +587,9 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); -out: +out_unlock: mutex_unlock(&selinux_state.policy_mutex); +out: vfree(data); return length; } @@ -689,46 +646,13 @@ static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf, static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *page; - ssize_t length; - unsigned int new_value; - - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, - SECCLASS_SECURITY, SECURITY__SETCHECKREQPROT, - NULL); - if (length) - return length; - - if (count >= PAGE_SIZE) - return -ENOMEM; - - /* No partial writes. */ - if (*ppos != 0) - return -EINVAL; - - page = memdup_user_nul(buf, count); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (sscanf(page, "%u", &new_value) != 1) { - length = -EINVAL; - goto out; - } - length = count; - - if (new_value) { - char comm[sizeof(current->comm)]; - - strscpy(comm, current->comm); - pr_err("SELinux: %s (%d) set checkreqprot to 1. This is no longer supported.\n", - comm, current->pid); - } - - selinux_ima_measure_state(); - -out: - kfree(page); - return length; + /* + * Setting checkreqprot is no longer supported, see + * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-checkreqprot + */ + pr_err_once("SELinux: %s (%d) wrote to checkreqprot. This is no longer supported.\n", + current->comm, current->pid); + return count; } static const struct file_operations sel_checkreqprot_ops = { .read = sel_read_checkreqprot, @@ -1073,69 +997,11 @@ static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size) static ssize_t sel_write_user(struct file *file, char *buf, size_t size) { - char *con = NULL, *user = NULL, *ptr; - u32 sid, *sids = NULL; - ssize_t length; - char *newcon; - int rc; - u32 i, len, nsids; - - pr_warn_ratelimited("SELinux: %s (%d) wrote to /sys/fs/selinux/user!" - " This will not be supported in the future; please update your" - " userspace.\n", current->comm, current->pid); - ssleep(5); - - length = avc_has_perm(current_sid(), SECINITSID_SECURITY, - SECCLASS_SECURITY, SECURITY__COMPUTE_USER, - NULL); - if (length) - goto out; - - length = -ENOMEM; - con = kzalloc(size + 1, GFP_KERNEL); - if (!con) - goto out; - - length = -ENOMEM; - user = kzalloc(size + 1, GFP_KERNEL); - if (!user) - goto out; - - length = -EINVAL; - if (sscanf(buf, "%s %s", con, user) != 2) - goto out; - - length = security_context_str_to_sid(con, &sid, GFP_KERNEL); - if (length) - goto out; - - length = security_get_user_sids(sid, user, &sids, &nsids); - if (length) - goto out; - - length = sprintf(buf, "%u", nsids) + 1; - ptr = buf + length; - for (i = 0; i < nsids; i++) { - rc = security_sid_to_context(sids[i], &newcon, &len); - if (rc) { - length = rc; - goto out; - } - if ((length + len) >= SIMPLE_TRANSACTION_LIMIT) { - kfree(newcon); - length = -ERANGE; - goto out; - } - memcpy(ptr, newcon, len); - kfree(newcon); - ptr += len; - length += len; - } -out: - kfree(sids); - kfree(user); - kfree(con); - return length; + pr_err_once("SELinux: %s (%d) wrote to user. This is no longer supported.\n", + current->comm, current->pid); + buf[0] = '0'; + buf[1] = 0; + return 2; } static ssize_t sel_write_member(struct file *file, char *buf, size_t size) diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index e8e7ccbd1e44..143021c5e326 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2746,131 +2746,6 @@ int security_node_sid(u16 domain, return rc; } -#define SIDS_NEL 25 - -/** - * security_get_user_sids - Obtain reachable SIDs for a user. - * @fromsid: starting SID - * @username: username - * @sids: array of reachable SIDs for user - * @nel: number of elements in @sids - * - * Generate the set of SIDs for legal security contexts - * for a given user that can be reached by @fromsid. - * Set *@sids to point to a dynamically allocated - * array containing the set of SIDs. Set *@nel to the - * number of elements in the array. - */ - -int security_get_user_sids(u32 fromsid, - const char *username, - u32 **sids, - u32 *nel) -{ - struct selinux_policy *policy; - struct policydb *policydb; - struct sidtab *sidtab; - struct context *fromcon, usercon; - u32 *mysids = NULL, *mysids2, sid; - u32 i, j, mynel, maxnel = SIDS_NEL; - struct user_datum *user; - struct role_datum *role; - struct ebitmap_node *rnode, *tnode; - int rc; - - *sids = NULL; - *nel = 0; - - if (!selinux_initialized()) - return 0; - - mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); - if (!mysids) - return -ENOMEM; - -retry: - mynel = 0; - rcu_read_lock(); - policy = rcu_dereference(selinux_state.policy); - policydb = &policy->policydb; - sidtab = policy->sidtab; - - context_init(&usercon); - - rc = -EINVAL; - fromcon = sidtab_search(sidtab, fromsid); - if (!fromcon) - goto out_unlock; - - rc = -EINVAL; - user = symtab_search(&policydb->p_users, username); - if (!user) - goto out_unlock; - - usercon.user = user->value; - - ebitmap_for_each_positive_bit(&user->roles, rnode, i) { - role = policydb->role_val_to_struct[i]; - usercon.role = i + 1; - ebitmap_for_each_positive_bit(&role->types, tnode, j) { - usercon.type = j + 1; - - if (mls_setup_user_range(policydb, fromcon, user, - &usercon)) - continue; - - rc = sidtab_context_to_sid(sidtab, &usercon, &sid); - if (rc == -ESTALE) { - rcu_read_unlock(); - goto retry; - } - if (rc) - goto out_unlock; - if (mynel < maxnel) { - mysids[mynel++] = sid; - } else { - rc = -ENOMEM; - maxnel += SIDS_NEL; - mysids2 = kcalloc(maxnel, sizeof(*mysids2), GFP_ATOMIC); - if (!mysids2) - goto out_unlock; - memcpy(mysids2, mysids, mynel * sizeof(*mysids2)); - kfree(mysids); - mysids = mysids2; - mysids[mynel++] = sid; - } - } - } - rc = 0; -out_unlock: - rcu_read_unlock(); - if (rc || !mynel) { - kfree(mysids); - return rc; - } - - rc = -ENOMEM; - mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); - if (!mysids2) { - kfree(mysids); - return rc; - } - for (i = 0, j = 0; i < mynel; i++) { - struct av_decision dummy_avd; - rc = avc_has_perm_noaudit(fromsid, mysids[i], - SECCLASS_PROCESS, /* kernel value */ - PROCESS__TRANSITION, AVC_STRICT, - &dummy_avd); - if (!rc) - mysids2[j++] = mysids[i]; - cond_resched(); - } - kfree(mysids); - *sids = mysids2; - *nel = j; - return 0; -} - /** * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem * @policy: policy diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 6673601246b3..eff29645719b 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -793,9 +793,10 @@ #define MSR_AMD64_LBR_SELECT 0xc000010e /* Zen4 */ -#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG 0xc001102e #define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 /* Fam 19h MSRs */ #define MSR_F19H_UMC_PERF_CTL 0xc0010800 diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index c53cde425406..457498259494 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -3,7 +3,6 @@ #define _LINUX_STDDEF_H - #ifndef __always_inline #define __always_inline __inline__ #endif @@ -36,6 +35,11 @@ struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ } ATTRS +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union * @@ -52,3 +56,23 @@ TYPE NAME[]; \ } #endif + +#ifndef __counted_by +#define __counted_by(m) +#endif + +#ifndef __counted_by_le +#define __counted_by_le(m) +#endif + +#ifndef __counted_by_be +#define __counted_by_be(m) +#endif + +#ifndef __counted_by_ptr +#define __counted_by_ptr(m) +#endif + +#define __kernel_nonstring + +#endif /* _LINUX_STDDEF_H */ diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 08205f9fc525..cc53b2f21c44 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -15,9 +15,11 @@ UAPI_PATH:=../../../../include/uapi/ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) get_hdr_inc2=-D$(1) -D$(2) -include $(UAPI_PATH)/linux/$(3) +CFLAGS_dev-energymodel:=$(call get_hdr_inc,_LINUX_DEV_ENERGYMODEL_H,dev_energymodel.h) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) -CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_TYPELIMITS_H,typelimits.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index 0e1e486c1185..cdc3646f2642 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -3212,6 +3212,8 @@ def render_uapi(family, cw): for const in family['definitions']: if const.get('header'): continue + if const.get('scope', 'uapi') != 'uapi': + continue if const['type'] != 'const': cw.writes_defines(defines) @@ -3339,6 +3341,25 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def render_scoped_consts(family, cw, scope): + defines = [] + for const in family['definitions']: + if const['type'] != 'const': + continue + if const.get('header'): + continue + if const.get('scope') != scope: + continue + name_pfx = const.get('name-prefix', f"{family.ident_name}-") + defines.append([ + c_upper(family.get('c-define-name', + f"{name_pfx}{const['name']}")), + const['value']]) + if defines: + cw.writes_defines(defines) + cw.nl() + + def _render_user_ntf_entry(ri, op): if not ri.family.is_classic(): ri.cw.block_start(line=f"[{op.enum_name}] = ") @@ -3504,8 +3525,12 @@ def main(): cw.p('#include "ynl.h"') headers = [] for definition in parsed['definitions'] + parsed['attribute-sets']: - if 'header' in definition: - headers.append(definition['header']) + if 'header' not in definition: + continue + scope = definition.get('scope', 'uapi') + if scope != 'uapi' and scope != args.mode: + continue + headers.append(definition['header']) if args.mode == 'user': headers.append(parsed.uapi_header) seen_header = [] @@ -3522,6 +3547,7 @@ def main(): for one in args.user_header: cw.p(f'#include "{one}"') else: + render_scoped_consts(parsed, cw, 'user') cw.p('struct ynl_sock;') cw.nl() render_user_family(parsed, cw, True) @@ -3529,6 +3555,7 @@ def main(): if args.mode == "kernel": if args.header: + render_scoped_consts(parsed, cw, 'kernel') for _, struct in sorted(parsed.pure_nested_structs.items()): if struct.request: cw.p('/* Common nested types */') diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index f829b6f09bc9..fe30181e6336 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -112,6 +112,10 @@ static void test_cubic(void) ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called"); + ASSERT_TRUE(cubic_skel->bss->nodelay_init_reject, "init reject nodelay option"); + ASSERT_TRUE(cubic_skel->bss->nodelay_cwnd_event_tx_start_reject, + "cwnd_event_tx_start reject nodelay option"); + bpf_link__destroy(link); bpf_cubic__destroy(cubic_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 53637431ec5d..3a41c517b918 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -190,7 +190,7 @@ static int getsetsockopt(void) fd = socket(AF_NETLINK, SOCK_RAW, 0); if (fd < 0) { log_err("Failed to create AF_NETLINK socket"); - return -1; + goto err; } buf.u32 = 1; @@ -211,6 +211,21 @@ static int getsetsockopt(void) } ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + /* Trick bpf_tcp_sock() with IPPROTO_TCP */ + close(fd); + fd = socket(AF_INET, SOCK_RAW, IPPROTO_TCP); + if (!ASSERT_OK_FD(fd, "socket")) + goto err; + + /* The BPF prog intercepts this before the kernel sees it, any + * optlen works. Go with 4 bytes for simplicity. + */ + buf.u32 = 1; + optlen = sizeof(buf.u32); + err = setsockopt(fd, SOL_TCP, TCP_SAVED_SYN, &buf, optlen); + if (!ASSERT_ERR(err, "setsockopt(TCP_SAVED_SYN)")) + goto err; + free(big_buf); close(fd); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c index 56685fc03c7e..80e6315da2a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c @@ -507,6 +507,10 @@ static void misc(void) ASSERT_EQ(misc_skel->bss->nr_hwtstamp, 0, "nr_hwtstamp"); + ASSERT_TRUE(misc_skel->bss->nodelay_est_ok, "nodelay_est_ok"); + ASSERT_TRUE(misc_skel->bss->nodelay_hdr_len_reject, "nodelay_hdr_len_reject"); + ASSERT_TRUE(misc_skel->bss->nodelay_write_hdr_reject, "nodelay_write_hdr_reject"); + check_linum: ASSERT_FALSE(check_error_linum(&sk_fds), "check_error_linum"); sk_fds_close(&sk_fds); diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index ce18a4db813f..ebd5a1e69f56 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -16,6 +16,7 @@ #include "bpf_tracing_net.h" #include +#include char _license[] SEC("license") = "GPL"; @@ -170,10 +171,18 @@ static void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } +bool nodelay_init_reject = false; +bool nodelay_cwnd_event_tx_start_reject = false; + SEC("struct_ops") void BPF_PROG(bpf_cubic_init, struct sock *sk) { struct bpf_bictcp *ca = inet_csk_ca(sk); + int true_val = 1, ret; + + ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_init_reject = true; bictcp_reset(ca); @@ -189,8 +198,13 @@ void BPF_PROG(bpf_cubic_cwnd_event_tx_start, struct sock *sk) { struct bpf_bictcp *ca = inet_csk_ca(sk); __u32 now = tcp_jiffies32; + int true_val = 1, ret; __s32 delta; + ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_cwnd_event_tx_start_reject = true; + delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index cb990a7d3d45..5e0b27e7855c 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -149,6 +149,20 @@ int _setsockopt(struct bpf_sockopt *ctx) if (sk && sk->family == AF_NETLINK) goto out; + if (sk && sk->family == AF_INET && sk->type == SOCK_RAW) { + struct bpf_tcp_sock *tp = bpf_tcp_sock(sk); + + if (tp) { + char saved_syn[60]; + + bpf_getsockopt(sk, SOL_TCP, TCP_SAVED_SYN, + &saved_syn, sizeof(saved_syn)); + goto consumed; + } + + goto out; + } + /* Make sure bpf_get_netns_cookie is callable. */ if (bpf_get_netns_cookie(NULL) == 0) @@ -224,6 +238,8 @@ int _setsockopt(struct bpf_sockopt *ctx) return 0; /* couldn't get sk storage */ storage->val = optval[0]; + +consumed: ctx->optlen = -1; /* BPF has consumed this option, don't call kernel * setsockopt handler. */ diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index d487153a839d..ed5a0011b863 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -29,6 +29,10 @@ unsigned int nr_syn = 0; unsigned int nr_fin = 0; unsigned int nr_hwtstamp = 0; +bool nodelay_est_ok = false; +bool nodelay_hdr_len_reject = false; +bool nodelay_write_hdr_reject = false; + /* Check the header received from the active side */ static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn) { @@ -300,7 +304,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { - int true_val = 1; + int true_val = 1, false_val = 0, ret; switch (skops->op) { case BPF_SOCK_OPS_TCP_LISTEN_CB: @@ -316,10 +320,19 @@ int misc_estab(struct bpf_sock_ops *skops) case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: return handle_parse_hdr(skops); case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_hdr_len_reject = true; return handle_hdr_opt_len(skops); case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_write_hdr_reject = true; return handle_write_hdr_opt(skops); case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &false_val, sizeof(false_val)); + if (!ret) + nodelay_est_ok = true; return handle_passive_estab(skops); } diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c index 6a7295347e90..42f54936f4bb 100644 --- a/tools/testing/selftests/cgroup/lib/cgroup_util.c +++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c @@ -106,8 +106,9 @@ int cg_read_strcmp(const char *cgroup, const char *control, /* Handle the case of comparing against empty string */ if (!expected) return -1; - else - size = strlen(expected) + 1; + + /* needs size > 1, otherwise cg_read() reads 0 bytes */ + size = (expected[0] == '\0') ? 2 : strlen(expected) + 1; buf = malloc(size); if (!buf) diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh index 42a6628fb8bc..1c0444729e70 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh @@ -18,7 +18,7 @@ write_test() { echo "testing $interface $value" echo $value > $dir/$interface new=$(cat $dir/$interface) - [[ $value -ne $(cat $dir/$interface) ]] && { + [[ "$value" != "$new" ]] && { echo "$interface write $value failed: new:$new" exit 1 } diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index eeabd34bf083..12f59925500b 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -368,11 +368,15 @@ static int test_percpu_basic(const char *root) for (i = 0; i < 1000; i++) { child = cg_name_indexed(parent, "child", i); - if (!child) - return -1; - - if (cg_create(child)) + if (!child) { + ret = -1; goto cleanup_children; + } + + if (cg_create(child)) { + free(child); + goto cleanup_children; + } free(child); } diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py index 11310f19bfa0..e39d270e688d 100755 --- a/tools/testing/selftests/drivers/net/shaper.py +++ b/tools/testing/selftests/drivers/net/shaper.py @@ -1,7 +1,10 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx +import errno + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, ksft_raises, ksft_true, KsftSkipEx from lib.py import EthtoolFamily, NetshaperFamily from lib.py import NetDrvEnv from lib.py import NlError @@ -438,6 +441,21 @@ def queue_update(cfg, nl_shaper) -> None: nl_shaper.delete({'ifindex': cfg.ifindex, 'handle': {'scope': 'queue', 'id': i}}) +def dup_leaves(cfg, nl_shaper) -> None: + """ Ensure that the kernel rejects duplicate leaves. """ + if not cfg.groups: + raise KsftSkipEx("device does not support node scope") + + with ksft_raises(NlError) as cm: + nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 0}}, + {'handle': {'scope': 'queue', 'id': 0}}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 10000}) + ksft_eq(cm.exception.error, errno.EINVAL) + def main() -> None: with NetDrvEnv(__file__, queue_count=4) as cfg: cfg.queues = False @@ -453,7 +471,9 @@ def main() -> None: basic_groups, qgroups, delegation, - queue_update], args=(cfg, NetshaperFamily())) + dup_leaves, + queue_update], + args=(cfg, NetshaperFamily())) ksft_exit() diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index d6528c6f5e03..253e748c1d4a 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -510,7 +510,12 @@ static void test_guest_memfd_guest(void) "Default VM type should support INIT_SHARED, supported flags = 0x%x", vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); - size = vm->page_size; + /* + * Use the max of the host or guest page size for all operations, as + * KVM requires guest_memfd files and memslots to be sized to multiples + * of the host page size. + */ + size = max_t(size_t, vm->page_size, page_size); fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED); vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); @@ -519,7 +524,7 @@ static void test_guest_memfd_guest(void) memset(mem, 0xaa, size); kvm_munmap(mem, size); - virt_pg_map(vm, gpa, gpa); + virt_map(vm, gpa, gpa, size / vm->page_size); vcpu_args_set(vcpu, 2, gpa, size); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 7df2bc8eec02..76fcdd1fd3cb 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -220,6 +220,8 @@ static void check_steal_time_uapi(void) }; vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, 1, 0); + virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, 1); st_ipa = (ulong)ST_GPA_BASE | 1; ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 4ef90823b652..50d69e22ee7a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,14 +14,20 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ - param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \ - syscall_errors_test slice_test +TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test \ + param_test_benchmark param_test_mm_cid_benchmark -TEST_GEN_PROGS_EXTENDED = librseq.so +TEST_GEN_PROGS_EXTENDED = librseq.so \ + param_test \ + param_test_compare_twice \ + param_test_mm_cid \ + param_test_mm_cid_compare_twice \ + syscall_errors_test \ + legacy_check \ + slice_test \ + check_optimized -TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh +TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh run_legacy_check.sh run_timeslice_test.sh TEST_FILES := settings @@ -62,3 +68,6 @@ $(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) $(OUTPUT)/slice_test: slice_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ + +$(OUTPUT)/check_optimized: check_optimized.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h + $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ diff --git a/tools/testing/selftests/rseq/check_optimized.c b/tools/testing/selftests/rseq/check_optimized.c new file mode 100644 index 000000000000..a13e3f2c8fc6 --- /dev/null +++ b/tools/testing/selftests/rseq/check_optimized.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include + +#include "rseq.h" + +int main(int argc, char **argv) +{ + if (__rseq_register_current_thread(true, false)) + return -1; + return 0; +} diff --git a/tools/testing/selftests/rseq/legacy_check.c b/tools/testing/selftests/rseq/legacy_check.c new file mode 100644 index 000000000000..3f7de4e28303 --- /dev/null +++ b/tools/testing/selftests/rseq/legacy_check.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#include +#include +#include +#include + +#include "rseq.h" + +#include "../kselftest_harness.h" + +FIXTURE(legacy) +{ +}; + +static int cpu_id_in_sigfn = -1; + +static void sigfn(int sig) +{ + struct rseq_abi *rs = rseq_get_abi(); + + cpu_id_in_sigfn = rs->cpu_id_start; +} + +FIXTURE_SETUP(legacy) +{ + int res = __rseq_register_current_thread(true, true); + + switch (res) { + case -ENOSYS: + SKIP(return, "RSEQ not enabled\n"); + case -EBUSY: + SKIP(return, "GLIBC owns RSEQ. Disable GLIBC RSEQ registration\n"); + default: + ASSERT_EQ(res, 0); + } + + ASSERT_NE(signal(SIGUSR1, sigfn), SIG_ERR); +} + +FIXTURE_TEARDOWN(legacy) +{ +} + +TEST_F(legacy, legacy_test) +{ + struct rseq_abi *rs = rseq_get_abi(); + + ASSERT_NE(rs, NULL); + + /* Overwrite rs::cpu_id_start */ + rs->cpu_id_start = -1; + sleep(1); + ASSERT_NE(rs->cpu_id_start, -1); + + rs->cpu_id_start = -1; + ASSERT_EQ(raise(SIGUSR1), 0); + ASSERT_NE(rs->cpu_id_start, -1); + ASSERT_NE(cpu_id_in_sigfn, -1); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 05d03e679e06..e1e98dbabe4b 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -38,7 +38,7 @@ static int opt_modulo, verbose; static int opt_yield, opt_signal, opt_sleep, opt_disable_rseq, opt_threads = 200, opt_disable_mod = 0, opt_test = 's'; - +static bool opt_rseq_legacy; static long long opt_reps = 5000; static __thread __attribute__((tls_model("initial-exec"))) @@ -281,9 +281,12 @@ unsigned int yield_mod_cnt, nr_abort; } \ } +#define rseq_no_glibc true + #else #define printf_verbose(fmt, ...) +#define rseq_no_glibc false #endif /* BENCHMARK */ @@ -481,7 +484,7 @@ void *test_percpu_spinlock_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -558,7 +561,7 @@ void *test_percpu_inc_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -712,7 +715,7 @@ void *test_percpu_list_thread(void *arg) long long i, reps; struct percpu_list *list = (struct percpu_list *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -895,7 +898,7 @@ void *test_percpu_buffer_thread(void *arg) long long i, reps; struct percpu_buffer *buffer = (struct percpu_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1105,7 +1108,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) long long i, reps; struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1258,7 +1261,7 @@ void *test_membarrier_worker_thread(void *arg) const int iters = opt_reps; int i; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1323,7 +1326,7 @@ void *test_membarrier_manager_thread(void *arg) intptr_t expect_a = 0, expect_b = 0; int cpu_a = 0, cpu_b = 0; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1475,6 +1478,7 @@ static void show_usage(int argc, char **argv) printf(" [-D M] Disable rseq for each M threads\n"); printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n"); printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n"); + printf(" [-O] Test with optimized RSEQ\n"); printf(" [-v] Verbose output.\n"); printf(" [-h] Show this help.\n"); printf("\n"); @@ -1602,6 +1606,9 @@ int main(int argc, char **argv) case 'M': opt_mo = RSEQ_MO_RELEASE; break; + case 'L': + opt_rseq_legacy = true; + break; default: show_usage(argc, argv); goto error; @@ -1618,7 +1625,7 @@ int main(int argc, char **argv) if (set_signal_handler()) goto error; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) goto error; if (!opt_disable_rseq && !rseq_validate_cpu_id()) { fprintf(stderr, "Error: cpu id getter unavailable\n"); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h index ecef315204b2..5f4ea2152c2f 100644 --- a/tools/testing/selftests/rseq/rseq-abi.h +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -191,10 +191,15 @@ struct rseq_abi { */ struct rseq_abi_slice_ctrl slice_ctrl; + /* + * Place holder to push the size above 32 bytes. + */ + __u8 __reserved; + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(256))); #endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index a736727b83c1..be0d0a97031e 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -56,6 +56,7 @@ ptrdiff_t rseq_offset; * unsuccessful. */ unsigned int rseq_size = -1U; +static unsigned int rseq_alloc_size; /* Flags used during rseq registration. */ unsigned int rseq_flags; @@ -115,29 +116,17 @@ bool rseq_available(void) } } -/* The rseq areas need to be at least 32 bytes. */ -static -unsigned int get_rseq_min_alloc_size(void) -{ - unsigned int alloc_size = rseq_size; - - if (alloc_size < ORIG_RSEQ_ALLOC_SIZE) - alloc_size = ORIG_RSEQ_ALLOC_SIZE; - return alloc_size; -} - /* * Return the feature size supported by the kernel. * * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE): * - * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) + * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE). * * It should never return a value below ORIG_RSEQ_FEATURE_SIZE. */ -static -unsigned int get_rseq_kernel_feature_size(void) +static unsigned int get_rseq_kernel_feature_size(void) { unsigned long auxv_rseq_feature_size, auxv_rseq_align; @@ -152,15 +141,24 @@ unsigned int get_rseq_kernel_feature_size(void) return ORIG_RSEQ_FEATURE_SIZE; } -int rseq_register_current_thread(void) +int __rseq_register_current_thread(bool nolibc, bool legacy) { + unsigned int size; int rc; if (!rseq_ownership) { /* Treat libc's ownership as a successful registration. */ - return 0; + return nolibc ? -EBUSY : 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); + + /* The minimal allocation size is 32, which is the legacy allocation size */ + size = get_rseq_kernel_feature_size(); + if (legacy || size < ORIG_RSEQ_ALLOC_SIZE) + rseq_alloc_size = ORIG_RSEQ_ALLOC_SIZE; + else + rseq_alloc_size = size; + + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, 0, RSEQ_SIG); if (rc) { /* * After at least one thread has registered successfully @@ -179,9 +177,8 @@ int rseq_register_current_thread(void) * The first thread to register sets the rseq_size to mimic the libc * behavior. */ - if (RSEQ_READ_ONCE(rseq_size) == 0) { - RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); - } + if (RSEQ_READ_ONCE(rseq_size) == 0) + RSEQ_WRITE_ONCE(rseq_size, size); return 0; } @@ -194,7 +191,7 @@ int rseq_unregister_current_thread(void) /* Treat libc's ownership as a successful unregistration. */ return 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); if (rc) return -1; return 0; diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index f51a5fdb0444..c62ebb9290c0 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -8,6 +8,7 @@ #ifndef RSEQ_H #define RSEQ_H +#include #include #include #include @@ -142,7 +143,12 @@ static inline struct rseq_abi *rseq_get_abi(void) * succeed. A restartable sequence executed from a non-registered * thread will always fail. */ -int rseq_register_current_thread(void); +int __rseq_register_current_thread(bool nolibc, bool legacy); + +static inline int rseq_register_current_thread(void) +{ + return __rseq_register_current_thread(false, false); +} /* * Unregister rseq for current thread. diff --git a/tools/testing/selftests/rseq/run_legacy_check.sh b/tools/testing/selftests/rseq/run_legacy_check.sh new file mode 100755 index 000000000000..5577b46ea092 --- /dev/null +++ b/tools/testing/selftests/rseq/run_legacy_check.sh @@ -0,0 +1,4 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./legacy_check diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh index 8d31426ab41f..69a3fa049929 100755 --- a/tools/testing/selftests/rseq/run_param_test.sh +++ b/tools/testing/selftests/rseq/run_param_test.sh @@ -34,6 +34,11 @@ REPS=1000 SLOW_REPS=100 NR_THREADS=$((6*${NR_CPUS})) +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy and +# performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + function do_tests() { local i=0 @@ -103,6 +108,40 @@ function inject_blocking() NR_LOOPS= } +echo "Testing in legacy RSEQ mode" +echo "Yield injection (25%)" +inject_blocking -m 4 -y -L + +echo "Yield injection (50%)" +inject_blocking -m 2 -y -L + +echo "Yield injection (100%)" +inject_blocking -m 1 -y -L + +echo "Kill injection (25%)" +inject_blocking -m 4 -k -L + +echo "Kill injection (50%)" +inject_blocking -m 2 -k -L + +echo "Kill injection (100%)" +inject_blocking -m 1 -k -L + +echo "Sleep injection (1ms, 25%)" +inject_blocking -m 4 -s 1 -L + +echo "Sleep injection (1ms, 50%)" +inject_blocking -m 2 -s 1 -L + +echo "Sleep injection (1ms, 100%)" +inject_blocking -m 1 -s 1 -L + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +echo "Testing in optimized RSEQ mode" echo "Yield injection (25%)" inject_blocking -m 4 -y diff --git a/tools/testing/selftests/rseq/run_timeslice_test.sh b/tools/testing/selftests/rseq/run_timeslice_test.sh new file mode 100755 index 000000000000..551ebed71ec6 --- /dev/null +++ b/tools/testing/selftests/rseq/run_timeslice_test.sh @@ -0,0 +1,14 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ + +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy +# and performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +./slice_test diff --git a/tools/testing/selftests/rseq/slice_test.c b/tools/testing/selftests/rseq/slice_test.c index 357122dcb487..e402d4440bc2 100644 --- a/tools/testing/selftests/rseq/slice_test.c +++ b/tools/testing/selftests/rseq/slice_test.c @@ -124,6 +124,13 @@ FIXTURE_SETUP(slice_ext) { cpu_set_t affinity; + if (__rseq_register_current_thread(true, false)) + SKIP(return, "RSEQ not supported\n"); + + if (prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, + PR_RSEQ_SLICE_EXT_ENABLE, 0, 0)) + SKIP(return, "Time slice extension not supported\n"); + ASSERT_EQ(sched_getaffinity(0, sizeof(affinity), &affinity), 0); /* Pin it on a single CPU. Avoid CPU 0 */ @@ -137,11 +144,6 @@ FIXTURE_SETUP(slice_ext) break; } - ASSERT_EQ(rseq_register_current_thread(), 0); - - ASSERT_EQ(prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, - PR_RSEQ_SLICE_EXT_ENABLE, 0, 0), 0); - self->noise_params.noise_nsecs = variant->noise_nsecs; self->noise_params.sleep_nsecs = variant->sleep_nsecs; self->noise_params.run = 1; diff --git a/tools/testing/selftests/sched_ext/dequeue.c b/tools/testing/selftests/sched_ext/dequeue.c index 4e93262703ca..383d06e972a4 100644 --- a/tools/testing/selftests/sched_ext/dequeue.c +++ b/tools/testing/selftests/sched_ext/dequeue.c @@ -33,6 +33,7 @@ static void worker_fn(int id) /* Do some work to trigger scheduling events */ for (j = 0; j < 10000; j++) sum += j; + asm volatile("" : : "r"(sum)); /* Sleep to trigger dequeue */ usleep(1000 + (id * 100)); diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index b1f856cf62c1..848696c373fc 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1284,5 +1284,46 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "3a62", + "name": "Try to create a qlen underflow with QFQ/CBS", + "category": [ + "qdisc", + "qfq", + "cbs" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY classid 1:1 parent 1: qfq", + "$TC class add dev $DUMMY classid 1:2 parent 1: qfq", + "$TC qdisc add dev $DUMMY handle 2: parent 1:1 cbs", + "$TC qdisc add dev $DUMMY handle 3: parent 2: netem delay 5000000000", + "$TC filter add dev $DUMMY parent 1: prio 1 u32 match ip dst 10.10.10.1 classid 1:1 action ok", + "$TC filter add dev $DUMMY parent 1: prio 2 u32 match ip dst 10.10.10.2 classid 1:2 action ok", + "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "$IP l set $DUMMY down", + "$IP l set $DUMMY up", + "$TC qdisc replace dev $DUMMY handle 4: parent 2: pfifo" + ], + "cmdUnderTest": "ping -c 1 10.10.10.2 -W0.01 -I$DUMMY", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [ + { + "kind": "cbs", + "handle": "2:", + "bytes": 0, + "packets": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 02bc6b00d76c..572b854edf74 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -63,7 +63,8 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); - if (!memslot || (offset + __fls(mask)) >= memslot->npages) + if (!memslot || offset >= memslot->npages || + offset + __fls(mask) >= memslot->npages) return; KVM_MMU_LOCK(kvm);