diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2024-12-05 22:48:58 +0300 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2024-12-19 22:35:07 +0300 |
| commit | 07e5c4eb94e6aba96fa11b424b39c5e5576a7713 (patch) | |
| tree | ab7c48de9389e6e3c30586630b19ead62ae43637 | |
| parent | 6b3099ebca13ecc5d0e7d07b438672addbd65da6 (diff) | |
| parent | 8faabc041a001140564f718dabe37753e88b37fa (diff) | |
| download | linux-07e5c4eb94e6aba96fa11b424b39c5e5576a7713.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR (net-6.13-rc4).
No conflicts.
Adjacent changes:
drivers/net/ethernet/renesas/rswitch.h
32fd46f5b69e ("net: renesas: rswitch: remove speed from gwca structure")
922b4b955a03 ("net: renesas: rswitch: rework ts tags management")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
367 files changed, 4106 insertions, 2056 deletions
diff --git a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml index 6d6d211883ae..daee0c0fc915 100644 --- a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml @@ -113,11 +113,8 @@ allOf: maxItems: 1 - if: - properties: - compatible: - contains: - enum: - - fsl,imx95-usb-phy + required: + - orientation-switch then: $ref: /schemas/usb/usb-switch.yaml# diff --git a/Documentation/devicetree/bindings/regulator/qcom,qca6390-pmu.yaml b/Documentation/devicetree/bindings/regulator/qcom,qca6390-pmu.yaml index ca401a209cca..47c425c9fff1 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,qca6390-pmu.yaml +++ b/Documentation/devicetree/bindings/regulator/qcom,qca6390-pmu.yaml @@ -18,6 +18,7 @@ properties: compatible: enum: - qcom,qca6390-pmu + - qcom,wcn6750-pmu - qcom,wcn6855-pmu - qcom,wcn7850-pmu @@ -27,6 +28,9 @@ properties: vddaon-supply: description: VDD_AON supply regulator handle + vddasd-supply: + description: VDD_ASD supply regulator handle + vdddig-supply: description: VDD_DIG supply regulator handle @@ -42,6 +46,9 @@ properties: vddio1p2-supply: description: VDD_IO_1P2 supply regulator handle + vddrfa0p8-supply: + description: VDD_RFA_0P8 supply regulator handle + vddrfa0p95-supply: description: VDD_RFA_0P95 supply regulator handle @@ -51,12 +58,18 @@ properties: vddrfa1p3-supply: description: VDD_RFA_1P3 supply regulator handle + vddrfa1p7-supply: + description: VDD_RFA_1P7 supply regulator handle + vddrfa1p8-supply: description: VDD_RFA_1P8 supply regulator handle vddrfa1p9-supply: description: VDD_RFA_1P9 supply regulator handle + vddrfa2p2-supply: + description: VDD_RFA_2P2 supply regulator handle + vddpcie1p3-supply: description: VDD_PCIE_1P3 supply regulator handle @@ -123,6 +136,20 @@ allOf: properties: compatible: contains: + const: qcom,wcn6750-pmu + then: + required: + - vddaon-supply + - vddasd-supply + - vddpmu-supply + - vddrfa0p8-supply + - vddrfa1p2-supply + - vddrfa1p7-supply + - vddrfa2p2-supply + - if: + properties: + compatible: + contains: const: qcom,wcn6855-pmu then: required: diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 53d1996460ab..12f429359a82 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -347,7 +347,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_resume_and_get(struct device *dev);` - run pm_runtime_resume(dev) and if successful, increment the device's - usage counter; return the result of pm_runtime_resume + usage counter; returns 0 on success (whether or not the device's + runtime PM status was already 'active') or the error code from + pm_runtime_resume() on failure. `int pm_request_idle(struct device *dev);` - submit a request to execute the subsystem-level idle callback for the diff --git a/MAINTAINERS b/MAINTAINERS index 907b379af010..e67e0c188349 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3900,7 +3900,7 @@ W: http://www.baycom.org/~tom/ham/ham.html F: drivers/net/hamradio/baycom* BCACHE (BLOCK LAYER CACHE) -M: Coly Li <colyli@suse.de> +M: Coly Li <colyli@kernel.org> M: Kent Overstreet <kent.overstreet@linux.dev> L: linux-bcache@vger.kernel.org S: Maintained @@ -8460,7 +8460,7 @@ F: include/video/s1d13xxxfb.h EROFS FILE SYSTEM M: Gao Xiang <xiang@kernel.org> M: Chao Yu <chao@kernel.org> -R: Yue Hu <huyue2@coolpad.com> +R: Yue Hu <zbestahu@gmail.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> R: Sandeep Dhavale <dhavale@google.com> L: linux-erofs@lists.ozlabs.org @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5b2488142041..ea5a1dcb133b 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -297,7 +297,6 @@ config ARC_PAGE_SIZE_16K config ARC_PAGE_SIZE_4K bool "4KB" select HAVE_PAGE_SIZE_4KB - depends on ARC_MMU_V3 || ARC_MMU_V4 endchoice @@ -474,7 +473,8 @@ config HIGHMEM config ARC_HAS_PAE40 bool "Support for the 40-bit Physical Address Extension" - depends on ISA_ARCV2 + depends on ARC_MMU_V4 + depends on !ARC_PAGE_SIZE_4K select HIGHMEM select PHYS_ADDR_T_64BIT help diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 2390dd042e36..fb98478ed1ab 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,7 +6,7 @@ KBUILD_DEFCONFIG := haps_hs_smp_defconfig ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) +CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-) endif cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 2a151607b080..88bcc7ab6f5a 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -54,7 +54,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index c0a812674ce9..9a2dc39a5cff 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -62,7 +62,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 67556f4b7057..f31382cb8be4 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -69,7 +69,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index b64435385304..3add2fe257f8 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -250,7 +250,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; }; @@ -258,7 +258,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <1>; }; @@ -266,7 +266,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <2>; }; }; @@ -281,7 +281,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; }; @@ -289,7 +289,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <10>; + ngpios = <10>; reg = <1>; }; @@ -297,7 +297,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <2>; }; }; diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 41b980df862b..98bb850722a4 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -308,7 +308,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <24>; + ngpios = <24>; reg = <0>; }; }; diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 4b13f60fe7ca..005d9e4d187a 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -146,7 +146,7 @@ #ifndef __ASSEMBLY__ -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> /* Helpers */ #define TO_KB(bytes) ((bytes) >> 10) diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 58045c898340..76f43db0890f 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -48,7 +48,7 @@ \ switch(sizeof((_p_))) { \ case 1: \ - _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ + _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ break; \ case 4: \ _prev_ = __cmpxchg(_p_, _o_, _n_); \ diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h index d85dc0721907..41412642f279 100644 --- a/arch/arc/include/asm/mmu-arcv2.h +++ b/arch/arc/include/asm/mmu-arcv2.h @@ -9,7 +9,7 @@ #ifndef _ASM_ARC_MMU_ARCV2_H #define _ASM_ARC_MMU_ARCV2_H -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> /* * TLB Management regs diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 4458e409ca0a..6d989b6d88c6 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -2916,7 +2916,7 @@ bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond) addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal; disp = get_displacement(curr_off + addendum, targ_off); - if (ARC_CC_AL) + if (cond == ARC_CC_AL) return is_valid_far_disp(disp); else return is_valid_near_disp(disp); diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 19973ab4ea6b..9e10d7a6b5a2 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -233,7 +233,7 @@ #interrupt-cells = <0x1>; compatible = "pci-host-ecam-generic"; device_type = "pci"; - bus-range = <0x0 0x1>; + bus-range = <0x0 0xff>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 85ef966c08cd..4ef52d7245bb 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -87,7 +87,7 @@ 1 << PMSCR_EL2_PA_SHIFT) msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter .Lskip_spe_el2_\@: - mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) + mov x0, #MDCR_EL2_E2PB_MASK orr x2, x2, x0 // If we don't have VHE, then // use EL1&0 translation. @@ -100,7 +100,7 @@ and x0, x0, TRBIDR_EL1_P cbnz x0, .Lskip_trace_\@ // If TRBE is available at EL2 - mov x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT) + mov x0, #MDCR_EL2_E2TB_MASK orr x2, x2, x0 // allow the EL1&0 translation // to own it. diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 65f76064c86b..ae990da1eae5 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -114,8 +114,8 @@ SYM_CODE_START_LOCAL(__finalise_el2) // Use EL2 translations for SPE & TRBE and disable access from EL1 mrs x0, mdcr_el2 - bic x0, x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) - bic x0, x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT) + bic x0, x0, #MDCR_EL2_E2PB_MASK + bic x0, x0, #MDCR_EL2_E2TB_MASK msr mdcr_el2, x0 // Transfer the MM state from EL1 to EL2 diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 14ac6fdb872b..37e24f1bd227 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -1462,10 +1462,33 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, struct rt_sigframe_user_layout *user, int usig) { __sigrestore_t sigtramp; + int err; + + if (ksig->ka.sa.sa_flags & SA_RESTORER) + sigtramp = ksig->ka.sa.sa_restorer; + else + sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); + + err = gcs_signal_entry(sigtramp, ksig); + if (err) + return err; + + /* + * We must not fail from this point onwards. We are going to update + * registers, including SP, in order to invoke the signal handler. If + * we failed and attempted to deliver a nested SIGSEGV to a handler + * after that point, the subsequent sigreturn would end up restoring + * the (partial) state for the original signal handler. + */ regs->regs[0] = usig; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + regs->regs[1] = (unsigned long)&user->sigframe->info; + regs->regs[2] = (unsigned long)&user->sigframe->uc; + } regs->sp = (unsigned long)user->sigframe; regs->regs[29] = (unsigned long)&user->next_frame->fp; + regs->regs[30] = (unsigned long)sigtramp; regs->pc = (unsigned long)ksig->ka.sa.sa_handler; /* @@ -1506,14 +1529,7 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, sme_smstop(); } - if (ksig->ka.sa.sa_flags & SA_RESTORER) - sigtramp = ksig->ka.sa.sa_restorer; - else - sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); - - regs->regs[30] = (unsigned long)sigtramp; - - return gcs_signal_entry(sigtramp, ksig); + return 0; } static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, @@ -1537,14 +1553,16 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, err |= __save_altstack(&frame->uc.uc_stack, regs->sp); err |= setup_sigframe(&user, regs, set, &ua_state); - if (err == 0) { + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + err |= copy_siginfo_to_user(&frame->info, &ksig->info); + + if (err == 0) err = setup_return(regs, ksig, &user, usig); - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - err |= copy_siginfo_to_user(&frame->info, &ksig->info); - regs->regs[1] = (unsigned long)&frame->info; - regs->regs[2] = (unsigned long)&frame->uc; - } - } + + /* + * We must not fail if setup_return() succeeded - see comment at the + * beginning of setup_return(). + */ if (err == 0) set_handler_user_access_state(); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index caef85462acb..1d9d51d7627f 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -26,7 +26,6 @@ enum kunwind_source { KUNWIND_SOURCE_CALLER, KUNWIND_SOURCE_TASK, KUNWIND_SOURCE_REGS_PC, - KUNWIND_SOURCE_REGS_LR, }; union unwind_flags { @@ -138,8 +137,10 @@ kunwind_recover_return_address(struct kunwind_state *state) orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, state->common.pc, (void *)state->common.fp); - if (WARN_ON_ONCE(state->common.pc == orig_pc)) + if (state->common.pc == orig_pc) { + WARN_ON_ONCE(state->task == current); return -EINVAL; + } state->common.pc = orig_pc; state->flags.fgraph = 1; } @@ -178,23 +179,8 @@ int kunwind_next_regs_pc(struct kunwind_state *state) state->regs = regs; state->common.pc = regs->pc; state->common.fp = regs->regs[29]; - state->source = KUNWIND_SOURCE_REGS_PC; - return 0; -} - -static __always_inline int -kunwind_next_regs_lr(struct kunwind_state *state) -{ - /* - * The stack for the regs was consumed by kunwind_next_regs_pc(), so we - * cannot consume that again here, but we know the regs are safe to - * access. - */ - state->common.pc = state->regs->regs[30]; - state->common.fp = state->regs->regs[29]; state->regs = NULL; - state->source = KUNWIND_SOURCE_REGS_LR; - + state->source = KUNWIND_SOURCE_REGS_PC; return 0; } @@ -215,12 +201,12 @@ kunwind_next_frame_record_meta(struct kunwind_state *state) case FRAME_META_TYPE_FINAL: if (meta == &task_pt_regs(tsk)->stackframe) return -ENOENT; - WARN_ON_ONCE(1); + WARN_ON_ONCE(tsk == current); return -EINVAL; case FRAME_META_TYPE_PT_REGS: return kunwind_next_regs_pc(state); default: - WARN_ON_ONCE(1); + WARN_ON_ONCE(tsk == current); return -EINVAL; } } @@ -274,11 +260,8 @@ kunwind_next(struct kunwind_state *state) case KUNWIND_SOURCE_FRAME: case KUNWIND_SOURCE_CALLER: case KUNWIND_SOURCE_TASK: - case KUNWIND_SOURCE_REGS_LR: - err = kunwind_next_frame_record(state); - break; case KUNWIND_SOURCE_REGS_PC: - err = kunwind_next_regs_lr(state); + err = kunwind_next_frame_record(state); break; default: err = -EINVAL; @@ -436,7 +419,6 @@ static const char *state_source_string(const struct kunwind_state *state) case KUNWIND_SOURCE_CALLER: return "C"; case KUNWIND_SOURCE_TASK: return "T"; case KUNWIND_SOURCE_REGS_PC: return "P"; - case KUNWIND_SOURCE_REGS_LR: return "L"; default: return "U"; } } diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 8c5d7990e5b3..3d7eb395e33d 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -739,8 +739,15 @@ static u64 compute_par_s12(struct kvm_vcpu *vcpu, u64 s1_par, final_attr = s1_parattr; break; default: - /* MemAttr[2]=0, Device from S2 */ - final_attr = s2_memattr & GENMASK(1,0) << 2; + /* + * MemAttr[2]=0, Device from S2. + * + * FWB does not influence the way that stage 1 + * memory types and attributes are combined + * with stage 2 Device type and attributes. + */ + final_attr = min(s2_memattr_to_attr(s2_memattr), + s1_parattr); } } else { /* Combination of R_HMNDG, R_TNHFM and R_GQFSF */ diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 01616c39a810..071993c16de8 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -126,7 +126,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) /* Trap SPE */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) { mdcr_set |= MDCR_EL2_TPMS; - mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; + mdcr_clear |= MDCR_EL2_E2PB_MASK; } /* Trap Trace Filter */ @@ -143,7 +143,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) /* Trap External Trace */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids)) - mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT; + mdcr_clear |= MDCR_EL2_E2TB_MASK; vcpu->arch.mdcr_el2 |= mdcr_set; vcpu->arch.mdcr_el2 &= ~mdcr_clear; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 83c6b4a07ef5..e2a5c2918d9e 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2618,7 +2618,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 | ID_AA64MMFR0_EL1_TGRAN4_2 | ID_AA64MMFR0_EL1_TGRAN64_2 | - ID_AA64MMFR0_EL1_TGRAN16_2)), + ID_AA64MMFR0_EL1_TGRAN16_2 | + ID_AA64MMFR0_EL1_ASIDBITS)), ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 | ID_AA64MMFR1_EL1_HCX | ID_AA64MMFR1_EL1_TWED | diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index f4c4494645c3..fb96802799c6 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -608,12 +608,22 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, lockdep_assert_held(&its->its_lock); vgic_get_irq_kref(irq); + old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); + + /* + * Put the reference taken on @irq if the store fails. Intentionally do + * not return the error as the translation cache is best effort. + */ + if (xa_is_err(old)) { + vgic_put_irq(kvm, irq); + return; + } + /* * We could have raced with another CPU caching the same * translation behind our back, ensure we don't leak a * reference if that is the case. */ - old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); if (old) vgic_put_irq(kvm, old); } diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index 440711d7bf40..ce6f2b08a35e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -239,6 +239,8 @@ handler: ;\ /* =====================================================[ exceptions] === */ + __REF + /* ---[ 0x100: RESET exception ]----------------------------------------- */ EXCEPTION_ENTRY(_tng_kernel_start) diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 439e00f81e5d..bd760066f1cd 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -26,15 +26,15 @@ #include <asm/asm-offsets.h> #include <linux/of_fdt.h> -#define tophys(rd,rs) \ - l.movhi rd,hi(-KERNELBASE) ;\ +#define tophys(rd,rs) \ + l.movhi rd,hi(-KERNELBASE) ;\ l.add rd,rd,rs -#define CLEAR_GPR(gpr) \ +#define CLEAR_GPR(gpr) \ l.movhi gpr,0x0 -#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ - l.movhi gpr,hi(symbol) ;\ +#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ + l.movhi gpr,hi(symbol) ;\ l.ori gpr,gpr,lo(symbol) @@ -326,21 +326,21 @@ l.addi r1,r1,-(INT_FRAME_SIZE) ;\ /* r1 is KSP, r30 is __pa(KSP) */ ;\ tophys (r30,r1) ;\ - l.sw PT_GPR12(r30),r12 ;\ + l.sw PT_GPR12(r30),r12 ;\ l.mfspr r12,r0,SPR_EPCR_BASE ;\ l.sw PT_PC(r30),r12 ;\ l.mfspr r12,r0,SPR_ESR_BASE ;\ l.sw PT_SR(r30),r12 ;\ /* save r31 */ ;\ EXCEPTION_T_LOAD_GPR30(r12) ;\ - l.sw PT_GPR30(r30),r12 ;\ + l.sw PT_GPR30(r30),r12 ;\ /* save r10 as was prior to exception */ ;\ EXCEPTION_T_LOAD_GPR10(r12) ;\ - l.sw PT_GPR10(r30),r12 ;\ - /* save PT_SP as was prior to exception */ ;\ + l.sw PT_GPR10(r30),r12 ;\ + /* save PT_SP as was prior to exception */ ;\ EXCEPTION_T_LOAD_SP(r12) ;\ l.sw PT_SP(r30),r12 ;\ - l.sw PT_GPR13(r30),r13 ;\ + l.sw PT_GPR13(r30),r13 ;\ /* --> */ ;\ /* save exception r4, set r4 = EA */ ;\ l.sw PT_GPR4(r30),r4 ;\ @@ -357,6 +357,8 @@ /* =====================================================[ exceptions] === */ + __HEAD + /* ---[ 0x100: RESET exception ]----------------------------------------- */ .org 0x100 /* Jump to .init code at _start which lives in the .head section @@ -394,7 +396,7 @@ _dispatch_do_ipage_fault: .org 0x500 EXCEPTION_HANDLE(_timer_handler) -/* ---[ 0x600: Alignment exception ]-------------------------------------- */ +/* ---[ 0x600: Alignment exception ]------------------------------------- */ .org 0x600 EXCEPTION_HANDLE(_alignment_handler) @@ -424,7 +426,7 @@ _dispatch_do_ipage_fault: .org 0xc00 EXCEPTION_HANDLE(_sys_call_handler) -/* ---[ 0xd00: Floating point exception ]--------------------------------- */ +/* ---[ 0xd00: Floating point exception ]-------------------------------- */ .org 0xd00 EXCEPTION_HANDLE(_fpe_trap_handler) @@ -506,10 +508,10 @@ _dispatch_do_ipage_fault: /* .text*/ -/* This early stuff belongs in HEAD, but some of the functions below definitely +/* This early stuff belongs in the .init.text section, but some of the functions below definitely * don't... */ - __HEAD + __INIT .global _start _start: /* Init r0 to zero as per spec */ @@ -816,7 +818,7 @@ secondary_start: #endif -/* ========================================[ cache ]=== */ +/* ==========================================================[ cache ]=== */ /* alignment here so we don't change memory offsets with * memory controller defined diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index bc1306047837..049bff45f612 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS .text : AT(ADDR(.text) - LOAD_OFFSET) { _stext = .; + HEAD_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT @@ -83,8 +84,6 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_begin = .; - HEAD_TEXT_SECTION - /* Page aligned */ INIT_TEXT_SECTION(PAGE_SIZE) diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 7388edd88986..d08bf7fb3aee 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); return true; } diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c index 6eee6f736f68..654ed159c830 100644 --- a/arch/riscv/kernel/jump_label.c +++ b/arch/riscv/kernel/jump_label.c @@ -36,9 +36,15 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, insn = RISCV_INSN_NOP; } - mutex_lock(&text_mutex); - patch_insn_write(addr, &insn, sizeof(insn)); - mutex_unlock(&text_mutex); + if (early_boot_irqs_disabled) { + riscv_patch_in_stop_machine = 1; + patch_insn_write(addr, &insn, sizeof(insn)); + riscv_patch_in_stop_machine = 0; + } else { + mutex_lock(&text_mutex); + patch_insn_write(addr, &insn, sizeof(insn)); + mutex_unlock(&text_mutex); + } return true; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 016b48fcd6f2..45010e71df86 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -227,7 +227,7 @@ static void __init init_resources(void) static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) { + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { const char *name = of_flat_dt_get_machine_name(); if (name) { diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index dcced4db7fe8..19afd1f23537 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -590,7 +590,7 @@ void kvm_riscv_aia_enable(void) csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) - csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); } void kvm_riscv_aia_disable(void) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..fc53ce748c80 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1566,7 +1566,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) pmd_clear(pmd); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) { struct page *page = pud_page(*pud); struct ptdesc *ptdesc = page_ptdesc(page); @@ -1579,7 +1579,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - pagetable_pmd_dtor(ptdesc); + if (!is_vmemmap) + pagetable_pmd_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1703,7 +1704,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); if (pgtable_l4_enabled) - free_pmd_table(pmd_base, pudp); + free_pmd_table(pmd_base, pudp, is_vmemmap); } } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index abe6e6c0ab98..6087d38c7235 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -234,6 +234,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..3fa28db2fe59 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } @@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } @@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index edbb52ce3f1e..7d12a1305fc9 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..20e6009381ed 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -230,6 +230,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..3e9037690814 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1661,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9eed0c144dad 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(!early_boot_irqs_disabled); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..6a17396c8174 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 097bdc022d0f..ae0b438a2c99 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -36,6 +36,26 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); +struct cpuid_xstate_sizes { + u32 eax; + u32 ebx; + u32 ecx; +}; + +static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init; + +void __init kvm_init_xstate_sizes(void) +{ + u32 ign; + int i; + + for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) { + struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; + + cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign); + } +} + u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { - u32 eax, ebx, ecx, edx, offset; - cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit]; + u32 offset; + /* ECX[1]: 64B alignment in compacted form */ if (compacted) - offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; + offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret; else - offset = ebx; - ret = max(ret, offset + eax); + offset = xs->ebx; + ret = max(ret, offset + xs->eax); } xstate_bv >>= 1; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c8dc66eddefd..f16a7b2c2adc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -31,6 +31,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +void __init kvm_init_xstate_sizes(void); u32 xstate_required_size(u64 xstate_bv, bool compacted); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2e713480933a..c8160baf3838 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13997,6 +13997,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { + kvm_init_xstate_sizes(); + kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..43dcd8c7badc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include <linux/console.h> #include <linux/cpu.h> +#include <linux/instrumentation.h> #include <linux/kexec.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * can safely tag the function body as "instrumentation ok", since + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..a8eb7e0c473c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,10 +20,33 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + +/* * Disabling events is simply a matter of making the event mask * non-zero. */ @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f6c69dbb816..9252652afe59 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include <linux/elfnote.h> #include <linux/init.h> +#include <linux/instrumentation.h> #include <asm/boot.h> #include <asm/asm.h> +#include <asm/frame.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/percpu.h> @@ -20,28 +22,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page; - xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/block/bio.c b/block/bio.c index 699a78c85c75..d5bdc31d88d3 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1171,7 +1171,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) } EXPORT_SYMBOL_GPL(__bio_release_pages); -void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) +void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter) { WARN_ON_ONCE(bio->bi_max_vecs); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e68c725cf8d9..45a395862fbc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 384aa15e8260..a5894ec9696e 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1098,7 +1098,14 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { - inuse = clamp_t(u32, inuse, 1, active); + /* + * It may be tempting to turn this into a clamp expression with + * a lower limit of 1 but active may be 0, which cannot be used + * as an upper limit in that situation. This expression allows + * active to clamp inuse unless it is 0, in which case inuse + * becomes 1. + */ + inuse = min(inuse, active) ?: 1; } iocg->last_inuse = iocg->inuse; diff --git a/block/blk-map.c b/block/blk-map.c index b5fd1d857461..894009b2d881 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -574,7 +574,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL); if (!bio) return -ENOMEM; - bio_iov_bvec_set(bio, (struct iov_iter *)iter); + bio_iov_bvec_set(bio, iter); /* check that the data layout matches the hardware restrictions */ ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 156e9bb07abf..cd5ea6eaa76b 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -275,15 +275,13 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned long i; - mutex_lock(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_dir_lock); + if (!q->mq_sysfs_init_done) - goto unlock; + return; queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); - -unlock: - mutex_unlock(&q->sysfs_dir_lock); } int blk_mq_sysfs_register_hctxs(struct request_queue *q) @@ -292,9 +290,10 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) unsigned long i; int ret = 0; - mutex_lock(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_dir_lock); + if (!q->mq_sysfs_init_done) - goto unlock; + return ret; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -302,8 +301,5 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) break; } -unlock: - mutex_unlock(&q->sysfs_dir_lock); - return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index aa340b097b6e..6b6111513986 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1544,19 +1544,17 @@ static void blk_mq_requeue_work(struct work_struct *work) while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); + list_del_init(&rq->queuelist); /* - * If RQF_DONTPREP ist set, the request has been started by the + * If RQF_DONTPREP is set, the request has been started by the * driver already and might have driver-specific data allocated * already. Insert it into the hctx dispatch list to avoid * block layer merges for the request. */ - if (rq->rq_flags & RQF_DONTPREP) { - list_del_init(&rq->queuelist); + if (rq->rq_flags & RQF_DONTPREP) blk_mq_request_bypass_insert(rq, 0); - } else { - list_del_init(&rq->queuelist); + else blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); - } } while (!list_empty(&flush_list)) { @@ -4455,7 +4453,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, unsigned long i, j; /* protect against switching io scheduler */ - mutex_lock(&q->sysfs_lock); + lockdep_assert_held(&q->sysfs_lock); + for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4488,7 +4487,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); - mutex_unlock(&q->sysfs_lock); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); @@ -4520,10 +4518,14 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, xa_init(&q->hctx_table); + mutex_lock(&q->sysfs_lock); + blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; + mutex_unlock(&q->sysfs_lock); + INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); @@ -4542,6 +4544,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: + mutex_unlock(&q->sysfs_lock); blk_mq_release(q); err_exit: q->mq_ops = NULL; @@ -4922,12 +4925,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, return false; /* q->elevator needs protection from ->sysfs_lock */ - mutex_lock(&q->sysfs_lock); + lockdep_assert_held(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); - goto unlock; + goto out; } INIT_LIST_HEAD(&qe->node); @@ -4937,9 +4940,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); -unlock: - mutex_unlock(&q->sysfs_lock); - +out: return true; } @@ -4968,11 +4969,9 @@ static void blk_mq_elv_switch_back(struct list_head *head, list_del(&qe->node); kfree(qe); - mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); - mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, @@ -4992,8 +4991,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { + mutex_lock(&q->sysfs_dir_lock); + mutex_lock(&q->sysfs_lock); blk_mq_freeze_queue(q); + } /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5049,8 +5051,11 @@ switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); - list_for_each_entry(q, &set->tag_list, tag_set_list) + list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_unfreeze_queue(q); + mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->sysfs_dir_lock); + } /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 4241aea84161..64f70c713d2f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -263,7 +263,7 @@ static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page) static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page) { - return queue_var_show(blk_queue_passthrough_stat(disk->queue), page); + return queue_var_show(!!blk_queue_passthrough_stat(disk->queue), page); } static ssize_t queue_iostats_passthrough_store(struct gendisk *disk, @@ -706,11 +706,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, if (entry->load_module) entry->load_module(disk, page, length); - blk_mq_freeze_queue(q); mutex_lock(&q->sysfs_lock); + blk_mq_freeze_queue(q); res = entry->store(disk, page, length); - mutex_unlock(&q->sysfs_lock); blk_mq_unfreeze_queue(q); + mutex_unlock(&q->sysfs_lock); return res; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 263e28b72053..84da1eadff64 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -41,7 +41,6 @@ static const char *const zone_cond_name[] = { /* * Per-zone write plug. * @node: hlist_node structure for managing the plug using a hash table. - * @link: To list the plug in the zone write plug error list of the disk. * @ref: Zone write plug reference counter. A zone write plug reference is * always at least 1 when the plug is hashed in the disk plug hash table. * The reference is incremented whenever a new BIO needing plugging is @@ -63,7 +62,6 @@ static const char *const zone_cond_name[] = { */ struct blk_zone_wplug { struct hlist_node node; - struct list_head link; refcount_t ref; spinlock_t lock; unsigned int flags; @@ -80,8 +78,8 @@ struct blk_zone_wplug { * - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged, * that is, that write BIOs are being throttled due to a write BIO already * being executed or the zone write plug bio list is not empty. - * - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be - * recovered with a report zone to update the zone write pointer offset. + * - BLK_ZONE_WPLUG_NEED_WP_UPDATE: Indicates that we lost track of a zone + * write pointer offset and need to update it. * - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed * from the disk hash table and that the initial reference to the zone * write plug set when the plug was first added to the hash table has been @@ -91,11 +89,9 @@ struct blk_zone_wplug { * freed once all remaining references from BIOs or functions are dropped. */ #define BLK_ZONE_WPLUG_PLUGGED (1U << 0) -#define BLK_ZONE_WPLUG_ERROR (1U << 1) +#define BLK_ZONE_WPLUG_NEED_WP_UPDATE (1U << 1) #define BLK_ZONE_WPLUG_UNHASHED (1U << 2) -#define BLK_ZONE_WPLUG_BUSY (BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR) - /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. * @zone_cond: BLK_ZONE_COND_XXX. @@ -115,6 +111,30 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) } EXPORT_SYMBOL_GPL(blk_zone_cond_str); +struct disk_report_zones_cb_args { + struct gendisk *disk; + report_zones_cb user_cb; + void *user_data; +}; + +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone); + +static int disk_report_zones_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct disk_report_zones_cb_args *args = data; + struct gendisk *disk = args->disk; + + if (disk->zone_wplugs_hash) + disk_zone_wplug_sync_wp_offset(disk, zone); + + if (!args->user_cb) + return 0; + + return args->user_cb(zone, idx, args->user_data); +} + /** * blkdev_report_zones - Get zones information * @bdev: Target block device @@ -139,6 +159,11 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, { struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); + struct disk_report_zones_cb_args args = { + .disk = disk, + .user_cb = cb, + .user_data = data, + }; if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; @@ -146,7 +171,8 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, if (!nr_zones || sector >= capacity) return 0; - return disk->fops->report_zones(disk, sector, nr_zones, cb, data); + return disk->fops->report_zones(disk, sector, nr_zones, + disk_report_zones_cb, &args); } EXPORT_SYMBOL_GPL(blkdev_report_zones); @@ -427,7 +453,7 @@ static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) { if (refcount_dec_and_test(&zwplug->ref)) { WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); - WARN_ON_ONCE(!list_empty(&zwplug->link)); + WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)); call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); @@ -441,8 +467,8 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return false; - /* If the zone write plug is still busy, it cannot be removed. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + /* If the zone write plug is still plugged, it cannot be removed. */ + if (zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) return false; /* @@ -525,12 +551,11 @@ again: return NULL; INIT_HLIST_NODE(&zwplug->node); - INIT_LIST_HEAD(&zwplug->link); refcount_set(&zwplug->ref, 2); spin_lock_init(&zwplug->lock); zwplug->flags = 0; zwplug->zone_no = zno; - zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1); + zwplug->wp_offset = bdev_offset_from_zone_start(disk->part0, sector); bio_list_init(&zwplug->bio_list); INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work); zwplug->disk = disk; @@ -574,124 +599,81 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) } /* - * Abort (fail) all plugged BIOs of a zone write plug that are not aligned - * with the assumed write pointer location of the zone when the BIO will - * be unplugged. + * Set a zone write plug write pointer offset to the specified value. + * This aborts all plugged BIOs, which is fine as this function is called for + * a zone reset operation, a zone finish operation or if the zone needs a wp + * update from a report zone after a write error. */ -static void disk_zone_wplug_abort_unaligned(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - unsigned int wp_offset = zwplug->wp_offset; - struct bio_list bl = BIO_EMPTY_LIST; - struct bio *bio; - - while ((bio = bio_list_pop(&zwplug->bio_list))) { - if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) || - (bio_op(bio) != REQ_OP_ZONE_APPEND && - bio_offset_from_zone_start(bio) != wp_offset)) { - blk_zone_wplug_bio_io_error(zwplug, bio); - continue; - } - - wp_offset += bio_sectors(bio); - bio_list_add(&bl, bio); - } - - bio_list_merge(&zwplug->bio_list, &bl); -} - -static inline void disk_zone_wplug_set_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) +static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, + struct blk_zone_wplug *zwplug, + unsigned int wp_offset) { - unsigned long flags; + lockdep_assert_held(&zwplug->lock); - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) - return; + /* Update the zone write pointer and abort all plugged BIOs. */ + zwplug->flags &= ~BLK_ZONE_WPLUG_NEED_WP_UPDATE; + zwplug->wp_offset = wp_offset; + disk_zone_wplug_abort(zwplug); /* - * At this point, we already have a reference on the zone write plug. - * However, since we are going to add the plug to the disk zone write - * plugs work list, increase its reference count. This reference will - * be dropped in disk_zone_wplugs_work() once the error state is - * handled, or in disk_zone_wplug_clear_error() if the zone is reset or - * finished. + * The zone write plug now has no BIO plugged: remove it from the + * hash table so that it cannot be seen. The plug will be freed + * when the last reference is dropped. */ - zwplug->flags |= BLK_ZONE_WPLUG_ERROR; - refcount_inc(&zwplug->ref); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); + if (disk_should_remove_zone_wplug(disk, zwplug)) + disk_remove_zone_wplug(disk, zwplug); } -static inline void disk_zone_wplug_clear_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) +static unsigned int blk_zone_wp_offset(struct blk_zone *zone) { - unsigned long flags; - - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - return; - - /* - * We are racing with the error handling work which drops the reference - * on the zone write plug after handling the error state. So remove the - * plug from the error list and drop its reference count only if the - * error handling has not yet started, that is, if the zone write plug - * is still listed. - */ - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - if (!list_empty(&zwplug->link)) { - list_del_init(&zwplug->link); - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - disk_put_zone_wplug(zwplug); + switch (zone->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + return zone->wp - zone->start; + case BLK_ZONE_COND_FULL: + return zone->len; + case BLK_ZONE_COND_EMPTY: + return 0; + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + default: + /* + * Conventional, offline and read-only zones do not have a valid + * write pointer. + */ + return UINT_MAX; } - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); } -/* - * Set a zone write plug write pointer offset to either 0 (zone reset case) - * or to the zone size (zone finish case). This aborts all plugged BIOs, which - * is fine to do as doing a zone reset or zone finish while writes are in-flight - * is a mistake from the user which will most likely cause all plugged BIOs to - * fail anyway. - */ -static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, - struct blk_zone_wplug *zwplug, - unsigned int wp_offset) +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone) { + struct blk_zone_wplug *zwplug; unsigned long flags; - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * Make sure that a BIO completion or another zone reset or finish - * operation has not already removed the plug from the hash table. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { - spin_unlock_irqrestore(&zwplug->lock, flags); + zwplug = disk_get_zone_wplug(disk, zone->start); + if (!zwplug) return; - } - /* Update the zone write pointer and abort all plugged BIOs. */ - zwplug->wp_offset = wp_offset; - disk_zone_wplug_abort(zwplug); + spin_lock_irqsave(&zwplug->lock, flags); + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + disk_zone_wplug_set_wp_offset(disk, zwplug, + blk_zone_wp_offset(zone)); + spin_unlock_irqrestore(&zwplug->lock, flags); - /* - * Updating the write pointer offset puts back the zone - * in a good state. So clear the error flag and decrement the - * error count if we were in error state. - */ - disk_zone_wplug_clear_error(disk, zwplug); + disk_put_zone_wplug(zwplug); +} - /* - * The zone write plug now has no BIO plugged: remove it from the - * hash table so that it cannot be seen. The plug will be freed - * when the last reference is dropped. - */ - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); +static int disk_zone_sync_wp_offset(struct gendisk *disk, sector_t sector) +{ + struct disk_report_zones_cb_args args = { + .disk = disk, + }; - spin_unlock_irqrestore(&zwplug->lock, flags); + return disk->fops->report_zones(disk, sector, 1, + disk_report_zones_cb, &args); } static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, @@ -700,6 +682,7 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, struct gendisk *disk = bio->bi_bdev->bd_disk; sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; + unsigned long flags; /* Conventional zones cannot be reset nor finished. */ if (!bdev_zone_is_seq(bio->bi_bdev, sector)) { @@ -708,6 +691,15 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, } /* + * No-wait reset or finish BIOs do not make much sense as the callers + * issue these as blocking operations in most cases. To avoid issues + * the BIO execution potentially failing with BLK_STS_AGAIN, warn about + * REQ_NOWAIT being set and ignore that flag. + */ + if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) + bio->bi_opf &= ~REQ_NOWAIT; + + /* * If we have a zone write plug, set its write pointer offset to 0 * (reset case) or to the zone size (finish case). This will abort all * BIOs plugged for the target zone. It is fine as resetting or @@ -716,7 +708,9 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, */ zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } @@ -727,6 +721,7 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug; + unsigned long flags; sector_t sector; /* @@ -738,7 +733,9 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) sector += disk->queue->limits.chunk_sectors) { zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, 0); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } } @@ -746,10 +743,26 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) return false; } -static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, - struct bio *bio, unsigned int nr_segs) +static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, + struct blk_zone_wplug *zwplug) { /* + * Take a reference on the zone write plug and schedule the submission + * of the next plugged BIO. blk_zone_wplug_bio_work() will release the + * reference we take here. + */ + WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); + refcount_inc(&zwplug->ref); + queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); +} + +static inline void disk_zone_wplug_add_bio(struct gendisk *disk, + struct blk_zone_wplug *zwplug, + struct bio *bio, unsigned int nr_segs) +{ + bool schedule_bio_work = false; + + /* * Grab an extra reference on the BIO request queue usage counter. * This reference will be reused to submit a request for the BIO for * blk-mq devices and dropped when the BIO is failed and after @@ -765,6 +778,16 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, bio_clear_polled(bio); /* + * REQ_NOWAIT BIOs are always handled using the zone write plug BIO + * work, which can block. So clear the REQ_NOWAIT flag and schedule the + * work if this is the first BIO we are plugging. + */ + if (bio->bi_opf & REQ_NOWAIT) { + schedule_bio_work = !(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); + bio->bi_opf &= ~REQ_NOWAIT; + } + + /* * Reuse the poll cookie field to store the number of segments when * split to the hardware limits. */ @@ -777,6 +800,11 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, * at the tail of the list to preserve the sequential write order. */ bio_list_add(&zwplug->bio_list, bio); + + zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; + + if (schedule_bio_work) + disk_zone_wplug_schedule_bio_work(disk, zwplug); } /* @@ -890,12 +918,22 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, struct gendisk *disk = bio->bi_bdev->bd_disk; /* + * If we lost track of the zone write pointer due to a write error, + * the user must either execute a report zones, reset the zone or finish + * the to recover a reliable write pointer position. Fail BIOs if the + * user did not do that as we cannot handle emulated zone append + * otherwise. + */ + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + return false; + + /* * Check that the user is not attempting to write to a full zone. * We know such BIO will fail, and that would potentially overflow our * write pointer offset beyond the end of the zone. */ if (disk_zone_wplug_is_full(disk, zwplug)) - goto err; + return false; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { /* @@ -914,24 +952,18 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, bio_set_flag(bio, BIO_EMULATES_ZONE_APPEND); } else { /* - * Check for non-sequential writes early because we avoid a - * whole lot of error handling trouble if we don't send it off - * to the driver. + * Check for non-sequential writes early as we know that BIOs + * with a start sector not unaligned to the zone write pointer + * will fail. */ if (bio_offset_from_zone_start(bio) != zwplug->wp_offset) - goto err; + return false; } /* Advance the zone write pointer offset. */ zwplug->wp_offset += bio_sectors(bio); return true; - -err: - /* We detected an invalid write BIO: schedule error recovery. */ - disk_zone_wplug_set_error(disk, zwplug); - kblockd_schedule_work(&disk->zone_wplugs_work); - return false; } static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) @@ -970,7 +1002,10 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags); if (!zwplug) { - bio_io_error(bio); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + else + bio_io_error(bio); return true; } @@ -978,18 +1013,20 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* - * If the zone is already plugged or has a pending error, add the BIO - * to the plug BIO list. Otherwise, plug and let the BIO execute. + * If the zone is already plugged, add the BIO to the plug BIO list. + * Do the same for REQ_NOWAIT BIOs to ensure that we will not see a + * BLK_STS_AGAIN failure if we let the BIO execute. + * Otherwise, plug and let the BIO execute. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + if ((zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) || + (bio->bi_opf & REQ_NOWAIT)) goto plug; - /* - * If an error is detected when preparing the BIO, add it to the BIO - * list so that error recovery can deal with it. - */ - if (!blk_zone_wplug_prepare_bio(zwplug, bio)) - goto plug; + if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { + spin_unlock_irqrestore(&zwplug->lock, flags); + bio_io_error(bio); + return true; + } zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; @@ -998,8 +1035,7 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) return false; plug: - zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; - blk_zone_wplug_add_bio(zwplug, bio, nr_segs); + disk_zone_wplug_add_bio(disk, zwplug, bio, nr_segs); spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1083,19 +1119,6 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) } EXPORT_SYMBOL_GPL(blk_zone_plug_bio); -static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - /* - * Take a reference on the zone write plug and schedule the submission - * of the next plugged BIO. blk_zone_wplug_bio_work() will release the - * reference we take here. - */ - WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); - refcount_inc(&zwplug->ref); - queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); -} - static void disk_zone_wplug_unplug_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug) { @@ -1103,16 +1126,6 @@ static void disk_zone_wplug_unplug_bio(struct gendisk *disk, spin_lock_irqsave(&zwplug->lock, flags); - /* - * If we had an error, schedule error recovery. The recovery work - * will restart submission of plugged BIOs. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) { - spin_unlock_irqrestore(&zwplug->lock, flags); - kblockd_schedule_work(&disk->zone_wplugs_work); - return; - } - /* Schedule submission of the next plugged BIO if we have one. */ if (!bio_list_empty(&zwplug->bio_list)) { disk_zone_wplug_schedule_bio_work(disk, zwplug); @@ -1155,12 +1168,13 @@ void blk_zone_write_plug_bio_endio(struct bio *bio) } /* - * If the BIO failed, mark the plug as having an error to trigger - * recovery. + * If the BIO failed, abort all plugged BIOs and mark the plug as + * needing a write pointer update. */ if (bio->bi_status != BLK_STS_OK) { spin_lock_irqsave(&zwplug->lock, flags); - disk_zone_wplug_set_error(disk, zwplug); + disk_zone_wplug_abort(zwplug); + zwplug->flags |= BLK_ZONE_WPLUG_NEED_WP_UPDATE; spin_unlock_irqrestore(&zwplug->lock, flags); } @@ -1216,6 +1230,7 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) */ spin_lock_irqsave(&zwplug->lock, flags); +again: bio = bio_list_pop(&zwplug->bio_list); if (!bio) { zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; @@ -1224,10 +1239,8 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) } if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { - /* Error recovery will decide what to do with the BIO. */ - bio_list_add_head(&zwplug->bio_list, bio); - spin_unlock_irqrestore(&zwplug->lock, flags); - goto put_zwplug; + blk_zone_wplug_bio_io_error(zwplug, bio); + goto again; } spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1249,120 +1262,6 @@ put_zwplug: disk_put_zone_wplug(zwplug); } -static unsigned int blk_zone_wp_offset(struct blk_zone *zone) -{ - switch (zone->cond) { - case BLK_ZONE_COND_IMP_OPEN: - case BLK_ZONE_COND_EXP_OPEN: - case BLK_ZONE_COND_CLOSED: - return zone->wp - zone->start; - case BLK_ZONE_COND_FULL: - return zone->len; - case BLK_ZONE_COND_EMPTY: - return 0; - case BLK_ZONE_COND_NOT_WP: - case BLK_ZONE_COND_OFFLINE: - case BLK_ZONE_COND_READONLY: - default: - /* - * Conventional, offline and read-only zones do not have a valid - * write pointer. - */ - return UINT_MAX; - } -} - -static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone, - unsigned int idx, void *data) -{ - struct blk_zone *zonep = data; - - *zonep = *zone; - return 0; -} - -static void disk_zone_wplug_handle_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - sector_t zone_start_sector = - bdev_zone_sectors(disk->part0) * zwplug->zone_no; - unsigned int noio_flag; - struct blk_zone zone; - unsigned long flags; - int ret; - - /* Get the current zone information from the device. */ - noio_flag = memalloc_noio_save(); - ret = disk->fops->report_zones(disk, zone_start_sector, 1, - blk_zone_wplug_report_zone_cb, &zone); - memalloc_noio_restore(noio_flag); - - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * A zone reset or finish may have cleared the error already. In such - * case, do nothing as the report zones may have seen the "old" write - * pointer value before the reset/finish operation completed. - */ - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - goto unlock; - - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - - if (ret != 1) { - /* - * We failed to get the zone information, meaning that something - * is likely really wrong with the device. Abort all remaining - * plugged BIOs as otherwise we could endup waiting forever on - * plugged BIOs to complete if there is a queue freeze on-going. - */ - disk_zone_wplug_abort(zwplug); - goto unplug; - } - - /* Update the zone write pointer offset. */ - zwplug->wp_offset = blk_zone_wp_offset(&zone); - disk_zone_wplug_abort_unaligned(disk, zwplug); - - /* Restart BIO submission if we still have any BIO left. */ - if (!bio_list_empty(&zwplug->bio_list)) { - disk_zone_wplug_schedule_bio_work(disk, zwplug); - goto unlock; - } - -unplug: - zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); - -unlock: - spin_unlock_irqrestore(&zwplug->lock, flags); -} - -static void disk_zone_wplugs_work(struct work_struct *work) -{ - struct gendisk *disk = - container_of(work, struct gendisk, zone_wplugs_work); - struct blk_zone_wplug *zwplug; - unsigned long flags; - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - - while (!list_empty(&disk->zone_wplugs_err_list)) { - zwplug = list_first_entry(&disk->zone_wplugs_err_list, - struct blk_zone_wplug, link); - list_del_init(&zwplug->link); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); - - disk_zone_wplug_handle_error(disk, zwplug); - disk_put_zone_wplug(zwplug); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - } - - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); -} - static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) { return 1U << disk->zone_wplugs_hash_bits; @@ -1371,8 +1270,6 @@ static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) void disk_init_zone_resources(struct gendisk *disk) { spin_lock_init(&disk->zone_wplugs_lock); - INIT_LIST_HEAD(&disk->zone_wplugs_err_list); - INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work); } /* @@ -1471,8 +1368,6 @@ void disk_free_zone_resources(struct gendisk *disk) if (!disk->zone_wplugs_pool) return; - cancel_work_sync(&disk->zone_wplugs_work); - if (disk->zone_wplugs_wq) { destroy_workqueue(disk->zone_wplugs_wq); disk->zone_wplugs_wq = NULL; @@ -1669,6 +1564,8 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx, if (!disk->zone_wplugs_hash) return 0; + disk_zone_wplug_sync_wp_offset(disk, zone); + wp_offset = blk_zone_wp_offset(zone); if (!wp_offset || wp_offset >= zone->capacity) return 0; @@ -1799,6 +1696,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) memalloc_noio_restore(noio_flag); return ret; } + ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); if (!ret) { @@ -1835,6 +1733,48 @@ int blk_revalidate_disk_zones(struct gendisk *disk) } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); +/** + * blk_zone_issue_zeroout - zero-fill a block range in a zone + * @bdev: blockdev to write + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * + * Description: + * Zero-fill a block range in a zone (@sector must be equal to the zone write + * pointer), handling potential errors due to the (initially unknown) lack of + * hardware offload (See blkdev_issue_zeroout()). + */ +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask) +{ + int ret; + + if (WARN_ON_ONCE(!bdev_is_zoned(bdev))) + return -EIO; + + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, + BLKDEV_ZERO_NOFALLBACK); + if (ret != -EOPNOTSUPP) + return ret; + + /* + * The failed call to blkdev_issue_zeroout() advanced the zone write + * pointer. Undo this using a report zone to update the zone write + * pointer to the correct current value. + */ + ret = disk_zone_sync_wp_offset(bdev->bd_disk, sector); + if (ret != 1) + return ret < 0 ? ret : -EIO; + + /* + * Retry without BLKDEV_ZERO_NOFALLBACK to force the fallback to a + * regular write with zero-pages. + */ + return blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, 0); +} +EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout); + #ifdef CONFIG_BLK_DEBUG_FS int queue_zone_wplugs_show(void *data, struct seq_file *m) diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 91b3789f710e..5528347b5fcf 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -698,8 +698,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, list_add(&rq->queuelist, &per_prio->dispatch); rq->fifo_time = jiffies; } else { - struct list_head *insert_before; - deadline_add_rq_rb(per_prio, rq); if (rq_mergeable(rq)) { @@ -712,8 +710,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * set expire time and add to fifo list */ rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - insert_before = &per_prio->fifo_list[data_dir]; - list_add_tail(&rq->queuelist, insert_before); + list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); } } diff --git a/crypto/rsassa-pkcs1.c b/crypto/rsassa-pkcs1.c index 4d077fc96076..f68ffd338f48 100644 --- a/crypto/rsassa-pkcs1.c +++ b/crypto/rsassa-pkcs1.c @@ -163,10 +163,6 @@ static int rsassa_pkcs1_sign(struct crypto_sig *tfm, struct rsassa_pkcs1_inst_ctx *ictx = sig_instance_ctx(inst); const struct hash_prefix *hash_prefix = ictx->hash_prefix; struct rsassa_pkcs1_ctx *ctx = crypto_sig_ctx(tfm); - unsigned int child_reqsize = crypto_akcipher_reqsize(ctx->child); - struct akcipher_request *child_req __free(kfree_sensitive) = NULL; - struct scatterlist in_sg[3], out_sg; - struct crypto_wait cwait; unsigned int pad_len; unsigned int ps_end; unsigned int len; @@ -187,37 +183,25 @@ static int rsassa_pkcs1_sign(struct crypto_sig *tfm, pad_len = ctx->key_size - slen - hash_prefix->size - 1; - child_req = kmalloc(sizeof(*child_req) + child_reqsize + pad_len, - GFP_KERNEL); - if (!child_req) - return -ENOMEM; - /* RFC 8017 sec 8.2.1 step 1 - EMSA-PKCS1-v1_5 encoding generation */ - in_buf = (u8 *)(child_req + 1) + child_reqsize; + in_buf = dst; + memmove(in_buf + pad_len + hash_prefix->size, src, slen); + memcpy(in_buf + pad_len, hash_prefix->data, hash_prefix->size); + ps_end = pad_len - 1; in_buf[0] = 0x01; memset(in_buf + 1, 0xff, ps_end - 1); in_buf[ps_end] = 0x00; - /* RFC 8017 sec 8.2.1 step 2 - RSA signature */ - crypto_init_wait(&cwait); - sg_init_table(in_sg, 3); - sg_set_buf(&in_sg[0], in_buf, pad_len); - sg_set_buf(&in_sg[1], hash_prefix->data, hash_prefix->size); - sg_set_buf(&in_sg[2], src, slen); - sg_init_one(&out_sg, dst, dlen); - akcipher_request_set_tfm(child_req, ctx->child); - akcipher_request_set_crypt(child_req, in_sg, &out_sg, - ctx->key_size - 1, dlen); - akcipher_request_set_callback(child_req, CRYPTO_TFM_REQ_MAY_SLEEP, - crypto_req_done, &cwait); - err = crypto_akcipher_decrypt(child_req); - err = crypto_wait_req(err, &cwait); - if (err) + /* RFC 8017 sec 8.2.1 step 2 - RSA signature */ + err = crypto_akcipher_sync_decrypt(ctx->child, in_buf, + ctx->key_size - 1, in_buf, + ctx->key_size); + if (err < 0) return err; - len = child_req->dst_len; + len = err; pad_len = ctx->key_size - len; /* Four billion to one */ @@ -239,8 +223,8 @@ static int rsassa_pkcs1_verify(struct crypto_sig *tfm, struct rsassa_pkcs1_ctx *ctx = crypto_sig_ctx(tfm); unsigned int child_reqsize = crypto_akcipher_reqsize(ctx->child); struct akcipher_request *child_req __free(kfree_sensitive) = NULL; - struct scatterlist in_sg, out_sg; struct crypto_wait cwait; + struct scatterlist sg; unsigned int dst_len; unsigned int pos; u8 *out_buf; @@ -259,13 +243,12 @@ static int rsassa_pkcs1_verify(struct crypto_sig *tfm, return -ENOMEM; out_buf = (u8 *)(child_req + 1) + child_reqsize; + memcpy(out_buf, src, slen); crypto_init_wait(&cwait); - sg_init_one(&in_sg, src, slen); - sg_init_one(&out_sg, out_buf, ctx->key_size); + sg_init_one(&sg, out_buf, slen); akcipher_request_set_tfm(child_req, ctx->child); - akcipher_request_set_crypt(child_req, &in_sg, &out_sg, - slen, ctx->key_size); + akcipher_request_set_crypt(child_req, &sg, &sg, slen, slen); akcipher_request_set_callback(child_req, CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &cwait); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 95f78383bbdb..bff2d099f469 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -232,8 +232,6 @@ acpi_remove_address_space_handler(acpi_handle device, /* Now we can delete the handler object */ - acpi_os_release_mutex(handler_obj->address_space. - context_mutex); acpi_ut_remove_reference(handler_obj); goto unlock_and_exit; } diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 5429ec9ef06f..a5d47819b3a4 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -454,8 +454,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, if (cmd_rc) *cmd_rc = -EINVAL; - if (cmd == ND_CMD_CALL) + if (cmd == ND_CMD_CALL) { + if (!buf || buf_len < sizeof(*call_pkg)) + return -EINVAL; + call_pkg = buf; + } + func = cmd_to_func(nfit_mem, cmd, call_pkg, &family); if (func < 0) return func; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 7fe842dae1ec..821867de43be 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -250,6 +250,9 @@ static bool acpi_decode_space(struct resource_win *win, switch (addr->resource_type) { case ACPI_MEMORY_RANGE: acpi_dev_memresource_flags(res, len, wp); + + if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) + res->flags |= IORESOURCE_PREFETCH; break; case ACPI_IO_RANGE: acpi_dev_ioresource_flags(res, len, iodec, @@ -265,9 +268,6 @@ static bool acpi_decode_space(struct resource_win *win, if (addr->producer_consumer == ACPI_PRODUCER) res->flags |= IORESOURCE_WINDOW; - if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) - res->flags |= IORESOURCE_PREFETCH; - return !(res->flags & IORESOURCE_DISABLED); } diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index b1b40e9551de..c8c817c51230 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -348,6 +348,7 @@ static int highbank_initialize_phys(struct device *dev, void __iomem *addr) phy_nodes[phy] = phy_data.np; cphy_base[phy] = of_iomap(phy_nodes[phy], 0); if (cphy_base[phy] == NULL) { + of_node_put(phy_data.np); return 0; } phy_count += 1; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c index 1b9b7bccdeff..45e130b901eb 100644 --- a/drivers/crypto/hisilicon/debugfs.c +++ b/drivers/crypto/hisilicon/debugfs.c @@ -192,7 +192,7 @@ static int qm_sqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->sqc) { - memcpy(&sqc, qm->sqc + qp_id * sizeof(struct qm_sqc), sizeof(struct qm_sqc)); + memcpy(&sqc, qm->sqc + qp_id, sizeof(struct qm_sqc)); sqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); sqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &sqc, sizeof(struct qm_sqc), "SOFT SQC"); @@ -229,7 +229,7 @@ static int qm_cqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->cqc) { - memcpy(&cqc, qm->cqc + qp_id * sizeof(struct qm_cqc), sizeof(struct qm_cqc)); + memcpy(&cqc, qm->cqc + qp_id, sizeof(struct qm_cqc)); cqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); cqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &cqc, sizeof(struct qm_cqc), "SOFT CQC"); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index d77899650798..b98b1ccffd1c 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region_params *p = &cxlr->params; struct cxl_decoder *cxld = cxl_rr->decoder; struct cxl_switch_decoder *cxlsd; + struct cxl_port *iter = port; u16 eig, peig; u8 eiw, peiw; @@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port, cxlsd = to_cxl_switch_decoder(&cxld->dev); if (cxl_rr->nr_targets_set) { - int i, distance; + int i, distance = 1; + struct cxl_region_ref *cxl_rr_iter; /* - * Passthrough decoders impose no distance requirements between - * peers + * The "distance" between peer downstream ports represents which + * endpoint positions in the region interleave a given port can + * host. + * + * For example, at the root of a hierarchy the distance is + * always 1 as every index targets a different host-bridge. At + * each subsequent switch level those ports map every Nth region + * position where N is the width of the switch == distance. */ - if (cxl_rr->nr_targets == 1) - distance = 0; - else - distance = p->nr_targets / cxl_rr->nr_targets; + do { + cxl_rr_iter = cxl_rr_load(iter, cxlr); + distance *= cxl_rr_iter->nr_targets; + iter = to_cxl_port(iter->dev.parent); + } while (!is_cxl_root(iter)); + distance *= cxlrd->cxlsd.cxld.interleave_ways; + for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 0241d1d7133a..6d94ff4a4f1a 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -836,6 +836,9 @@ static ssize_t rcd_pcie_cap_emit(struct device *dev, u16 offset, char *buf, size if (!root_dev) return -ENXIO; + if (!dport->regs.rcd_pcie_cap) + return -ENXIO; + guard(device)(root_dev); if (!root_dev->driver) return -ENXIO; @@ -1032,8 +1035,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - rc = cxl_pci_ras_unmask(pdev); - if (rc) + if (cxl_pci_ras_unmask(pdev)) dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); pci_save_state(pdev); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ddfbdb66b794..5d356b7c4589 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3362,36 +3362,24 @@ static bool dct_ecc_enabled(struct amd64_pvt *pvt) static bool umc_ecc_enabled(struct amd64_pvt *pvt) { - u8 umc_en_mask = 0, ecc_en_mask = 0; - u16 nid = pvt->mc_node_id; struct amd64_umc *umc; - u8 ecc_en = 0, i; + bool ecc_en = false; + int i; + /* Check whether at least one UMC is enabled: */ for_each_umc(i) { umc = &pvt->umc[i]; - /* Only check enabled UMCs. */ - if (!(umc->sdp_ctrl & UMC_SDP_INIT)) - continue; - - umc_en_mask |= BIT(i); - - if (umc->umc_cap_hi & UMC_ECC_ENABLED) - ecc_en_mask |= BIT(i); + if (umc->sdp_ctrl & UMC_SDP_INIT && + umc->umc_cap_hi & UMC_ECC_ENABLED) { + ecc_en = true; + break; + } } - /* Check whether at least one UMC is enabled: */ - if (umc_en_mask) - ecc_en = umc_en_mask == ecc_en_mask; - else - edac_dbg(0, "Node %d: No enabled UMCs.\n", nid); - - edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled")); + edac_dbg(3, "Node %d: DRAM ECC %s.\n", pvt->mc_node_id, (ecc_en ? "enabled" : "disabled")); - if (!ecc_en) - return false; - else - return true; + return ecc_en; } static inline void diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index eb17d03b66fe..dfda5ffc14db 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) return valid; } -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { int id, ret; + uuid_t uuid; struct device *dev; struct ffa_device *ffa_dev; + if (!part_info) + return NULL; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); if (id < 0) return NULL; @@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; - ffa_dev->vm_id = vm_id; + ffa_dev->vm_id = part_info->id; + ffa_dev->properties = part_info->properties; ffa_dev->ops = ops; - uuid_copy(&ffa_dev->uuid, uuid); + import_uuid(&uuid, (u8 *)part_info->uuid); + uuid_copy(&ffa_dev->uuid, &uuid); ret = device_register(&ffa_dev->dev); if (ret) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b14cbdae94e8..2c2ec3c35f15 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = { static int ffa_setup_partitions(void) { int count, idx, ret; - uuid_t uuid; struct ffa_device *ffa_dev; struct ffa_dev_part_info *info; struct ffa_partition_info *pbuf, *tpbuf; @@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void) xa_init(&drv_info->partition_info); for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) { - import_uuid(&uuid, (u8 *)tpbuf->uuid); - /* Note that if the UUID will be uuid_null, that will require * ffa_bus_notifier() to find the UUID of this partition id * with help of ffa_device_match_uuid(). FF-A v1.1 and above * provides UUID here for each partition as part of the * discovery API and the same is passed. */ - ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops); + ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops); if (!ffa_dev) { pr_err("%s: failed to register partition ID 0x%x\n", __func__, tpbuf->id); continue; } - ffa_dev->properties = tpbuf->properties; - if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) ffa_mode_32bit_set(ffa_dev); diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 2883ed24a84d..a01bf5e47301 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT config IMX_SCMI_MISC_EXT tristate "i.MX SCMI MISC EXTENSION" depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + depends on IMX_SCMI_MISC_DRV default y if ARCH_MXC help This enables i.MX System MISC control logic such as gpio expander diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index e312d731f4a3..5fe61b9ab5f9 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -76,10 +76,6 @@ config EFI_ZBOOT bool "Enable the generic EFI decompressor" depends on EFI_GENERIC_STUB && !ARM select HAVE_KERNEL_GZIP - select HAVE_KERNEL_LZ4 - select HAVE_KERNEL_LZMA - select HAVE_KERNEL_LZO - select HAVE_KERNEL_XZ select HAVE_KERNEL_ZSTD help Create the bootable image as an EFI application that carries the diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index 7a81c0ce4780..4bb7b0584bc9 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -75,8 +75,6 @@ static LIST_HEAD(entry_list); struct esre_attribute { struct attribute attr; ssize_t (*show)(struct esre_entry *entry, char *buf); - ssize_t (*store)(struct esre_entry *entry, - const char *buf, size_t count); }; static struct esre_entry *to_entry(struct kobject *kobj) diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 65ffd0b760b2..48842b5c106b 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -12,22 +12,16 @@ quiet_cmd_copy_and_pad = PAD $@ $(obj)/vmlinux.bin: $(obj)/$(EFI_ZBOOT_PAYLOAD) FORCE $(call if_changed,copy_and_pad) -comp-type-$(CONFIG_KERNEL_GZIP) := gzip -comp-type-$(CONFIG_KERNEL_LZ4) := lz4 -comp-type-$(CONFIG_KERNEL_LZMA) := lzma -comp-type-$(CONFIG_KERNEL_LZO) := lzo -comp-type-$(CONFIG_KERNEL_XZ) := xzkern -comp-type-$(CONFIG_KERNEL_ZSTD) := zstd22 - # in GZIP, the appended le32 carrying the uncompressed size is part of the # format, but in other cases, we just append it at the end for convenience, # causing the original tools to complain when checking image integrity. -# So disregard it when calculating the payload size in the zimage header. -zboot-method-y := $(comp-type-y)_with_size -zboot-size-len-y := 4 +comp-type-y := gzip +zboot-method-y := gzip +zboot-size-len-y := 0 -zboot-method-$(CONFIG_KERNEL_GZIP) := gzip -zboot-size-len-$(CONFIG_KERNEL_GZIP) := 0 +comp-type-$(CONFIG_KERNEL_ZSTD) := zstd +zboot-method-$(CONFIG_KERNEL_ZSTD) := zstd22_with_size +zboot-size-len-$(CONFIG_KERNEL_ZSTD) := 4 $(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE $(call if_changed,$(zboot-method-y)) diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 477d3f32d99a..907cd149c40a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,7 +25,6 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" - depends on IMX_SCMI_MISC_EXT || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 56fee58e281e..93ee3aa092f8 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -482,8 +482,9 @@ config GPIO_MT7621 Say yes here to support the Mediatek MT7621 SoC GPIO device. config GPIO_MVEBU - def_bool y + bool "Marvell Orion and EBU GPIO support" if COMPILE_TEST depends on PLAT_ORION || ARCH_MVEBU || COMPILE_TEST + default PLAT_ORION || ARCH_MVEBU select GENERIC_IRQ_CHIP select REGMAP_MMIO diff --git a/drivers/gpio/gpio-graniterapids.c b/drivers/gpio/gpio-graniterapids.c index f2e911a3d2ca..ad6a045fd3d2 100644 --- a/drivers/gpio/gpio-graniterapids.c +++ b/drivers/gpio/gpio-graniterapids.c @@ -32,12 +32,14 @@ #define GNR_PINS_PER_REG 32 #define GNR_NUM_REGS DIV_ROUND_UP(GNR_NUM_PINS, GNR_PINS_PER_REG) -#define GNR_CFG_BAR 0x00 +#define GNR_CFG_PADBAR 0x00 #define GNR_CFG_LOCK_OFFSET 0x04 -#define GNR_GPI_STATUS_OFFSET 0x20 +#define GNR_GPI_STATUS_OFFSET 0x14 #define GNR_GPI_ENABLE_OFFSET 0x24 -#define GNR_CFG_DW_RX_MASK GENMASK(25, 22) +#define GNR_CFG_DW_HOSTSW_MODE BIT(27) +#define GNR_CFG_DW_RX_MASK GENMASK(23, 22) +#define GNR_CFG_DW_INTSEL_MASK GENMASK(21, 14) #define GNR_CFG_DW_RX_DISABLE FIELD_PREP(GNR_CFG_DW_RX_MASK, 2) #define GNR_CFG_DW_RX_EDGE FIELD_PREP(GNR_CFG_DW_RX_MASK, 1) #define GNR_CFG_DW_RX_LEVEL FIELD_PREP(GNR_CFG_DW_RX_MASK, 0) @@ -50,6 +52,7 @@ * struct gnr_gpio - Intel Granite Rapids-D vGPIO driver state * @gc: GPIO controller interface * @reg_base: base address of the GPIO registers + * @pad_base: base address of the vGPIO pad configuration registers * @ro_bitmap: bitmap of read-only pins * @lock: guard the registers * @pad_backup: backup of the register state for suspend @@ -57,6 +60,7 @@ struct gnr_gpio { struct gpio_chip gc; void __iomem *reg_base; + void __iomem *pad_base; DECLARE_BITMAP(ro_bitmap, GNR_NUM_PINS); raw_spinlock_t lock; u32 pad_backup[]; @@ -65,7 +69,7 @@ struct gnr_gpio { static void __iomem *gnr_gpio_get_padcfg_addr(const struct gnr_gpio *priv, unsigned int gpio) { - return priv->reg_base + gpio * sizeof(u32); + return priv->pad_base + gpio * sizeof(u32); } static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, @@ -88,6 +92,20 @@ static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, return 0; } +static int gnr_gpio_request(struct gpio_chip *gc, unsigned int gpio) +{ + struct gnr_gpio *priv = gpiochip_get_data(gc); + u32 dw; + + dw = readl(gnr_gpio_get_padcfg_addr(priv, gpio)); + if (!(dw & GNR_CFG_DW_HOSTSW_MODE)) { + dev_warn(gc->parent, "GPIO %u is not owned by host", gpio); + return -EBUSY; + } + + return 0; +} + static int gnr_gpio_get(struct gpio_chip *gc, unsigned int gpio) { const struct gnr_gpio *priv = gpiochip_get_data(gc); @@ -139,6 +157,7 @@ static int gnr_gpio_direction_output(struct gpio_chip *gc, unsigned int gpio, in static const struct gpio_chip gnr_gpio_chip = { .owner = THIS_MODULE, + .request = gnr_gpio_request, .get = gnr_gpio_get, .set = gnr_gpio_set, .get_direction = gnr_gpio_get_direction, @@ -166,7 +185,7 @@ static void gnr_gpio_irq_ack(struct irq_data *d) guard(raw_spinlock_irqsave)(&priv->lock); reg = readl(addr); - reg &= ~BIT(bit_idx); + reg |= BIT(bit_idx); writel(reg, addr); } @@ -209,10 +228,18 @@ static void gnr_gpio_irq_unmask(struct irq_data *d) static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - irq_hw_number_t pin = irqd_to_hwirq(d); - u32 mask = GNR_CFG_DW_RX_MASK; + struct gnr_gpio *priv = gpiochip_get_data(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + u32 reg; u32 set; + /* Allow interrupts only if Interrupt Select field is non-zero */ + reg = readl(gnr_gpio_get_padcfg_addr(priv, hwirq)); + if (!(reg & GNR_CFG_DW_INTSEL_MASK)) { + dev_dbg(gc->parent, "GPIO %lu cannot be used as IRQ", hwirq); + return -EPERM; + } + /* Falling edge and level low triggers not supported by the GPIO controller */ switch (type) { case IRQ_TYPE_NONE: @@ -230,10 +257,11 @@ static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) return -EINVAL; } - return gnr_gpio_configure_line(gc, pin, mask, set); + return gnr_gpio_configure_line(gc, hwirq, GNR_CFG_DW_RX_MASK, set); } static const struct irq_chip gnr_gpio_irq_chip = { + .name = "gpio-graniterapids", .irq_ack = gnr_gpio_irq_ack, .irq_mask = gnr_gpio_irq_mask, .irq_unmask = gnr_gpio_irq_unmask, @@ -291,6 +319,7 @@ static int gnr_gpio_probe(struct platform_device *pdev) struct gnr_gpio *priv; void __iomem *regs; int irq, ret; + u32 offset; priv = devm_kzalloc(dev, struct_size(priv, pad_backup, num_backup_pins), GFP_KERNEL); if (!priv) @@ -302,6 +331,10 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (IS_ERR(regs)) return PTR_ERR(regs); + priv->reg_base = regs; + offset = readl(priv->reg_base + GNR_CFG_PADBAR); + priv->pad_base = priv->reg_base + offset; + irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; @@ -311,8 +344,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to request interrupt\n"); - priv->reg_base = regs + readl(regs + GNR_CFG_BAR); - gnr_gpio_init_pin_ro_bits(dev, priv->reg_base + GNR_CFG_LOCK_OFFSET, priv->ro_bitmap); @@ -324,7 +355,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) girq = &priv->gc.irq; gpio_irq_chip_set_chip(girq, &gnr_gpio_irq_chip); - girq->chip->name = dev_name(dev); girq->parent_handler = NULL; girq->num_parents = 0; girq->parents = NULL; diff --git a/drivers/gpio/gpio-idio-16.c b/drivers/gpio/gpio-idio-16.c index 2c9512589297..0103be977c66 100644 --- a/drivers/gpio/gpio-idio-16.c +++ b/drivers/gpio/gpio-idio-16.c @@ -3,6 +3,9 @@ * GPIO library for the ACCES IDIO-16 family * Copyright (C) 2022 William Breathitt Gray */ + +#define DEFAULT_SYMBOL_NAMESPACE "GPIO_IDIO_16" + #include <linux/bits.h> #include <linux/device.h> #include <linux/err.h> @@ -14,8 +17,6 @@ #include "gpio-idio-16.h" -#define DEFAULT_SYMBOL_NAMESPACE "GPIO_IDIO_16" - #define IDIO_16_DAT_BASE 0x0 #define IDIO_16_OUT_BASE IDIO_16_DAT_BASE #define IDIO_16_IN_BASE (IDIO_16_DAT_BASE + 1) diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index 503d2441c58f..817ecb12d550 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -82,9 +82,9 @@ static int ljca_gpio_config(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id, int ret; mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; packet->item[0].index = gpio_id; packet->item[0].value = config | ljca_gpio->connect_mode[gpio_id]; - packet->num = 1; ret = ljca_transfer(ljca_gpio->ljca, LJCA_GPIO_CONFIG, (u8 *)packet, struct_size(packet, item, packet->num), NULL, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d891ab779ca7..5df21529b3b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1801,13 +1801,18 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket) return -EINVAL; + /* Make sure VRAM is allocated contigiously */ (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); - for (i = 0; i < (*bo)->placement.num_placement; i++) - (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; - r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); - if (r) - return r; + if ((*bo)->tbo.resource->mem_type == TTM_PL_VRAM && + !((*bo)->tbo.resource->placement & TTM_PL_FLAG_CONTIGUOUS)) { + + amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); + for (i = 0; i < (*bo)->placement.num_placement; i++) + (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; + r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); + if (r) + return r; + } return amdgpu_ttm_alloc_gart(&(*bo)->tbo); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 96316111300a..d272d95dd5b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -145,7 +145,7 @@ const char *amdgpu_asic_name[] = { "LAST", }; -#define AMDGPU_IP_BLK_MASK_ALL GENMASK(AMDGPU_MAX_IP_NUM, 0) +#define AMDGPU_IP_BLK_MASK_ALL GENMASK(AMD_IP_BLOCK_TYPE_NUM - 1, 0) /* * Default init level where all blocks are expected to be initialized. This is * the level of initialization expected by default and also after a full reset diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 31fd30dcd593..65bb26215e86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -551,6 +551,8 @@ static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo) for (i = 0; i < abo->placement.num_placement; ++i) { abo->placements[i].fpfn = 0 >> PAGE_SHIFT; abo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT; + if (abo->placements[i].mem_type == TTM_PL_VRAM) + abo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8d9bf7a0857f..ddd7f05e4db9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -674,12 +674,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping && ring->funcs->emit_wreg; - if (adev->gfx.enable_cleaner_shader && - ring->funcs->emit_cleaner_shader && - job->enforce_isolation) - ring->funcs->emit_cleaner_shader(ring); - - if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync) + if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync && + !(job->enforce_isolation && !job->vmid)) return 0; amdgpu_ring_ib_begin(ring); @@ -690,6 +686,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (need_pipe_sync) amdgpu_ring_emit_pipeline_sync(ring); + if (adev->gfx.enable_cleaner_shader && + ring->funcs->emit_cleaner_shader && + job->enforce_isolation) + ring->funcs->emit_cleaner_shader(ring); + if (vm_flush_needed) { trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr); amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index e2b3dda57030..54459254bd37 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -45,6 +45,8 @@ MODULE_FIRMWARE("amdgpu/gc_9_4_3_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_4_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_3_rlc.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_4_rlc.bin"); +MODULE_FIRMWARE("amdgpu/gc_9_4_3_sjt_mec.bin"); +MODULE_FIRMWARE("amdgpu/gc_9_4_4_sjt_mec.bin"); #define GFX9_MEC_HPD_SIZE 4096 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L @@ -574,8 +576,12 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, { int err; - err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, - "amdgpu/%s_mec.bin", chip_name); + if (amdgpu_sriov_vf(adev)) + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, + "amdgpu/%s_sjt_mec.bin", chip_name); + else + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, + "amdgpu/%s_mec.bin", chip_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 079131aeb2f7..3c8ab8698af8 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -1288,7 +1288,7 @@ static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_job *job, struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); + struct amdgpu_ring *ring = amdgpu_job_ring(job); unsigned i; /* No patching necessary for the first instance */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 7b826a136ceb..e5324c5bc6c7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1423,6 +1423,7 @@ err: static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, + bool cache_line_size_missing, struct kfd_gpu_cache_info *pcache_info) { struct amdgpu_device *adev = kdev->adev; @@ -1437,6 +1438,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_tcp_per_wpg / 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcp_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Instruction Cache per SQC */ @@ -1449,6 +1452,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_instruction_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Data Cache per SQC */ @@ -1460,6 +1465,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_scalar_data_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 64; i++; } /* GL1 Data Cache per SA */ @@ -1472,7 +1479,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + if (cache_line_size_missing) + pcache_info[i].cache_line_size = 128; i++; } /* L2 Data Cache per GPU (Total Tex Cache) */ @@ -1484,6 +1492,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcc_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* L3 Data Cache per GPU */ @@ -1494,7 +1504,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + pcache_info[i].cache_line_size = 64; i++; } return i; @@ -1569,6 +1579,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config_v2(struct kfd_dev *kdev, int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pcache_info) { int num_of_cache_types = 0; + bool cache_line_size_missing = false; switch (kdev->adev->asic_type) { case CHIP_KAVERI: @@ -1692,10 +1703,17 @@ int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pc case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): case IP_VERSION(11, 5, 2): + /* Cacheline size not available in IP discovery for gc11. + * kfd_fill_gpu_cache_info_from_gfx_config to hard code it + */ + cache_line_size_missing = true; + fallthrough; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): num_of_cache_types = - kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, *pcache_info); + kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, + cache_line_size_missing, + *pcache_info); break; default: *pcache_info = dummy_cache_info; 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 c79fe9069e22..16b5daaa272f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -207,6 +207,21 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (!down_read_trylock(&adev->reset_domain->sem)) return -EIO; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input)); queue_input.process_id = qpd->pqm->process->pasid; queue_input.page_table_base_addr = qpd->page_table_base; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index eacfeb32f35d..4b275937d05e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -306,7 +306,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, spage = migrate_pfn_to_page(migrate->src[i]); if (spage && !is_zone_device_page(spage)) { src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, - DMA_TO_DEVICE); + DMA_BIDIRECTIONAL); r = dma_mapping_error(dev, src[i]); if (r) { dev_err(dev, "%s: fail %d dma_map_page\n", @@ -629,7 +629,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, goto out_oom; } - dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); r = dma_mapping_error(dev, dst[i]); if (r) { dev_err(adev->dev, "%s: fail %d dma_map_page\n", __func__, r); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 87cd52cf4ee9..d0ee173acf82 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1076,7 +1076,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) kfd_free_process_doorbells(pdd->dev->kfd, pdd); - if (pdd->dev->kfd->shared_resources.enable_mes) + if (pdd->dev->kfd->shared_resources.enable_mes && + pdd->proc_ctx_cpu_ptr) amdgpu_amdkfd_free_gtt_mem(pdd->dev->adev, &pdd->proc_ctx_bo); /* @@ -1608,7 +1609,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, struct kfd_process *p) { struct kfd_process_device *pdd = NULL; - int retval = 0; if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) return NULL; @@ -1632,21 +1632,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, pdd->user_gpu_id = dev->id; atomic64_set(&pdd->evict_duration_counter, 0); - if (dev->kfd->shared_resources.enable_mes) { - retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, - AMDGPU_MES_PROC_CTX_SIZE, - &pdd->proc_ctx_bo, - &pdd->proc_ctx_gpu_addr, - &pdd->proc_ctx_cpu_ptr, - false); - if (retval) { - dev_err(dev->adev->dev, - "failed to allocate process context bo\n"); - goto err_free_pdd; - } - memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); - } - p->pdds[p->n_pdds++] = pdd; if (kfd_dbg_is_per_vmid_supported(pdd->dev)) pdd->spi_dbg_override = pdd->dev->kfd2kgd->disable_debug_trap( @@ -1658,10 +1643,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, idr_init(&pdd->alloc_idr); return pdd; - -err_free_pdd: - kfree(pdd); - return NULL; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index c76db22a1000..59b92d66e958 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -212,13 +212,17 @@ static void pqm_clean_queue_resource(struct process_queue_manager *pqm, void pqm_uninit(struct process_queue_manager *pqm) { struct process_queue_node *pqn, *next; - struct kfd_process_device *pdd; list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) { if (pqn->q) { - pdd = kfd_get_process_device_data(pqn->q->device, pqm->process); - kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); - kfd_queue_release_buffers(pdd, &pqn->q->properties); + struct kfd_process_device *pdd = kfd_get_process_device_data(pqn->q->device, + pqm->process); + if (pdd) { + kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); + kfd_queue_release_buffers(pdd, &pqn->q->properties); + } else { + WARN_ON(!pdd); + } pqm_clean_queue_resource(pqm, pqn); } diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 67a5de573943..d7acdd42d80f 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -164,6 +164,7 @@ enum amd_pp_task { }; enum PP_SMC_POWER_PROFILE { + PP_SMC_POWER_PROFILE_UNKNOWN = -1, PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT = 0x0, PP_SMC_POWER_PROFILE_FULLSCREEN3D = 0x1, PP_SMC_POWER_PROFILE_POWERSAVING = 0x2, diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 5eae14fe79f1..21bd635bcdfc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -764,6 +764,7 @@ static int smu_early_init(struct amdgpu_ip_block *ip_block) smu->smu_baco.platform_support = false; smu->smu_baco.maco_support = false; smu->user_dpm_profile.fan_mode = -1; + smu->power_profile_mode = PP_SMC_POWER_PROFILE_UNKNOWN; mutex_init(&smu->message_lock); @@ -1248,6 +1249,21 @@ static bool smu_is_workload_profile_available(struct smu_context *smu, return smu->workload_map && smu->workload_map[profile].valid_mapping; } +static void smu_init_power_profile(struct smu_context *smu) +{ + if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_UNKNOWN) { + if (smu->is_apu || + !smu_is_workload_profile_available( + smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D)) + smu->power_profile_mode = + PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; + else + smu->power_profile_mode = + PP_SMC_POWER_PROFILE_FULLSCREEN3D; + } + smu_power_profile_mode_get(smu, smu->power_profile_mode); +} + static int smu_sw_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -1269,13 +1285,7 @@ static int smu_sw_init(struct amdgpu_ip_block *ip_block) atomic_set(&smu->smu_power.power_gate.vpe_gated, 1); atomic_set(&smu->smu_power.power_gate.umsch_mm_gated, 1); - if (smu->is_apu || - !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D)) - smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; - else - smu->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D; - smu_power_profile_mode_get(smu, smu->power_profile_mode); - + smu_init_power_profile(smu); smu->display_config = &adev->pm.pm_display_cfg; smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index f4ac403b8b36..aabb94796005 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2810,4 +2810,5 @@ void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) smu->workload_map = smu_v13_0_7_workload_map; smu->smc_driver_if_version = SMU13_0_7_DRIVER_IF_VERSION; smu_v13_0_set_smu_mailbox_registers(smu); + smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; } diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 09500cddc009..ef2d490965ba 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -929,7 +929,6 @@ impl QrImage<'_> { /// * `tmp` must be valid for reading and writing for `tmp_size` bytes. /// /// They must remain valid for the duration of the function call. - #[no_mangle] pub unsafe extern "C" fn drm_panic_qr_generate( url: *const i8, diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 174753625bca..7cd902bbd244 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -1343,6 +1343,17 @@ static void ilk_lut_write(const struct intel_crtc_state *crtc_state, intel_de_write_fw(display, reg, val); } +static void ilk_lut_write_indexed(const struct intel_crtc_state *crtc_state, + i915_reg_t reg, u32 val) +{ + struct intel_display *display = to_intel_display(crtc_state); + + if (crtc_state->dsb_color_vblank) + intel_dsb_reg_write_indexed(crtc_state->dsb_color_vblank, reg, val); + else + intel_de_write_fw(display, reg, val); +} + static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state, const struct drm_property_blob *blob) { @@ -1357,19 +1368,29 @@ static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state, lut = blob->data; /* - * DSB fails to correctly load the legacy LUT - * unless we either write each entry twice, - * or use non-posted writes + * DSB fails to correctly load the legacy LUT unless + * we either write each entry twice when using posted + * writes, or we use non-posted writes. + * + * If palette anti-collision is active during LUT + * register writes: + * - posted writes simply get dropped and thus the LUT + * contents may not be correctly updated + * - non-posted writes are blocked and thus the LUT + * contents are always correct, but simultaneous CPU + * MMIO access will start to fail + * + * Choose the lesser of two evils and use posted writes. + * Using posted writes is also faster, even when having + * to write each register twice. */ - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_start(crtc_state->dsb_color_vblank); - - for (i = 0; i < 256; i++) + for (i = 0; i < 256; i++) { ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), i9xx_lut_8(&lut[i])); - - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_end(crtc_state->dsb_color_vblank); + if (crtc_state->dsb_color_vblank) + ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), + i9xx_lut_8(&lut[i])); + } } static void ilk_load_lut_10(const struct intel_crtc_state *crtc_state, @@ -1458,8 +1479,8 @@ static void bdw_load_lut_10(const struct intel_crtc_state *crtc_state, prec_index); for (i = 0; i < lut_size; i++) - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_10(&lut[i])); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_10(&lut[i])); /* * Reset the index, otherwise it prevents the legacy palette to be @@ -1612,16 +1633,16 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state, * ToDo: Extend to max 7.0. Enable 32 bit input value * as compared to just 16 to achieve this. */ - ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe), - DISPLAY_VER(display) >= 14 ? - mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i])); + ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe), + DISPLAY_VER(display) >= 14 ? + mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i])); } /* Clamp values > 1.0. */ while (i++ < glk_degamma_lut_size(display)) - ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe), - DISPLAY_VER(display) >= 14 ? - 1 << 24 : 1 << 16); + ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe), + DISPLAY_VER(display) >= 14 ? + 1 << 24 : 1 << 16); ilk_lut_write(crtc_state, PRE_CSC_GAMC_INDEX(pipe), 0); } @@ -1687,10 +1708,10 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state) for (i = 0; i < 9; i++) { const struct drm_color_lut *entry = &lut[i]; - ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), + ilk_lut_12p4_udw(entry)); } ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_INDEX(pipe), @@ -1726,10 +1747,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) for (i = 1; i < 257; i++) { entry = &lut[i * 8]; - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_udw(entry)); } /* @@ -1747,10 +1768,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) for (i = 0; i < 256; i++) { entry = &lut[i * 8 * 128]; - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_udw(entry)); } ilk_lut_write(crtc_state, PREC_PAL_INDEX(pipe), diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index b7b44399adaa..4d3785f5cb52 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -273,16 +273,20 @@ static bool intel_dsb_prev_ins_is_indexed_write(struct intel_dsb *dsb, i915_reg_ } /** - * intel_dsb_reg_write() - Emit register wriite to the DSB context + * intel_dsb_reg_write_indexed() - Emit register wriite to the DSB context * @dsb: DSB context * @reg: register address. * @val: value. * * This function is used for writing register-value pair in command * buffer of DSB. + * + * Note that indexed writes are slower than normal MMIO writes + * for a small number (less than 5 or so) of writes to the same + * register. */ -void intel_dsb_reg_write(struct intel_dsb *dsb, - i915_reg_t reg, u32 val) +void intel_dsb_reg_write_indexed(struct intel_dsb *dsb, + i915_reg_t reg, u32 val) { /* * For example the buffer will look like below for 3 dwords for auto @@ -340,6 +344,15 @@ void intel_dsb_reg_write(struct intel_dsb *dsb, } } +void intel_dsb_reg_write(struct intel_dsb *dsb, + i915_reg_t reg, u32 val) +{ + intel_dsb_emit(dsb, val, + (DSB_OPCODE_MMIO_WRITE << DSB_OPCODE_SHIFT) | + (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) | + i915_mmio_reg_offset(reg)); +} + static u32 intel_dsb_mask_to_byte_en(u32 mask) { return (!!(mask & 0xff000000) << 3 | diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h index 33e0fc2ab380..da6df07a3c83 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.h +++ b/drivers/gpu/drm/i915/display/intel_dsb.h @@ -34,6 +34,8 @@ void intel_dsb_finish(struct intel_dsb *dsb); void intel_dsb_cleanup(struct intel_dsb *dsb); void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val); +void intel_dsb_reg_write_indexed(struct intel_dsb *dsb, + i915_reg_t reg, u32 val); void intel_dsb_reg_write_masked(struct intel_dsb *dsb, i915_reg_t reg, u32 mask, u32 val); void intel_dsb_noop(struct intel_dsb *dsb, int count); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 4eb58887819a..71c0daef1996 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1643,9 +1643,21 @@ capture_engine(struct intel_engine_cs *engine, return NULL; intel_engine_get_hung_entity(engine, &ce, &rq); - if (rq && !i915_request_started(rq)) - drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", - engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + if (rq && !i915_request_started(rq)) { + /* + * We want to know also what is the guc_id of the context, + * but if we don't have the context reference, then skip + * printing it. + */ + if (ce) + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + else + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno); + } if (rq) { capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 762127dd56c5..70a854557e6e 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -506,6 +506,6 @@ int __init i915_scheduler_module_init(void) return 0; err_priorities: - kmem_cache_destroy(slab_priorities); + kmem_cache_destroy(slab_dependencies); return -ENOMEM; } diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 1a192a2a941b..3bbdb362d6f0 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -224,8 +224,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_PINNED); if (IS_ERR(tiny)) { - KUNIT_FAIL(test, "Failed to allocate fake pt: %li\n", - PTR_ERR(pt)); + KUNIT_FAIL(test, "Failed to allocate tiny fake pt: %li\n", + PTR_ERR(tiny)); goto free_pt; } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 3cb228c773cd..6146d1776bda 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -65,6 +65,14 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe __invalidation_fence_signal(xe, fence); } +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence) +{ + if (WARN_ON_ONCE(!fence->gt)) + return; + + __invalidation_fence_signal(gt_to_xe(fence->gt), fence); +} + static void xe_gt_tlb_fence_timeout(struct work_struct *work) { struct xe_gt *gt = container_of(work, struct xe_gt, diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index f430d5797af7..00b1c6c01e8d 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, bool stack); +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence); static inline void xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence) diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index f27f579f4d85..797576690356 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1333,8 +1333,7 @@ static void invalidation_fence_cb(struct dma_fence *fence, queue_work(system_wq, &ifence->work); } else { ifence->base.base.error = ifence->fence->error; - dma_fence_signal(&ifence->base.base); - dma_fence_put(&ifence->base.base); + xe_gt_tlb_invalidation_fence_signal(&ifence->base); } dma_fence_put(ifence->fence); } diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c index e1a0e27cda14..c13123008e90 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr.c +++ b/drivers/gpu/drm/xe/xe_reg_sr.c @@ -27,46 +27,27 @@ #include "xe_reg_whitelist.h" #include "xe_rtp_types.h" -#define XE_REG_SR_GROW_STEP_DEFAULT 16 - static void reg_sr_fini(struct drm_device *drm, void *arg) { struct xe_reg_sr *sr = arg; + struct xe_reg_sr_entry *entry; + unsigned long reg; + + xa_for_each(&sr->xa, reg, entry) + kfree(entry); xa_destroy(&sr->xa); - kfree(sr->pool.arr); - memset(&sr->pool, 0, sizeof(sr->pool)); } int xe_reg_sr_init(struct xe_reg_sr *sr, const char *name, struct xe_device *xe) { xa_init(&sr->xa); - memset(&sr->pool, 0, sizeof(sr->pool)); - sr->pool.grow_step = XE_REG_SR_GROW_STEP_DEFAULT; sr->name = name; return drmm_add_action_or_reset(&xe->drm, reg_sr_fini, sr); } EXPORT_SYMBOL_IF_KUNIT(xe_reg_sr_init); -static struct xe_reg_sr_entry *alloc_entry(struct xe_reg_sr *sr) -{ - if (sr->pool.used == sr->pool.allocated) { - struct xe_reg_sr_entry *arr; - - arr = krealloc_array(sr->pool.arr, - ALIGN(sr->pool.allocated + 1, sr->pool.grow_step), - sizeof(*arr), GFP_KERNEL); - if (!arr) - return NULL; - - sr->pool.arr = arr; - sr->pool.allocated += sr->pool.grow_step; - } - - return &sr->pool.arr[sr->pool.used++]; -} - static bool compatible_entries(const struct xe_reg_sr_entry *e1, const struct xe_reg_sr_entry *e2) { @@ -112,7 +93,7 @@ int xe_reg_sr_add(struct xe_reg_sr *sr, return 0; } - pentry = alloc_entry(sr); + pentry = kmalloc(sizeof(*pentry), GFP_KERNEL); if (!pentry) { ret = -ENOMEM; goto fail; diff --git a/drivers/gpu/drm/xe/xe_reg_sr_types.h b/drivers/gpu/drm/xe/xe_reg_sr_types.h index ad48a52b824a..ebe11f237fa2 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr_types.h +++ b/drivers/gpu/drm/xe/xe_reg_sr_types.h @@ -20,12 +20,6 @@ struct xe_reg_sr_entry { }; struct xe_reg_sr { - struct { - struct xe_reg_sr_entry *arr; - unsigned int used; - unsigned int allocated; - unsigned int grow_step; - } pool; struct xarray xa; const char *name; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index c38dcdfcb914..a99112e6f0b8 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -756,7 +756,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * adding succeeded, it is ok to proceed even if the memory was * not onlined in time. */ - wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ); + wait_for_completion_timeout(&dm_device.ol_waitevent, secs_to_jiffies(5)); post_status(&dm_device); } } @@ -1373,7 +1373,8 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, + secs_to_jiffies(1)); /* * The host expects us to post information on the memory * pressure every second. @@ -1748,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1806,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index d35b60c06114..7400a5a4d2bd 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -655,7 +655,7 @@ void hv_kvp_onchannelcallback(void *context) if (host_negotiatied == NEGO_NOT_STARTED) { host_negotiatied = NEGO_IN_PROGRESS; schedule_delayed_work(&kvp_host_handshake_work, - HV_UTIL_NEGO_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_NEGO_TIMEOUT)); } return; } @@ -724,7 +724,7 @@ void hv_kvp_onchannelcallback(void *context) */ schedule_work(&kvp_sendkey_work); schedule_delayed_work(&kvp_timeout_work, - HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_TIMEOUT)); return; @@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv) */ kvp_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_kvp_init_transport(void) +{ hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL, kvp_on_msg, kvp_on_reset); if (!hvt) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 0d2184be1691..bde637a96c37 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -193,7 +193,8 @@ static void vss_send_op(void) vss_transaction.state = HVUTIL_USERSPACE_REQ; schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ? - VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(VSS_FREEZE_TIMEOUT) : + secs_to_jiffies(HV_UTIL_TIMEOUT)); rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL); if (rc) { @@ -388,6 +389,12 @@ hv_vss_init(struct hv_util_service *srv) */ vss_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_vss_init_transport(void) +{ hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); if (!hvt) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c4f525325790..36ee89c0358b 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = { static struct hv_util_service util_kvp = { .util_cb = hv_kvp_onchannelcallback, .util_init = hv_kvp_init, + .util_init_transport = hv_kvp_init_transport, .util_pre_suspend = hv_kvp_pre_suspend, .util_pre_resume = hv_kvp_pre_resume, .util_deinit = hv_kvp_deinit, @@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = { static struct hv_util_service util_vss = { .util_cb = hv_vss_onchannelcallback, .util_init = hv_vss_init, + .util_init_transport = hv_vss_init_transport, .util_pre_suspend = hv_vss_pre_suspend, .util_pre_resume = hv_vss_pre_resume, .util_deinit = hv_vss_deinit, @@ -590,10 +592,8 @@ static int util_probe(struct hv_device *dev, srv->channel = dev->channel; if (srv->util_init) { ret = srv->util_init(srv); - if (ret) { - ret = -ENODEV; + if (ret) goto error1; - } } /* @@ -613,6 +613,13 @@ static int util_probe(struct hv_device *dev, if (ret) goto error; + if (srv->util_init_transport) { + ret = srv->util_init_transport(); + if (ret) { + vmbus_close(dev->channel); + goto error; + } + } return 0; error: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index d2856023d53c..52cb744b4d7f 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data); void vmbus_on_msg_dpc(unsigned long data); int hv_kvp_init(struct hv_util_service *srv); +int hv_kvp_init_transport(void); void hv_kvp_deinit(void); int hv_kvp_pre_suspend(void); int hv_kvp_pre_resume(void); void hv_kvp_onchannelcallback(void *context); int hv_vss_init(struct hv_util_service *srv); +int hv_vss_init_transport(void); void hv_vss_deinit(void); int hv_vss_pre_suspend(void); int hv_vss_pre_resume(void); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 6d89d37b069a..2892b8da20a5 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2507,7 +2507,7 @@ static int vmbus_bus_resume(struct device *dev) vmbus_request_offers(); if (wait_for_completion_timeout( - &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0) + &vmbus_connection.ready_for_resume_event, secs_to_jiffies(10)) == 0) pr_err("Some vmbus device is missing after suspending?\n"); /* Reset the event for the next suspend. */ diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c index efb33802804f..d2877e4cc28d 100644 --- a/drivers/i2c/busses/i2c-nomadik.c +++ b/drivers/i2c/busses/i2c-nomadik.c @@ -1075,6 +1075,7 @@ static const struct of_device_id nmk_i2c_eyeq_match_table[] = { .compatible = "mobileye,eyeq6h-i2c", .data = (void *)NMK_I2C_EYEQ_FLAG_32B_BUS, }, + { /* sentinel */ } }; static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id) diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index d4d139b97513..9a1af5bbd604 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -95,7 +95,7 @@ enum { static inline int wait_timeout(struct i2c_pnx_algo_data *data) { - long timeout = data->timeout; + long timeout = jiffies_to_msecs(data->timeout); while (timeout > 0 && (ioread32(I2C_REG_STS(data)) & mstatus_active)) { mdelay(1); @@ -106,7 +106,7 @@ static inline int wait_timeout(struct i2c_pnx_algo_data *data) static inline int wait_reset(struct i2c_pnx_algo_data *data) { - long timeout = data->timeout; + long timeout = jiffies_to_msecs(data->timeout); while (timeout > 0 && (ioread32(I2C_REG_CTL(data)) & mcntrl_reset)) { mdelay(1); diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index c218f73c3650..9264adc97ca9 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -352,7 +352,7 @@ static int riic_init_hw(struct riic_dev *riic) if (brl <= (0x1F + 3)) break; - total_ticks /= 2; + total_ticks = DIV_ROUND_UP(total_ticks, 2); rate /= 2; } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 3f691e1fd22c..16f40b8000d7 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1415,6 +1415,7 @@ static int domain_flush_pages_v2(struct protection_domain *pdom, struct iommu_cmd cmd; int ret = 0; + lockdep_assert_held(&pdom->lock); list_for_each_entry(dev_data, &pdom->dev_list, list) { struct amd_iommu *iommu = get_amd_iommu_from_dev(dev_data->dev); u16 domid = dev_data->gcr3_info.domid; @@ -1464,6 +1465,8 @@ static void __domain_flush_pages(struct protection_domain *domain, ioasid_t pasid = IOMMU_NO_PASID; bool gn = false; + lockdep_assert_held(&domain->lock); + if (pdom_is_v2_pgtbl_mode(domain)) { gn = true; ret = domain_flush_pages_v2(domain, address, size); @@ -1585,6 +1588,8 @@ void amd_iommu_update_and_flush_device_table(struct protection_domain *domain) { struct iommu_dev_data *dev_data; + lockdep_assert_held(&domain->lock); + list_for_each_entry(dev_data, &domain->dev_list, list) { struct amd_iommu *iommu = rlookup_amd_iommu(dev_data->dev); @@ -2073,6 +2078,7 @@ static int attach_device(struct device *dev, struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev); struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data); struct pci_dev *pdev; + unsigned long flags; int ret = 0; mutex_lock(&dev_data->mutex); @@ -2113,7 +2119,9 @@ static int attach_device(struct device *dev, /* Update data structures */ dev_data->domain = domain; + spin_lock_irqsave(&domain->lock, flags); list_add(&dev_data->list, &domain->dev_list); + spin_unlock_irqrestore(&domain->lock, flags); /* Update device table */ dev_update_dte(dev_data, true); @@ -2160,6 +2168,7 @@ static void detach_device(struct device *dev) /* Flush IOTLB and wait for the flushes to finish */ spin_lock_irqsave(&domain->lock, flags); amd_iommu_domain_flush_all(domain); + list_del(&dev_data->list); spin_unlock_irqrestore(&domain->lock, flags); /* Clear GCR3 table */ @@ -2168,7 +2177,6 @@ static void detach_device(struct device *dev) /* Update data structures */ dev_data->domain = NULL; - list_del(&dev_data->list); /* decrease reference counters - needs to happen after the flushes */ pdom_detach_iommu(iommu, domain); diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index c8ec74f089f3..6e41ddaa24d6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -339,7 +339,7 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu, * one CPU at a time can enter the process, while the others * will be spinning at the same lock. */ - lidx = smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; + lidx = raw_smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; vcmdq = vintf->lvcmdqs[lidx]; if (!vcmdq || !READ_ONCE(vcmdq->enabled)) return NULL; diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index e5b89f728ad3..09694cca8752 100644 --- a/drivers/iommu/intel/cache.c +++ b/drivers/iommu/intel/cache.c @@ -105,12 +105,35 @@ static void cache_tag_unassign(struct dmar_domain *domain, u16 did, spin_unlock_irqrestore(&domain->cache_lock, flags); } +/* domain->qi_batch will be freed in iommu_free_domain() path. */ +static int domain_qi_batch_alloc(struct dmar_domain *domain) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&domain->cache_lock, flags); + if (domain->qi_batch) + goto out_unlock; + + domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_ATOMIC); + if (!domain->qi_batch) + ret = -ENOMEM; +out_unlock: + spin_unlock_irqrestore(&domain->cache_lock, flags); + + return ret; +} + static int __cache_tag_assign_domain(struct dmar_domain *domain, u16 did, struct device *dev, ioasid_t pasid) { struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -139,6 +162,10 @@ static int __cache_tag_assign_parent_domain(struct dmar_domain *domain, u16 did, struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_NESTING_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -190,13 +217,6 @@ int cache_tag_assign_domain(struct dmar_domain *domain, u16 did = domain_get_id_for_dev(domain, dev); int ret; - /* domain->qi_bach will be freed in iommu_free_domain() path. */ - if (!domain->qi_batch) { - domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_KERNEL); - if (!domain->qi_batch) - return -ENOMEM; - } - ret = __cache_tag_assign_domain(domain, did, dev, pasid); if (ret || domain->domain.type != IOMMU_DOMAIN_NESTED) return ret; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7d0acb74d5a5..79e0da9eb626 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3220,6 +3220,9 @@ void device_block_translation(struct device *dev) struct intel_iommu *iommu = info->iommu; unsigned long flags; + if (info->domain) + cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); + iommu_disable_pci_caps(info); if (!dev_is_real_dma_subdevice(dev)) { if (sm_supported(iommu)) @@ -3236,7 +3239,6 @@ void device_block_translation(struct device *dev) list_del(&info->link); spin_unlock_irqrestore(&info->domain->lock, flags); - cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); domain_detach_iommu(info->domain, iommu); info->domain = NULL; } diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 0f2a926d3bd5..5b7d85f1e143 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -265,7 +265,8 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); devtlb_invalidation_with_pasid(iommu, dev, pasid); - intel_iommu_drain_pasid_prq(dev, pasid); + if (!fault_ignore) + intel_iommu_drain_pasid_prq(dev, pasid); } /* diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 34db379d066a..79d8cc80693c 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -161,7 +161,22 @@ static bool cpus_have_group0 __ro_after_init; static void __init gic_prio_init(void) { - cpus_have_security_disabled = gic_dist_security_disabled(); + bool ds; + + ds = gic_dist_security_disabled(); + if (!ds) { + u32 val; + + val = readl_relaxed(gic_data.dist_base + GICD_CTLR); + val |= GICD_CTLR_DS; + writel_relaxed(val, gic_data.dist_base + GICD_CTLR); + + ds = gic_dist_security_disabled(); + if (ds) + pr_warn("Broken GIC integration, security disabled"); + } + + cpus_have_security_disabled = ds; cpus_have_group0 = gic_has_group0(); /* diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 8fae6dc01024..6503573557fd 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -64,7 +64,7 @@ static void gic_check_cpu_features(void) union gic_base { void __iomem *common_base; - void __percpu * __iomem *percpu_base; + void __iomem * __percpu *percpu_base; }; struct gic_chip_data { diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d58db9a27e6c..76e2c6868548 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -76,9 +76,9 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, * pointer and the requested position. */ nr_blocks = block - wp_block; - ret = blkdev_issue_zeroout(dev->bdev, - dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), - dmz_blk2sect(nr_blocks), GFP_NOIO, 0); + ret = blk_zone_issue_zeroout(dev->bdev, + dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), + dmz_blk2sect(nr_blocks), GFP_NOIO); if (ret) { dmz_dev_err(dev, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index efb0d2d5716b..af445d3f8e2a 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -3070,6 +3070,7 @@ release_clk: msdc_gate_clock(host); platform_set_drvdata(pdev, NULL); release_mem: + device_init_wakeup(&pdev->dev, false); if (host->dma.gpd) dma_free_coherent(&pdev->dev, 2 * sizeof(struct mt_gpdma_desc), @@ -3103,6 +3104,7 @@ static void msdc_drv_remove(struct platform_device *pdev) host->dma.gpd, host->dma.gpd_addr); dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc), host->dma.bd, host->dma.bd_addr); + device_init_wakeup(&pdev->dev, false); } static void msdc_save_reg(struct msdc_host *host) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 4d402b601883..b2f5c3f8b839 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 533bcb77c9f9..97cd8bbf2e32 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + m_can_coalescing_update(cdev, ir); if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); @@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } + /* Write the INIT bit, in case no hardware reset has happened before + * the probe (for example, it was observed that the Intel Elkhart Lake + * SoCs do not properly reset the CAN controllers on reboot) + */ + err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (err) + return err; + if (!cdev->is_peripheral) netif_napi_add(dev, &cdev->napi, m_can_poll); @@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - /* Forcing standby mode should be redundant, as the chip should be in - * standby after a reset. Write the INIT bit anyways, should the chip - * be configured by previous stage. - */ - return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + return 0; } static void m_can_stop(struct net_device *dev) diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 92b2bd8628e6..ef39e8e527ab 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { int pm_clock_support; int pm_wake_source; int is_peripheral; + bool irq_edge_triggered; // Cached M_CAN_IE register content u32 active_interrupts; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index d72fe771dfc7..9ad7419f88f8 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->pm_clock_support = 1; mcan_class->pm_wake_source = 0; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index ecce23cecbea..4e266ce41180 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac) static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; struct bgmac *bgmac; struct resource *regs; int ret; @@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset; bgmac->get_bus_clock = platform_bgmac_get_bus_clock; bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32; - if (of_parse_phandle(np, "phy-handle", 0)) { + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + of_node_put(phy_node); bgmac->phy_connect = platform_phy_connect; } else { bgmac->phy_connect = bgmac_phy_connect_direct; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 96fd31d75dfd..daa1ebaef511 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * driver. Once driver synthesizes cpl_pass_accept_req the skb will go * through the regular cpl_pass_accept_req processing in TOM. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req)) - + pktshift, GFP_ATOMIC); if (unlikely(!skb)) return NULL; __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 890f213da8d1..ae1f523d6841 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,6 +172,7 @@ err_init_txq: hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; return err; } @@ -268,6 +269,7 @@ err_init_rxq: hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; return err; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 6c913a703df6..41e4bd49402a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -101,6 +101,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_PF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 34f4118c7bc0..2fa9c36e33c9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3604,21 +3604,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) /** * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings * @q_vector: pointer to q_vector - * @type: itr index - * @itr: itr value */ -static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector, - const int type, u16 itr) +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector) { - u32 itr_val; + u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m; + int type = IDPF_NO_ITR_UPDATE_IDX; + u16 itr = 0; + + if (q_vector->wb_on_itr) { + /* + * Trigger a software interrupt when exiting wb_on_itr, to make + * sure we catch any pending write backs that might have been + * missed due to interrupt state transition. + */ + itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m | + q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m; + type = IDPF_SW_ITR_UPDATE_IDX; + itr = IDPF_ITR_20K; + } itr &= IDPF_ITR_MASK; /* Don't clear PBA because that can cause lost interrupts that * came in while we were cleaning/polling */ - itr_val = q_vector->intr_reg.dyn_ctl_intena_m | - (type << q_vector->intr_reg.dyn_ctl_itridx_s) | - (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); + itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); return itr_val; } @@ -3716,9 +3726,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /* net_dim() updates ITR out-of-band using a work item */ idpf_net_dim(q_vector); + intval = idpf_vport_intr_buildreg_itr(q_vector); q_vector->wb_on_itr = false; - intval = idpf_vport_intr_buildreg_itr(q_vector, - IDPF_NO_ITR_UPDATE_IDX, 0); writel(intval, q_vector->intr_reg.dyn_ctl); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 9c1fe84108ed..0f71a6f5557b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -354,6 +354,8 @@ struct idpf_vec_regs { * @dyn_ctl_itridx_m: Mask for ITR index * @dyn_ctl_intrvl_s: Register bit offset for ITR interval * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature + * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index + * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable * @rx_itr: RX ITR register * @tx_itr: TX ITR register * @icr_ena: Interrupt cause register offset @@ -367,6 +369,8 @@ struct idpf_intr_reg { u32 dyn_ctl_itridx_m; u32 dyn_ctl_intrvl_s; u32 dyn_ctl_wb_on_itr_m; + u32 dyn_ctl_sw_itridx_ena_m; + u32 dyn_ctl_swint_trig_m; void __iomem *rx_itr; void __iomem *tx_itr; void __iomem *icr_ena; @@ -437,7 +441,7 @@ struct idpf_q_vector { cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; -libeth_cacheline_set_assert(struct idpf_q_vector, 112, +libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), 8 + sizeof(cpumask_var_t)); @@ -471,6 +475,8 @@ struct idpf_tx_queue_stats { #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode) #define IDPF_ITR_TX_DEF IDPF_ITR_20K #define IDPF_ITR_RX_DEF IDPF_ITR_20K +/* Index used for 'SW ITR' update in DYN_CTL register */ +#define IDPF_SW_ITR_UPDATE_IDX 2 /* Index used for 'No ITR' update in DYN_CTL register */ #define IDPF_NO_ITR_UPDATE_IDX 3 #define IDPF_ITR_IDX_SPACING(spacing, dflt) (spacing ? spacing : dflt) diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c index aad62e270ae4..aba828abcb17 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_VF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 232b10740c13..04e08e06f30f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -680,14 +680,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) ndev->features |= ndev->hw_features; eth_hw_addr_random(ndev); err = rvu_rep_devlink_port_register(rep); - if (err) + if (err) { + free_netdev(ndev); goto exit; + } SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port); err = register_netdev(ndev); if (err) { NL_SET_ERR_MSG_MOD(extack, "PFVF representor registration failed"); + rvu_rep_devlink_port_unregister(rep); free_netdev(ndev); goto exit; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 3d72aa7b1305..ef93df520887 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); + ocelot_ifh_set_src(ifh, ocelot->num_phys_ports); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index f9c0dcd965c2..db200e4ec284 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -113,6 +113,7 @@ struct oa_tc6 { struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + spinlock_t tx_skb_lock; /* Protects tx skb handling */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; void *spi_data_tx_buf; @@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; used_tx_credits++) { if (!tc6->ongoing_tx_skb) { + spin_lock_bh(&tc6->tx_skb_lock); tc6->ongoing_tx_skb = tc6->waiting_tx_skb; tc6->waiting_tx_skb = NULL; + spin_unlock_bh(&tc6->tx_skb_lock); } if (!tc6->ongoing_tx_skb) break; @@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data) /* This kthread will be waken up if there is a tx skb or mac-phy * interrupt to perform spi transfer with tx chunks. */ - wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || - tc6->int_flag || + wait_event_interruptible(tc6->spi_wq, tc6->int_flag || + (tc6->waiting_tx_skb && + tc6->tx_credits) || kthread_should_stop()); if (kthread_should_stop()) @@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) return NETDEV_TX_OK; } + spin_lock_bh(&tc6->tx_skb_lock); tc6->waiting_tx_skb = skb; + spin_unlock_bh(&tc6->tx_skb_lock); /* Wake spi kthread to perform spi transfer */ wake_up_interruptible(&tc6->spi_wq); @@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) tc6->netdev = netdev; SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); + spin_lock_init(&tc6->tx_skb_lock); /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9e42d599840d..57edcde9e6f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; - destroy_workqueue(ionic->wq); + if (ionic->wq) { + destroy_workqueue(ionic->wq); + ionic->wq = NULL; + } mutex_destroy(&idev->cmb_inuse_lock); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 720092b1633a..a2d4336d2766 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -1001,8 +1001,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev, len = min_t(u32, sizeof(xcvr->sprom), ee->len); do { - memcpy(data, xcvr->sprom, len); - memcpy(tbuf, xcvr->sprom, len); + memcpy(data, &xcvr->sprom[ee->offset], len); + memcpy(tbuf, &xcvr->sprom[ee->offset], len); /* Let's make sure we got a consistent copy */ if (!memcmp(data, tbuf, len)) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 05fb46effe0d..7707a9e53c43 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3863,8 +3863,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index b45efc272fdb..c7f497c36f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3358,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); + nvm_info.num_images = 0; goto out; } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index aae26098bc0c..84d09a8973b7 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -557,7 +557,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) desc = &gq->ts_ring[gq->ring_size]; desc->desc.die_dt = DT_LINKFIX; rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); return 0; } @@ -1013,9 +1012,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) static void rswitch_ts(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - struct rswitch_gwca_ts_info *ts_info, *ts_info2; struct skb_shared_hwtstamps shhwtstamps; struct rswitch_ts_desc *desc; + struct rswitch_device *rdev; + struct sk_buff *ts_skb; struct timespec64 ts; unsigned int num; u32 tag, port; @@ -1025,23 +1025,28 @@ static void rswitch_ts(struct rswitch_private *priv) dma_rmb(); port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); - tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); - - list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { - if (!(ts_info->port == port && ts_info->tag == tag)) - continue; - - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - ts.tv_sec = __le32_to_cpu(desc->ts_sec); - ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(ts_info->skb, &shhwtstamps); - dev_consume_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - break; - } + if (unlikely(port >= RSWITCH_NUM_PORTS)) + goto next; + rdev = priv->rdev[port]; + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(tag >= TS_TAGS_PER_PORT)) + goto next; + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + smp_mb(); /* order rdev->ts_skb[] read before bitmap update */ + clear_bit(tag, rdev->ts_skb_used); + + if (unlikely(!ts_skb)) + goto next; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_skb, &shhwtstamps); + dev_consume_skb_irq(ts_skb); + +next: gq->cur = rswitch_next_queue_index(gq, true, 1); desc = &gq->ts_ring[gq->cur]; } @@ -1606,8 +1611,9 @@ static int rswitch_open(struct net_device *ndev) static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct sk_buff *ts_skb; unsigned long flags; + unsigned int tag; netif_tx_stop_all_queues(ndev); @@ -1624,12 +1630,13 @@ static int rswitch_stop(struct net_device *ndev) if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); - list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { - if (ts_info->port != rdev->port) - continue; - dev_kfree_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); + for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + tag < TS_TAGS_PER_PORT; + tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) { + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + clear_bit(tag, rdev->ts_skb_used); + if (ts_skb) + dev_kfree_skb(ts_skb); } return 0; @@ -1642,20 +1649,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev, desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct rswitch_gwca_ts_info *ts_info; + unsigned int tag; - ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) + tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + if (tag == TS_TAGS_PER_PORT) return false; + smp_mb(); /* order bitmap read before rdev->ts_skb[] write */ + rdev->ts_skb[tag] = skb_get(skb); + set_bit(tag, rdev->ts_skb_used); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - rdev->ts_tag++; - desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); - - ts_info->skb = skb_get(skb); - ts_info->port = rdev->port; - ts_info->tag = rdev->ts_tag; - list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC); skb_tx_timestamp(skb); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 35ee73766396..532192cbca4b 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -967,14 +967,6 @@ struct rswitch_gwca_queue { }; }; -struct rswitch_gwca_ts_info { - struct sk_buff *skb; - struct list_head list; - - int port; - u8 tag; -}; - #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { unsigned int index; @@ -984,13 +976,13 @@ struct rswitch_gwca { struct rswitch_gwca_queue *queues; int num_queues; struct rswitch_gwca_queue ts_queue; - struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; }; #define NUM_QUEUES_PER_NDEV 2 +#define TS_TAGS_PER_PORT 256 struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; @@ -998,7 +990,8 @@ struct rswitch_device { void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; - u8 ts_tag; + struct sk_buff *ts_skb[TS_TAGS_PER_PORT]; + DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT); bool disabled; int port; diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index b156493d7084..aea0f0357568 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) static struct mii_timestamper * fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) { + struct mii_timestamper *mii_ts; struct of_phandle_args arg; int err; @@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) else if (err) return ERR_PTR(err); - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); + if (arg.args_count != 1) { + mii_ts = ERR_PTR(-EINVAL); + goto put_node; + } + + mii_ts = register_mii_timestamper(arg.np, arg.args[0]); - return register_mii_timestamper(arg.np, arg.args[0]); +put_node: + of_node_put(arg.np); + return mii_ts; } int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 70e8bdf34be9..688f05316b5e 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; break_msg = memdup_user_nul(data, count); if (IS_ERR(break_msg)) return PTR_ERR(break_msg); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 0be47fed4efc..e068a9761c09 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -635,10 +635,10 @@ nsim_pp_hold_write(struct file *file, const char __user *data, page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } - rtnl_unlock(); exit: - return count; + rtnl_unlock(); + return ret; } static const struct file_operations nsim_pp_hold_fops = { diff --git a/drivers/net/phy/aquantia/aquantia_leds.c b/drivers/net/phy/aquantia/aquantia_leds.c index 00ad2313fed3..951f46104eff 100644 --- a/drivers/net/phy/aquantia/aquantia_leds.c +++ b/drivers/net/phy/aquantia/aquantia_leds.c @@ -156,5 +156,5 @@ int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long if (force_active_high || force_active_low) return aqr_phy_led_active_low_set(phydev, index, force_active_low); - unreachable(); + return -EINVAL; } diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index b672c55a7a4e..e6ed2413e514 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -529,7 +529,7 @@ static int xway_gphy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, XWAY_MDIO_LED, XWAY_GPHY_LED_INV(index)); - unreachable(); + return -EINVAL; } static struct phy_driver xway_gphy[] = { diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index db3c1f72b407..a8ccf257c109 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -1014,7 +1014,7 @@ static int gpy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, PHY_LED, PHY_LED_POLARITY(index)); - unreachable(); + return -EINVAL; } static struct phy_driver gpy_drivers[] = { diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 69ea2c3c76bf..c7690adec8db 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -998,9 +998,13 @@ static void __team_compute_features(struct team *team) unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + rcu_read_lock(); + if (list_empty(&team->port_list)) + goto done; + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); - rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, @@ -1010,11 +1014,11 @@ static void __team_compute_features(struct team *team) port->dev->hw_enc_features, TEAM_ENC_FEATURES); - dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } +done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 41e3eeac06fd..28624cca91f8 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1485,7 +1485,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9fe7f704a2f7..e9208a8d2bfa 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1429,6 +1429,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/platform/x86/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c index 77465ed9b449..341d01d3e3e4 100644 --- a/drivers/platform/x86/dell/alienware-wmi.c +++ b/drivers/platform/x86/dell/alienware-wmi.c @@ -190,7 +190,7 @@ static struct quirk_entry quirk_asm201 = { }; static struct quirk_entry quirk_g_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -199,7 +199,7 @@ static struct quirk_entry quirk_g_series = { }; static struct quirk_entry quirk_x_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -243,6 +243,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = { }, { .callback = dmi_matched, + .ident = "Alienware m16 R1 AMD", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), + }, + .driver_data = &quirk_x_series, + }, + { + .callback = dmi_matched, .ident = "Alienware m17 R5", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -687,6 +696,9 @@ static void alienware_zone_exit(struct platform_device *dev) { u8 zone; + if (!quirks->num_zones) + return; + sysfs_remove_group(&dev->dev.kobj, &zone_attribute_group); led_classdev_unregister(&global_led); if (zone_dev_attrs) { @@ -1229,9 +1241,11 @@ static int __init alienware_wmi_init(void) goto fail_prep_thermal_profile; } - ret = alienware_zone_init(platform_device); - if (ret) - goto fail_prep_zones; + if (quirks->num_zones > 0) { + ret = alienware_zone_init(platform_device); + if (ret) + goto fail_prep_zones; + } return 0; diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c index bc252b883210..1ae50702bdb7 100644 --- a/drivers/platform/x86/intel/ifs/core.c +++ b/drivers/platform/x86/intel/ifs/core.c @@ -20,6 +20,7 @@ static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, ARRAY_GEN0), X86_MATCH(INTEL_GRANITERAPIDS_D, ARRAY_GEN0), X86_MATCH(INTEL_ATOM_CRESTMONT_X, ARRAY_GEN1), + X86_MATCH(INTEL_ATOM_DARKMONT_X, ARRAY_GEN1), {} }; MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 4a85aad2475a..8272f1dd0fbc 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -423,6 +423,7 @@ static const struct intel_vsec_platform_info lnl_info = { #define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d #define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d +#define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, @@ -432,6 +433,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) }, { } }; MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids); diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index d51eb0db0626..cbbb0f809704 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -43,6 +43,7 @@ struct p2sb_res_cache { }; static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; +static bool p2sb_hidden_by_bios; static void p2sb_get_devfn(unsigned int *devfn) { @@ -97,6 +98,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + */ + pci_bus_write_config_dword(bus, devfn, P2SBC, 0); + /* Scan the P2SB device and cache its BAR0 */ p2sb_scan_and_cache_devfn(bus, devfn); @@ -104,6 +111,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) if (devfn == P2SB_DEVFN_GOLDMONT) p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); + pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE); + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; @@ -129,7 +138,7 @@ static int p2sb_cache_resources(void) u32 value = P2SBC_HIDE; struct pci_bus *bus; u16 class; - int ret; + int ret = 0; /* Get devfn for P2SB device itself */ p2sb_get_devfn(&devfn_p2sb); @@ -152,22 +161,53 @@ static int p2sb_cache_resources(void) */ pci_lock_rescan_remove(); + pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); + p2sb_hidden_by_bios = value & P2SBC_HIDE; + /* - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * Unhide the P2SB device here, if needed. + * If the BIOS does not hide the P2SB device then its resources + * are accesilble. Cache them only if the P2SB device is hidden. */ - pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); + if (p2sb_hidden_by_bios) + ret = p2sb_scan_and_cache(bus, devfn_p2sb); - ret = p2sb_scan_and_cache(bus, devfn_p2sb); + pci_unlock_rescan_remove(); - /* Hide the P2SB device, if it was hidden */ - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE); + return ret; +} - pci_unlock_rescan_remove(); +static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; + + if (cache->bus_dev_id != bus->dev.id) + return -ENODEV; + + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); + + return 0; +} + +static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct pci_dev *pdev; + int ret = 0; + + pdev = pci_get_slot(bus, devfn); + if (!pdev) + return -ENODEV; + + if (p2sb_valid_resource(pci_resource_n(pdev, 0))) + p2sb_read_bar0(pdev, mem); + else + ret = -ENOENT; + + pci_dev_put(pdev); return ret; } @@ -188,8 +228,6 @@ static int p2sb_cache_resources(void) */ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) { - struct p2sb_res_cache *cache; - bus = p2sb_get_bus(bus); if (!bus) return -ENODEV; @@ -197,15 +235,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (!devfn) p2sb_get_devfn(&devfn); - cache = &p2sb_resources[PCI_FUNC(devfn)]; - if (cache->bus_dev_id != bus->dev.id) - return -ENODEV; + if (p2sb_hidden_by_bios) + return p2sb_read_from_cache(bus, devfn, mem); - if (!p2sb_valid_resource(&cache->res)) - return -ENOENT; - - memcpy(mem, &cache->res, sizeof(*mem)); - return 0; + return p2sb_read_from_dev(bus, devfn, mem); } EXPORT_SYMBOL_GPL(p2sb_bar); diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0a39f68c641d..bdc19cd8d3ed 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -855,6 +855,23 @@ static const struct ts_dmi_data rwc_nanote_next_data = { .properties = rwc_nanote_next_props, }; +static const struct property_entry sary_tab_3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1730), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1151), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-sary-tab-3.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data sary_tab_3_data = { + .acpi_name = "MSSL1680:00", + .properties = sary_tab_3_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1616,6 +1633,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* SARY Tab 3 */ + .driver_data = (void *)&sary_tab_3_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SARY"), + DMI_MATCH(DMI_PRODUCT_NAME, "C210C"), + DMI_MATCH(DMI_PRODUCT_SKU, "TAB3"), + }, + }, + { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, .matches = { diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index b889e64522c3..17e591f61efb 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -84,7 +84,7 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, wfhw->ccer = TIM_CCER_CCxE(ch + 1); if (priv->have_complementary_output) - wfhw->ccer = TIM_CCER_CCxNE(ch + 1); + wfhw->ccer |= TIM_CCER_CCxNE(ch + 1); rate = clk_get_rate(priv->clk); diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index e3cc59b82ea6..dca99cfb7cbb 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -371,8 +371,8 @@ .ops = &axp20x_ops, \ } -#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ - _vmask, _ereg, _emask) \ +#define AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -388,9 +388,15 @@ .vsel_mask = (_vmask), \ .enable_reg = (_ereg), \ .enable_mask = (_emask), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops, \ } +#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask) \ + AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, 0) + #define AXP_DESC_SW(_family, _id, _match, _supply, _ereg, _emask) \ [_family##_##_id] = { \ .name = (_match), \ @@ -419,8 +425,8 @@ .ops = &axp20x_ops_fixed \ } -#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ - _vreg, _vmask, _ereg, _emask) \ +#define AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -436,9 +442,15 @@ .enable_mask = (_emask), \ .linear_ranges = (_ranges), \ .n_linear_ranges = ARRAY_SIZE(_ranges), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops_range, \ } +#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask) \ + AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, \ + _n_voltages, _vreg, _vmask, _ereg, _emask, 0) + static const int axp209_dcdc2_ldo3_slew_rates[] = { 1600, 800, @@ -781,21 +793,21 @@ static const struct linear_range axp717_dcdc3_ranges[] = { }; static const struct regulator_desc axp717_regulators[] = { - AXP_DESC_RANGES(AXP717, DCDC1, "dcdc1", "vin1", + AXP_DESC_RANGES_DELAY(AXP717, DCDC1, "dcdc1", "vin1", axp717_dcdc1_ranges, AXP717_DCDC1_NUM_VOLTAGES, AXP717_DCDC1_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(0)), - AXP_DESC_RANGES(AXP717, DCDC2, "dcdc2", "vin2", + AXP717_DCDC_OUTPUT_CONTROL, BIT(0), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC2, "dcdc2", "vin2", axp717_dcdc2_ranges, AXP717_DCDC2_NUM_VOLTAGES, AXP717_DCDC2_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(1)), - AXP_DESC_RANGES(AXP717, DCDC3, "dcdc3", "vin3", + AXP717_DCDC_OUTPUT_CONTROL, BIT(1), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC3, "dcdc3", "vin3", axp717_dcdc3_ranges, AXP717_DCDC3_NUM_VOLTAGES, AXP717_DCDC3_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(2)), - AXP_DESC(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, + AXP717_DCDC_OUTPUT_CONTROL, BIT(2), 640), + AXP_DESC_DELAY(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, AXP717_DCDC4_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(3)), + AXP717_DCDC_OUTPUT_CONTROL, BIT(3), 6400), AXP_DESC(AXP717, ALDO1, "aldo1", "aldoin", 500, 3500, 100, AXP717_ALDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(0)), diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index 8eb843ddb25f..e9beae95dded 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -239,7 +239,7 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, offset, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; if (op->dummy.buswidth && op->dummy.nbytes) { for (i = 0; i < op->dummy.nbytes / op->dummy.buswidth; i++) @@ -249,8 +249,9 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, aspeed_spi_set_io_mode(chip, io_mode); aspeed_spi_read_from_ahb(buf, chip->ahb_base, len); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, @@ -261,10 +262,11 @@ static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, aspeed_spi_start_user(chip); ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, op->addr.val, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, op->data.nbytes); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } /* support for 1-1-1, 1-1-2 or 1-1-4 */ diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 0b45b7b2b3ab..a031ecb358e0 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -43,6 +43,7 @@ static_assert(CQSPI_MAX_CHIPSELECT <= SPI_CS_CNT_MAX); #define CQSPI_SLOW_SRAM BIT(4) #define CQSPI_NEEDS_APB_AHB_HAZARD_WAR BIT(5) #define CQSPI_RD_NO_IRQ BIT(6) +#define CQSPI_DISABLE_STIG_MODE BIT(7) /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) @@ -103,6 +104,7 @@ struct cqspi_st { bool apb_ahb_hazard; bool is_jh7110; /* Flag for StarFive JH7110 SoC */ + bool disable_stig_mode; const struct cqspi_driver_platdata *ddata; }; @@ -1416,7 +1418,8 @@ static int cqspi_mem_process(struct spi_mem *mem, const struct spi_mem_op *op) * reads, prefer STIG mode for such small reads. */ if (!op->addr.nbytes || - op->data.nbytes <= CQSPI_STIG_DATA_LEN_MAX) + (op->data.nbytes <= CQSPI_STIG_DATA_LEN_MAX && + !cqspi->disable_stig_mode)) return cqspi_command_read(f_pdata, op); return cqspi_read(f_pdata, op); @@ -1880,6 +1883,8 @@ static int cqspi_probe(struct platform_device *pdev) if (ret) goto probe_reset_failed; } + if (ddata->quirks & CQSPI_DISABLE_STIG_MODE) + cqspi->disable_stig_mode = true; if (of_device_is_compatible(pdev->dev.of_node, "xlnx,versal-ospi-1.0")) { @@ -2043,7 +2048,8 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = { static const struct cqspi_driver_platdata socfpga_qspi = { .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION - | CQSPI_SLOW_SRAM, + | CQSPI_SLOW_SRAM + | CQSPI_DISABLE_STIG_MODE, }; static const struct cqspi_driver_platdata versal_ospi = { diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 864e58167417..1bc012fce7cb 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -241,6 +241,20 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable) struct spi_controller *ctlr = spi->controller; struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); bool cs_asserted = spi->mode & SPI_CS_HIGH ? enable : !enable; + bool cs_actual; + + /* + * SPI subsystem tries to avoid no-op calls that would break the PM + * refcount below. It can't however for the first time it is used. + * To detect this case we read it here and bail out early for no-ops. + */ + if (spi_get_csgpiod(spi, 0)) + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & 1); + else + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & + BIT(spi_get_chipselect(spi, 0))); + if (unlikely(cs_actual == cs_asserted)) + return; if (cs_asserted) { /* Keep things powered as long as CS is asserted */ diff --git a/drivers/staging/gpib/Kconfig b/drivers/staging/gpib/Kconfig index 95308d15a555..259f3ff33646 100644 --- a/drivers/staging/gpib/Kconfig +++ b/drivers/staging/gpib/Kconfig @@ -50,6 +50,7 @@ config GPIB_CEC_PCI tristate "CEC PCI board" depends on PCI depends on HAS_IOPORT + depends on !X86_PAE select GPIB_COMMON select GPIB_NEC7210 help @@ -62,6 +63,8 @@ config GPIB_CEC_PCI config GPIB_NI_PCI_ISA tristate "NI PCI/ISA compatible boards" depends on ISA_BUS || PCI || PCMCIA + depends on HAS_IOPORT + depends on !X86_PAE select GPIB_COMMON select GPIB_NEC7210 help @@ -85,6 +88,7 @@ config GPIB_CB7210 tristate "Measurement Computing compatible boards" depends on HAS_IOPORT depends on ISA_BUS || PCI || PCMCIA + depends on !X86_PAE select GPIB_COMMON select GPIB_NEC7210 help @@ -128,7 +132,7 @@ config GPIB_FMH tristate "FMH FPGA based devices" select GPIB_COMMON select GPIB_NEC7210 - depends on BROKEN + depends on !PPC depends on OF && PCI help GPIB driver for fmhess FPGA based devices @@ -174,6 +178,7 @@ config GPIB_INES tristate "INES" depends on PCI || ISA_BUS || PCMCIA depends on HAS_IOPORT + depends on !X86_PAE select GPIB_COMMON select GPIB_NEC7210 help diff --git a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 796c3a5be545..267651a15fa0 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -901,7 +901,7 @@ static int usb_gpib_read(gpib_board_t *board, } else { /* we are in the closing <DLE><ETX> sequence */ - + c = nc; if (c == ETX) { c = one_char(board, &b); if (c == ACK) { diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 4d63d80e78a9..649e74e9b52f 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -467,7 +467,8 @@ static void set_io_from_upio(struct uart_port *p) break; #endif default: - WARN(1, "Unsupported UART type %x\n", p->iotype); + WARN(p->iotype != UPIO_PORT || p->iobase, + "Unsupported UART type %x\n", p->iotype); p->serial_in = no_serial_in; p->serial_out = no_serial_out; } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index b7ec5797d5ba..8a01e4393159 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5556,6 +5556,7 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag, lrbp = &hba->lrb[task_tag]; lrbp->compl_time_stamp = ktime_get(); + lrbp->compl_time_stamp_local_clock = local_clock(); cmd = lrbp->cmd; if (cmd) { if (unlikely(ufshcd_should_inform_monitor(hba, lrbp))) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 500dc35e6477..0b2490347b9f 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2794,8 +2794,14 @@ int usb_add_hcd(struct usb_hcd *hcd, int retval; struct usb_device *rhdev; struct usb_hcd *shared_hcd; + int skip_phy_initialization; - if (!hcd->skip_phy_initialization) { + if (usb_hcd_is_primary_hcd(hcd)) + skip_phy_initialization = hcd->skip_phy_initialization; + else + skip_phy_initialization = hcd->primary_hcd->skip_phy_initialization; + + if (!skip_phy_initialization) { if (usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); if (IS_ERR(hcd->phy_roothub)) diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index cb54390e7de4..8c3941ecaaf5 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -3546,11 +3546,9 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, port_status |= USB_PORT_STAT_C_OVERCURRENT << 16; } - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return 0's for the remainder of the port status + * Just return 0's for the remainder of the port status * since the port register can't be read if the core * is in device mode. */ @@ -3620,13 +3618,11 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, if (wvalue != USB_PORT_FEAT_TEST && (!windex || windex > 1)) goto error; - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return without doing anything since the port - * register can't be written if the core is in device - * mode. + * Just return 0's for the remainder of the port status + * since the port register can't be read if the core + * is in device mode. */ break; } @@ -4349,7 +4345,7 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) if (hsotg->bus_suspended) goto skip_power_saving; - if (hsotg->flags.b.port_connect_status == 0) + if (!(dwc2_read_hprt0(hsotg) & HPRT0_CONNSTS)) goto skip_power_saving; switch (hsotg->params.power_down) { @@ -4431,6 +4427,7 @@ static int _dwc2_hcd_resume(struct usb_hcd *hcd) * Power Down mode. */ if (hprt0 & HPRT0_CONNSTS) { + set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); hsotg->lx_state = DWC2_L0; goto unlock; } diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c index 356812cbcd88..3edc5aca76f9 100644 --- a/drivers/usb/dwc3/dwc3-imx8mp.c +++ b/drivers/usb/dwc3/dwc3-imx8mp.c @@ -129,6 +129,16 @@ static void dwc3_imx8mp_wakeup_disable(struct dwc3_imx8mp *dwc3_imx) writel(val, dwc3_imx->hsio_blk_base + USB_WAKEUP_CTRL); } +static const struct property_entry dwc3_imx8mp_properties[] = { + PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"), + PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"), + {}, +}; + +static const struct software_node dwc3_imx8mp_swnode = { + .properties = dwc3_imx8mp_properties, +}; + static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) { struct dwc3_imx8mp *dwc3_imx = _dwc3_imx; @@ -148,17 +158,6 @@ static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) return IRQ_HANDLED; } -static int dwc3_imx8mp_set_software_node(struct device *dev) -{ - struct property_entry props[3] = { 0 }; - int prop_idx = 0; - - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"); - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"); - - return device_create_managed_software_node(dev, props, NULL); -} - static int dwc3_imx8mp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -221,17 +220,17 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) if (err < 0) goto disable_rpm; - err = dwc3_imx8mp_set_software_node(dev); + err = device_add_software_node(dev, &dwc3_imx8mp_swnode); if (err) { err = -ENODEV; - dev_err(dev, "failed to create software node\n"); + dev_err(dev, "failed to add software node\n"); goto disable_rpm; } err = of_platform_populate(node, NULL, NULL, dev); if (err) { dev_err(&pdev->dev, "failed to create dwc3 core\n"); - goto disable_rpm; + goto remove_swnode; } dwc3_imx->dwc3 = of_find_device_by_node(dwc3_np); @@ -255,6 +254,8 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) depopulate: of_platform_depopulate(dev); +remove_swnode: + device_remove_software_node(dev); disable_rpm: pm_runtime_disable(dev); pm_runtime_put_noidle(dev); @@ -268,6 +269,7 @@ static void dwc3_imx8mp_remove(struct platform_device *pdev) pm_runtime_get_sync(dev); of_platform_depopulate(dev); + device_remove_software_node(dev); pm_runtime_disable(dev); pm_runtime_put_noidle(dev); diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c index e3738e1610db..a33a42ba0249 100644 --- a/drivers/usb/dwc3/dwc3-xilinx.c +++ b/drivers/usb/dwc3/dwc3-xilinx.c @@ -121,8 +121,11 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data) * in use but the usb3-phy entry is missing from the device tree. * Therefore, skip these operations in this case. */ - if (!priv_data->usb3_phy) + if (!priv_data->usb3_phy) { + /* Deselect the PIPE Clock Select bit in FPD PIPE Clock register */ + writel(PIPE_CLK_DESELECT, priv_data->regs + XLNX_USB_FPD_PIPE_CLK); goto skip_usb3_phy; + } crst = devm_reset_control_get_exclusive(dev, "usb_crst"); if (IS_ERR(crst)) { diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index ee3d9e3578f7..12e866fb311d 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1591,7 +1591,11 @@ static int f_midi2_create_card(struct f_midi2 *midi2) fb->info.midi_ci_version = b->midi_ci_version; fb->info.ui_hint = reverse_dir(b->ui_hint); fb->info.sysex8_streams = b->sysex8_streams; - fb->info.flags |= b->is_midi1; + if (b->is_midi1 < 2) + fb->info.flags |= b->is_midi1; + else + fb->info.flags |= SNDRV_UMP_BLOCK_IS_MIDI1 | + SNDRV_UMP_BLOCK_IS_LOWSPEED; strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 0a8c05b2746b..53d9fc41acc5 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -579,9 +579,12 @@ static int gs_start_io(struct gs_port *port) * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { - gs_free_requests(ep, head, &port->read_allocated); - gs_free_requests(port->port_usb->in, &port->write_pool, - &port->write_allocated); + /* Free reqs only if we are still connected */ + if (port->port_usb) { + gs_free_requests(ep, head, &port->read_allocated); + gs_free_requests(port->port_usb->in, &port->write_pool, + &port->write_allocated); + } status = -EIO; } diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c index 5d0d972fb7b1..2d23690d72c5 100644 --- a/drivers/usb/host/ehci-sh.c +++ b/drivers/usb/host/ehci-sh.c @@ -119,8 +119,12 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) if (IS_ERR(priv->iclk)) priv->iclk = NULL; - clk_enable(priv->fclk); - clk_enable(priv->iclk); + ret = clk_enable(priv->fclk); + if (ret) + goto fail_request_resource; + ret = clk_enable(priv->iclk); + if (ret) + goto fail_iclk; ret = usb_add_hcd(hcd, irq, IRQF_SHARED); if (ret != 0) { @@ -136,6 +140,7 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) fail_add_hcd: clk_disable(priv->iclk); +fail_iclk: clk_disable(priv->fclk); fail_request_resource: diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index 9fe4f48b1898..0881fdd1823e 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -779,11 +779,17 @@ max3421_check_unlink(struct usb_hcd *hcd) retval = 1; dev_dbg(&spi->dev, "%s: URB %p unlinked=%d", __func__, urb, urb->unlinked); - usb_hcd_unlink_urb_from_ep(hcd, urb); - spin_unlock_irqrestore(&max3421_hcd->lock, - flags); - usb_hcd_giveback_urb(hcd, urb, 0); - spin_lock_irqsave(&max3421_hcd->lock, flags); + if (urb == max3421_hcd->curr_urb) { + max3421_hcd->urb_done = 1; + max3421_hcd->hien &= ~(BIT(MAX3421_HI_HXFRDN_BIT) | + BIT(MAX3421_HI_RCVDAV_BIT)); + } else { + usb_hcd_unlink_urb_from_ep(hcd, urb); + spin_unlock_irqrestore(&max3421_hcd->lock, + flags); + usb_hcd_giveback_urb(hcd, urb, 0); + spin_lock_irqsave(&max3421_hcd->lock, flags); + } } } } diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c index 36b11127280f..75ac3c6aa92d 100644 --- a/drivers/usb/misc/onboard_usb_dev.c +++ b/drivers/usb/misc/onboard_usb_dev.c @@ -407,8 +407,10 @@ static int onboard_dev_probe(struct platform_device *pdev) } if (of_device_is_compatible(pdev->dev.of_node, "usb424,2744") || - of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) + of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) { err = onboard_dev_5744_i2c_init(client); + onboard_dev->always_powered_in_suspend = true; + } put_device(&client->dev); if (err < 0) diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index d1e7c487ddfb..0ae0a5ee3fae 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -290,6 +290,8 @@ struct anx7411_data { struct power_supply *psy; struct power_supply_desc psy_desc; struct device *dev; + struct fwnode_handle *switch_node; + struct fwnode_handle *mux_node; }; static u8 snk_identity[] = { @@ -1021,6 +1023,16 @@ static void anx7411_port_unregister_altmodes(struct typec_altmode **adev) } } +static void anx7411_port_unregister(struct typec_params *typecp) +{ + fwnode_handle_put(typecp->caps.fwnode); + anx7411_port_unregister_altmodes(typecp->port_amode); + if (typecp->port) + typec_unregister_port(typecp->port); + if (typecp->role_sw) + usb_role_switch_put(typecp->role_sw); +} + static int anx7411_usb_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state) { @@ -1089,6 +1101,7 @@ static void anx7411_unregister_mux(struct anx7411_data *ctx) if (ctx->typec.typec_mux) { typec_mux_unregister(ctx->typec.typec_mux); ctx->typec.typec_mux = NULL; + fwnode_handle_put(ctx->mux_node); } } @@ -1097,6 +1110,7 @@ static void anx7411_unregister_switch(struct anx7411_data *ctx) if (ctx->typec.typec_switch) { typec_switch_unregister(ctx->typec.typec_switch); ctx->typec.typec_switch = NULL; + fwnode_handle_put(ctx->switch_node); } } @@ -1104,28 +1118,29 @@ static int anx7411_typec_switch_probe(struct anx7411_data *ctx, struct device *dev) { int ret; - struct device_node *node; - node = of_get_child_by_name(dev->of_node, "orientation_switch"); - if (!node) + ctx->switch_node = device_get_named_child_node(dev, "orientation_switch"); + if (!ctx->switch_node) return 0; - ret = anx7411_register_switch(ctx, dev, &node->fwnode); + ret = anx7411_register_switch(ctx, dev, ctx->switch_node); if (ret) { dev_err(dev, "failed register switch"); + fwnode_handle_put(ctx->switch_node); return ret; } - node = of_get_child_by_name(dev->of_node, "mode_switch"); - if (!node) { + ctx->mux_node = device_get_named_child_node(dev, "mode_switch"); + if (!ctx->mux_node) { dev_err(dev, "no typec mux exist"); ret = -ENODEV; goto unregister_switch; } - ret = anx7411_register_mux(ctx, dev, &node->fwnode); + ret = anx7411_register_mux(ctx, dev, ctx->mux_node); if (ret) { dev_err(dev, "failed register mode switch"); + fwnode_handle_put(ctx->mux_node); ret = -ENODEV; goto unregister_switch; } @@ -1154,34 +1169,34 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = fwnode_property_read_string(fwnode, "power-role", &buf); if (ret) { dev_err(dev, "power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->type = ret; ret = fwnode_property_read_string(fwnode, "data-role", &buf); if (ret) { dev_err(dev, "data-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_data_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->data = ret; ret = fwnode_property_read_string(fwnode, "try-power-role", &buf); if (ret) { dev_err(dev, "try-power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->prefer_role = ret; /* Get source pdos */ @@ -1193,7 +1208,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->src_pdo_nr); if (ret < 0) { dev_err(dev, "source cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } typecp->caps_flags |= HAS_SOURCE_CAP; @@ -1207,7 +1222,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->sink_pdo_nr); if (ret < 0) { dev_err(dev, "sink cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } for (i = 0; i < typecp->sink_pdo_nr; i++) { @@ -1251,13 +1266,21 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = PTR_ERR(ctx->typec.port); ctx->typec.port = NULL; dev_err(dev, "Failed to register type c port %d\n", ret); - return ret; + goto put_usb_role_switch; } typec_port_register_altmodes(ctx->typec.port, NULL, ctx, ctx->typec.port_amode, MAX_ALTMODE); return 0; + +put_usb_role_switch: + if (ctx->typec.role_sw) + usb_role_switch_put(ctx->typec.role_sw); +put_fwnode: + fwnode_handle_put(fwnode); + + return ret; } static int anx7411_typec_check_connection(struct anx7411_data *ctx) @@ -1523,8 +1546,7 @@ free_wq: destroy_workqueue(plat->workqueue); free_typec_port: - typec_unregister_port(plat->typec.port); - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); free_typec_switch: anx7411_unregister_switch(plat); @@ -1548,17 +1570,11 @@ static void anx7411_i2c_remove(struct i2c_client *client) i2c_unregister_device(plat->spi_client); - if (plat->typec.role_sw) - usb_role_switch_put(plat->typec.role_sw); - anx7411_unregister_mux(plat); anx7411_unregister_switch(plat); - if (plat->typec.port) - typec_unregister_port(plat->typec.port); - - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); } static const struct i2c_device_id anx7411_id[] = { diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index c435c0835744..fcf499cc9458 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -46,11 +46,11 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci) ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); if (cci & UCSI_CCI_ACK_COMPLETE && - test_bit(ACK_PENDING, &ucsi->flags)) + test_and_clear_bit(ACK_PENDING, &ucsi->flags)) complete(&ucsi->complete); if (cci & UCSI_CCI_COMMAND_COMPLETE && - test_bit(COMMAND_PENDING, &ucsi->flags)) + test_and_clear_bit(COMMAND_PENDING, &ucsi->flags)) complete(&ucsi->complete); } EXPORT_SYMBOL_GPL(ucsi_notify_common); @@ -65,6 +65,8 @@ int ucsi_sync_control_common(struct ucsi *ucsi, u64 command) else set_bit(COMMAND_PENDING, &ucsi->flags); + reinit_completion(&ucsi->complete); + ret = ucsi->ops->async_control(ucsi, command); if (ret) goto out_clear_bit; @@ -651,7 +653,8 @@ static void ucsi_unregister_altmodes(struct ucsi_connector *con, u8 recipient) static int ucsi_get_connector_status(struct ucsi_connector *con, bool conn_ack) { u64 command = UCSI_GET_CONNECTOR_STATUS | UCSI_CONNECTOR_NUMBER(con->num); - size_t size = min(UCSI_GET_CONNECTOR_STATUS_SIZE, UCSI_MAX_DATA_LENGTH(con->ucsi)); + size_t size = min(sizeof(con->status), + UCSI_MAX_DATA_LENGTH(con->ucsi)); int ret; ret = ucsi_send_command_common(con->ucsi, command, &con->status, size, conn_ack); diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4d..7ea6f0b43b95 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..2c341956a01c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3c6f7fecbb9a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..dfeee033f31f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 586446e02ef7..ec23da8405ff 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -51,7 +51,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, * * VariableName-12345678-1234-1234-1234-1234567891bc */ -bool efivarfs_valid_name(const char *str, int len) +static bool efivarfs_valid_name(const char *str, int len) { const char *s = str + len - EFI_VARIABLE_GUID_LEN; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index d71d2e08422f..74f0602a9e01 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -60,7 +60,6 @@ bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; -extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, const struct inode *dir, int mode, dev_t dev, bool is_removable); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index a929f1b613be..beba15673be8 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -144,9 +144,6 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) const unsigned char *s = qstr->name; unsigned int len = qstr->len; - if (!efivarfs_valid_name(s, len)) - return -EINVAL; - while (len-- > EFI_VARIABLE_GUID_LEN) hash = partial_name_hash(*s++, hash); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..f5956474bfde 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..19ef4ff2a134 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1792,9 +1792,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..0dd65cefce33 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index c9f9b6e97964..9d96b833015c 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -2043,6 +2043,7 @@ exit_cifs(void) destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); destroy_workqueue(serverclose_wq); + destroy_workqueue(cfid_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 668098d3b108..f146e06c97eb 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1947,6 +1947,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } + netfs_wait_for_outstanding_io(inode); cifs_close_deferred_file_under_dentry(tcon, full_path); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -2464,8 +2465,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } cifs_close_deferred_file_under_dentry(tcon, from_name); - if (d_inode(target_dentry) != NULL) + if (d_inode(target_dentry) != NULL) { + netfs_wait_for_outstanding_io(d_inode(target_dentry)); cifs_close_deferred_file_under_dentry(tcon, to_name); + } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 50b1aba20008..d88b41133e00 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -676,7 +676,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf return -ENOMEM; symname_utf16_len = utf8s_to_utf16s(buf->PathBuffer, symname_utf8_len, UTF16_LITTLE_ENDIAN, - symname_utf16, symname_utf8_len * 2); + (wchar_t *) symname_utf16, symname_utf8_len * 2); if (symname_utf16_len < 0) { kfree(symname_utf16); return symname_utf16_len; diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 0bb77f9ec686..3306fb655136 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -488,11 +488,11 @@ cifs_ses_add_channel(struct cifs_ses *ses, if (iface->sockaddr.ss_family == AF_INET) cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv4->sin_addr); else cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI6)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv6->sin6_addr); /* diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 1d1ffd0acaca..2a5b4a96bf99 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1016,6 +1016,8 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; + if (enc) + ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); return 0; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index df92d746e89c..71c6939dfbf1 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -263,8 +263,10 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); - if (sess) + if (sess) { sess->last_active = jiffies; + ksmbd_user_session_get(sess); + } up_read(&conn->session_lock); return sess; } @@ -275,6 +277,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + ksmbd_user_session_get(sess); up_read(&sessions_table_lock); return sess; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 930d7566b52e..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,14 +241,14 @@ send: if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); if (rc < 0) conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); } + if (work->sess) + ksmbd_user_session_put(work->sess); ksmbd_conn_write(work); } @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..94187628ff08 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4f539eeadbb0..23e21845f928 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -67,8 +67,10 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) return false; sess = ksmbd_session_lookup_all(conn, id); - if (sess) + if (sess) { + ksmbd_user_session_put(sess); return true; + } pr_err("Invalid user session id: %llu\n", id); return false; } @@ -605,10 +607,8 @@ int smb2_check_user_session(struct ksmbd_work *work) /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); - if (work->sess) { - ksmbd_user_session_get(work->sess); + if (work->sess) return 1; - } ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); return -ENOENT; } @@ -1097,6 +1097,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1248,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -1701,29 +1703,35 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; + ksmbd_user_session_put(sess); goto out_err; } + ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; @@ -1731,7 +1739,8 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (ksmbd_session_lookup(conn, sess_id)) { + sess = ksmbd_session_lookup(conn, sess_id); + if (!sess) { rc = -EACCES; goto out_err; } @@ -1742,7 +1751,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = true; - ksmbd_user_session_get(sess); } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { @@ -1769,7 +1777,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = false; - ksmbd_user_session_get(sess); } work->sess = sess; @@ -2197,9 +2204,9 @@ err_out: int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_logoff_req *req; struct smb2_logoff_rsp *rsp; - struct ksmbd_session *sess; u64 sess_id; int err; @@ -2221,11 +2228,6 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); - /* - * Re-lookup session to validate if session is deleted - * while waiting request complete - */ - sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -4228,6 +4230,7 @@ static bool __query_dir(struct dir_context *ctx, const char *name, int namlen, /* dot and dotdot entries are already reserved */ if (!strcmp(".", name) || !strcmp("..", name)) return true; + d_info->num_scan++; if (ksmbd_share_veto_filename(priv->work->tcon->share_conf, name)) return true; if (!match_pattern(name, namlen, priv->search_pattern)) @@ -4390,9 +4393,18 @@ int smb2_query_dir(struct ksmbd_work *work) query_dir_private.info_level = req->FileInformationClass; dir_fp->readdir_data.private = &query_dir_private; set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir); - +again: + d_info.num_scan = 0; rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx); /* + * num_entry can be 0 if the directory iteration stops before reaching + * the end of the directory and no file is matched with the search + * pattern. + */ + if (rc >= 0 && !d_info.num_entry && d_info.num_scan && + d_info.out_buf_len > 0) + goto again; + /* * req->OutputBufferLength is too small to contain even one entry. * In this case, it immediately returns OutputBufferLength 0 to client. */ @@ -6016,15 +6028,13 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - attrs.ia_valid |= ATTR_CTIME; if (file_info->ChangeTime) - attrs.ia_ctime = ksmbd_NTtimeToUnix(file_info->ChangeTime); - else - attrs.ia_ctime = inode_get_ctime(inode); + inode_set_ctime_to_ts(inode, + ksmbd_NTtimeToUnix(file_info->ChangeTime)); if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); - attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); + attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET | ATTR_CTIME); } if (file_info->Attributes) { @@ -6066,8 +6076,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, return -EACCES; inode_lock(inode); - inode_set_ctime_to_ts(inode, attrs.ia_ctime); - attrs.ia_valid &= ~ATTR_CTIME; rc = notify_change(idmap, dentry, &attrs, NULL); inode_unlock(inode); } @@ -8982,6 +8990,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) le64_to_cpu(tr_hdr->SessionId)); return -ECONNABORTED; } + ksmbd_user_session_put(sess); iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..befaf42b84cc 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cb76f4b5bafe..06903024a2d8 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -43,6 +43,7 @@ struct ksmbd_dir_info { char *rptr; int name_len; int out_buf_len; + int num_scan; int num_entry; int data_count; int last_entry_offset; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 2b5fc5fd1643..68ee1c299c25 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3557,14 +3557,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. + * + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -5144,7 +5161,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -5154,7 +5171,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 3b739459ebb0..c5bff273cae2 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -484,7 +484,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 9b34896dd1a3..6f270d8f4270 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -744,6 +744,7 @@ xfs_finobt_count_blocks( { struct xfs_buf *agbp = NULL; struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); @@ -751,9 +752,10 @@ xfs_finobt_count_blocks( return error; cur = xfs_finobt_init_cursor(pag, tp, agbp); - error = xfs_btree_count_blocks(cur, tree_blocks); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index e74bb059f24f..4f3bfc884aff 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -496,7 +496,7 @@ xfs_rtginode_create( error = xfs_metadir_create(&upd, S_IFREG); if (error) - return error; + goto out_cancel; xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a809513a290c..3b5623611eba 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -494,12 +494,13 @@ xfs_validate_sb_common( return -EINVAL; } - if (!sbp->sb_spino_align || - sbp->sb_spino_align > sbp->sb_inoalignmt || - (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0) { + if (sbp->sb_spino_align && + (sbp->sb_spino_align > sbp->sb_inoalignmt || + (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { xfs_warn(mp, - "Sparse inode alignment (%u) is invalid.", - sbp->sb_spino_align); +"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", + sbp->sb_spino_align, + sbp->sb_inoalignmt); return -EINVAL; } } else if (sbp->sb_spino_align) { diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index f228127a88ff..fb47a76ead18 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -92,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 61f80a6410c7..9f8c312dfd3c 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -60,6 +60,32 @@ xchk_superblock_xref( } /* + * Calculate the ondisk superblock size in bytes given the feature set of the + * mounted filesystem (aka the primary sb). This is subtlely different from + * the logic in xfs_repair, which computes the size of a secondary sb given the + * featureset listed in the secondary sb. + */ +STATIC size_t +xchk_superblock_ondisk_size( + struct xfs_mount *mp) +{ + if (xfs_has_metadir(mp)) + return offsetofend(struct xfs_dsb, sb_pad); + if (xfs_has_metauuid(mp)) + return offsetofend(struct xfs_dsb, sb_meta_uuid); + if (xfs_has_crc(mp)) + return offsetofend(struct xfs_dsb, sb_lsn); + if (xfs_sb_version_hasmorebits(&mp->m_sb)) + return offsetofend(struct xfs_dsb, sb_bad_features2); + if (xfs_has_logv2(mp)) + return offsetofend(struct xfs_dsb, sb_logsunit); + if (xfs_has_sector(mp)) + return offsetofend(struct xfs_dsb, sb_logsectsize); + /* only support dirv2 or more recent */ + return offsetofend(struct xfs_dsb, sb_dirblklog); +} + +/* * Scrub the filesystem superblock. * * Note: We do /not/ attempt to check AG 0's superblock. Mount is @@ -75,6 +101,7 @@ xchk_superblock( struct xfs_buf *bp; struct xfs_dsb *sb; struct xfs_perag *pag; + size_t sblen; xfs_agnumber_t agno; uint32_t v2_ok; __be32 features_mask; @@ -145,8 +172,11 @@ xchk_superblock( xchk_block_set_preen(sc, bp); if (xfs_has_metadir(sc->mp)) { - if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) - xchk_block_set_preen(sc, bp); + if (sb->sb_rbmino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rsumino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); } else { if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino)) xchk_block_set_preen(sc, bp); @@ -229,7 +259,13 @@ xchk_superblock( * sb_icount, sb_ifree, sb_fdblocks, sb_frexents */ - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_uquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_gquotino != cpu_to_be64(0)) + xchk_block_set_preen(sc, bp); + } else { if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino)) xchk_block_set_preen(sc, bp); @@ -281,15 +317,8 @@ xchk_superblock( if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok))) xchk_block_set_corrupt(sc, bp); - if (xfs_has_metadir(mp)) { - if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) - xchk_block_set_corrupt(sc, bp); - if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) - xchk_block_set_preen(sc, bp); - } else { - if (sb->sb_features2 != sb->sb_bad_features2) - xchk_block_set_preen(sc, bp); - } + if (sb->sb_features2 != sb->sb_bad_features2) + xchk_block_set_preen(sc, bp); } /* Check sb_features2 flags that are set at mkfs time. */ @@ -351,7 +380,10 @@ xchk_superblock( if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align)) xchk_block_set_corrupt(sc, bp); - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_pquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + } else { if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino)) xchk_block_set_preen(sc, bp); } @@ -366,16 +398,25 @@ xchk_superblock( } if (xfs_has_metadir(mp)) { + if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) + xchk_block_set_preen(sc, bp); + if (sb->sb_rgcount != cpu_to_be32(mp->m_sb.sb_rgcount)) xchk_block_set_corrupt(sc, bp); if (sb->sb_rgextents != cpu_to_be32(mp->m_sb.sb_rgextents)) xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) + xchk_block_set_corrupt(sc, bp); + + if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) + xchk_block_set_corrupt(sc, bp); } /* Everything else must be zero. */ - if (memchr_inv(sb + 1, 0, - BBTOB(bp->b_length) - sizeof(struct xfs_dsb))) + sblen = xchk_superblock_ondisk_size(mp); + if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) xchk_block_set_corrupt(sc, bp); xchk_superblock_xref(sc, bp); @@ -458,7 +499,7 @@ xchk_agf_xref_btreeblks( { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; struct xfs_mount *mp = sc->mp; - xfs_agblock_t blocks; + xfs_filblks_t blocks; xfs_agblock_t btreeblks; int error; @@ -507,7 +548,7 @@ xchk_agf_xref_refcblks( struct xfs_scrub *sc) { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; if (!sc->sa.refc_cur) @@ -840,7 +881,7 @@ xchk_agi_xref_fiblocks( struct xfs_scrub *sc) { struct xfs_agi *agi = sc->sa.agi_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error = 0; if (!xfs_has_inobtcounts(sc->mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 0fad0baaba2f..b45d2b32051a 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -256,7 +256,7 @@ xrep_agf_calc_from_btrees( struct xfs_agf *agf = agf_bp->b_addr; struct xfs_mount *mp = sc->mp; xfs_agblock_t btreeblks; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; /* Update the AGF counters from the bnobt. */ @@ -946,7 +946,7 @@ xrep_agi_calc_from_btrees( if (error) goto err; if (xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; error = xfs_btree_count_blocks(cur, &blocks); if (error) @@ -959,7 +959,7 @@ xrep_agi_calc_from_btrees( agi->agi_freecount = cpu_to_be32(freecount); if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; cur = xfs_finobt_init_cursor(sc->sa.pag, sc->tp, agi_bp); error = xfs_btree_count_blocks(cur, &blocks); diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 4a50f8e00040..ca23cf4db6c5 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -261,7 +261,7 @@ xchk_fscount_btreeblks( struct xchk_fscounters *fsc, xfs_agnumber_t agno) { - xfs_extlen_t blocks; + xfs_filblks_t blocks; int error; error = xchk_ag_init_existing(sc, agno, &sc->sa); diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index ce86bdad37fa..ccc6ca5934ca 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -71,7 +71,8 @@ /* Map our scrub type to a sick mask and a set of health update functions. */ enum xchk_health_group { - XHG_FS = 1, + XHG_NONE = 1, + XHG_FS, XHG_AG, XHG_INO, XHG_RTGROUP, @@ -83,6 +84,7 @@ struct xchk_health_map { }; static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { + [XFS_SCRUB_TYPE_PROBE] = { XHG_NONE, 0 }, [XFS_SCRUB_TYPE_SB] = { XHG_AG, XFS_SICK_AG_SB }, [XFS_SCRUB_TYPE_AGF] = { XHG_AG, XFS_SICK_AG_AGF }, [XFS_SCRUB_TYPE_AGFL] = { XHG_AG, XFS_SICK_AG_AGFL }, @@ -133,7 +135,7 @@ xchk_mark_healthy_if_clean( { if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT))) - sc->sick_mask |= mask; + sc->healthy_mask |= mask; } /* @@ -189,6 +191,7 @@ xchk_update_health( { struct xfs_perag *pag; struct xfs_rtgroup *rtg; + unsigned int mask = sc->sick_mask; bool bad; /* @@ -203,50 +206,56 @@ xchk_update_health( return; } - if (!sc->sick_mask) - return; - bad = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT)); + if (!bad) + mask |= sc->healthy_mask; switch (type_to_health_flag[sc->sm->sm_type].group) { + case XHG_NONE: + break; case XHG_AG: + if (!mask) + return; pag = xfs_perag_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(pag_group(pag), sc->sick_mask); + xfs_group_mark_corrupt(pag_group(pag), mask); else - xfs_group_mark_healthy(pag_group(pag), sc->sick_mask); + xfs_group_mark_healthy(pag_group(pag), mask); xfs_perag_put(pag); break; case XHG_INO: if (!sc->ip) return; - if (bad) { - unsigned int mask = sc->sick_mask; - - /* - * If we're coming in for repairs then we don't want - * sickness flags to propagate to the incore health - * status if the inode gets inactivated before we can - * fix it. - */ - if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) - mask |= XFS_SICK_INO_FORGET; + /* + * If we're coming in for repairs then we don't want sickness + * flags to propagate to the incore health status if the inode + * gets inactivated before we can fix it. + */ + if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) + mask |= XFS_SICK_INO_FORGET; + if (!mask) + return; + if (bad) xfs_inode_mark_corrupt(sc->ip, mask); - } else - xfs_inode_mark_healthy(sc->ip, sc->sick_mask); + else + xfs_inode_mark_healthy(sc->ip, mask); break; case XHG_FS: + if (!mask) + return; if (bad) - xfs_fs_mark_corrupt(sc->mp, sc->sick_mask); + xfs_fs_mark_corrupt(sc->mp, mask); else - xfs_fs_mark_healthy(sc->mp, sc->sick_mask); + xfs_fs_mark_healthy(sc->mp, mask); break; case XHG_RTGROUP: + if (!mask) + return; rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_corrupt(rtg_group(rtg), mask); else - xfs_group_mark_healthy(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_healthy(rtg_group(rtg), mask); xfs_rtgroup_put(rtg); break; default: diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index abad54c3621d..4dc7c83dc08a 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -650,8 +650,8 @@ xchk_iallocbt_xref_rmap_btreeblks( struct xfs_scrub *sc) { xfs_filblks_t blocks; - xfs_extlen_t inobt_blocks = 0; - xfs_extlen_t finobt_blocks = 0; + xfs_filblks_t inobt_blocks = 0; + xfs_filblks_t finobt_blocks = 0; int error; if (!sc->sa.ino_cur || !sc->sa.rmap_cur || diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index b78db6513465..c678cba1ffc3 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -171,23 +171,13 @@ static int xchk_setup_metapath_quotadir( struct xfs_scrub *sc) { - struct xfs_trans *tp; - struct xfs_inode *dp = NULL; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; - error = xfs_dqinode_load_parent(tp, &dp); - xfs_trans_cancel(tp); - if (error) - return error; + if (!qi || !qi->qi_dirip) + return -ENOENT; - error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, - kasprintf(GFP_KERNEL, "quota"), dp); - xfs_irele(dp); - return error; + return xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, + kstrdup("quota", GFP_KERNEL), qi->qi_dirip); } /* Scan a quota inode under the /quota directory. */ @@ -196,37 +186,31 @@ xchk_setup_metapath_dqinode( struct xfs_scrub *sc, xfs_dqtype_t type) { - struct xfs_trans *tp = NULL; - struct xfs_inode *dp = NULL; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; struct xfs_inode *ip = NULL; - const char *path; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; - error = xfs_dqinode_load_parent(tp, &dp); - if (error) - goto out_cancel; - - error = xfs_dqinode_load(tp, dp, type, &ip); - if (error) - goto out_dp; - - xfs_trans_cancel(tp); - tp = NULL; + if (!qi) + return -ENOENT; - path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type)); - error = xchk_setup_metapath_scan(sc, dp, path, ip); + switch (type) { + case XFS_DQTYPE_USER: + ip = qi->qi_uquotaip; + break; + case XFS_DQTYPE_GROUP: + ip = qi->qi_gquotaip; + break; + case XFS_DQTYPE_PROJ: + ip = qi->qi_pquotaip; + break; + default: + ASSERT(0); + return -EINVAL; + } + if (!ip) + return -ENOENT; - xfs_irele(ip); -out_dp: - xfs_irele(dp); -out_cancel: - if (tp) - xfs_trans_cancel(tp); - return error; + return xchk_setup_metapath_scan(sc, qi->qi_dirip, + kstrdup(xfs_dqinode_path(type), GFP_KERNEL), ip); } #else # define xchk_setup_metapath_quotadir(...) (-ENOENT) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 2b6be75e9424..1c5e45cc6419 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -491,7 +491,7 @@ xchk_refcount_xref_rmap( struct xfs_scrub *sc, xfs_filblks_t cow_blocks) { - xfs_extlen_t refcbt_blocks = 0; + xfs_filblks_t refcbt_blocks = 0; xfs_filblks_t blocks; int error; diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index a7fda3e2b013..5dbbe93cb49b 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -184,6 +184,12 @@ struct xfs_scrub { */ unsigned int sick_mask; + /* + * Clear these XFS_SICK_* flags but only if the scan is ok. Useful for + * removing ZAPPED flags after a repair. + */ + unsigned int healthy_mask; + /* next time we want to cond_resched() */ struct xchk_relax relax; diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index d015a86ef460..953ce7be78dc 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -36,6 +36,7 @@ #include "scrub/tempfile.h" #include "scrub/tempexch.h" #include "scrub/reap.h" +#include "scrub/health.h" /* * Symbolic Link Repair @@ -233,7 +234,7 @@ xrep_symlink_salvage( * target zapped flag. */ if (buflen == 0) { - sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED; + xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED); sprintf(target_buf, DUMMY_TARGET); } diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 4b7f7860e37e..2d7ca7e1bbca 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -184,11 +184,18 @@ out_release_dquots: } /* + * Move sc->tempip from the regular directory tree to the metadata directory + * tree if sc->ip is part of the metadata directory tree and tempip has an + * eligible file mode. + * * Temporary files have to be created before we even know which inode we're * going to scrub, so we assume that they will be part of the regular directory * tree. If it turns out that we're actually scrubbing a file from the * metadata directory tree, we have to subtract the temp file from the root - * dquots and detach the dquots. + * dquots and detach the dquots prior to setting the METADATA iflag. However, + * the scrub setup functions grab sc->ip and create sc->tempip before we + * actually get around to checking if the file mode is the right type for the + * scrubber. */ int xrep_tempfile_adjust_directory_tree( @@ -204,6 +211,9 @@ xrep_tempfile_adjust_directory_tree( if (!sc->ip || !xfs_is_metadir_inode(sc->ip)) return 0; + if (!S_ISDIR(VFS_I(sc->tempip)->i_mode) && + !S_ISREG(VFS_I(sc->tempip)->i_mode)) + return 0; xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -223,6 +233,7 @@ xrep_tempfile_adjust_directory_tree( if (error) goto out_ilock; + xfs_iflags_set(sc->tempip, XFS_IRECOVERY); xfs_qm_dqdetach(sc->tempip); out_ilock: xrep_tempfile_iunlock(sc); @@ -246,6 +257,8 @@ xrep_tempfile_remove_metadir( ASSERT(sc->tp == NULL); + xfs_iflags_clear(sc->tempip, XFS_IRECOVERY); + xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -945,10 +958,13 @@ xrep_is_tempfile( /* * Files in the metadata directory tree also have S_PRIVATE set and - * IOP_XATTR unset, so we must distinguish them separately. + * IOP_XATTR unset, so we must distinguish them separately. We (ab)use + * the IRECOVERY flag to mark temporary metadir inodes knowing that the + * end of log recovery clears IRECOVERY, so the only ones that can + * exist during online repair are the ones we create. */ if (xfs_has_metadir(mp) && (ip->i_diflags2 & XFS_DIFLAG2_METADATA)) - return false; + return __xfs_iflags_test(ip, XFS_IRECOVERY); if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR)) return true; diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 9b38f5ad1eaf..d2ae7e93acb0 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -605,7 +605,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error, TP_fast_assign( xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level); __entry->dev = sc->mp->m_super->s_dev; - __entry->ino = sc->ip->i_ino; + __entry->ino = cur->bc_ino.ip->i_ino; __entry->whichfork = cur->bc_ino.whichfork; __entry->type = sc->sm->sm_type; __assign_str(name); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a59bbe767a7d..0836fea2d6d8 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -103,7 +103,7 @@ xfs_bmap_count_blocks( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - xfs_extlen_t btblocks = 0; + xfs_filblks_t btblocks = 0; int error; *nextents = 0; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index ff982d983989..f11d475898f2 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -69,6 +69,30 @@ xfs_dquot_mark_sick( } /* + * Detach the dquot buffer if it's still attached, because we can get called + * through dqpurge after a log shutdown. Caller must hold the dqflock or have + * otherwise isolated the dquot. + */ +void +xfs_dquot_detach_buf( + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_buf *bp = NULL; + + spin_lock(&qlip->qli_lock); + if (qlip->qli_item.li_buf) { + bp = qlip->qli_item.li_buf; + qlip->qli_item.li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) { + list_del_init(&qlip->qli_item.li_bio_list); + xfs_buf_rele(bp); + } +} + +/* * This is called to free all the memory associated with a dquot */ void @@ -76,6 +100,7 @@ xfs_qm_dqdestroy( struct xfs_dquot *dqp) { ASSERT(list_empty(&dqp->q_lru)); + ASSERT(dqp->q_logitem.qli_item.li_buf == NULL); kvfree(dqp->q_logitem.qli_item.li_lv_shadow); mutex_destroy(&dqp->q_qlock); @@ -1142,9 +1167,11 @@ static void xfs_qm_dqflush_done( struct xfs_log_item *lip) { - struct xfs_dq_logitem *qip = (struct xfs_dq_logitem *)lip; - struct xfs_dquot *dqp = qip->qli_dquot; + struct xfs_dq_logitem *qlip = + container_of(lip, struct xfs_dq_logitem, qli_item); + struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_ail *ailp = lip->li_ailp; + struct xfs_buf *bp = NULL; xfs_lsn_t tail_lsn; /* @@ -1156,12 +1183,12 @@ xfs_qm_dqflush_done( * holding the lock before removing the dquot from the AIL. */ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) && - ((lip->li_lsn == qip->qli_flush_lsn) || + (lip->li_lsn == qlip->qli_flush_lsn || test_bit(XFS_LI_FAILED, &lip->li_flags))) { spin_lock(&ailp->ail_lock); xfs_clear_li_failed(lip); - if (lip->li_lsn == qip->qli_flush_lsn) { + if (lip->li_lsn == qlip->qli_flush_lsn) { /* xfs_ail_update_finish() drops the AIL lock */ tail_lsn = xfs_ail_delete_one(ailp, lip); xfs_ail_update_finish(ailp, tail_lsn); @@ -1171,6 +1198,20 @@ xfs_qm_dqflush_done( } /* + * If this dquot hasn't been dirtied since initiating the last dqflush, + * release the buffer reference. We already unlinked this dquot item + * from the buffer. + */ + spin_lock(&qlip->qli_lock); + if (!qlip->qli_dirty) { + bp = lip->li_buf; + lip->li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) + xfs_buf_rele(bp); + + /* * Release the dq's flush lock since we're done with it. */ xfs_dqfunlock(dqp); @@ -1196,7 +1237,7 @@ xfs_buf_dquot_io_fail( spin_lock(&bp->b_mount->m_ail->ail_lock); list_for_each_entry(lip, &bp->b_li_list, li_bio_list) - xfs_set_li_failed(lip, bp); + set_bit(XFS_LI_FAILED, &lip->li_flags); spin_unlock(&bp->b_mount->m_ail->ail_lock); } @@ -1239,6 +1280,111 @@ xfs_qm_dqflush_check( } /* + * Get the buffer containing the on-disk dquot. + * + * Requires dquot flush lock, will clear the dirty flag, delete the quota log + * item from the AIL, and shut down the system if something goes wrong. + */ +static int +xfs_dquot_read_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_mount *mp = dqp->q_mount; + struct xfs_buf *bp = NULL; + int error; + + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, + &bp, &xfs_dquot_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_dquot_mark_sick(dqp); + if (error) + goto out_abort; + + *bpp = bp; + return 0; + +out_abort: + dqp->q_flags &= ~XFS_DQFLAG_DIRTY; + xfs_trans_ail_delete(&dqp->q_logitem.qli_item, 0); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; +} + +/* + * Attach a dquot buffer to this dquot to avoid allocating a buffer during a + * dqflush, since dqflush can be called from reclaim context. + */ +int +xfs_dquot_attach_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; + int error; + + spin_lock(&qlip->qli_lock); + if (!lip->li_buf) { + struct xfs_buf *bp = NULL; + + spin_unlock(&qlip->qli_lock); + error = xfs_dquot_read_buf(tp, dqp, &bp); + if (error) + return error; + + /* + * Attach the dquot to the buffer so that the AIL does not have + * to read the dquot buffer to push this item. + */ + xfs_buf_hold(bp); + spin_lock(&qlip->qli_lock); + lip->li_buf = bp; + xfs_trans_brelse(tp, bp); + } + qlip->qli_dirty = true; + spin_unlock(&qlip->qli_lock); + + return 0; +} + +/* + * Get a new reference the dquot buffer attached to this dquot for a dqflush + * operation. + * + * Returns 0 and a NULL bp if none was attached to the dquot; 0 and a locked + * bp; or -EAGAIN if the buffer could not be locked. + */ +int +xfs_dquot_use_attached_buf( + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_buf *bp = dqp->q_logitem.qli_item.li_buf; + + /* + * A NULL buffer can happen if the dquot dirty flag was set but the + * filesystem shut down before transaction commit happened. In that + * case we're not going to flush anyway. + */ + if (!bp) { + ASSERT(xfs_is_shutdown(dqp->q_mount)); + + *bpp = NULL; + return 0; + } + + if (!xfs_buf_trylock(bp)) + return -EAGAIN; + + xfs_buf_hold(bp); + *bpp = bp; + return 0; +} + +/* * Write a modified dquot to disk. * The dquot must be locked and the flush lock too taken by caller. * The flush lock will not be unlocked until the dquot reaches the disk, @@ -1249,11 +1395,11 @@ xfs_qm_dqflush_check( int xfs_qm_dqflush( struct xfs_dquot *dqp, - struct xfs_buf **bpp) + struct xfs_buf *bp) { struct xfs_mount *mp = dqp->q_mount; - struct xfs_log_item *lip = &dqp->q_logitem.qli_item; - struct xfs_buf *bp; + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; struct xfs_dqblk *dqblk; xfs_failaddr_t fa; int error; @@ -1263,28 +1409,12 @@ xfs_qm_dqflush( trace_xfs_dqflush(dqp); - *bpp = NULL; - xfs_qm_dqunpin_wait(dqp); - /* - * Get the buffer containing the on-disk dquot - */ - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK, - &bp, &xfs_dquot_buf_ops); - if (error == -EAGAIN) - goto out_unlock; - if (xfs_metadata_is_sick(error)) - xfs_dquot_mark_sick(dqp); - if (error) - goto out_abort; - fa = xfs_qm_dqflush_check(dqp); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", dqp->q_id, fa); - xfs_buf_relse(bp); xfs_dquot_mark_sick(dqp); error = -EFSCORRUPTED; goto out_abort; @@ -1299,8 +1429,15 @@ xfs_qm_dqflush( */ dqp->q_flags &= ~XFS_DQFLAG_DIRTY; - xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn, - &dqp->q_logitem.qli_item.li_lsn); + /* + * We hold the dquot lock, so nobody can dirty it while we're + * scheduling the write out. Clear the dirty-since-flush flag. + */ + spin_lock(&qlip->qli_lock); + qlip->qli_dirty = false; + spin_unlock(&qlip->qli_lock); + + xfs_trans_ail_copy_lsn(mp->m_ail, &qlip->qli_flush_lsn, &lip->li_lsn); /* * copy the lsn into the on-disk dquot now while we have the in memory @@ -1312,7 +1449,7 @@ xfs_qm_dqflush( * of a dquot without an up-to-date CRC getting to disk. */ if (xfs_has_crc(mp)) { - dqblk->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn); + dqblk->dd_lsn = cpu_to_be64(lip->li_lsn); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } @@ -1322,7 +1459,7 @@ xfs_qm_dqflush( * the AIL and release the flush lock once the dquot is synced to disk. */ bp->b_flags |= _XBF_DQUOTS; - list_add_tail(&dqp->q_logitem.qli_item.li_bio_list, &bp->b_li_list); + list_add_tail(&lip->li_bio_list, &bp->b_li_list); /* * If the buffer is pinned then push on the log so we won't @@ -1334,14 +1471,12 @@ xfs_qm_dqflush( } trace_xfs_dqflush_done(dqp); - *bpp = bp; return 0; out_abort: dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); -out_unlock: xfs_dqfunlock(dqp); return error; } diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index d73d179df009..c617bac75361 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -214,7 +214,7 @@ void xfs_dquot_to_disk(struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp); #define XFS_DQ_IS_DIRTY(dqp) ((dqp)->q_flags & XFS_DQFLAG_DIRTY) void xfs_qm_dqdestroy(struct xfs_dquot *dqp); -int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf **bpp); +int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf *bp); void xfs_qm_dqunpin_wait(struct xfs_dquot *dqp); void xfs_qm_adjust_dqtimers(struct xfs_dquot *d); void xfs_qm_adjust_dqlimits(struct xfs_dquot *d); @@ -237,6 +237,10 @@ void xfs_dqlockn(struct xfs_dqtrx *q); void xfs_dquot_set_prealloc_limits(struct xfs_dquot *); +int xfs_dquot_attach_buf(struct xfs_trans *tp, struct xfs_dquot *dqp); +int xfs_dquot_use_attached_buf(struct xfs_dquot *dqp, struct xfs_buf **bpp); +void xfs_dquot_detach_buf(struct xfs_dquot *dqp); + static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp) { xfs_dqlock(dqp); diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 7d19091215b0..271b195ebb93 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -123,8 +123,9 @@ xfs_qm_dquot_logitem_push( __releases(&lip->li_ailp->ail_lock) __acquires(&lip->li_ailp->ail_lock) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; - struct xfs_buf *bp = lip->li_buf; + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + struct xfs_buf *bp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -155,14 +156,25 @@ xfs_qm_dquot_logitem_push( spin_unlock(&lip->li_ailp->ail_lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + rval = XFS_ITEM_LOCKED; + goto out_relock_ail; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend does it on + * success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; - xfs_buf_relse(bp); - } else if (error == -EAGAIN) - rval = XFS_ITEM_LOCKED; + } + xfs_buf_relse(bp); +out_relock_ail: spin_lock(&lip->li_ailp->ail_lock); out_unlock: xfs_dqunlock(dqp); @@ -195,12 +207,10 @@ xfs_qm_dquot_logitem_committing( } #ifdef DEBUG_EXPENSIVE -static int -xfs_qm_dquot_logitem_precommit( - struct xfs_trans *tp, - struct xfs_log_item *lip) +static void +xfs_qm_dquot_logitem_precommit_check( + struct xfs_dquot *dqp) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; struct xfs_mount *mp = dqp->q_mount; struct xfs_disk_dquot ddq = { }; xfs_failaddr_t fa; @@ -216,13 +226,24 @@ xfs_qm_dquot_logitem_precommit( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); ASSERT(fa == NULL); } - - return 0; } #else -# define xfs_qm_dquot_logitem_precommit NULL +# define xfs_qm_dquot_logitem_precommit_check(...) ((void)0) #endif +static int +xfs_qm_dquot_logitem_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + + xfs_qm_dquot_logitem_precommit_check(dqp); + + return xfs_dquot_attach_buf(tp, dqp); +} + static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, .iop_precommit = xfs_qm_dquot_logitem_precommit, @@ -247,5 +268,7 @@ xfs_qm_dquot_logitem_init( xfs_log_item_init(dqp->q_mount, &lp->qli_item, XFS_LI_DQUOT, &xfs_dquot_item_ops); + spin_lock_init(&lp->qli_lock); lp->qli_dquot = dqp; + lp->qli_dirty = false; } diff --git a/fs/xfs/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h index 794710c24474..d66e52807d76 100644 --- a/fs/xfs/xfs_dquot_item.h +++ b/fs/xfs/xfs_dquot_item.h @@ -14,6 +14,13 @@ struct xfs_dq_logitem { struct xfs_log_item qli_item; /* common portion */ struct xfs_dquot *qli_dquot; /* dquot ptr */ xfs_lsn_t qli_flush_lsn; /* lsn at last flush */ + + /* + * We use this spinlock to coordinate access to the li_buf pointer in + * the log item and the qli_dirty flag. + */ + spinlock_t qli_lock; + bool qli_dirty; /* dirtied since last flush? */ }; void xfs_qm_dquot_logitem_init(struct xfs_dquot *dqp); diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 9ab05ad224d1..265c42449893 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -854,7 +854,7 @@ xfs_ioc_start_commit( struct xfs_commit_range __user *argp) { struct xfs_commit_range args = { }; - struct timespec64 ts; + struct kstat kstat = { }; struct xfs_commit_range_fresh *kern_f; struct xfs_commit_range_fresh __user *user_f; struct inode *inode2 = file_inode(file); @@ -871,12 +871,12 @@ xfs_ioc_start_commit( memcpy(&kern_f->fsid, ip2->i_mount->m_fixedfsid, sizeof(xfs_fsid_t)); xfs_ilock(ip2, lockflags); - ts = inode_get_ctime(inode2); - kern_f->file2_ctime = ts.tv_sec; - kern_f->file2_ctime_nsec = ts.tv_nsec; - ts = inode_get_mtime(inode2); - kern_f->file2_mtime = ts.tv_sec; - kern_f->file2_mtime_nsec = ts.tv_nsec; + /* Force writing of a distinct ctime if any writes happen. */ + fill_mg_cmtime(&kstat, STATX_CTIME | STATX_MTIME, inode2); + kern_f->file2_ctime = kstat.ctime.tv_sec; + kern_f->file2_ctime_nsec = kstat.ctime.tv_nsec; + kern_f->file2_mtime = kstat.mtime.tv_sec; + kern_f->file2_mtime_nsec = kstat.mtime.tv_nsec; kern_f->file2_ino = ip2->i_ino; kern_f->file2_gen = inode2->i_generation; kern_f->magic = XCR_FRESH_MAGIC; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4a0b7de4f7ae..9a435b1ff264 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1242,6 +1242,14 @@ out_unlock: xfs_iunlock2_remapping(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + /* + * If the caller did not set CAN_SHORTEN, then it is not prepared to + * handle partial results -- either the whole remap succeeds, or we + * must say why it did not. In this case, any error should be returned + * to the caller. + */ + if (ret && remapped < len && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return ret; return remapped > 0 ? remapped : ret; } diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 82f2e0dd2249..3290dd8524a6 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -163,7 +163,8 @@ struct xfs_getfsmap_info { xfs_daddr_t next_daddr; /* next daddr we expect */ /* daddr of low fsmap key when we're using the rtbitmap */ xfs_daddr_t low_daddr; - xfs_daddr_t end_daddr; /* daddr of high fsmap key */ + /* daddr of high fsmap key, or the last daddr on the device */ + xfs_daddr_t end_daddr; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ /* @@ -387,8 +388,8 @@ xfs_getfsmap_group_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) - frec->start_daddr = info->end_daddr; + if (info->last) + frec->start_daddr = info->end_daddr + 1; else frec->start_daddr = xfs_gbno_to_daddr(xg, startblock); @@ -736,11 +737,10 @@ xfs_getfsmap_rtdev_rtbitmap_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) { - frec.start_daddr = info->end_daddr; - } else { + if (info->last) + frec.start_daddr = info->end_daddr + 1; + else frec.start_daddr = xfs_rtb_to_daddr(mp, start_rtb); - } frec.len_daddr = XFS_FSB_TO_BB(mp, rtbcount); return xfs_getfsmap_helper(tp, info, &frec); @@ -933,7 +933,10 @@ xfs_getfsmap( struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; - struct xfs_getfsmap_info info = { NULL }; + struct xfs_getfsmap_info info = { + .fsmap_recs = fsmap_recs, + .head = head, + }; bool use_rmap; int i; int error = 0; @@ -998,9 +1001,6 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.end_daddr = XFS_BUF_DADDR_NULL; - info.fsmap_recs = fsmap_recs; - info.head = head; /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { @@ -1013,17 +1013,23 @@ xfs_getfsmap( break; /* - * If this device number matches the high key, we have - * to pass the high key to the handler to limit the - * query results. If the device number exceeds the - * low key, zero out the low key so that we get - * everything from the beginning. + * If this device number matches the high key, we have to pass + * the high key to the handler to limit the query results, and + * set the end_daddr so that we can synthesize records at the + * end of the query range or device. */ if (handlers[i].dev == head->fmh_keys[1].fmr_device) { dkeys[1] = head->fmh_keys[1]; info.end_daddr = min(handlers[i].nr_sectors - 1, dkeys[1].fmr_physical); + } else { + info.end_daddr = handlers[i].nr_sectors - 1; } + + /* + * If the device number exceeds the low key, zero out the low + * key so that we get everything from the beginning. + */ if (handlers[i].dev > head->fmh_keys[0].fmr_device) memset(&dkeys[0], 0, sizeof(struct xfs_fsmap)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b0de3d924d4c..1648dc5a8068 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -231,7 +231,7 @@ xfs_iflags_clear(xfs_inode_t *ip, unsigned long flags) } static inline int -__xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) +__xfs_iflags_test(const struct xfs_inode *ip, unsigned long flags) { return (ip->i_flags & flags); } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 61ee110b47d7..dc8b1010d4d3 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -148,17 +148,29 @@ xfs_qm_dqpurge( * We don't care about getting disk errors here. We need * to purge this dquot anyway, so we go ahead regardless. */ - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + dqp->q_flags &= ~XFS_DQFLAG_FREEING; + goto out_unlock; + } + if (!bp) + goto out_funlock; + + /* + * dqflush completes dqflock on error, and the bwrite ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { error = xfs_bwrite(bp); xfs_buf_relse(bp); - } else if (error == -EAGAIN) { - dqp->q_flags &= ~XFS_DQFLAG_FREEING; - goto out_unlock; } xfs_dqflock(dqp); } + xfs_dquot_detach_buf(dqp); +out_funlock: ASSERT(atomic_read(&dqp->q_pincount) == 0); ASSERT(xlog_is_shutdown(dqp->q_logitem.qli_item.li_log) || !test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags)); @@ -241,6 +253,10 @@ xfs_qm_destroy_quotainos( xfs_irele(qi->qi_pquotaip); qi->qi_pquotaip = NULL; } + if (qi->qi_dirip) { + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; + } } /* @@ -490,7 +506,17 @@ xfs_qm_dquot_isolate( /* we have to drop the LRU lock to flush the dquot */ spin_unlock(&lru->lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (!bp || error == -EAGAIN) { + xfs_dqfunlock(dqp); + goto out_unlock_dirty; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (error) goto out_unlock_dirty; @@ -498,6 +524,8 @@ xfs_qm_dquot_isolate( xfs_buf_relse(bp); goto out_unlock_dirty; } + + xfs_dquot_detach_buf(dqp); xfs_dqfunlock(dqp); /* @@ -646,8 +674,7 @@ xfs_qm_init_timelimits( static int xfs_qm_load_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { struct xfs_trans *tp; int error; @@ -656,7 +683,7 @@ xfs_qm_load_metadir_qinos( if (error) return error; - error = xfs_dqinode_load_parent(tp, dpp); + error = xfs_dqinode_load_parent(tp, &qi->qi_dirip); if (error == -ENOENT) { /* no quota dir directory, but we'll create one later */ error = 0; @@ -666,21 +693,21 @@ xfs_qm_load_metadir_qinos( goto out_trans; if (XFS_IS_UQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_USER, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_GQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_GROUP, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_PQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_PROJ, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error && error != -ENOENT) goto out_trans; @@ -696,34 +723,40 @@ out_trans: STATIC int xfs_qm_create_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { int error; - if (!*dpp) { - error = xfs_dqinode_mkdir_parent(mp, dpp); + if (!qi->qi_dirip) { + error = xfs_dqinode_mkdir_parent(mp, &qi->qi_dirip); if (error && error != -EEXIST) return error; + /* + * If the /quotas dirent points to an inode that isn't + * loadable, qi_dirip will be NULL but mkdir_parent will return + * -EEXIST. In this case the metadir is corrupt, so bail out. + */ + if (XFS_IS_CORRUPT(mp, qi->qi_dirip == NULL)) + return -EFSCORRUPTED; } if (XFS_IS_UQUOTA_ON(mp) && !qi->qi_uquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_USER, - &qi->qi_uquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error) return error; } if (XFS_IS_GQUOTA_ON(mp) && !qi->qi_gquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_GROUP, - &qi->qi_gquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error) return error; } if (XFS_IS_PQUOTA_ON(mp) && !qi->qi_pquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_PROJ, - &qi->qi_pquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error) return error; } @@ -768,7 +801,6 @@ xfs_qm_init_metadir_qinos( struct xfs_mount *mp) { struct xfs_quotainfo *qi = mp->m_quotainfo; - struct xfs_inode *dp = NULL; int error; if (!xfs_has_quota(mp)) { @@ -777,20 +809,22 @@ xfs_qm_init_metadir_qinos( return error; } - error = xfs_qm_load_metadir_qinos(mp, qi, &dp); + error = xfs_qm_load_metadir_qinos(mp, qi); if (error) goto out_err; - error = xfs_qm_create_metadir_qinos(mp, qi, &dp); + error = xfs_qm_create_metadir_qinos(mp, qi); if (error) goto out_err; - xfs_irele(dp); + /* The only user of the quota dir inode is online fsck */ +#if !IS_ENABLED(CONFIG_XFS_ONLINE_SCRUB) + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; +#endif return 0; out_err: xfs_qm_destroy_quotainos(mp->m_quotainfo); - if (dp) - xfs_irele(dp); return error; } @@ -1304,6 +1338,10 @@ xfs_qm_quotacheck_dqadjust( return error; } + error = xfs_dquot_attach_buf(NULL, dqp); + if (error) + return error; + trace_xfs_dqadjust(dqp); /* @@ -1486,11 +1524,17 @@ xfs_qm_flush_one( goto out_unlock; } - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); if (error) goto out_unlock; + if (!bp) { + error = -EFSCORRUPTED; + goto out_unlock; + } - xfs_buf_delwri_queue(bp, buffer_list); + error = xfs_qm_dqflush(dqp, bp); + if (!error) + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); out_unlock: xfs_dqunlock(dqp); diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index e919c7f62f57..35b64bc3a7a8 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -55,6 +55,7 @@ struct xfs_quotainfo { struct xfs_inode *qi_uquotaip; /* user quota inode */ struct xfs_inode *qi_gquotaip; /* group quota inode */ struct xfs_inode *qi_pquotaip; /* project quota inode */ + struct xfs_inode *qi_dirip; /* quota metadir */ struct list_lru qi_lru; int qi_dquots; struct mutex qi_quotaofflock;/* to serialize quotaoff */ diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index fa1317cc396c..d7565462af3d 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -101,7 +101,8 @@ extern void xfs_trans_free_dqinfo(struct xfs_trans *); extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); -extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); +void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *tp, + bool already_locked); int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, @@ -173,7 +174,7 @@ static inline void xfs_trans_mod_dquot_byino(struct xfs_trans *tp, { } #define xfs_trans_apply_dquot_deltas(tp) -#define xfs_trans_unreserve_and_mod_dquots(tp) +#define xfs_trans_unreserve_and_mod_dquots(tp, a) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 0cb534d71119..fcfa6e0eb3ad 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1827,7 +1827,7 @@ xfs_rtallocate_rtg( * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ - if (bno_hint) + if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (!xfs_has_rtgroups(args.mp) && initial_user_data) start = xfs_rtpick_extent(args.rtg, tp, maxlen); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 30fbed27cf05..4cd25717c9d1 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -860,29 +860,17 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); - error = xfs_trans_run_precommits(tp); - if (error) { - if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) - xfs_defer_cancel(tp); - goto out_unreserve; - } - /* - * Finish deferred items on final commit. Only permanent transactions - * should ever have deferred ops. + * Commit per-transaction changes that are not already tracked through + * log items. This can add dirty log items to the transaction. */ - WARN_ON_ONCE(!list_empty(&tp->t_dfops) && - !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); - if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) { - error = xfs_defer_finish_noroll(&tp); - if (error) - goto out_unreserve; + if (tp->t_flags & XFS_TRANS_SB_DIRTY) + xfs_trans_apply_sb_deltas(tp); + xfs_trans_apply_dquot_deltas(tp); - /* Run precommits from final tx in defer chain. */ - error = xfs_trans_run_precommits(tp); - if (error) - goto out_unreserve; - } + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; /* * If there is nothing to be logged by the transaction, @@ -907,13 +895,6 @@ __xfs_trans_commit( ASSERT(tp->t_ticket != NULL); - /* - * If we need to update the superblock, then do it now. - */ - if (tp->t_flags & XFS_TRANS_SB_DIRTY) - xfs_trans_apply_sb_deltas(tp); - xfs_trans_apply_dquot_deltas(tp); - xlog_cil_commit(log, tp, &commit_seq, regrant); xfs_trans_free(tp); @@ -939,7 +920,7 @@ out_unreserve: * the dqinfo portion to be. All that means is that we have some * (non-persistent) quota reservations that need to be unreserved. */ - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, true); if (tp->t_ticket) { if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); @@ -958,6 +939,20 @@ int xfs_trans_commit( struct xfs_trans *tp) { + /* + * Finish deferred items on final commit. Only permanent transactions + * should ever have deferred ops. + */ + WARN_ON_ONCE(!list_empty(&tp->t_dfops) && + !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); + if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) { + int error = xfs_defer_finish_noroll(&tp); + if (error) { + xfs_trans_cancel(tp); + return error; + } + } + return __xfs_trans_commit(tp, false); } @@ -1019,7 +1014,7 @@ xfs_trans_cancel( } #endif xfs_trans_unreserve_and_mod_sb(tp); - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, false); if (tp->t_ticket) { xfs_log_ticket_ungrant(log, tp->t_ticket); @@ -1435,5 +1430,8 @@ done: out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (dp != ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 8ede9d099d1f..f56d62dced97 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -360,7 +360,7 @@ xfsaild_resubmit_item( /* protected by ail_lock */ list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (bp->b_flags & _XBF_INODES) + if (bp->b_flags & (_XBF_INODES | _XBF_DQUOTS)) clear_bit(XFS_LI_FAILED, &lip->li_flags); else xfs_clear_li_failed(lip); diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 481ba3dc9f19..713b6d243e56 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -606,6 +606,24 @@ xfs_trans_apply_dquot_deltas( ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); + + /* + * We've applied the count changes and given back + * whatever reservation we didn't use. Zero out the + * dqtrx fields. + */ + qtrx->qt_blk_res = 0; + qtrx->qt_bcount_delta = 0; + qtrx->qt_delbcnt_delta = 0; + + qtrx->qt_rtblk_res = 0; + qtrx->qt_rtblk_res_used = 0; + qtrx->qt_rtbcount_delta = 0; + qtrx->qt_delrtb_delta = 0; + + qtrx->qt_ino_res = 0; + qtrx->qt_ino_res_used = 0; + qtrx->qt_icount_delta = 0; } } } @@ -642,7 +660,8 @@ xfs_trans_unreserve_and_mod_dquots_hook( */ void xfs_trans_unreserve_and_mod_dquots( - struct xfs_trans *tp) + struct xfs_trans *tp, + bool already_locked) { int i, j; struct xfs_dquot *dqp; @@ -671,10 +690,12 @@ xfs_trans_unreserve_and_mod_dquots( * about the number of blocks used field, or deltas. * Also we don't bother to zero the fields. */ - locked = false; + locked = already_locked; if (qtrx->qt_blk_res) { - xfs_dqlock(dqp); - locked = true; + if (!locked) { + xfs_dqlock(dqp); + locked = true; + } dqp->q_blk.reserved -= (xfs_qcnt_t)qtrx->qt_blk_res; } @@ -695,7 +716,7 @@ xfs_trans_unreserve_and_mod_dquots( dqp->q_rtb.reserved -= (xfs_qcnt_t)qtrx->qt_rtblk_res; } - if (locked) + if (locked && !already_locked) xfs_dqunlock(dqp); } diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index a28e2a6a13d0..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 60830a6a5939..7a1b3b1a8fed 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -423,7 +423,7 @@ void __bio_add_page(struct bio *bio, struct page *page, void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); -void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); +void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 08a727b40816..378d3a1a22fc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,8 +200,6 @@ struct gendisk { spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; - struct list_head zone_wplugs_err_list; - struct work_struct zone_wplugs_work; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -1421,6 +1419,9 @@ static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector) return is_seq; } +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); + static inline unsigned int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ec3acb16359e..9ef57f6f584a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1527,6 +1527,7 @@ struct bpf_prog_aux { bool is_extended; /* true if extended by freplace program */ bool jits_use_priv_stack; bool priv_stack_requested; + bool changes_pkt_data; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; @@ -2193,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); + RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); + + if (unlikely(!array)) + return ret; - rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; - array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); - if (unlikely(!array)) - goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -2227,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); -out: migrate_enable(); - rcu_read_unlock_trace(); return ret; } @@ -3516,10 +3514,4 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog) return prog->aux->func_idx != 0; } -static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog) -{ - return prog->type == BPF_PROG_TYPE_TRACING && - prog->expected_attach_type == BPF_TRACE_RAW_TP; -} - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f4290c179bee..48b7b2eeb7e2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -659,6 +659,7 @@ struct bpf_subprog_info { bool args_cached: 1; /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; + bool changes_pkt_data: 1; enum priv_stack_mode priv_stack_mode; u8 arg_cnt; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 469a64dd6495..240c632c5b95 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + +#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -/** - * offset_to_ptr - convert a relative memory offset to an absolute pointer - * @off: the address of the 32-bit offset value - */ -static inline void *offset_to_ptr(const int *off) -{ - return (void *)((unsigned long)off + *off); -} +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; -#endif /* __ASSEMBLY__ */ +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) #ifdef __CHECKER__ #define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) diff --git a/include/linux/filter.h b/include/linux/filter.h index 9a5d23ae3855..a3ea46281595 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1122,7 +1122,7 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); bool bpf_jit_supports_private_stack(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); -bool bpf_helper_changes_pkt_data(void *func); +bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 0d99bf11d260..e4ce1cae03bf 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, return false; } +/* + * To work around what seems to be an optimizer bug, the macro arguments + * need to have const copies or the values end up changed by the time they + * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture + * __bos() results in const temp vars") for more details. + */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ @@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ + /* Keep a mutable version of the size for the final copy. */ \ + size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ @@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ - __underlying_##op(p, q, __fortify_size); \ + /* Hide only the run-time size from value range tracking to */ \ + /* silence compile-time false positive bounds warnings. */ \ + if (!__builtin_constant_p(__copy_size)) \ + OPTIMIZER_HIDE_VAR(__copy_size); \ + __underlying_##op(p, q, __copy_size); \ }) /* diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb91042..02a226bcf0ed 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1559,6 +1559,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index d380bffee2ef..66b311fbd5d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -656,6 +656,12 @@ struct sched_dl_entity { * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * + * @dl_server_active tells if the dlserver is active(started). + * dlserver is started on first cfs enqueue on an idle runqueue + * and is stopped when a dequeue results in 0 cfs tasks on the + * runqueue. In other words, dlserver is active only when cpu's + * runqueue has atleast one cfs task. + * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ @@ -664,6 +670,7 @@ struct sched_dl_entity { unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2a5df5b62cfc..91b8ffbdfa8c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -273,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -324,6 +325,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -340,6 +342,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), @@ -352,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) diff --git a/include/soc/arc/aux.h b/include/soc/arc/arc_aux.h index 9c2eff6140b6..9c2eff6140b6 100644 --- a/include/soc/arc/aux.h +++ b/include/soc/arc/arc_aux.h diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index d1a93c73f006..a78dacd149f1 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -8,7 +8,7 @@ #ifndef __SOC_ARC_MCIP_H #define __SOC_ARC_MCIP_H -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> #define ARC_REG_MCIP_BCR 0x0d0 #define ARC_REG_MCIP_IDU_BCR 0x0D5 diff --git a/include/soc/arc/timers.h b/include/soc/arc/timers.h index ae99d3e855f1..51a74166296c 100644 --- a/include/soc/arc/timers.h +++ b/include/soc/arc/timers.h @@ -6,7 +6,7 @@ #ifndef __SOC_ARC_TIMERS_H #define __SOC_ARC_TIMERS_H -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> /* Timer related Aux registers */ #define ARC_REG_TIMER0_LIMIT 0x23 /* timer 0 limit */ diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index 94e8185c4795..3dc7a1551ac3 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -271,12 +271,6 @@ struct cs35l56_base { struct gpio_desc *reset_gpio; }; -/* Temporary to avoid a build break with the HDA driver */ -static inline int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base) -{ - return 0; -} - static inline bool cs35l56_is_otp_register(unsigned int reg) { return (reg >> 16) == 3; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index adaae8630932..077f84684c18 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1036,8 +1036,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx out_put_free: i = data.nr; while (i--) { - io_buffer_unmap(src_ctx, data.nodes[i]); - kfree(data.nodes[i]); + if (data.nodes[i]) { + io_buffer_unmap(src_ctx, data.nodes[i]); + kfree(data.nodes[i]); + } } out_unlock: io_rsrc_data_free(ctx, &data); diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 9762bdddf1de..410028633621 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -53,3 +53,9 @@ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o + +CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e7a59e6462a9..e5a5f023cedd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6439,6 +6439,101 @@ int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, return off; } +struct bpf_raw_tp_null_args { + const char *func; + u64 mask; +}; + +static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { + /* sched */ + { "sched_pi_setprio", 0x10 }, + /* ... from sched_numa_pair_template event class */ + { "sched_stick_numa", 0x100 }, + { "sched_swap_numa", 0x100 }, + /* afs */ + { "afs_make_fs_call", 0x10 }, + { "afs_make_fs_calli", 0x10 }, + { "afs_make_fs_call1", 0x10 }, + { "afs_make_fs_call2", 0x10 }, + { "afs_protocol_error", 0x1 }, + { "afs_flock_ev", 0x10 }, + /* cachefiles */ + { "cachefiles_lookup", 0x1 | 0x200 }, + { "cachefiles_unlink", 0x1 }, + { "cachefiles_rename", 0x1 }, + { "cachefiles_prep_read", 0x1 }, + { "cachefiles_mark_active", 0x1 }, + { "cachefiles_mark_failed", 0x1 }, + { "cachefiles_mark_inactive", 0x1 }, + { "cachefiles_vfs_error", 0x1 }, + { "cachefiles_io_error", 0x1 }, + { "cachefiles_ondemand_open", 0x1 }, + { "cachefiles_ondemand_copen", 0x1 }, + { "cachefiles_ondemand_close", 0x1 }, + { "cachefiles_ondemand_read", 0x1 }, + { "cachefiles_ondemand_cread", 0x1 }, + { "cachefiles_ondemand_fd_write", 0x1 }, + { "cachefiles_ondemand_fd_release", 0x1 }, + /* ext4, from ext4__mballoc event class */ + { "ext4_mballoc_discard", 0x10 }, + { "ext4_mballoc_free", 0x10 }, + /* fib */ + { "fib_table_lookup", 0x100 }, + /* filelock */ + /* ... from filelock_lock event class */ + { "posix_lock_inode", 0x10 }, + { "fcntl_setlk", 0x10 }, + { "locks_remove_posix", 0x10 }, + { "flock_lock_inode", 0x10 }, + /* ... from filelock_lease event class */ + { "break_lease_noblock", 0x10 }, + { "break_lease_block", 0x10 }, + { "break_lease_unblock", 0x10 }, + { "generic_delete_lease", 0x10 }, + { "time_out_leases", 0x10 }, + /* host1x */ + { "host1x_cdma_push_gather", 0x10000 }, + /* huge_memory */ + { "mm_khugepaged_scan_pmd", 0x10 }, + { "mm_collapse_huge_page_isolate", 0x1 }, + { "mm_khugepaged_scan_file", 0x10 }, + { "mm_khugepaged_collapse_file", 0x10 }, + /* kmem */ + { "mm_page_alloc", 0x1 }, + { "mm_page_pcpu_drain", 0x1 }, + /* .. from mm_page event class */ + { "mm_page_alloc_zone_locked", 0x1 }, + /* netfs */ + { "netfs_failure", 0x10 }, + /* power */ + { "device_pm_callback_start", 0x10 }, + /* qdisc */ + { "qdisc_dequeue", 0x1000 }, + /* rxrpc */ + { "rxrpc_recvdata", 0x1 }, + { "rxrpc_resend", 0x10 }, + /* sunrpc */ + { "xs_stream_read_data", 0x1 }, + /* ... from xprt_cong_event event class */ + { "xprt_reserve_cong", 0x10 }, + { "xprt_release_cong", 0x10 }, + { "xprt_get_cong", 0x10 }, + { "xprt_put_cong", 0x10 }, + /* tcp */ + { "tcp_send_reset", 0x11 }, + /* tegra_apb_dma */ + { "tegra_dma_tx_status", 0x100 }, + /* timer_migration */ + { "tmigr_update_events", 0x1 }, + /* writeback, from writeback_folio_template event class */ + { "writeback_dirty_folio", 0x10 }, + { "folio_wait_writeback", 0x10 }, + /* rdma */ + { "mr_integ_alloc", 0x2000 }, + /* bpf_testmod */ + { "bpf_testmod_test_read", 0x0 }, +}; + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -6449,6 +6544,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; + bool ptr_err_raw_tp = false; const char *tag_value; u32 nr_args, arg; int i, ret; @@ -6543,6 +6639,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; } + if (size != sizeof(u64)) { + bpf_log(log, "func '%s' size %d must be 8\n", + tname, size); + return false; + } + /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; @@ -6588,12 +6690,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (prog_args_trusted(prog)) info->reg_type |= PTR_TRUSTED; - /* Raw tracepoint arguments always get marked as maybe NULL */ - if (bpf_prog_is_raw_tp(prog)) - info->reg_type |= PTR_MAYBE_NULL; - else if (btf_param_match_suffix(btf, &args[arg], "__nullable")) + if (btf_param_match_suffix(btf, &args[arg], "__nullable")) info->reg_type |= PTR_MAYBE_NULL; + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { + struct btf *btf = prog->aux->attach_btf; + const struct btf_type *t; + const char *tname; + + /* BTF lookups cannot fail, return false on error */ + t = btf_type_by_id(btf, prog->aux->attach_btf_id); + if (!t) + return false; + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) + return false; + /* Checked by bpf_check_attach_target */ + tname += sizeof("btf_trace_") - 1; + for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) { + /* Is this a func with potential NULL args? */ + if (strcmp(tname, raw_tp_null_args[i].func)) + continue; + if (raw_tp_null_args[i].mask & (0x1 << (arg * 4))) + info->reg_type |= PTR_MAYBE_NULL; + /* Is the current arg IS_ERR? */ + if (raw_tp_null_args[i].mask & (0x2 << (arg * 4))) + ptr_err_raw_tp = true; + break; + } + /* If we don't know NULL-ness specification and the tracepoint + * is coming from a loadable module, be conservative and mark + * argument as PTR_MAYBE_NULL. + */ + if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf)) + info->reg_type |= PTR_MAYBE_NULL; + } + if (tgt_prog) { enum bpf_prog_type tgt_type; @@ -6638,6 +6770,15 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + + /* Perform all checks on the validity of type for this argument, but if + * we know it can be IS_ERR at runtime, scrub pointer type and mark as + * scalar. + */ + if (ptr_err_raw_tp) { + bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg); + info->reg_type = SCALAR_VALUE; + } return true; } EXPORT_SYMBOL_GPL(btf_ctx_access); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a2327c4fdc8b..da729cbbaeb9 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -539,6 +539,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { + int err; + /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ @@ -546,7 +548,9 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; - return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); + err = bpf_adj_branches(prog, off, off + cnt, off, false); + WARN_ON_ONCE(err); + return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) @@ -2936,7 +2940,7 @@ void __weak bpf_jit_compile(struct bpf_prog *prog) { } -bool __weak bpf_helper_changes_pkt_data(void *func) +bool __weak bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { return false; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 01fbef9576e0..f7f892a52a37 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -420,25 +420,6 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) return rec; } -static bool mask_raw_tp_reg_cond(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return reg->type == (PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL) && - bpf_prog_is_raw_tp(env->prog) && !reg->ref_obj_id; -} - -static bool mask_raw_tp_reg(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) -{ - if (!mask_raw_tp_reg_cond(env, reg)) - return false; - reg->type &= ~PTR_MAYBE_NULL; - return true; -} - -static void unmask_raw_tp_reg(struct bpf_reg_state *reg, bool result) -{ - if (result) - reg->type |= PTR_MAYBE_NULL; -} - static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; @@ -2597,16 +2578,36 @@ static int cmp_subprogs(const void *a, const void *b) ((struct bpf_subprog_info *)b)->start; } +/* Find subprogram that contains instruction at 'off' */ +static struct bpf_subprog_info *find_containing_subprog(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *vals = env->subprog_info; + int l, r, m; + + if (off >= env->prog->len || off < 0 || env->subprog_cnt == 0) + return NULL; + + l = 0; + r = env->subprog_cnt - 1; + while (l < r) { + m = l + (r - l + 1) / 2; + if (vals[m].start <= off) + l = m; + else + r = m - 1; + } + return &vals[l]; +} + +/* Find subprogram that starts exactly at 'off' */ static int find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; - p = bsearch(&off, env->subprog_info, env->subprog_cnt, - sizeof(env->subprog_info[0]), cmp_subprogs); - if (!p) + p = find_containing_subprog(env, off); + if (!p || p->start != off) return -ENOENT; return p - env->subprog_info; - } static int add_subprog(struct bpf_verifier_env *env, int off) @@ -6781,7 +6782,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, const char *field_name = NULL; enum bpf_type_flag flag = 0; u32 btf_id = 0; - bool mask; int ret; if (!env->allow_ptr_leaks) { @@ -6853,21 +6853,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - /* For raw_tp progs, we allow dereference of PTR_MAYBE_NULL - * trusted PTR_TO_BTF_ID, these are the ones that are possibly - * arguments to the raw_tp. Since internal checks in for trusted - * reg in check_ptr_to_btf_access would consider PTR_MAYBE_NULL - * modifier as problematic, mask it out temporarily for the - * check. Don't apply this to pointers with ref_obj_id > 0, as - * those won't be raw_tp args. - * - * We may end up applying this relaxation to other trusted - * PTR_TO_BTF_ID with maybe null flag, since we cannot - * distinguish PTR_MAYBE_NULL tagged for arguments vs normal - * tagging, but that should expand allowed behavior, and not - * cause regression for existing behavior. - */ - mask = mask_raw_tp_reg(env, reg); + if (ret != PTR_TO_BTF_ID) { /* just mark; */ @@ -6928,13 +6914,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, clear_trusted_flags(&flag); } - if (atype == BPF_READ && value_regno >= 0) { + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); - /* We've assigned a new type to regno, so don't undo masking. */ - if (regno == value_regno) - mask = false; - } - unmask_raw_tp_reg(reg, mask); return 0; } @@ -7309,7 +7290,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && - (mask_raw_tp_reg_cond(env, reg) || !type_may_be_null(reg->type))) { + !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { @@ -9012,7 +8993,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; int err = 0; - bool mask; if (arg_type == ARG_DONTCARE) return 0; @@ -9053,11 +9033,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); + if (err) + return err; - err = err ?: check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); + err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; @@ -9852,17 +9832,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, return ret; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { struct bpf_call_arg_meta meta; - bool mask; int err; if (register_is_null(reg) && type_may_be_null(arg->arg_type)) continue; memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); - unmask_raw_tp_reg(reg, mask); if (err) return err; } else { @@ -10022,6 +9999,8 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, verbose(env, "Func#%d ('%s') is global and assumed valid.\n", subprog, sub_name); + if (env->subprog_info[subprog].changes_pkt_data) + clear_all_pkt_pointers(env); /* mark global subprog for verifying after main prog */ subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); @@ -10708,7 +10687,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } /* With LD_ABS/IND some JITs save/restore skb from r1. */ - changes_data = bpf_helper_changes_pkt_data(fn->func); + changes_data = bpf_helper_changes_pkt_data(func_id); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", func_id_name(func_id), func_id); @@ -12183,7 +12162,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1, ref_id, type_size; bool is_ret_buf_sz = false; - bool mask = false; int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); @@ -12242,15 +12220,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } - mask = mask_raw_tp_reg(env, reg); if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && (register_is_null(reg) || type_may_be_null(reg->type)) && !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); - unmask_raw_tp_reg(reg, mask); return -EACCES; } - unmask_raw_tp_reg(reg, mask); if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { @@ -12308,24 +12283,16 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; - /* Allow passing maybe NULL raw_tp arguments to - * kfuncs for compatibility. Don't apply this to - * arguments with ref_obj_id > 0. - */ - mask = mask_raw_tp_reg(env, reg); if (!is_trusted_reg(reg)) { if (!is_kfunc_rcu(meta)) { verbose(env, "R%d must be referenced or trusted\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } if (!is_rcu_reg(reg)) { verbose(env, "R%d must be a rcu pointer\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } } - unmask_raw_tp_reg(reg, mask); fallthrough; case KF_ARG_PTR_TO_CTX: case KF_ARG_PTR_TO_DYNPTR: @@ -12348,9 +12315,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_release(meta) && reg->ref_obj_id) arg_type |= OBJ_RELEASE; - mask = mask_raw_tp_reg(env, reg); ret = check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; @@ -12527,7 +12492,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ ref_tname = btf_name_by_offset(btf, ref_t->name_off); fallthrough; case KF_ARG_PTR_TO_BTF_ID: - mask = mask_raw_tp_reg(env, reg); /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && @@ -12536,11 +12500,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "expected %s or socket\n", reg_type_str(env, base_type(reg->type) | (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; break; @@ -13513,7 +13475,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env, */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, - struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; @@ -13527,7 +13489,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; - bool mask; int ret; dst_reg = ®s[dst]; @@ -13554,14 +13515,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - mask = mask_raw_tp_reg(env, ptr_reg); if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); - unmask_raw_tp_reg(ptr_reg, mask); return -EACCES; } - unmask_raw_tp_reg(ptr_reg, mask); switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: @@ -16226,6 +16184,29 @@ enforce_retval: return 0; } +static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *subprog; + + subprog = find_containing_subprog(env, off); + subprog->changes_pkt_data = true; +} + +/* 't' is an index of a call-site. + * 'w' is a callee entry point. + * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED. + * Rely on DFS traversal order and absence of recursive calls to guarantee that + * callee's change_pkt_data marks would be correct at that moment. + */ +static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) +{ + struct bpf_subprog_info *caller, *callee; + + caller = find_containing_subprog(env, t); + callee = find_containing_subprog(env, w); + caller->changes_pkt_data |= callee->changes_pkt_data; +} + /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered @@ -16359,6 +16340,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, bool visit_callee) { int ret, insn_sz; + int w; insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); @@ -16370,8 +16352,10 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, mark_jmp_point(env, t + insn_sz); if (visit_callee) { + w = t + insns[t].imm + 1; mark_prune_point(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); + merge_callee_effects(env, t, w); + ret = push_insn(t, w, BRANCH, env); } return ret; } @@ -16688,6 +16672,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) mark_prune_point(env, t); mark_jmp_point(env, t); } + if (bpf_helper_call(insn) && bpf_helper_changes_pkt_data(insn->imm)) + mark_subprog_changes_pkt_data(env, t); if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; @@ -16822,6 +16808,7 @@ walk_cfg: } } ret = 0; /* cfg looks good */ + env->prog->aux->changes_pkt_data = env->subprog_info[0].changes_pkt_data; err_free: kvfree(insn_state); @@ -20075,7 +20062,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: - case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: if (type == BPF_READ) { if (BPF_MODE(insn->code) == BPF_MEM) insn->code = BPF_LDX | BPF_PROBE_MEM | @@ -20311,6 +20297,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; + func[i]->aux->changes_pkt_data = env->subprog_info[i].changes_pkt_data; if (!i) func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(func[i]); @@ -22141,6 +22128,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; + bool tgt_changes_pkt_data; if (bpf_prog_is_dev_bound(prog->aux) && !bpf_prog_dev_bound_match(prog, tgt_prog)) { @@ -22175,6 +22163,14 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, "Extension programs should be JITed\n"); return -EINVAL; } + tgt_changes_pkt_data = aux->func + ? aux->func[subprog]->aux->changes_pkt_data + : aux->changes_pkt_data; + if (prog->aux->changes_pkt_data && !tgt_changes_pkt_data) { + bpf_log(log, + "Extension program changes packet data, while original does not\n"); + return -EINVAL; + } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); @@ -22640,10 +22636,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret < 0) goto skip_full_check; - ret = check_attach_btf_id(env); - if (ret) - goto skip_full_check; - ret = resolve_pseudo_ldimm64(env); if (ret < 0) goto skip_full_check; @@ -22658,6 +22650,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret < 0) goto skip_full_check; + ret = check_attach_btf_id(env); + if (ret) + goto skip_full_check; + ret = mark_fastcall_patterns(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c6d8232ad9ee..3e5a6bf587f9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1341,7 +1341,7 @@ bool sched_can_stop_tick(struct rq *rq) if (scx_enabled() && !scx_can_stop_tick(rq)) return false; - if (rq->cfs.nr_running > 1) + if (rq->cfs.h_nr_running > 1) return false; /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index db47f33cb7d2..d94f2ed6d1f4 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1647,6 +1647,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) if (!dl_se->dl_runtime) return; + dl_se->dl_server_active = 1; enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP); if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl)) resched_curr(dl_se->rq); @@ -1661,6 +1662,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se) hrtimer_try_to_cancel(&dl_se->dl_timer); dl_se->dl_defer_armed = 0; dl_se->dl_throttled = 0; + dl_se->dl_server_active = 0; } void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, @@ -2421,8 +2423,10 @@ again: if (dl_server(dl_se)) { p = dl_se->server_pick_task(dl_se); if (!p) { - dl_se->dl_yielded = 1; - update_curr_dl_se(rq, dl_se, 0); + if (dl_server_active(dl_se)) { + dl_se->dl_yielded = 1; + update_curr_dl_se(rq, dl_se, 0); + } goto again; } rq->dl_server = dl_se; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a48b2a701ec2..a1be00a988bf 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -845,6 +845,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread)); SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed); SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", cfs_rq->idle_nr_running); SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index aa0238ee4857..3e9ca38512de 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1159,8 +1159,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec) trace_sched_stat_runtime(p, delta_exec); account_group_exec_runtime(p, delta_exec); cgroup_account_cputime(p, delta_exec); - if (p->dl_server) - dl_server_update(p->dl_server, delta_exec); } static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr) @@ -1237,11 +1235,16 @@ static void update_curr(struct cfs_rq *cfs_rq) update_curr_task(p, delta_exec); /* - * Any fair task that runs outside of fair_server should - * account against fair_server such that it can account for - * this time and possibly avoid running this period. + * If the fair_server is active, we need to account for the + * fair_server time whether or not the task is running on + * behalf of fair_server or not: + * - If the task is running on behalf of fair_server, we need + * to limit its time based on the assigned runtime. + * - Fair task that runs outside of fair_server should account + * against fair_server such that it can account for this time + * and possibly avoid running this period. */ - if (p->dl_server != &rq->fair_server) + if (dl_server_active(&rq->fair_server)) dl_server_update(&rq->fair_server, delta_exec); } @@ -5471,9 +5474,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); -static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +static void set_delayed(struct sched_entity *se) +{ + se->sched_delayed = 1; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed++; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static void clear_delayed(struct sched_entity *se) { se->sched_delayed = 0; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed--; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +{ + clear_delayed(se); if (sched_feat(DELAY_ZERO) && se->vlag > 0) se->vlag = 0; } @@ -5484,6 +5511,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) bool sleep = flags & DEQUEUE_SLEEP; update_curr(cfs_rq); + clear_buddies(cfs_rq, se); if (flags & DEQUEUE_DELAYED) { SCHED_WARN_ON(!se->sched_delayed); @@ -5500,10 +5528,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { - if (cfs_rq->next == se) - cfs_rq->next = NULL; update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 1; + set_delayed(se); return false; } } @@ -5526,8 +5552,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_stats_dequeue_fair(cfs_rq, se, flags); - clear_buddies(cfs_rq, se); - update_entity_lag(cfs_rq, se); if (sched_feat(PLACE_REL_DEADLINE) && !sleep) { se->deadline -= se->vruntime; @@ -5917,7 +5941,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta, dequeue = 1; + long task_delta, idle_task_delta, delayed_delta, dequeue = 1; long rq_h_nr_running = rq->cfs.h_nr_running; raw_spin_lock(&cfs_b->lock); @@ -5950,6 +5974,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5973,6 +5998,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -5995,6 +6021,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; } /* At this point se is NULL and we are at root level*/ @@ -6020,7 +6047,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta; + long task_delta, idle_task_delta, delayed_delta; long rq_h_nr_running = rq->cfs.h_nr_running; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6056,6 +6083,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6073,6 +6101,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6090,6 +6119,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6943,7 +6973,7 @@ requeue_delayed_entity(struct sched_entity *se) } update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 0; + clear_delayed(se); } /* @@ -6957,6 +6987,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int h_nr_delayed = 0; int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_running = rq->cfs.h_nr_running; u64 slice = 0; @@ -6983,6 +7014,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (p->in_iowait) cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); + if (task_new) + h_nr_delayed = !!se->sched_delayed; + for_each_sched_entity(se) { if (se->on_rq) { if (se->sched_delayed) @@ -7005,6 +7039,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7028,6 +7063,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7090,6 +7126,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) struct task_struct *p = NULL; int idle_h_nr_running = 0; int h_nr_running = 0; + int h_nr_delayed = 0; struct cfs_rq *cfs_rq; u64 slice = 0; @@ -7097,6 +7134,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) p = task_of(se); h_nr_running = 1; idle_h_nr_running = task_has_idle_policy(p); + if (!task_sleep && !task_delayed) + h_nr_delayed = !!se->sched_delayed; } else { cfs_rq = group_cfs_rq(se); slice = cfs_rq_min_slice(cfs_rq); @@ -7114,6 +7153,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; @@ -7152,6 +7192,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; @@ -8780,7 +8821,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) return; - if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) { + if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) { set_next_buddy(pse); } diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index fc07382361a8..fee75cc2c47b 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->h_nr_running, + cfs_rq->h_nr_running - cfs_rq->h_nr_delayed, cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 76f5f53a645f..c5d67a43fe52 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -398,6 +398,11 @@ extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq extern int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init); +static inline bool dl_server_active(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_server_active; +} + #ifdef CONFIG_CGROUP_SCHED extern struct list_head task_groups; @@ -649,6 +654,7 @@ struct cfs_rq { unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int idle_nr_running; /* SCHED_IDLE */ unsigned int idle_h_nr_running; /* SCHED_IDLE */ + unsigned int h_nr_delayed; s64 avg_vruntime; u64 avg_load; @@ -898,8 +904,11 @@ struct dl_rq { static inline void se_update_runnable(struct sched_entity *se) { - if (!entity_is_task(se)) - se->runnable_weight = se->my_q->h_nr_running; + if (!entity_is_task(se)) { + struct cfs_rq *cfs_rq = se->my_q; + + se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed; + } } static inline long se_runnable(struct sched_entity *se) diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 949a3870946c..1b8db5aee9d3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2250,6 +2250,9 @@ void perf_event_detach_bpf_prog(struct perf_event *event) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); + if (!old_array) + goto put; + ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); @@ -2258,6 +2261,14 @@ void perf_event_detach_bpf_prog(struct perf_event *event) bpf_prog_array_free_sleepable(old_array); } +put: + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + bpf_prog_put(event->prog); event->prog = NULL; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 0bf78517b5d4..ddedcb50917f 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1223,6 +1223,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..7cc18b9bce27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; - - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } - - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); + list_for_each_entry(field, head, link) { + const char *str; + bool good; - p += i + 3; + if (!field->needs_test) continue; - } - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } - - if (star) - len = va_arg(ap, int); - - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); + str = *(const char **)(ptr + field->offset); - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -10777,8 +10630,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..9691b47b5f3d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1413,7 +1412,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 77e68efbd43e..1545cc8b49d0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -265,16 +265,129 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; + } + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; +} + +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { + return true; } return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + struct trace_event_fields *field; + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -284,13 +397,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call) static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -374,8 +488,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -403,42 +525,47 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; + } + + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); } - next_arg: - i--; + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored @@ -2471,7 +2598,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 74c353164ca1..d358c9935164 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) static __always_inline unsigned long function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) { diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index da748b7cbc4d..03d56f711ad1 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index fed382b7881b..4875e7f5de3d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1402,9 +1402,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, #ifdef CONFIG_BPF_EVENTS if (bpf_prog_array_valid(call)) { + const struct bpf_prog_array *array; u32 ret; - ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run); + rcu_read_lock_trace(); + array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); + ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run); + rcu_read_unlock_trace(); if (!ret) return; } diff --git a/mm/slub.c b/mm/slub.c index 19980419b176..c2151c9fee22 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2189,9 +2189,24 @@ bool memcg_slab_post_charge(void *p, gfp_t flags) folio = virt_to_folio(p); if (!folio_test_slab(folio)) { - return folio_memcg_kmem(folio) || - (__memcg_kmem_charge_page(folio_page(folio, 0), flags, - folio_order(folio)) == 0); + int size; + + if (folio_memcg_kmem(folio)) + return true; + + if (__memcg_kmem_charge_page(folio_page(folio, 0), flags, + folio_order(folio))) + return false; + + /* + * This folio has already been accounted in the global stats but + * not in the memcg stats. So, subtract from the global and use + * the interface which adds to both global and memcg stats. + */ + size = folio_size(folio); + node_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, -size); + lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, size); + return true; } slab = folio_slab(folio); diff --git a/net/core/filter.c b/net/core/filter.c index 5fea874025d3..56fe194a76af 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7898,42 +7898,37 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { #endif /* CONFIG_INET */ -bool bpf_helper_changes_pkt_data(void *func) -{ - if (func == bpf_skb_vlan_push || - func == bpf_skb_vlan_pop || - func == bpf_skb_store_bytes || - func == bpf_skb_change_proto || - func == bpf_skb_change_head || - func == sk_skb_change_head || - func == bpf_skb_change_tail || - func == sk_skb_change_tail || - func == bpf_skb_adjust_room || - func == sk_skb_adjust_room || - func == bpf_skb_pull_data || - func == sk_skb_pull_data || - func == bpf_clone_redirect || - func == bpf_l3_csum_replace || - func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head || - func == bpf_xdp_adjust_meta || - func == bpf_msg_pull_data || - func == bpf_msg_push_data || - func == bpf_msg_pop_data || - func == bpf_xdp_adjust_tail || -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) - func == bpf_lwt_seg6_store_bytes || - func == bpf_lwt_seg6_adjust_srh || - func == bpf_lwt_seg6_action || -#endif -#ifdef CONFIG_INET - func == bpf_sock_ops_store_hdr_opt || -#endif - func == bpf_lwt_in_push_encap || - func == bpf_lwt_xmit_push_encap) +bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_clone_redirect: + case BPF_FUNC_l3_csum_replace: + case BPF_FUNC_l4_csum_replace: + case BPF_FUNC_lwt_push_encap: + case BPF_FUNC_lwt_seg6_action: + case BPF_FUNC_lwt_seg6_adjust_srh: + case BPF_FUNC_lwt_seg6_store_bytes: + case BPF_FUNC_msg_pop_data: + case BPF_FUNC_msg_pull_data: + case BPF_FUNC_msg_push_data: + case BPF_FUNC_skb_adjust_room: + case BPF_FUNC_skb_change_head: + case BPF_FUNC_skb_change_proto: + case BPF_FUNC_skb_change_tail: + case BPF_FUNC_skb_pull_data: + case BPF_FUNC_skb_store_bytes: + case BPF_FUNC_skb_vlan_pop: + case BPF_FUNC_skb_vlan_push: + case BPF_FUNC_store_hdr_opt: + case BPF_FUNC_xdp_adjust_head: + case BPF_FUNC_xdp_adjust_meta: + case BPF_FUNC_xdp_adjust_tail: + /* tail-called program could call any of the above */ + case BPF_FUNC_tail_call: return true; - - return false; + default: + return false; + } } const struct bpf_func_proto bpf_event_output_data_proto __weak; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 9527dd46e4dc..2d3ae0cd3ad2 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -430,10 +430,10 @@ static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { - int err = 0; + int err; if (!(netdev->flags & IFF_UP)) - return err; + return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) @@ -488,24 +488,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { int err = 0; - int i; if (!(netdev->flags & IFF_UP)) return err; - for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; - ctx->rxq_idx = i++; } - for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; - ctx->txq_idx = i++; } return err; @@ -671,7 +668,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->rxq_idx = i++; + ctx->rxq_idx = ++i; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { @@ -679,7 +676,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->txq_idx = i++; + ctx->txq_idx = ++i; } ctx->rxq_idx = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d9e363d9fa31..6b745096809d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3819,6 +3819,7 @@ out_unregister: } static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, + struct nlattr *tbp[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -3826,7 +3827,7 @@ static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, int err; if (!data || !data[ops->peer_type]) - return NULL; + return rtnl_link_get_net_ifla(tbp); err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack); if (err < 0) @@ -3971,7 +3972,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, } if (ops->peer_type) { - peer_net = rtnl_get_peer_net(ops, data, extack); + peer_net = rtnl_get_peer_net(ops, tb, data, extack); if (IS_ERR(peer_net)) { ret = PTR_ERR(peer_net); goto put_ops; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 78347d7d25ef..f1b9b3958792 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -159,6 +159,7 @@ static void sock_map_del_link(struct sock *sk, verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); + break; } } spin_unlock_bh(&psock->link_lock); @@ -411,12 +412,11 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { - struct sock *sk; + struct sock *sk = NULL; int err = 0; spin_lock_bh(&stab->lock); - sk = *psk; - if (!sk_test || sk_test == sk) + if (!sk_test || sk_test == *psk) sk = xchg(psk, NULL); if (likely(sk)) diff --git a/net/dsa/tag.h b/net/dsa/tag.h index d5707870906b..5d80ddad4ff6 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path * @skb: Pointer to socket buffer (packet) * - * Receive path method for switches which cannot avoid tagging all packets - * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or - * ds->untag_vlan_aware_bridge_pvid is set to true. + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. * * As a side effect of this method, any VLAN tag from the skb head is moved * to hwaccel. @@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) { struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); - u16 vid; + u16 vid, proto; + int err; /* software untagging for standalone ports not yet necessary */ if (!br) return skb; + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb)) { + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { skb = skb_vlan_untag(skb); if (!skb) return NULL; diff --git a/net/mctp/route.c b/net/mctp/route.c index 597e9cf5aa64..3f2bd65ff5e3 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) msk = NULL; rc = -EINVAL; - /* we may be receiving a locally-routed packet; drop source sk - * accounting + /* We may be receiving a locally-routed packet; drop source sk + * accounting. + * + * From here, we will either queue the skb - either to a frag_queue, or + * to a receiving socket. When that succeeds, we clear the skb pointer; + * a non-NULL skb on exit will be otherwise unowned, and hence + * kfree_skb()-ed. */ skb_orphan(skb); @@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * pending key. */ if (flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(&msk->sk, skb); + rc = sock_queue_rcv_skb(&msk->sk, skb); + if (!rc) + skb = NULL; if (key) { /* we've hit a pending reassembly; not much we * can do but drop it @@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) MCTP_TRACE_KEY_REPLIED); key = NULL; } - rc = 0; goto out_unlock; } @@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (!rc) + if (!rc) { trace_mctp_key_acquire(key); + skb = NULL; + } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); + if (!rc) + skb = NULL; } } @@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) else rc = mctp_frag_queue(key, skb); + if (rc) + goto out_unlock; + + /* we've queued; the queue owns the skb now */ + skb = NULL; + /* end of message? deliver to socket, and we're done with * the reassembly/response key */ - if (!rc && flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(key->sk, key->reasm_head); - key->reasm_head = NULL; + if (flags & MCTP_HDR_FLAG_EOM) { + rc = sock_queue_rcv_skb(key->sk, key->reasm_head); + if (!rc) + key->reasm_head = NULL; __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -527,8 +544,7 @@ out_unlock: if (any_key) mctp_key_unref(any_key); out: - if (rc) - kfree_skb(skb); + kfree_skb(skb); return rc; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 8551dab1d1e6..17165b86ce22 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test) mctp_test_route_input_multiple_nets_key_fini(test, &t2); } +/* Input route to socket, using a single-packet message, where sock delivery + * fails. Ensure we're handling the failure appropriately. + */ +static void mctp_test_route_input_sk_fail_single(struct kunit *test) +{ + const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO); + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct socket *sock; + struct sk_buff *skb; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will + * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this. + */ + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + skb = mctp_test_create_skb(&hdr, 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + skb_get(skb); + + mctp_test_skb_set_dev(skb, dev); + + /* do route input, which should fail */ + rc = mctp_route_input(&rt->rt, skb); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to skb */ + KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1); + kfree_skb(skb); + + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* Input route to socket, using a fragmented message, where sock delivery fails. + */ +static void mctp_test_route_input_sk_fail_frag(struct kunit *test) +{ + const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) }; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skbs[2]; + struct socket *sock; + unsigned int i; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + for (i = 0; i < ARRAY_SIZE(skbs); i++) { + skbs[i] = mctp_test_create_skb(&hdrs[i], 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]); + skb_get(skbs[i]); + + mctp_test_skb_set_dev(skbs[i], dev); + } + + /* first route input should succeed, we're only queueing to the + * frag list + */ + rc = mctp_route_input(&rt->rt, skbs[0]); + KUNIT_EXPECT_EQ(test, rc, 0); + + /* final route input should fail to deliver to the socket */ + rc = mctp_route_input(&rt->rt, skbs[1]); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to both skbs */ + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1); + kfree_skb(skbs[0]); + + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1); + kfree_skb(skbs[1]); + + __mctp_route_test_fini(test, dev, rt, sock); +} + #if IS_ENABLED(CONFIG_MCTP_FLOWS) static void mctp_test_flow_init(struct kunit *test, @@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_sk_fail_single), + KUNIT_CASE(mctp_test_route_input_sk_fail_frag), KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), KUNIT_CASE(mctp_test_route_input_multiple_nets_key), KUNIT_CASE(mctp_test_packet_flow), diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index bfae7066936b..db794fe1300e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) return true; } +static struct lock_class_key list_set_lockdep_key; + static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) @@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; + lockdep_set_class(&set->lock, &list_set_lockdep_key); set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 98d7dbe3d787..c0289f83f96d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,8 +1495,8 @@ int __init ip_vs_conn_init(void) max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); - max = clamp(max, min, max_avail); - ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); + max = clamp(max_avail, min, max); + ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/psample/psample.c b/net/psample/psample.c index a0ddae8a65f9..25f92ba0840c 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group, nla_total_size_64bit(sizeof(u64)) + /* timestamp */ nla_total_size(sizeof(u16)) + /* protocol */ (md->user_cookie_len ? - nla_total_size(md->user_cookie_len) : 0); /* user cookie */ + nla_total_size(md->user_cookie_len) : 0) + /* user cookie */ + (md->rate_as_probability ? + nla_total_size(0) : 0); /* rate as probability */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group, md->user_cookie)) goto error; - if (md->rate_as_probability) - nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + if (md->rate_as_probability && + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY)) + goto error; genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 19ebff1c2579..c370efcfe3e8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2035,6 +2035,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx) + return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -2148,6 +2150,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) + goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { @@ -2224,7 +2228,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, int rc = 0; /* check if ISM V1 is available */ - if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + if (!(ini->smcd_version & SMC_V1) || + !smcd_indicated(ini->smc_type_v1) || + !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); @@ -2275,7 +2281,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ @@ -2884,6 +2891,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock, } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_state != SMC_INIT) { + /* Race breaker the same way as tcp_poll(). */ + smp_mb__after_atomic(); + if (atomic_read(&smc->conn.sndbuf_space)) + mask |= EPOLLOUT | EPOLLWRNORM; + } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 33fa787c28eb..521f5df80e10 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx || + pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX) + return false; + if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; @@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + @@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); + if (len < recvlen) { + smc->sk.sk_err = EPROTO; + reason_code = -EPROTO; + goto out; + } datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 5fd6f5b8ef03..767289925410 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) { + u16 offset = ntohs(pclc->iparea_offset); + + if (offset > sizeof(struct smc_clc_msg_smcd)) + return NULL; return (struct smc_clc_msg_proposal_prefix *) - ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); + ((u8 *)pclc + sizeof(*pclc) + offset); } static inline bool smcr_indicated(int smc_type) @@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) @@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) static inline struct smc_clc_smcd_v2_extension * smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) { + u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_v2_extension, hdr) - + offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset); + if (!prop_v2ext) return NULL; - if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) || + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_smcd_v2_extension *) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index ede4d5f3111b..ccf57b7fe602 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1823,7 +1823,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); - schedule_work(&lnk->link_down_wrk); + smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ + if (!schedule_work(&lnk->link_down_wrk)) + smcr_link_put(lnk); } } @@ -1855,11 +1857,14 @@ static void smc_link_down_work(struct work_struct *work) struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) - return; + goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); + +out: + smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, diff --git a/rust/Makefile b/rust/Makefile index 9da9042fd627..a40a3936126d 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -280,9 +280,22 @@ endif # architecture instead of generating `usize`. bindgen_c_flags_final = $(bindgen_c_flags_lto) -fno-builtin -D__BINDGEN__ +# Each `bindgen` release may upgrade the list of Rust target versions. By +# default, the highest stable release in their list is used. Thus we need to set +# a `--rust-target` to avoid future `bindgen` releases emitting code that +# `rustc` may not understand. On top of that, `bindgen` does not support passing +# an unknown Rust target version. +# +# Therefore, the Rust target for `bindgen` can be only as high as the minimum +# Rust version the kernel supports and only as high as the greatest stable Rust +# target supported by the minimum `bindgen` version the kernel supports (that +# is, if we do not test the actual `rustc`/`bindgen` versions running). +# +# Starting with `bindgen` 0.71.0, we will be able to set any future Rust version +# instead, i.e. we will be able to set here our minimum supported Rust version. quiet_cmd_bindgen = BINDGEN $@ cmd_bindgen = \ - $(BINDGEN) $< $(bindgen_target_flags) \ + $(BINDGEN) $< $(bindgen_target_flags) --rust-target 1.68 \ --use-core --with-derive-default --ctypes-prefix ffi --no-layout-tests \ --no-debug '.*' --enable-function-attribute-detection \ -o $@ -- $(bindgen_c_flags_final) -DMODULE \ diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index 00c3100f5ebd..eeb49597f4f4 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -860,7 +860,7 @@ impl DeviceMask { /// ]; /// #[cfg(MODULE)] /// #[no_mangle] -/// static __mod_mdio__phydev_device_table: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; +/// static __mod_device_table__mdio__phydev: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; /// ``` #[macro_export] macro_rules! module_phy_driver { @@ -883,7 +883,7 @@ macro_rules! module_phy_driver { #[cfg(MODULE)] #[no_mangle] - static __mod_mdio__phydev_device_table: [$crate::bindings::mdio_device_id; + static __mod_device_table__mdio__phydev: [$crate::bindings::mdio_device_id; $crate::module_phy_driver!(@count_devices $($dev),+) + 1] = _DEVICE_TABLE; }; diff --git a/scripts/head-object-list.txt b/scripts/head-object-list.txt index f12b4a7b8406..7274dfc65af6 100644 --- a/scripts/head-object-list.txt +++ b/scripts/head-object-list.txt @@ -24,7 +24,6 @@ arch/m68k/kernel/head.o arch/m68k/kernel/sun3-head.o arch/microblaze/kernel/head.o arch/nios2/kernel/head.o -arch/openrisc/kernel/head.o arch/parisc/kernel/head.o arch/powerpc/kernel/head_44x.o arch/powerpc/kernel/head_64.o diff --git a/scripts/kernel-doc b/scripts/kernel-doc index f66070176ba3..4ee843d3600e 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -267,7 +267,7 @@ my $doc_inline_sect = '\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)'; my $doc_inline_end = '^\s*\*/\s*$'; my $doc_inline_oneline = '^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$'; my $export_symbol = '^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*;'; -my $export_symbol_ns = '^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*\w+\)\s*;'; +my $export_symbol_ns = '^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*"\S+"\)\s*;'; my $function_pointer = qr{([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)}; my $attribute = qr{__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)}i; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 971c45d576ba..3d5c563cfc4c 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -979,7 +979,10 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, return; break; default: - BUG(); + pr_warn_once( + "SELinux: unknown extended permission (%u) will be ignored\n", + node->datum.u.xperms->specified); + return; } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { @@ -998,7 +1001,8 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { - BUG(); + pr_warn_once("SELinux: unknown specified key (%u)\n", + node->key.specified); } } diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 65a1ebe87776..e33dfcf863cf 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -668,10 +668,16 @@ static void snd_ctl_led_sysfs_add(struct snd_card *card) goto cerr; led->cards[card->number] = led_card; snprintf(link_name, sizeof(link_name), "led-%s", led->name); - WARN(sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, link_name), - "can't create symlink to controlC%i device\n", card->number); - WARN(sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, "card"), - "can't create symlink to card%i\n", card->number); + if (sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, + link_name)) + dev_err(card->dev, + "%s: can't create symlink to controlC%i device\n", + __func__, card->number); + if (sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, + "card")) + dev_err(card->dev, + "%s: can't create symlink to card%i\n", + __func__, card->number); continue; cerr: diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index d96266c8cb38..4ef7878e8fd4 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -151,10 +151,6 @@ static int cs35l56_hda_runtime_resume(struct device *dev) } } - ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base); - if (ret) - goto err; - return 0; err: @@ -1059,9 +1055,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) regmap_multi_reg_write(cs35l56->base.regmap, cs35l56_hda_dai_config, ARRAY_SIZE(cs35l56_hda_dai_config)); - ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base); - if (ret) - goto dsp_err; /* * By default only enable one ASP1TXn, where n=amplifier index, @@ -1087,7 +1080,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) pm_err: pm_runtime_disable(cs35l56->base.dev); -dsp_err: cs_dsp_remove(&cs35l56->cs_dsp); err: gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 0); diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e4673a71551a..d40197fb5fbd 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1134,7 +1134,6 @@ struct ca0132_spec { struct hda_codec *codec; struct delayed_work unsol_hp_work; - int quirk; #ifdef ENABLE_TUNING_CONTROLS long cur_ctl_vals[TUNING_CTLS_COUNT]; @@ -1166,7 +1165,6 @@ struct ca0132_spec { * CA0132 quirks table */ enum { - QUIRK_NONE, QUIRK_ALIENWARE, QUIRK_ALIENWARE_M17XR4, QUIRK_SBZ, @@ -1176,10 +1174,11 @@ enum { QUIRK_R3D, QUIRK_AE5, QUIRK_AE7, + QUIRK_NONE = HDA_FIXUP_ID_NOT_SET, }; #ifdef CONFIG_PCI -#define ca0132_quirk(spec) ((spec)->quirk) +#define ca0132_quirk(spec) ((spec)->codec->fixup_id) #define ca0132_use_pci_mmio(spec) ((spec)->use_pci_mmio) #define ca0132_use_alt_functions(spec) ((spec)->use_alt_functions) #define ca0132_use_alt_controls(spec) ((spec)->use_alt_controls) @@ -1293,7 +1292,7 @@ static const struct hda_pintbl ae7_pincfgs[] = { {} }; -static const struct snd_pci_quirk ca0132_quirks[] = { +static const struct hda_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1028, 0x057b, "Alienware M17x R4", QUIRK_ALIENWARE_M17XR4), SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE), SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE), @@ -1316,6 +1315,19 @@ static const struct snd_pci_quirk ca0132_quirks[] = { {} }; +static const struct hda_model_fixup ca0132_quirk_models[] = { + { .id = QUIRK_ALIENWARE, .name = "alienware" }, + { .id = QUIRK_ALIENWARE_M17XR4, .name = "alienware-m17xr4" }, + { .id = QUIRK_SBZ, .name = "sbz" }, + { .id = QUIRK_ZXR, .name = "zxr" }, + { .id = QUIRK_ZXR_DBPRO, .name = "zxr-dbpro" }, + { .id = QUIRK_R3DI, .name = "r3di" }, + { .id = QUIRK_R3D, .name = "r3d" }, + { .id = QUIRK_AE5, .name = "ae5" }, + { .id = QUIRK_AE7, .name = "ae7" }, + {} +}; + /* Output selection quirk info structures. */ #define MAX_QUIRK_MMIO_GPIO_SET_VALS 3 #define MAX_QUIRK_SCP_SET_VALS 2 @@ -9957,17 +9969,15 @@ static int ca0132_prepare_verbs(struct hda_codec *codec) */ static void sbz_detect_quirk(struct hda_codec *codec) { - struct ca0132_spec *spec = codec->spec; - switch (codec->core.subsystem_id) { case 0x11020033: - spec->quirk = QUIRK_ZXR; + codec->fixup_id = QUIRK_ZXR; break; case 0x1102003f: - spec->quirk = QUIRK_ZXR_DBPRO; + codec->fixup_id = QUIRK_ZXR_DBPRO; break; default: - spec->quirk = QUIRK_SBZ; + codec->fixup_id = QUIRK_SBZ; break; } } @@ -9976,7 +9986,6 @@ static int patch_ca0132(struct hda_codec *codec) { struct ca0132_spec *spec; int err; - const struct snd_pci_quirk *quirk; codec_dbg(codec, "patch_ca0132\n"); @@ -9987,11 +9996,7 @@ static int patch_ca0132(struct hda_codec *codec) spec->codec = codec; /* Detect codec quirk */ - quirk = snd_pci_quirk_lookup(codec->bus->pci, ca0132_quirks); - if (quirk) - spec->quirk = quirk->value; - else - spec->quirk = QUIRK_NONE; + snd_hda_pick_fixup(codec, ca0132_quirk_models, ca0132_quirks, NULL); if (ca0132_quirk(spec) == QUIRK_SBZ) sbz_detect_quirk(codec); @@ -10068,7 +10073,7 @@ static int patch_ca0132(struct hda_codec *codec) spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20); if (spec->mem_base == NULL) { codec_warn(codec, "pci_iomap failed! Setting quirk to QUIRK_NONE."); - spec->quirk = QUIRK_NONE; + codec->fixup_id = QUIRK_NONE; } } #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 17392b21d5bf..61ba5dc35b8b 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7714,6 +7714,7 @@ enum { ALC274_FIXUP_HP_MIC, ALC274_FIXUP_HP_HEADSET_MIC, ALC274_FIXUP_HP_ENVY_GPIO, + ALC274_FIXUP_ASUS_ZEN_AIO_27, ALC256_FIXUP_ASUS_HPE, ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, ALC287_FIXUP_HP_GPIO_LED, @@ -9516,6 +9517,26 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc274_fixup_hp_envy_gpio, }, + [ALC274_FIXUP_ASUS_ZEN_AIO_27] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x10 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc420 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x40 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x8800 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x49 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0249 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x4a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x202b }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x62 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xa007 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x6b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5060 }, + {} + }, + .chained = true, + .chain_id = ALC2XX_FIXUP_HEADSET_MIC, + }, [ALC256_FIXUP_ASUS_HPE] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -10142,6 +10163,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), @@ -10630,6 +10652,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), + SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27), SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), @@ -11177,6 +11200,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"}, {.id = ALC285_FIXUP_HP_GPIO_AMP_INIT, .name = "alc285-hp-amp-init"}, {.id = ALC236_FIXUP_LENOVO_INV_DMIC, .name = "alc236-fixup-lenovo-inv-mic"}, + {.id = ALC2XX_FIXUP_HEADSET_MIC, .name = "alc2xx-fixup-headset-mic"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index e38c5885dadf..ecf57a6cb7c3 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -578,14 +578,19 @@ static int acp6x_probe(struct platform_device *pdev) handle = ACPI_HANDLE(pdev->dev.parent); ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); - if (!ACPI_FAILURE(ret)) + if (!ACPI_FAILURE(ret)) { wov_en = dmic_status; + if (!wov_en) + return -ENODEV; + } else { + /* Incase of ACPI method read failure then jump to check_dmi_entry */ + goto check_dmi_entry; + } - if (is_dmic_enable && wov_en) + if (is_dmic_enable) platform_set_drvdata(pdev, &acp6x_card); - else - return 0; +check_dmi_entry: /* check for any DMI overrides */ dmi_id = dmi_first_match(yc_acp_quirk_table); if (dmi_id) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index be2ca5eb6c93..fb8cd2284fe8 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -370,7 +370,7 @@ static void sngl_calib_start(struct tasdevice_priv *tas_priv, int i, tasdevice_dev_read(tas_priv, i, p[j].reg, (int *)&p[j].val[0]); } else { - switch (p[j].reg) { + switch (tas2781_cali_start_reg[j].reg) { case 0: { if (!reg[0]) continue; diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 8e88830e8e57..678540b78280 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -29,8 +29,8 @@ config SND_SOC_FSL_SAI config SND_SOC_FSL_MQS tristate "Medium Quality Sound (MQS) module support" depends on SND_SOC_FSL_SAI + depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV select REGMAP_MMIO - select IMX_SCMI_MISC_DRV if IMX_SCMI_MISC_EXT !=n help Say Y if you want to add Medium Quality Sound (MQS) support for the Freescale CPUs. diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index b6ff04f7138a..ee946e0d3f49 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1204,7 +1204,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = { }, /* DPLL lock info get controller */ { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = RX_SAMPLE_RATE_KCONTROL, .access = SNDRV_CTL_ELEM_ACCESS_READ | SNDRV_CTL_ELEM_ACCESS_VOLATILE, diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 1e0bfd59d511..9c184ab73468 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -171,7 +171,7 @@ static int fsl_xcvr_capds_put(struct snd_kcontrol *kcontrol, } static struct snd_kcontrol_new fsl_xcvr_earc_capds_kctl = { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = "Capabilities Data Structure", .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, .info = fsl_xcvr_type_capds_bytes_info, diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 5280c1b20d85..1f5c4e8ff1b9 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -771,7 +771,7 @@ static void graph_link_init(struct simple_util_priv *priv, of_node_get(port_codec); if (graph_lnk_is_multi(port_codec)) { ep_codec = graph_get_next_multi_ep(&port_codec); - of_node_put(port_cpu); + of_node_put(port_codec); port_codec = ep_to_port(ep_codec); } else { ep_codec = of_graph_get_next_port_endpoint(port_codec, NULL); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 810be7c949a5..f3369e569abc 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -1067,8 +1067,12 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) return ret; } - /* One per DAI link, worst case is a DAI link for every endpoint */ - sof_dais = kcalloc(num_ends, sizeof(*sof_dais), GFP_KERNEL); + /* + * One per DAI link, worst case is a DAI link for every endpoint, also + * add one additional to act as a terminator such that code can iterate + * until it hits an uninitialised DAI. + */ + sof_dais = kcalloc(num_ends + 1, sizeof(*sof_dais), GFP_KERNEL); if (!sof_dais) return -ENOMEM; diff --git a/sound/usb/format.c b/sound/usb/format.c index 0cbf1d4fbe6e..6049d957694c 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -60,6 +60,8 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, pcm_formats |= SNDRV_PCM_FMTBIT_SPECIAL; /* flag potentially raw DSD capable altsettings */ fp->dsd_raw = true; + /* clear special format bit to avoid "unsupported format" msg below */ + format &= ~UAC2_FORMAT_TYPE_I_RAW_DATA; } format <<= 1; @@ -71,8 +73,11 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, sample_width = as->bBitResolution; sample_bytes = as->bSubslotSize; - if (format & UAC3_FORMAT_TYPE_I_RAW_DATA) + if (format & UAC3_FORMAT_TYPE_I_RAW_DATA) { pcm_formats |= SNDRV_PCM_FMTBIT_SPECIAL; + /* clear special format bit to avoid "unsupported format" msg below */ + format &= ~UAC3_FORMAT_TYPE_I_RAW_DATA; + } format <<= 1; break; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 00101875d9a8..8ba0aff8be2e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2179,6 +2179,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIC_RES_384), DEVICE_FLG(0x046d, 0x09a4, /* Logitech QuickCam E 3500 */ QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x0499, 0x1506, /* Yamaha THR5 */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */ @@ -2323,6 +2325,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */ QUIRK_FLAG_SET_IFACE_FIRST), + DEVICE_FLG(0x262a, 0x9302, /* ddHiFi TC44C */ + QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */ diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 964df31da975..66736ff04011 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -484,6 +484,12 @@ enum { */ #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) +/* + * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call. + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN. + */ +#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 (1ULL << 0) + /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 23698d0f4bb4..17b6590748c0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -215,7 +215,7 @@ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ #define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ #define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ #define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ @@ -317,6 +317,9 @@ #define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_SHA512 (12*32+ 0) /* SHA512 instructions */ +#define X86_FEATURE_SM3 (12*32+ 1) /* SM3 instructions */ +#define X86_FEATURE_SM4 (12*32+ 2) /* SM4 instructions */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ @@ -348,6 +351,7 @@ #define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ #define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */ #define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -472,7 +476,9 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ -#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ +#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */ +#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ +#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ /* * BUG word(s) @@ -523,4 +529,5 @@ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index a8debbf2f702..88585c1de416 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -440,6 +440,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) #define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) +#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..0198321d14a2 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -468,8 +466,10 @@ int main(int argc, char *argv[]) */ ret = pread(fcopy_fd, &tmp, sizeof(int), 0); if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - continue; + goto close; } len = HV_RING_SIZE; diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4a..04ba035d67e9 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s", - "hv_set_ifconfig", if_filename, nm_filename); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 406f7718f9ad..51d2556af54a 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -19,4 +19,8 @@ #define MCL_FUTURE 2 /* lock all future mappings */ #define MCL_ONFAULT 4 /* lock all pages that are faulted in */ +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack marker in the shadow stack */ + + #endif /* __ASM_GENERIC_MMAN_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 5bf6148cac2b..88dc393c2bca 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -841,8 +841,17 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) #define __NR_mseal 462 __SYSCALL(__NR_mseal, sys_mseal) +#define __NR_setxattrat 463 +__SYSCALL(__NR_setxattrat, sys_setxattrat) +#define __NR_getxattrat 464 +__SYSCALL(__NR_getxattrat, sys_getxattrat) +#define __NR_listxattrat 465 +__SYSCALL(__NR_listxattrat, sys_listxattrat) +#define __NR_removexattrat 466 +__SYSCALL(__NR_removexattrat, sys_removexattrat) + #undef __NR_syscalls -#define __NR_syscalls 463 +#define __NR_syscalls 467 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 16122819edfe..7fba37b94401 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -1024,6 +1024,13 @@ struct drm_crtc_queue_sequence { __u64 user_data; /* user data passed to event */ }; +#define DRM_CLIENT_NAME_MAX_LEN 64 +struct drm_set_client_name { + __u64 name_len; + __u64 name; +}; + + #if defined(__cplusplus) } #endif @@ -1288,6 +1295,16 @@ extern "C" { */ #define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb) +/** + * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file + * + * Having a name allows for easier tracking and debugging. + * The length of the name (without null ending char) must be + * <= DRM_CLIENT_NAME_MAX_LEN. + * The call will fail if the name contains whitespaces or non-printable chars. + */ +#define DRM_IOCTL_SET_CLIENT_NAME DRM_IOWR(0xD1, struct drm_set_client_name) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 637efc055145..502ea63b5d2e 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1158,7 +1158,15 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_RISCV_AIA, #define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA + KVM_DEV_TYPE_LOONGARCH_IPI, +#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI + KVM_DEV_TYPE_LOONGARCH_EIOINTC, +#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC + KVM_DEV_TYPE_LOONGARCH_PCHPIC, +#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC + KVM_DEV_TYPE_MAX, + }; struct kvm_vfio_spapr_tce { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 4842c36fdf80..0524d541d4e3 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -511,7 +511,16 @@ struct perf_event_attr { __u16 sample_max_stack; __u16 __reserved_2; __u32 aux_sample_size; - __u32 __reserved_3; + + union { + __u32 aux_action; + struct { + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 29; + }; + }; /* * User provided data if sigtrap=1, passed back to user via diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index c6d67fc9e57e..83c43dc13313 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + } } else if (!evsel->own_cpus || evlist->has_user_cpus || (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { /* @@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel, *n; evlist->needs_map_propagation = true; - perf_evlist__for_each_evsel(evlist, evsel) + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 01ec01a90e76..eea29359a899 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -556,10 +556,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4ce176ad411f..76060da755b5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 1464c6be6eb3..c844cd5cda62 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -377,3 +377,7 @@ 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules 462 n64 mseal sys_mseal +463 n64 setxattrat sys_setxattrat +464 n64 getxattrat sys_getxattrat +465 n64 listxattrat sys_listxattrat +466 n64 removexattrat sys_removexattrat diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index ebae8415dfbb..d8b4ab78bef0 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -553,3 +553,7 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 01071182763e..e9115b4d8b63 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -465,3 +465,7 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal sys_mseal +463 common setxattrat sys_setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat sys_removexattrat diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index 534c74b14fab..4d0fb2fba7e2 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -468,3 +468,7 @@ 460 i386 lsm_set_self_attr sys_lsm_set_self_attr 461 i386 lsm_list_modules sys_lsm_list_modules 462 i386 mseal sys_mseal +463 i386 setxattrat sys_setxattrat +464 i386 getxattrat sys_getxattrat +465 i386 listxattrat sys_listxattrat +466 i386 removexattrat sys_removexattrat diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7093ee21c0d1..5eb708bff1c7 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -386,6 +386,10 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 272d3c70810e..a56cf8b0a7d4 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b) if (v1 > v2) return -1; - else + if (v1 < v2) return 1; + return 0; } static void print_profile_result(struct perf_ftrace *ftrace) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 8dcf74d3c0a3..4751dd3c6f67 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -508,7 +508,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], for (size_t x = 0; x < num_tests; x++) { struct child_test *child_test = child_tests[x]; - if (!child_test) + if (!child_test || child_test->process.pid <= 0) continue; pr_debug3("Killing %d pid %d\n", diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 41ff1affdfcd..726cf8d4da28 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -75,14 +75,12 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages; int ret; struct expr_parse_ctx *ctx; - bool is_intel = false; char strcmp_cpuid_buf[256]; struct perf_cpu cpu = {-1}; char *cpuid = get_cpuid_allow_env_override(cpu); char *escaped_cpuid1, *escaped_cpuid2; TEST_ASSERT_VAL("get_cpuid", cpuid); - is_intel = strstr(cpuid, "Intel") != NULL; TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); @@ -245,12 +243,19 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u if (num_dies) // Some platforms do not have CPU die support, for example s390 TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); - TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0); - if (is_intel) - TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0); - else - TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO); + if (expr__parse(&val, ctx, "#system_tsc_freq") == 0) { + bool is_intel = strstr(cpuid, "Intel") != NULL; + + if (is_intel) + TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0); + else + TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO); + } else { +#if defined(__i386__) || defined(__x86_64__) + TEST_ASSERT_VAL("#system_tsc_freq unsupported", 0); +#endif + } /* * Source count returns the number of events aggregating in a leader * event including the leader. Check parsing yields an id. diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c index f8bcee9660d5..d2b066a2b557 100644 --- a/tools/perf/tests/hwmon_pmu.c +++ b/tools/perf/tests/hwmon_pmu.c @@ -65,7 +65,7 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) { "temp2_label", "test hwmon event2\n", }, { "temp2_input", "50000\n", }, }; - int dirfd, file; + int hwmon_dirfd = -1, test_dirfd = -1, file; struct perf_pmu *hwm = NULL; ssize_t len; @@ -76,19 +76,24 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) dir[0] = '\0'; return NULL; } - dirfd = open(dir, O_DIRECTORY); - if (dirfd < 0) { + test_dirfd = open(dir, O_PATH|O_DIRECTORY); + if (test_dirfd < 0) { pr_err("Failed to open test directory \"%s\"\n", dir); goto err_out; } /* Create the test hwmon directory and give it a name. */ - if (mkdirat(dirfd, "hwmon1234", 0755) < 0) { + if (mkdirat(test_dirfd, "hwmon1234", 0755) < 0) { pr_err("Failed to mkdir hwmon directory\n"); goto err_out; } - file = openat(dirfd, "hwmon1234/name", O_WRONLY | O_CREAT, 0600); - if (!file) { + hwmon_dirfd = openat(test_dirfd, "hwmon1234", O_DIRECTORY); + if (hwmon_dirfd < 0) { + pr_err("Failed to open test hwmon directory \"%s/hwmon1234\"\n", dir); + goto err_out; + } + file = openat(hwmon_dirfd, "name", O_WRONLY | O_CREAT, 0600); + if (file < 0) { pr_err("Failed to open for writing file \"name\"\n"); goto err_out; } @@ -104,8 +109,8 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) for (size_t i = 0; i < ARRAY_SIZE(test_items); i++) { const struct test_item *item = &test_items[i]; - file = openat(dirfd, item->name, O_WRONLY | O_CREAT, 0600); - if (!file) { + file = openat(hwmon_dirfd, item->name, O_WRONLY | O_CREAT, 0600); + if (file < 0) { pr_err("Failed to open for writing file \"%s\"\n", item->name); goto err_out; } @@ -119,16 +124,18 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) } /* Make the PMU reading the files created above. */ - hwm = perf_pmus__add_test_hwmon_pmu(dirfd, "hwmon1234", test_hwmon_name); + hwm = perf_pmus__add_test_hwmon_pmu(hwmon_dirfd, "hwmon1234", test_hwmon_name); if (!hwm) pr_err("Test hwmon creation failed\n"); err_out: if (!hwm) { test_pmu_put(dir, hwm); - if (dirfd >= 0) - close(dirfd); + if (hwmon_dirfd >= 0) + close(hwmon_dirfd); } + if (test_dirfd >= 0) + close(test_dirfd); return hwm; } diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh index e3f13f96a27c..fac4d0c049fc 100755 --- a/tools/perf/trace/beauty/fs_at_flags.sh +++ b/tools/perf/trace/beauty/fs_at_flags.sh @@ -13,13 +13,14 @@ printf "static const char *fs_at_flags[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' # AT_EACCESS is only meaningful to faccessat, so we will special case it there... # AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC -# AT_HANDLE_FID and AT_HANDLE_MNT_ID_UNIQUE are reusing values and are valid only for name_to_handle_at() +# AT_HANDLE_FID, AT_HANDLE_MNT_ID_UNIQUE and AT_HANDLE_CONNECTABLE are reusing values and are valid only for name_to_handle_at() # AT_RENAME_NOREPLACE reuses 0x1 and is valid only for renameat2() grep -E $regex ${linux_fcntl} | \ grep -v AT_EACCESS | \ grep -v AT_STATX_SYNC_TYPE | \ grep -v AT_HANDLE_FID | \ grep -v AT_HANDLE_MNT_ID_UNIQUE | \ + grep -v AT_HANDLE_CONNECTABLE | \ grep -v AT_RENAME_NOREPLACE | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index 87e2dec79fea..6e6907e63bfc 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -153,9 +153,6 @@ object identity and may not be usable with open_by_handle_at(2). */ #define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */ - -#if defined(__KERNEL__) -#define AT_GETATTR_NOSEC 0x80000000 -#endif +#define AT_HANDLE_CONNECTABLE 0x002 /* Request a connectable file handle */ #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index 225bc366ffcb..c07008816aca 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 mnt_opts; /* [str] Mount options of the mount */ + __u32 mnt_opts; /* [str] Options (comma separated, escaped) */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -173,7 +173,13 @@ struct statmount { __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ __u64 mnt_ns_id; /* ID of the mount namespace */ - __u64 __spare2[49]; + __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */ + __u32 sb_source; /* [str] Source string of the mount */ + __u32 opt_num; /* Number of fs options */ + __u32 opt_array; /* [str] Array of nul terminated fs options */ + __u32 opt_sec_num; /* Number of security options */ + __u32 opt_sec_array; /* [str] Array of nul terminated security options */ + __u64 __spare2[46]; char str[]; /* Variable size part containing strings */ }; @@ -207,6 +213,10 @@ struct mnt_id_req { #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ #define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ #define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ +#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */ +#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */ +#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */ +#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */ /* * Special @mnt_id values that can be passed to listmount diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 35791791a879..5c6080680cb2 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -230,7 +230,7 @@ struct prctl_mm_map { # define PR_PAC_APDBKEY (1UL << 3) # define PR_PAC_APGAKEY (1UL << 4) -/* Tagged user address controls for arm64 */ +/* Tagged user address controls for arm64 and RISC-V */ #define PR_SET_TAGGED_ADDR_CTRL 55 #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) @@ -244,6 +244,9 @@ struct prctl_mm_map { # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) /* Unused; kept only for source compatibility */ # define PR_MTE_TCF_SHIFT 1 +/* RISC-V pointer masking tag length */ +# define PR_PMLEN_SHIFT 24 +# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT) /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 @@ -328,4 +331,26 @@ struct prctl_mm_map { # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ # define PR_PPC_DEXCR_CTRL_MASK 0x1f +/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 74 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 76 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8982f68e7230..e763e8d99a43 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid struct perf_record_header_build_id b; size_t len; - len = sizeof(b) + name_len + 1; + len = name_len + 1; len = PERF_ALIGN(len, sizeof(u64)); memset(&b, 0, sizeof(b)); @@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid misc |= PERF_RECORD_MISC_BUILD_ID_SIZE; b.pid = pid; b.header.misc = misc; - b.header.size = len; + b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); if (err < 0) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f745723d486b..d22c5df1701e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2571,12 +2571,12 @@ try_fallback: if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; - if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel)) - goto retry_open; - if (err == -EINVAL && evsel__detect_missing_features(evsel)) goto fallback_missing_features; + if (evsel__precise_ip_fallback(evsel)) + goto retry_open; + if (evsel__handle_error_quirks(evsel, err)) goto retry_open; diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index e61429b38ba7..4acb9bb19b84 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -258,8 +258,12 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) if (pmu->pmu.sysfs_aliases_loaded) return 0; - /* Use a dup-ed fd as closedir will close it. */ - dup_fd = dup(pmu->hwmon_dir_fd); + /* + * Use a dup-ed fd as closedir will close it. Use openat so that the + * directory contents are refreshed. + */ + dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY); + if (dup_fd == -1) return -ENOMEM; @@ -336,6 +340,9 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) close(fd); } } + if (hashmap__size(&pmu->events) == 0) + pr_debug2("hwmon_pmu: %s has no events\n", pmu->pmu.name); + hashmap__for_each_entry_safe((&pmu->events), cur, tmp, bkt) { union hwmon_pmu_event_key key = { .type_and_num = cur->key, @@ -343,8 +350,8 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) struct hwmon_pmu_event_value *value = cur->pvalue; if (!test_bit(HWMON_ITEM_INPUT, value->items)) { - pr_debug("hwmon_pmu: removing event '%s%d' that has no input file\n", - hwmon_type_strs[key.type], key.num); + pr_debug("hwmon_pmu: %s removing event '%s%d' that has no input file\n", + pmu->pmu.name, hwmon_type_strs[key.type], key.num); hashmap__delete(&pmu->events, key.type_and_num, &key, &value); zfree(&value->label); zfree(&value->name); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4f0ac998b0cc..27d5345d2b30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -134,6 +134,8 @@ struct machine *machine__new_host(void) if (machine__create_kernel_maps(machine) < 0) goto out_delete; + + machine->env = &perf_env; } return machine; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6d51a4c98ad7..eaa0318e9b87 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1370,7 +1370,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) { char *buf = strdup(arg); char *p; - int err; + int err = 0; if (!buf) return -ENOMEM; diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index df3230fdac39..66ab2e0bae5f 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -81,32 +81,31 @@ do_syscall: stp x27, x28, [sp, #96] // Set SVCR if we're doing SME - cbz x1, 1f + cbz x1, load_gpr adrp x2, svcr_in ldr x2, [x2, :lo12:svcr_in] msr S3_3_C4_C2_2, x2 -1: // Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, load_gpr mov w12, #0 ldr x2, =za_in -2: _ldr_za 12, 2 +1: _ldr_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, load_gpr adrp x2, zt_in add x2, x2, :lo12:zt_in _ldr_zt 2 -1: +load_gpr: // Load GPRs x8-x28, and save our SP/FP for later comparison ldr x2, =gpr_in add x2, x2, #64 @@ -125,9 +124,9 @@ do_syscall: str x30, [x2], #8 // LR // Load FPRs if we're not doing neither SVE nor streaming SVE - cbnz x0, 1f + cbnz x0, check_sve_in ldr x2, =svcr_in - tbnz x2, #SVCR_SM_SHIFT, 1f + tbnz x2, #SVCR_SM_SHIFT, check_sve_in ldr x2, =fpr_in ldp q0, q1, [x2] @@ -148,8 +147,8 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] b 2f -1: +check_sve_in: // Load the SVE registers if we're doing SVE/SME ldr x2, =z_in @@ -256,32 +255,31 @@ do_syscall: stp q30, q31, [x2, #16 * 30] // Save SVCR if we're doing SME - cbz x1, 1f + cbz x1, check_sve_out mrs x2, S3_3_C4_C2_2 adrp x3, svcr_out str x2, [x3, :lo12:svcr_out] -1: // Save ZA if it's enabled - uses x12 as scratch due to SME STR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, check_sve_out mov w12, #0 ldr x2, =za_out -2: _str_za 12, 2 +1: _str_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, check_sve_out adrp x2, zt_out add x2, x2, :lo12:zt_out _str_zt 2 -1: +check_sve_out: // Save the SVE state if we have some cbz x0, 1f diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c new file mode 100644 index 000000000000..7526de379081 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "bpf/libbpf.h" +#include "changes_pkt_data_freplace.skel.h" +#include "changes_pkt_data.skel.h" +#include <test_progs.h> + +static void print_verifier_log(const char *log) +{ + if (env.verbosity >= VERBOSE_VERY) + fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log); +} + +static void test_aux(const char *main_prog_name, + const char *to_be_replaced, + const char *replacement, + bool expect_load) +{ + struct changes_pkt_data_freplace *freplace = NULL; + struct bpf_program *freplace_prog = NULL; + struct bpf_program *main_prog = NULL; + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct changes_pkt_data *main = NULL; + char log[16*1024]; + int err; + + opts.kernel_log_buf = log; + opts.kernel_log_size = sizeof(log); + if (env.verbosity >= VERBOSE_SUPER) + opts.kernel_log_level = 1 | 2 | 4; + main = changes_pkt_data__open_opts(&opts); + if (!ASSERT_OK_PTR(main, "changes_pkt_data__open")) + goto out; + main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name); + if (!ASSERT_OK_PTR(main_prog, "main_prog")) + goto out; + bpf_program__set_autoload(main_prog, true); + err = changes_pkt_data__load(main); + print_verifier_log(log); + if (!ASSERT_OK(err, "changes_pkt_data__load")) + goto out; + freplace = changes_pkt_data_freplace__open_opts(&opts); + if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open")) + goto out; + freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement); + if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog")) + goto out; + bpf_program__set_autoload(freplace_prog, true); + bpf_program__set_autoattach(freplace_prog, true); + bpf_program__set_attach_target(freplace_prog, + bpf_program__fd(main_prog), + to_be_replaced); + err = changes_pkt_data_freplace__load(freplace); + print_verifier_log(log); + if (expect_load) { + ASSERT_OK(err, "changes_pkt_data_freplace__load"); + } else { + ASSERT_ERR(err, "changes_pkt_data_freplace__load"); + ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log"); + } + +out: + changes_pkt_data_freplace__destroy(freplace); + changes_pkt_data__destroy(main); +} + +/* There are two global subprograms in both changes_pkt_data.skel.h: + * - one changes packet data; + * - another does not. + * It is ok to freplace subprograms that change packet data with those + * that either do or do not. It is only ok to freplace subprograms + * that do not change packet data with those that do not as well. + * The below tests check outcomes for each combination of such freplace. + * Also test a case when main subprogram itself is replaced and is a single + * subprogram in a program. + */ +void test_changes_pkt_data_freplace(void) +{ + struct { + const char *main; + const char *to_be_replaced; + bool changes; + } mains[] = { + { "main_with_subprogs", "changes_pkt_data", true }, + { "main_with_subprogs", "does_not_change_pkt_data", false }, + { "main_changes", "main_changes", true }, + { "main_does_not_change", "main_does_not_change", false }, + }; + struct { + const char *func; + bool changes; + } replacements[] = { + { "changes_pkt_data", true }, + { "does_not_change_pkt_data", false } + }; + char buf[64]; + + for (int i = 0; i < ARRAY_SIZE(mains); ++i) { + for (int j = 0; j < ARRAY_SIZE(replacements); ++j) { + snprintf(buf, sizeof(buf), "%s_with_%s", + mains[i].to_be_replaced, replacements[j].func); + if (!test__start_subtest(buf)) + continue; + test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func, + mains[i].changes || !replacements[j].changes); + } + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c index 6fa19449297e..43676a9922dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c @@ -3,11 +3,14 @@ #include <test_progs.h> #include "raw_tp_null.skel.h" +#include "raw_tp_null_fail.skel.h" void test_raw_tp_null(void) { struct raw_tp_null *skel; + RUN_TESTS(raw_tp_null_fail); + skel = raw_tp_null__open_and_load(); if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index fdff0652d7ef..248754296d97 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -934,8 +934,10 @@ static void test_sockmap_same_sock(void) err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream); ASSERT_OK(err, "socketpair(af_unix, sock_stream)"); - if (err) + if (err) { + close(tcp); goto out; + } for (i = 0; i < 2; i++) { err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY); @@ -954,14 +956,14 @@ static void test_sockmap_same_sock(void) ASSERT_OK(err, "bpf_map_update_elem(tcp)"); } + close(tcp); err = bpf_map_delete_elem(map, &zero); - ASSERT_OK(err, "bpf_map_delete_elem(entry)"); + ASSERT_ERR(err, "bpf_map_delete_elem(entry)"); close(stream[0]); close(stream[1]); out: close(dgram); - close(tcp); close(udp); test_sockmap_pass_prog__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c new file mode 100644 index 000000000000..43cada48b28a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/changes_pkt_data.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline +long changes_pkt_data(struct __sk_buff *sk) +{ + return bpf_skb_pull_data(sk, 0); +} + +__noinline __weak +long does_not_change_pkt_data(struct __sk_buff *sk) +{ + return 0; +} + +SEC("?tc") +int main_with_subprogs(struct __sk_buff *sk) +{ + changes_pkt_data(sk); + does_not_change_pkt_data(sk); + return 0; +} + +SEC("?tc") +int main_changes(struct __sk_buff *sk) +{ + bpf_skb_pull_data(sk, 0); + return 0; +} + +SEC("?tc") +int main_does_not_change(struct __sk_buff *sk) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c new file mode 100644 index 000000000000..f9a622705f1b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("?freplace") +long changes_pkt_data(struct __sk_buff *sk) +{ + return bpf_skb_pull_data(sk, 0); +} + +SEC("?freplace") +long does_not_change_pkt_data(struct __sk_buff *sk) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c index 457f34c151e3..5927054b6dd9 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -17,16 +18,14 @@ int BPF_PROG(test_raw_tp_null, struct sk_buff *skb) if (task->pid != tid) return 0; - i = i + skb->mark + 1; - /* The compiler may move the NULL check before this deref, which causes - * the load to fail as deref of scalar. Prevent that by using a barrier. + /* If dead code elimination kicks in, the increment +=2 will be + * removed. For raw_tp programs attaching to tracepoints in kernel + * modules, we mark input arguments as PTR_MAYBE_NULL, so branch + * prediction should never kick in. */ - barrier(); - /* If dead code elimination kicks in, the increment below will - * be removed. For raw_tp programs, we mark input arguments as - * PTR_MAYBE_NULL, so branch prediction should never kick in. - */ - if (!skb) - i += 2; + asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;" + : [i]"+r"(i) + : [ctx]"r"(skb) + : "memory"); return 0; } diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c new file mode 100644 index 000000000000..38d669957bf1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +/* Ensure module parameter has PTR_MAYBE_NULL */ +SEC("tp_btf/bpf_testmod_test_raw_tp_null") +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") +int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) { + asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); + return 0; +} + +/* Check NULL marking */ +SEC("tp_btf/sched_pi_setprio") +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") +int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) { + asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c index d1a57f7d09bd..fe6249d99b31 100644 --- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c @@ -11,6 +11,8 @@ int subprog_tc(struct __sk_buff *skb) __sink(skb); __sink(ret); + /* let verifier know that 'subprog_tc' can change pointers to skb->data */ + bpf_skb_change_proto(skb, 0, 0); return ret; } diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index 5aaf2b065f86..bba3e37f749b 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -7,11 +7,7 @@ #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") -/* This used to be a failure test, but raw_tp nullable arguments can now - * directly be dereferenced, whether they have nullable annotation or not, - * and don't need to be explicitly checked. - */ -__success +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx) { return nullable_ctx->len; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c index a570e48b917a..28b939572cda 100644 --- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void btf_ctx_access_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\ + r2 = *(u64 *)(r1 + 8); /* load 2nd argument value (int pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); @@ -23,7 +23,43 @@ __success __retval(0) __naked void ctx_access_u32_pointer_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r2 = *(u64 *)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u32") +__failure __msg("size 4 must be 8") +__naked void ctx_access_u32_pointer_reject_32(void) +{ + asm volatile (" \ + r2 = *(u32 *)(r1 + 0); /* load 1st argument with narrow load */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u16") +__failure __msg("size 2 must be 8") +__naked void ctx_access_u32_pointer_reject_16(void) +{ + asm volatile (" \ + r2 = *(u16 *)(r1 + 0); /* load 1st argument with narrow load */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u8") +__failure __msg("size 1 must be 8") +__naked void ctx_access_u32_pointer_reject_8(void) +{ + asm volatile (" \ + r2 = *(u8 *)(r1 + 0); /* load 1st argument with narrow load */\ r0 = 0; \ exit; \ " ::: __clobber_all); diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c index ec79cbcfde91..87e51a215558 100644 --- a/tools/testing/selftests/bpf/progs/verifier_d_path.c +++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void d_path_accept(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ @@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe") __naked void d_path_reject(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c index d3e70e38e442..0d5e56dffabb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_sock.c +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -50,6 +50,13 @@ struct { __uint(map_flags, BPF_F_NO_PREALLOC); } sk_storage_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + SEC("cgroup/skb") __description("skb->sk: no NULL check") __failure __msg("invalid mem access 'sock_common_or_null'") @@ -1037,4 +1044,53 @@ __naked void sock_create_read_src_port(void) : __clobber_all); } +__noinline +long skb_pull_data2(struct __sk_buff *sk, __u32 len) +{ + return bpf_skb_pull_data(sk, len); +} + +__noinline +long skb_pull_data1(struct __sk_buff *sk, __u32 len) +{ + return skb_pull_data2(sk, len); +} + +/* global function calls bpf_skb_pull_data(), which invalidates packet + * pointers established before global function call. + */ +SEC("tc") +__failure __msg("invalid mem access") +int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + skb_pull_data1(sk, 0); + *p = 42; /* this is unsafe */ + return TCX_PASS; +} + +__noinline +int tail_call(struct __sk_buff *sk) +{ + bpf_tail_call_static(sk, &jmp_table, 0); + return 0; +} + +/* Tail calls invalidate packet pointers. */ +SEC("tc") +__failure __msg("invalid mem access") +int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + tail_call(sk); + *p = 42; /* this is unsafe */ + return TCX_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 30f29096e27c..9c5473abbd78 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -8,25 +8,28 @@ from lib.py import cmd import glob -def sys_get_queues(ifname) -> int: - folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*') +def sys_get_queues(ifname, qtype='rx') -> int: + folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') return len(folders) -def nl_get_queues(cfg, nl): +def nl_get_queues(cfg, nl, qtype='rx'): queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) if queues: - return len([q for q in queues if q['type'] == 'rx']) + return len([q for q in queues if q['type'] == qtype]) return None def get_queues(cfg, nl) -> None: - queues = nl_get_queues(cfg, nl) - if not queues: - raise KsftSkipEx('queue-get not supported by device') + snl = NetdevFamily(recv_size=4096) - expected = sys_get_queues(cfg.dev['ifname']) - ksft_eq(queues, expected) + for qtype in ['rx', 'tx']: + queues = nl_get_queues(cfg, snl, qtype) + if not queues: + raise KsftSkipEx('queue-get not supported by device') + + expected = sys_get_queues(cfg.dev['ifname'], qtype) + ksft_eq(queues, expected) def addremove_queues(cfg, nl) -> None: @@ -57,7 +60,7 @@ def addremove_queues(cfg, nl) -> None: def main() -> None: - with NetDrvEnv(__file__, queue_count=3) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 63e3c045a3b2..031ac9def6c0 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None: ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key) ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key) + # Sanity check the dumps + queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True) + # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}} + parsed = {} + for entry in queues: + ifindex = entry["ifindex"] + if ifindex not in parsed: + parsed[ifindex] = {"rx":[], "tx": []} + parsed[ifindex][entry["queue-type"]].append(entry['queue-id']) + # Now, validate + for ifindex, queues in parsed.items(): + for qtype in ['rx', 'tx']: + ksft_eq(len(queues[qtype]), len(set(queues[qtype])), + comment="repeated queue keys") + ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1, + comment="missing queue keys") + # Test invalid dumps # 0 is invalid with ksft_raises(NlError) as cm: @@ -158,7 +175,7 @@ def check_down(cfg) -> None: def main() -> None: - with NetDrvEnv(__file__) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, check_down], args=(cfg, )) diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index a0d689d58c57..076a7e8dc3eb 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -32,23 +32,23 @@ except ModuleNotFoundError as e: # Set schema='' to avoid jsonschema validation, it's slow # class EthtoolFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class RtnlFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetshaperFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } |