diff options
201 files changed, 1806 insertions, 1056 deletions
@@ -71,6 +71,9 @@ Ben M Cahill <ben.m.cahill@intel.com> Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net> Ben Widawsky <bwidawsk@kernel.org> <ben.widawsky@intel.com> Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com> +Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se> +Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org> +Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com> Björn Steinbrink <B.Steinbrink@gmx.de> Björn Töpel <bjorn@kernel.org> <bjorn.topel@gmail.com> Björn Töpel <bjorn@kernel.org> <bjorn.topel@intel.com> diff --git a/MAINTAINERS b/MAINTAINERS index f5ca4aefd184..72b9654f764c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2579,7 +2579,7 @@ W: http://www.armlinux.org.uk/ ARM/QUALCOMM SUPPORT M: Andy Gross <agross@kernel.org> -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> R: Konrad Dybcio <konrad.dybcio@somainline.org> L: linux-arm-msm@vger.kernel.org S: Maintained @@ -2670,7 +2670,6 @@ M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained W: http://www.armlinux.org.uk/ -F: arch/arm/include/asm/hardware/entry-macro-iomd.S F: arch/arm/include/asm/hardware/ioc.h F: arch/arm/include/asm/hardware/iomd.h F: arch/arm/include/asm/hardware/memc.h @@ -8944,7 +8943,7 @@ F: include/linux/hw_random.h HARDWARE SPINLOCK CORE M: Ohad Ben-Cohen <ohad@wizery.com> -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> R: Baolin Wang <baolin.wang7@gmail.com> L: linux-remoteproc@vger.kernel.org S: Maintained @@ -16126,7 +16125,7 @@ F: drivers/gpio/gpio-sama5d2-piobu.c F: drivers/pinctrl/pinctrl-at91* PIN CONTROLLER - QUALCOMM -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> L: linux-arm-msm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pinctrl/qcom,*.txt @@ -16819,7 +16818,7 @@ F: Documentation/devicetree/bindings/media/*camss* F: drivers/media/platform/qcom/camss/ QUALCOMM CLOCK DRIVERS -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> L: linux-arm-msm@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux.git @@ -17309,7 +17308,7 @@ S: Supported F: fs/reiserfs/ REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained @@ -17322,7 +17321,7 @@ F: include/linux/remoteproc.h F: include/linux/remoteproc/ REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM -M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Bjorn Andersson <andersson@kernel.org> M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained @@ -19961,7 +19960,7 @@ S: Supported F: drivers/net/team/ F: include/linux/if_team.h F: include/uapi/linux/if_team.h -F: tools/testing/selftests/net/team/ +F: tools/testing/selftests/drivers/net/team/ TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT M: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 7da42a5b959c..7e50fe633d8a 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -1502,8 +1502,7 @@ mmc1: mmc@0 { compatible = "ti,am335-sdhci"; ti,needs-special-reset; - dmas = <&edma_xbar 24 0 0 - &edma_xbar 25 0 0>; + dmas = <&edma 24 0>, <&edma 25 0>; dma-names = "tx", "rx"; interrupts = <64>; reg = <0x0 0x1000>; diff --git a/arch/arm/boot/dts/am5748.dtsi b/arch/arm/boot/dts/am5748.dtsi index c260aa1a85bd..a1f029e9d1f3 100644 --- a/arch/arm/boot/dts/am5748.dtsi +++ b/arch/arm/boot/dts/am5748.dtsi @@ -25,6 +25,10 @@ status = "disabled"; }; +&usb4_tm { + status = "disabled"; +}; + &atl_tm { status = "disabled"; }; diff --git a/arch/arm/boot/dts/integratorap-im-pd1.dts b/arch/arm/boot/dts/integratorap-im-pd1.dts index 4c22e4436271..cc514cf07bff 100644 --- a/arch/arm/boot/dts/integratorap-im-pd1.dts +++ b/arch/arm/boot/dts/integratorap-im-pd1.dts @@ -249,6 +249,7 @@ /* 640x480 16bpp @ 25.175MHz is 36827428 bytes/s */ max-memory-bandwidth = <40000000>; memory-region = <&impd1_ram>; + dma-ranges; port@0 { #address-cells = <1>; diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts index 9b652cc27b14..9148287fa0a9 100644 --- a/arch/arm/boot/dts/integratorap.dts +++ b/arch/arm/boot/dts/integratorap.dts @@ -160,6 +160,7 @@ pci: pciv3@62000000 { compatible = "arm,integrator-ap-pci", "v3,v360epc-pci"; + device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; @@ -261,7 +262,7 @@ lm0: bus@c0000000 { compatible = "simple-bus"; ranges = <0x00000000 0xc0000000 0x10000000>; - dma-ranges = <0x00000000 0x80000000 0x10000000>; + dma-ranges = <0x00000000 0xc0000000 0x10000000>; reg = <0xc0000000 0x10000000>; #address-cells = <1>; #size-cells = <1>; @@ -269,7 +270,7 @@ lm1: bus@d0000000 { compatible = "simple-bus"; ranges = <0x00000000 0xd0000000 0x10000000>; - dma-ranges = <0x00000000 0x80000000 0x10000000>; + dma-ranges = <0x00000000 0xd0000000 0x10000000>; reg = <0xd0000000 0x10000000>; #address-cells = <1>; #size-cells = <1>; @@ -277,7 +278,7 @@ lm2: bus@e0000000 { compatible = "simple-bus"; ranges = <0x00000000 0xe0000000 0x10000000>; - dma-ranges = <0x00000000 0x80000000 0x10000000>; + dma-ranges = <0x00000000 0xe0000000 0x10000000>; reg = <0xe0000000 0x10000000>; #address-cells = <1>; #size-cells = <1>; @@ -285,7 +286,7 @@ lm3: bus@f0000000 { compatible = "simple-bus"; ranges = <0x00000000 0xf0000000 0x10000000>; - dma-ranges = <0x00000000 0x80000000 0x10000000>; + dma-ranges = <0x00000000 0xf0000000 0x10000000>; reg = <0xf0000000 0x10000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/mach-sunplus/Kconfig b/arch/arm/mach-sunplus/Kconfig index 926cde5e3cd9..d0c2416e6f24 100644 --- a/arch/arm/mach-sunplus/Kconfig +++ b/arch/arm/mach-sunplus/Kconfig @@ -18,8 +18,8 @@ config SOC_SP7021 select ARM_PSCI select PINCTRL select PINCTRL_SPPCTL - select SERIAL_SUNPLUS - select SERIAL_SUNPLUS_CONSOLE + select SERIAL_SUNPLUS if TTY + select SERIAL_SUNPLUS_CONSOLE if TTY help Support for Sunplus SP7021 SoC. It is based on ARM 4-core Cortex-A7 with various peripherals (e.g.: I2C, SPI, SDIO, diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 13d7f267b289..dac3b69e314f 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -3374,6 +3374,8 @@ <&gem_noc MASTER_APPSS_PROC 0 &cnoc2 SLAVE_USB3_0 0>; interconnect-names = "usb-ddr", "apps-usb"; + wakeup-source; + usb_1_dwc3: usb@a600000 { compatible = "snps,dwc3"; reg = <0 0x0a600000 0 0xe000>; @@ -3384,7 +3386,6 @@ phys = <&usb_1_hsphy>, <&usb_1_ssphy>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; - wakeup-source; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index 84dc92dda0b8..4c404e2eafba 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -235,13 +235,13 @@ }; &remoteproc_adsp { - firmware-name = "qcom/sc8280xp/qcadsp8280.mbn"; + firmware-name = "qcom/sc8280xp/LENOVO/21BX/qcadsp8280.mbn"; status = "okay"; }; &remoteproc_nsp0 { - firmware-name = "qcom/sc8280xp/qccdsp8280.mbn"; + firmware-name = "qcom/sc8280xp/LENOVO/21BX/qccdsp8280.mbn"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 7d509ecd44da..916f12b799b7 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -3394,57 +3394,49 @@ compute-cb@1 { compatible = "qcom,fastrpc-compute-cb"; reg = <1>; - iommus = <&apps_smmu 0x1401 0x2040>, - <&apps_smmu 0x1421 0x0>, - <&apps_smmu 0x2001 0x420>, - <&apps_smmu 0x2041 0x0>; + iommus = <&apps_smmu 0x1001 0x0460>; }; compute-cb@2 { compatible = "qcom,fastrpc-compute-cb"; reg = <2>; - iommus = <&apps_smmu 0x2 0x3440>, - <&apps_smmu 0x22 0x3400>; + iommus = <&apps_smmu 0x1002 0x0460>; }; compute-cb@3 { compatible = "qcom,fastrpc-compute-cb"; reg = <3>; - iommus = <&apps_smmu 0x3 0x3440>, - <&apps_smmu 0x1423 0x0>, - <&apps_smmu 0x2023 0x0>; + iommus = <&apps_smmu 0x1003 0x0460>; }; compute-cb@4 { compatible = "qcom,fastrpc-compute-cb"; reg = <4>; - iommus = <&apps_smmu 0x4 0x3440>, - <&apps_smmu 0x24 0x3400>; + iommus = <&apps_smmu 0x1004 0x0460>; }; compute-cb@5 { compatible = "qcom,fastrpc-compute-cb"; reg = <5>; - iommus = <&apps_smmu 0x5 0x3440>, - <&apps_smmu 0x25 0x3400>; + iommus = <&apps_smmu 0x1005 0x0460>; }; compute-cb@6 { compatible = "qcom,fastrpc-compute-cb"; reg = <6>; - iommus = <&apps_smmu 0x6 0x3460>; + iommus = <&apps_smmu 0x1006 0x0460>; }; compute-cb@7 { compatible = "qcom,fastrpc-compute-cb"; reg = <7>; - iommus = <&apps_smmu 0x7 0x3460>; + iommus = <&apps_smmu 0x1007 0x0460>; }; compute-cb@8 { compatible = "qcom,fastrpc-compute-cb"; reg = <8>; - iommus = <&apps_smmu 0x8 0x3460>; + iommus = <&apps_smmu 0x1008 0x0460>; }; /* note: secure cb9 in downstream */ diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index e72a04411888..d9b08dfc2980 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -2128,7 +2128,7 @@ ufs_mem_phy: phy@1d87000 { compatible = "qcom,sm8350-qmp-ufs-phy"; - reg = <0 0x01d87000 0 0xe10>; + reg = <0 0x01d87000 0 0x1c4>; #address-cells = <2>; #size-cells = <2>; ranges; diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h index 6e8f6972ceb6..00db93edae1b 100644 --- a/arch/loongarch/include/asm/loongson.h +++ b/arch/loongarch/include/asm/loongson.h @@ -14,8 +14,6 @@ #include <asm/addrspace.h> #include <asm/bootinfo.h> -extern const struct plat_smp_ops loongson3_smp_ops; - #define LOONGSON_REG(x) \ (*(volatile u32 *)((char *)TO_UNCACHE(LOONGSON_REG_BASE) + (x))) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index c60eb66793e3..331864369e49 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -14,6 +14,8 @@ __REF + .align 12 + SYM_CODE_START(kernel_entry) # kernel entry point /* Config direct window and set PG */ diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index aa1c95aaf595..5010e95cef84 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -461,11 +461,9 @@ asmlinkage void noinstr do_watch(struct pt_regs *regs) asmlinkage void noinstr do_ri(struct pt_regs *regs) { - int status = -1; + int status = SIGILL; unsigned int opcode = 0; unsigned int __user *era = (unsigned int __user *)exception_era(regs); - unsigned long old_era = regs->csr_era; - unsigned long old_ra = regs->regs[1]; irqentry_state_t state = irqentry_enter(regs); local_irq_enable(); @@ -477,21 +475,12 @@ asmlinkage void noinstr do_ri(struct pt_regs *regs) die_if_kernel("Reserved instruction in kernel code", regs); - compute_return_era(regs); - if (unlikely(get_user(opcode, era) < 0)) { status = SIGSEGV; current->thread.error_code = 1; } - if (status < 0) - status = SIGILL; - - if (unlikely(status > 0)) { - regs->csr_era = old_era; /* Undo skip-over. */ - regs->regs[1] = old_ra; - force_sig(status); - } + force_sig(status); out: local_irq_disable(); diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 698274109c91..e712f80fe189 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -937,15 +937,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre pmd = *pmdp; pmd_clear(pmdp); - /* - * pmdp collapse_flush need to ensure that there are no parallel gup - * walk after this call. This is needed so that we can have stable - * page ref count when collapsing a page. We don't allow a collapse page - * if we have gup taken on the page. We can ensure that by sending IPI - * because gup walk happens with IRQ disabled. - */ - serialize_against_pte_lookup(vma->vm_mm); - radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); return pmd; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index c601939a74b1..c20d8cd47c48 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +EVENT_ATTR_STR(mem-loads, mem_ld_grt, "event=0xd0,umask=0x5,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_grt, "event=0xd0,umask=0x6"); + +static struct attribute *grt_mem_attrs[] = { + EVENT_PTR(mem_ld_grt), + EVENT_PTR(mem_st_grt), + NULL +}; + static struct extra_reg intel_grt_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), @@ -5975,6 +5984,36 @@ __init int intel_pmu_init(void) name = "Tremont"; break; + case INTEL_FAM6_ALDERLAKE_N: + x86_pmu.mid_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; + x86_pmu.extra_regs = intel_grt_extra_regs; + + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + + intel_pmu_pebs_data_source_grt(); + x86_pmu.pebs_latency_data = adl_latency_data_small; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + x86_pmu.limit_period = spr_limit_period; + td_attr = tnt_events_attrs; + mem_attr = grt_mem_attrs; + extra_attr = nhm_format_attr; + pr_cont("Gracemont events, "); + name = "gracemont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -6317,7 +6356,6 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ALDERLAKE_N: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: /* diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index de1f55d51784..ac973c6f82ad 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem) __intel_pmu_pebs_data_source_skl(pmem, pebs_data_source); } -static void __init intel_pmu_pebs_data_source_grt(u64 *data_source) +static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source) { data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); } +void __init intel_pmu_pebs_data_source_grt(void) +{ + __intel_pmu_pebs_data_source_grt(pebs_data_source); +} + void __init intel_pmu_pebs_data_source_adl(void) { u64 *data_source; @@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void) data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); - intel_pmu_pebs_data_source_grt(data_source); + __intel_pmu_pebs_data_source_grt(data_source); } static u64 precise_store_data(u64 status) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ba3d24a6a4ec..266143abcbd8 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem); void intel_pmu_pebs_data_source_adl(void); +void intel_pmu_pebs_data_source_grt(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index aeb38023a703..5d75fe229342 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -115,6 +115,9 @@ #define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_FAM6_RAPTORLAKE_S 0xBF +#define INTEL_FAM6_METEORLAKE 0xAC +#define INTEL_FAM6_METEORLAKE_L 0xAA + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 81a0211a372d..a73bced40e24 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,16 +21,6 @@ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_llc_shared_mask(int cpu) -{ - return per_cpu(cpu_llc_shared_map, cpu); -} - -static inline struct cpumask *cpu_l2c_shared_mask(int cpu) -{ - return per_cpu(cpu_l2c_shared_map, cpu); -} - DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); @@ -172,6 +162,16 @@ extern int safe_smp_processor_id(void); # define safe_smp_processor_id() smp_processor_id() #endif +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return per_cpu(cpu_llc_shared_map, cpu); +} + +static inline struct cpumask *cpu_l2c_shared_mask(int cpu) +{ + return per_cpu(cpu_l2c_shared_map, cpu); +} + #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) @@ -179,6 +179,11 @@ static inline int wbinvd_on_all_cpus(void) wbinvd(); return 0; } + +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return (struct cpumask *)cpumask_of(0); +} #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 62f6b8b7c4a5..4f3204364caa 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1319,22 +1319,23 @@ struct bp_patching_desc { atomic_t refs; }; -static struct bp_patching_desc *bp_desc; +static struct bp_patching_desc bp_desc; static __always_inline -struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +struct bp_patching_desc *try_get_desc(void) { - /* rcu_dereference */ - struct bp_patching_desc *desc = __READ_ONCE(*descp); + struct bp_patching_desc *desc = &bp_desc; - if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) + if (!arch_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; } -static __always_inline void put_desc(struct bp_patching_desc *desc) +static __always_inline void put_desc(void) { + struct bp_patching_desc *desc = &bp_desc; + smp_mb__before_atomic(); arch_atomic_dec(&desc->refs); } @@ -1367,15 +1368,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs) /* * Having observed our INT3 instruction, we now must observe - * bp_desc: + * bp_desc with non-zero refcount: * - * bp_desc = desc INT3 + * bp_desc.refs = 1 INT3 * WMB RMB - * write INT3 if (desc) + * write INT3 if (bp_desc.refs != 0) */ smp_rmb(); - desc = try_get_desc(&bp_desc); + desc = try_get_desc(); if (!desc) return 0; @@ -1429,7 +1430,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) ret = 1; out_put: - put_desc(desc); + put_desc(); return ret; } @@ -1460,18 +1461,20 @@ static int tp_vec_nr; */ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { - struct bp_patching_desc desc = { - .vec = tp, - .nr_entries = nr_entries, - .refs = ATOMIC_INIT(1), - }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ + bp_desc.vec = tp; + bp_desc.nr_entries = nr_entries; + + /* + * Corresponds to the implicit memory barrier in try_get_desc() to + * ensure reading a non-zero refcount provides up to date bp_desc data. + */ + atomic_set_release(&bp_desc.refs, 1); /* * Corresponding read barrier in int3 notifier for making sure the @@ -1559,12 +1562,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries text_poke_sync(); /* - * Remove and synchronize_rcu(), except we have a very primitive - * refcount based completion. + * Remove and wait for refs to be zero. */ - WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ - if (!atomic_dec_and_test(&desc.refs)) - atomic_cond_read_acquire(&desc.refs, !VAL); + if (!atomic_dec_and_test(&bp_desc.refs)) + atomic_cond_read_acquire(&bp_desc.refs, !VAL); } static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 24c1bb8eb196..8bdeae2fc309 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -344,8 +344,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, } va_page = sgx_encl_grow(encl, false); - if (IS_ERR(va_page)) + if (IS_ERR(va_page)) { + if (PTR_ERR(va_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; goto err_out_epc; + } if (va_page) list_add(&va_page->list, &encl->va_pages); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 515e2a5f25bb..0aad028f04d4 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list); * Reset post-kexec EPC pages to the uninitialized state. The pages are removed * from the input list, and made available for the page allocator. SECS pages * prepending their children in the input list are left intact. + * + * Return 0 when sanitization was successful or kthread was stopped, and the + * number of unsanitized pages otherwise. */ -static void __sgx_sanitize_pages(struct list_head *dirty_page_list) +static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list) { + unsigned long left_dirty = 0; struct sgx_epc_page *page; LIST_HEAD(dirty); int ret; @@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) /* dirty_page_list is thread-local, no need for a lock: */ while (!list_empty(dirty_page_list)) { if (kthread_should_stop()) - return; + return 0; page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); @@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) } else { /* The page is not yet clean - move to the dirty list. */ list_move_tail(&page->list, &dirty); + left_dirty++; } cond_resched(); } list_splice(&dirty, dirty_page_list); + return left_dirty; } static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -395,10 +401,7 @@ static int ksgxd(void *p) * required for SECS pages, whose child pages blocked EREMOVE. */ __sgx_sanitize_pages(&sgx_dirty_page_list); - __sgx_sanitize_pages(&sgx_dirty_page_list); - - /* sanity check: */ - WARN_ON(!list_empty(&sgx_dirty_page_list)); + WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list)); while (!kthread_should_stop()) { if (try_to_freeze()) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 4c1c2c06e96b..2796dde06302 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -902,8 +902,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = 0; } break; - case 9: - break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; union cpuid10_edx edx; diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index ad0139d25401..f1bb18617156 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -44,7 +44,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) * called from other contexts. */ pagefault_disable(); - ret = __copy_from_user_inatomic(to, from, n); + ret = raw_copy_from_user(to, from, n); pagefault_enable(); return ret; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index f8220fd2c169..829c1409ffbd 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -4,10 +4,12 @@ KCOV_INSTRUMENT_tlb.o := n KCOV_INSTRUMENT_mem_encrypt.o := n KCOV_INSTRUMENT_mem_encrypt_amd.o := n KCOV_INSTRUMENT_mem_encrypt_identity.o := n +KCOV_INSTRUMENT_pgprot.o := n KASAN_SANITIZE_mem_encrypt.o := n KASAN_SANITIZE_mem_encrypt_amd.o := n KASAN_SANITIZE_mem_encrypt_identity.o := n +KASAN_SANITIZE_pgprot.o := n # Disable KCSAN entirely, because otherwise we get warnings that some functions # reference __initdata sections. @@ -17,6 +19,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg CFLAGS_REMOVE_mem_encrypt_amd.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg +CFLAGS_REMOVE_pgprot.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 16a1663d02d4..9f40917c49ef 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -531,10 +531,27 @@ static void wait_for_freeze(void) /* No delay is needed if we are in guest */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; + /* + * Modern (>=Nehalem) Intel systems use ACPI via intel_idle, + * not this code. Assume that any Intel systems using this + * are ancient and may need the dummy wait. This also assumes + * that the motivating chipset issue was Intel-only. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; #endif - /* Dummy wait op - must do something useless after P_LVL2 read - because chipsets cannot guarantee that STPCLK# signal - gets asserted in time to freeze execution properly. */ + /* + * Dummy wait op - must do something useless after P_LVL2 read + * because chipsets cannot guarantee that STPCLK# signal gets + * asserted in time to freeze execution properly + * + * This workaround has been in place since the original ACPI + * implementation was merged, circa 2002. + * + * If a profile is pointing to this instruction, please first + * consider moving your system to a more modern idle + * mechanism. + */ inl(acpi_gbl_FADT.xpm_timer_block.address); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 826d41f341e4..c9a9aa607b62 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3988,6 +3988,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, + /* These specific Pioneer models have LPM issues */ + { "PIONEER BD-RW BDR-207M", NULL, ATA_HORKAGE_NOLPM }, + { "PIONEER BD-RW BDR-205", NULL, ATA_HORKAGE_NOLPM }, + /* Crucial BX100 SSD 500GB has broken LPM support */ { "CT500BX100SSD1", NULL, ATA_HORKAGE_NOLPM }, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 7a5fe41aa5ae..13b9d0fdd42c 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1018,26 +1018,25 @@ DEVICE_ATTR(sw_activity, S_IWUSR | S_IRUGO, ata_scsi_activity_show, EXPORT_SYMBOL_GPL(dev_attr_sw_activity); /** - * __ata_change_queue_depth - helper for ata_scsi_change_queue_depth - * @ap: ATA port to which the device change the queue depth + * ata_change_queue_depth - Set a device maximum queue depth + * @ap: ATA port of the target device + * @dev: target ATA device * @sdev: SCSI device to configure queue depth for * @queue_depth: new queue depth * - * libsas and libata have different approaches for associating a sdev to - * its ata_port. + * Helper to set a device maximum queue depth, usable with both libsas + * and libata. * */ -int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, - int queue_depth) +int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev, + struct scsi_device *sdev, int queue_depth) { - struct ata_device *dev; unsigned long flags; - if (queue_depth < 1 || queue_depth == sdev->queue_depth) + if (!dev || !ata_dev_enabled(dev)) return sdev->queue_depth; - dev = ata_scsi_find_dev(ap, sdev); - if (!dev || !ata_dev_enabled(dev)) + if (queue_depth < 1 || queue_depth == sdev->queue_depth) return sdev->queue_depth; /* NCQ enabled? */ @@ -1059,7 +1058,7 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, return scsi_change_queue_depth(sdev, queue_depth); } -EXPORT_SYMBOL_GPL(__ata_change_queue_depth); +EXPORT_SYMBOL_GPL(ata_change_queue_depth); /** * ata_scsi_change_queue_depth - SCSI callback for queue depth config @@ -1080,7 +1079,8 @@ int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth) { struct ata_port *ap = ata_shost_to_port(sdev->host); - return __ata_change_queue_depth(ap, sdev, queue_depth); + return ata_change_queue_depth(ap, ata_scsi_find_dev(ap, sdev), + sdev, queue_depth); } EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 29e2f55c6faa..ff9602a0e54e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1055,6 +1055,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_dma_need_drain); int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) { struct request_queue *q = sdev->request_queue; + int depth = 1; if (!ata_id_has_unload(dev->id)) dev->flags |= ATA_DFLAG_NO_UNLOAD; @@ -1100,13 +1101,10 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) if (dev->flags & ATA_DFLAG_AN) set_bit(SDEV_EVT_MEDIA_CHANGE, sdev->supported_events); - if (dev->flags & ATA_DFLAG_NCQ) { - int depth; - + if (dev->flags & ATA_DFLAG_NCQ) depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id)); - depth = min(ATA_MAX_QUEUE, depth); - scsi_change_queue_depth(sdev, depth); - } + depth = min(ATA_MAX_QUEUE, depth); + scsi_change_queue_depth(sdev, depth); if (dev->flags & ATA_DFLAG_TRUSTED) sdev->security_supported = 1; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 30255fcaf181..dd9a05174726 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -322,14 +322,14 @@ static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx, if (unlikely(status)) return status; - blk_mq_start_request(req); - vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr); if (unlikely(vbr->sg_table.nents < 0)) { virtblk_cleanup_cmd(req); return BLK_STS_RESOURCE; } + blk_mq_start_request(req); + return BLK_STS_OK; } @@ -391,8 +391,7 @@ static bool virtblk_prep_rq_batch(struct request *req) } static bool virtblk_add_req_batch(struct virtio_blk_vq *vq, - struct request **rqlist, - struct request **requeue_list) + struct request **rqlist) { unsigned long flags; int err; @@ -408,7 +407,7 @@ static bool virtblk_add_req_batch(struct virtio_blk_vq *vq, if (err) { virtblk_unmap_data(req, vbr); virtblk_cleanup_cmd(req); - rq_list_add(requeue_list, req); + blk_mq_requeue_request(req, true); } } @@ -436,7 +435,7 @@ static void virtio_queue_rqs(struct request **rqlist) if (!next || req->mq_hctx != next->mq_hctx) { req->rq_next = NULL; - kick = virtblk_add_req_batch(vq, rqlist, &requeue_list); + kick = virtblk_add_req_batch(vq, rqlist); if (kick) virtqueue_notify(vq->vq); diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c index 1a098db12062..680f9d8d357c 100644 --- a/drivers/clk/bcm/clk-iproc-pll.c +++ b/drivers/clk/bcm/clk-iproc-pll.c @@ -726,6 +726,7 @@ void iproc_pll_clk_setup(struct device_node *node, const char *parent_name; struct iproc_clk *iclk_array; struct clk_hw_onecell_data *clk_data; + const char *clk_name; if (WARN_ON(!pll_ctrl) || WARN_ON(!clk_ctrl)) return; @@ -773,7 +774,12 @@ void iproc_pll_clk_setup(struct device_node *node, iclk = &iclk_array[0]; iclk->pll = pll; - init.name = node->name; + ret = of_property_read_string_index(node, "clock-output-names", + 0, &clk_name); + if (WARN_ON(ret)) + goto err_pll_register; + + init.name = clk_name; init.ops = &iproc_pll_ops; init.flags = 0; parent_name = of_clk_get_parent_name(node, 0); @@ -793,13 +799,11 @@ void iproc_pll_clk_setup(struct device_node *node, goto err_pll_register; clk_data->hws[0] = &iclk->hw; + parent_name = clk_name; /* now initialize and register all leaf clocks */ for (i = 1; i < num_clks; i++) { - const char *clk_name; - memset(&init, 0, sizeof(init)); - parent_name = node->name; ret = of_property_read_string_index(node, "clock-output-names", i, &clk_name); diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c index fc1bd23d4583..598f3cf4eba4 100644 --- a/drivers/clk/imx/clk-imx6sx.c +++ b/drivers/clk/imx/clk-imx6sx.c @@ -280,13 +280,13 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node) hws[IMX6SX_CLK_SSI3_SEL] = imx_clk_hw_mux("ssi3_sel", base + 0x1c, 14, 2, ssi_sels, ARRAY_SIZE(ssi_sels)); hws[IMX6SX_CLK_SSI2_SEL] = imx_clk_hw_mux("ssi2_sel", base + 0x1c, 12, 2, ssi_sels, ARRAY_SIZE(ssi_sels)); hws[IMX6SX_CLK_SSI1_SEL] = imx_clk_hw_mux("ssi1_sel", base + 0x1c, 10, 2, ssi_sels, ARRAY_SIZE(ssi_sels)); - hws[IMX6SX_CLK_QSPI1_SEL] = imx_clk_hw_mux_flags("qspi1_sel", base + 0x1c, 7, 3, qspi1_sels, ARRAY_SIZE(qspi1_sels), CLK_SET_RATE_PARENT); + hws[IMX6SX_CLK_QSPI1_SEL] = imx_clk_hw_mux("qspi1_sel", base + 0x1c, 7, 3, qspi1_sels, ARRAY_SIZE(qspi1_sels)); hws[IMX6SX_CLK_PERCLK_SEL] = imx_clk_hw_mux("perclk_sel", base + 0x1c, 6, 1, perclk_sels, ARRAY_SIZE(perclk_sels)); hws[IMX6SX_CLK_VID_SEL] = imx_clk_hw_mux("vid_sel", base + 0x20, 21, 3, vid_sels, ARRAY_SIZE(vid_sels)); hws[IMX6SX_CLK_ESAI_SEL] = imx_clk_hw_mux("esai_sel", base + 0x20, 19, 2, audio_sels, ARRAY_SIZE(audio_sels)); hws[IMX6SX_CLK_CAN_SEL] = imx_clk_hw_mux("can_sel", base + 0x20, 8, 2, can_sels, ARRAY_SIZE(can_sels)); hws[IMX6SX_CLK_UART_SEL] = imx_clk_hw_mux("uart_sel", base + 0x24, 6, 1, uart_sels, ARRAY_SIZE(uart_sels)); - hws[IMX6SX_CLK_QSPI2_SEL] = imx_clk_hw_mux_flags("qspi2_sel", base + 0x2c, 15, 3, qspi2_sels, ARRAY_SIZE(qspi2_sels), CLK_SET_RATE_PARENT); + hws[IMX6SX_CLK_QSPI2_SEL] = imx_clk_hw_mux("qspi2_sel", base + 0x2c, 15, 3, qspi2_sels, ARRAY_SIZE(qspi2_sels)); hws[IMX6SX_CLK_SPDIF_SEL] = imx_clk_hw_mux("spdif_sel", base + 0x30, 20, 2, audio_sels, ARRAY_SIZE(audio_sels)); hws[IMX6SX_CLK_AUDIO_SEL] = imx_clk_hw_mux("audio_sel", base + 0x30, 7, 2, audio_sels, ARRAY_SIZE(audio_sels)); hws[IMX6SX_CLK_ENET_PRE_SEL] = imx_clk_hw_mux("enet_pre_sel", base + 0x34, 15, 3, enet_pre_sels, ARRAY_SIZE(enet_pre_sels)); diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index f5c9fa40491c..dcc41d178238 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -332,7 +332,7 @@ static struct platform_driver imx93_clk_driver = { .driver = { .name = "imx93-ccm", .suppress_bind_attrs = true, - .of_match_table = of_match_ptr(imx93_clk_of_match), + .of_match_table = imx93_clk_of_match, }, }; module_platform_driver(imx93_clk_driver); diff --git a/drivers/clk/ingenic/tcu.c b/drivers/clk/ingenic/tcu.c index 201bf6e6b6e0..d5544cbc5c48 100644 --- a/drivers/clk/ingenic/tcu.c +++ b/drivers/clk/ingenic/tcu.c @@ -101,15 +101,11 @@ static bool ingenic_tcu_enable_regs(struct clk_hw *hw) bool enabled = false; /* - * If the SoC has no global TCU clock, we must ungate the channel's - * clock to be able to access its registers. - * If we have a TCU clock, it will be enabled automatically as it has - * been attached to the regmap. + * According to the programming manual, a timer channel's registers can + * only be accessed when the channel's stop bit is clear. */ - if (!tcu->clk) { - enabled = !!ingenic_tcu_is_enabled(hw); - regmap_write(tcu->map, TCU_REG_TSCR, BIT(info->gate_bit)); - } + enabled = !!ingenic_tcu_is_enabled(hw); + regmap_write(tcu->map, TCU_REG_TSCR, BIT(info->gate_bit)); return enabled; } @@ -120,8 +116,7 @@ static void ingenic_tcu_disable_regs(struct clk_hw *hw) const struct ingenic_tcu_clk_info *info = tcu_clk->info; struct ingenic_tcu *tcu = tcu_clk->tcu; - if (!tcu->clk) - regmap_write(tcu->map, TCU_REG_TSSR, BIT(info->gate_bit)); + regmap_write(tcu->map, TCU_REG_TSSR, BIT(info->gate_bit)); } static u8 ingenic_tcu_get_parent(struct clk_hw *hw) diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index 070c3b896559..b6b89413e090 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -239,6 +239,11 @@ static const struct clk_ops mpfs_clk_cfg_ops = { .hw.init = CLK_HW_INIT(_name, _parent, &mpfs_clk_cfg_ops, 0), \ } +#define CLK_CPU_OFFSET 0u +#define CLK_AXI_OFFSET 1u +#define CLK_AHB_OFFSET 2u +#define CLK_RTCREF_OFFSET 3u + static struct mpfs_cfg_hw_clock mpfs_cfg_clks[] = { CLK_CFG(CLK_CPU, "clk_cpu", "clk_msspll", 0, 2, mpfs_div_cpu_axi_table, 0, REG_CLOCK_CONFIG_CR), @@ -362,7 +367,7 @@ static const struct clk_ops mpfs_periph_clk_ops = { _flags), \ } -#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].hw) +#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT##_OFFSET].hw) /* * Critical clocks: @@ -370,6 +375,8 @@ static const struct clk_ops mpfs_periph_clk_ops = { * trap handler * - CLK_MMUART0: reserved by the hss * - CLK_DDRC: provides clock to the ddr subsystem + * - CLK_RTC: the onboard RTC's AHB bus clock must be kept running as the rtc will stop + * if the AHB interface clock is disabled * - CLK_FICx: these provide the processor side clocks to the "FIC" (Fabric InterConnect) * clock domain crossers which provide the interface to the FPGA fabric. Disabling them * causes the FPGA fabric to go into reset. @@ -394,7 +401,7 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_CAN0, "clk_periph_can0", PARENT_CLK(AHB), 14, 0), CLK_PERIPH(CLK_CAN1, "clk_periph_can1", PARENT_CLK(AHB), 15, 0), CLK_PERIPH(CLK_USB, "clk_periph_usb", PARENT_CLK(AHB), 16, 0), - CLK_PERIPH(CLK_RTC, "clk_periph_rtc", PARENT_CLK(AHB), 18, 0), + CLK_PERIPH(CLK_RTC, "clk_periph_rtc", PARENT_CLK(AHB), 18, CLK_IS_CRITICAL), CLK_PERIPH(CLK_QSPI, "clk_periph_qspi", PARENT_CLK(AHB), 19, 0), CLK_PERIPH(CLK_GPIO0, "clk_periph_gpio0", PARENT_CLK(AHB), 20, 0), CLK_PERIPH(CLK_GPIO1, "clk_periph_gpio1", PARENT_CLK(AHB), 21, 0), diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index 30056da3e0af..42568c616181 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1191,9 +1191,13 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) if (IS_ERR(reg)) return PTR_ERR(reg); - /* Force PLL_GPU output divider bits to 0 */ + /* + * Force PLL_GPU output divider bits to 0 and adjust + * multiplier to sensible default value of 432 MHz. + */ val = readl(reg + SUN50I_H6_PLL_GPU_REG); - val &= ~BIT(0); + val &= ~(GENMASK(15, 8) | BIT(0)); + val |= 17 << 8; writel(val, reg + SUN50I_H6_PLL_GPU_REG); /* Force GPU_CLK divider bits to 0 */ diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2a60d0525cde..168195672e2e 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -56,6 +56,10 @@ static void virtio_crypto_akcipher_finalize_req( struct virtio_crypto_akcipher_request *vc_akcipher_req, struct akcipher_request *req, int err) { + kfree(vc_akcipher_req->src_buf); + kfree(vc_akcipher_req->dst_buf); + vc_akcipher_req->src_buf = NULL; + vc_akcipher_req->dst_buf = NULL; virtcrypto_clear_request(&vc_akcipher_req->base); crypto_finalize_akcipher_request(vc_akcipher_req->base.dataq->engine, req, err); diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c index 4e27c3d66a83..0e05a79de82d 100644 --- a/drivers/firmware/arm_scmi/scmi_pm_domain.c +++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c @@ -8,7 +8,6 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/module.h> -#include <linux/pm_clock.h> #include <linux/pm_domain.h> #include <linux/scmi_protocol.h> @@ -53,27 +52,6 @@ static int scmi_pd_power_off(struct generic_pm_domain *domain) return scmi_pd_power(domain, false); } -static int scmi_pd_attach_dev(struct generic_pm_domain *pd, struct device *dev) -{ - int ret; - - ret = pm_clk_create(dev); - if (ret) - return ret; - - ret = of_pm_clk_add_clks(dev); - if (ret >= 0) - return 0; - - pm_clk_destroy(dev); - return ret; -} - -static void scmi_pd_detach_dev(struct generic_pm_domain *pd, struct device *dev) -{ - pm_clk_destroy(dev); -} - static int scmi_pm_domain_probe(struct scmi_device *sdev) { int num_domains, i; @@ -124,10 +102,6 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) scmi_pd->genpd.name = scmi_pd->name; scmi_pd->genpd.power_off = scmi_pd_power_off; scmi_pd->genpd.power_on = scmi_pd_power_on; - scmi_pd->genpd.attach_dev = scmi_pd_attach_dev; - scmi_pd->genpd.detach_dev = scmi_pd_detach_dev; - scmi_pd->genpd.flags = GENPD_FLAG_PM_CLK | - GENPD_FLAG_ACTIVE_WAKEUP; pm_genpd_init(&scmi_pd->genpd, NULL, state == SCMI_POWER_STATE_GENERIC_OFF); diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index aa126ab80f0c..1bb317b8dcce 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -790,8 +790,12 @@ static int mvebu_pwm_probe(struct platform_device *pdev, u32 offset; u32 set; - if (of_device_is_compatible(mvchip->chip.of_node, - "marvell,armada-370-gpio")) { + if (mvchip->soc_variant == MVEBU_GPIO_SOC_VARIANT_A8K) { + int ret = of_property_read_u32(dev->of_node, + "marvell,pwm-offset", &offset); + if (ret < 0) + return 0; + } else { /* * There are only two sets of PWM configuration registers for * all the GPIO lines on those SoCs which this driver reserves @@ -801,13 +805,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev, if (!platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm")) return 0; offset = 0; - } else if (mvchip->soc_variant == MVEBU_GPIO_SOC_VARIANT_A8K) { - int ret = of_property_read_u32(dev->of_node, - "marvell,pwm-offset", &offset); - if (ret < 0) - return 0; - } else { - return 0; } if (IS_ERR(mvchip->clk)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 130060834b4e..48bd660ddb85 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1050,6 +1050,10 @@ bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { if (adev->flags & AMD_IS_APU) return false; + + if (amdgpu_sriov_vf(adev)) + return false; + return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index be7aff2d4a57..25e1f5ed7ead 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3152,7 +3152,8 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev) continue; if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC || - adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) { + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH || + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP && amdgpu_sriov_vf(adev))) { r = adev->ip_blocks[i].version->funcs->resume(adev); if (r) { @@ -4064,12 +4065,20 @@ static void amdgpu_device_evict_resources(struct amdgpu_device *adev) int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) { struct amdgpu_device *adev = drm_to_adev(dev); + int r = 0; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; adev->in_suspend = true; + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_fini_data_exchange(adev); + r = amdgpu_virt_request_full_gpu(adev, false); + if (r) + return r; + } + if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3)) DRM_WARN("smart shift update failed\n"); @@ -4093,6 +4102,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) amdgpu_device_ip_suspend_phase2(adev); + if (amdgpu_sriov_vf(adev)) + amdgpu_virt_release_full_gpu(adev, false); + return 0; } @@ -4111,6 +4123,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) struct amdgpu_device *adev = drm_to_adev(dev); int r = 0; + if (amdgpu_sriov_vf(adev)) { + r = amdgpu_virt_request_full_gpu(adev, true); + if (r) + return r; + } + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; @@ -4125,6 +4143,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) } r = amdgpu_device_ip_resume(adev); + + /* no matter what r is, always need to properly release full GPU */ + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_init_data_exchange(adev); + amdgpu_virt_release_full_gpu(adev, true); + } + if (r) { dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 8adeb7469f1e..d0d99ed607dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -400,7 +400,6 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring) /* We are not protected by ring lock when reading the last sequence * but it's ok to report slightly wrong fence count here. */ - amdgpu_fence_process(ring); emitted = 0x100000000ull; emitted -= atomic_read(&ring->fence_drv.last_seq); emitted += READ_ONCE(ring->fence_drv.sync_seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 23a696d38390..de5b936b016d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -304,6 +304,10 @@ struct amdgpu_gfx { uint32_t rlc_srlg_feature_version; uint32_t rlc_srls_fw_version; uint32_t rlc_srls_feature_version; + uint32_t rlcp_ucode_version; + uint32_t rlcp_ucode_feature_version; + uint32_t rlcv_ucode_version; + uint32_t rlcv_ucode_feature_version; uint32_t mec_feature_version; uint32_t mec2_feature_version; bool mec_fw_write_wait; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 7b46f6bf4187..ad980f4b66e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -222,6 +222,8 @@ struct mes_add_queue_input { uint64_t tba_addr; uint64_t tma_addr; uint32_t is_kfd_process; + uint32_t is_aql_queue; + uint32_t queue_size; }; struct mes_remove_queue_input { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index 6373bfb47d55..e23f6192c50e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -272,3 +272,267 @@ void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev) &adev->gfx.rlc.cp_table_gpu_addr, (void **)&adev->gfx.rlc.cp_table_ptr); } + +static int amdgpu_gfx_rlc_init_microcode_v2_0(struct amdgpu_device *adev) +{ + const struct common_firmware_header *common_hdr; + const struct rlc_firmware_header_v2_0 *rlc_hdr; + struct amdgpu_firmware_info *info; + unsigned int *tmp; + unsigned int i; + + rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; + + adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); + adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); + adev->gfx.rlc.save_and_restore_offset = + le32_to_cpu(rlc_hdr->save_and_restore_offset); + adev->gfx.rlc.clear_state_descriptor_offset = + le32_to_cpu(rlc_hdr->clear_state_descriptor_offset); + adev->gfx.rlc.avail_scratch_ram_locations = + le32_to_cpu(rlc_hdr->avail_scratch_ram_locations); + adev->gfx.rlc.reg_restore_list_size = + le32_to_cpu(rlc_hdr->reg_restore_list_size); + adev->gfx.rlc.reg_list_format_start = + le32_to_cpu(rlc_hdr->reg_list_format_start); + adev->gfx.rlc.reg_list_format_separate_start = + le32_to_cpu(rlc_hdr->reg_list_format_separate_start); + adev->gfx.rlc.starting_offsets_start = + le32_to_cpu(rlc_hdr->starting_offsets_start); + adev->gfx.rlc.reg_list_format_size_bytes = + le32_to_cpu(rlc_hdr->reg_list_format_size_bytes); + adev->gfx.rlc.reg_list_size_bytes = + le32_to_cpu(rlc_hdr->reg_list_size_bytes); + adev->gfx.rlc.register_list_format = + kmalloc(adev->gfx.rlc.reg_list_format_size_bytes + + adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL); + if (!adev->gfx.rlc.register_list_format) { + dev_err(adev->dev, "failed to allocate memory for rlc register_list_format\n"); + return -ENOMEM; + } + + tmp = (unsigned int *)((uintptr_t)rlc_hdr + + le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); + for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++) + adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]); + + adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i; + + tmp = (unsigned int *)((uintptr_t)rlc_hdr + + le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); + for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) + adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_G; + info->fw = adev->gfx.rlc_fw; + if (info->fw) { + common_hdr = (const struct common_firmware_header *)info->fw->data; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(common_hdr->ucode_size_bytes), PAGE_SIZE); + } + } + + return 0; +} + +static void amdgpu_gfx_rlc_init_microcode_v2_1(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_1 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver); + adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver); + adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes); + adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes); + adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver); + adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver); + adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes); + adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes); + adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver); + adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver); + adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes); + adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes); + adev->gfx.rlc.reg_list_format_direct_reg_list_length = + le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.save_restore_list_gpm_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.save_restore_list_srm_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_2(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_2 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); + adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); + adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); + adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.rlc_iram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.rlc_dram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_3(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_3 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data; + adev->gfx.rlcp_ucode_version = le32_to_cpu(rlc_hdr->rlcp_ucode_version); + adev->gfx.rlcp_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcp_ucode_feature_version); + adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes); + adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes); + + adev->gfx.rlcv_ucode_version = le32_to_cpu(rlc_hdr->rlcv_ucode_version); + adev->gfx.rlcv_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcv_ucode_feature_version); + adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes); + adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.rlcp_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_P; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.rlcv_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_V; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE); + } + } +} + +static void amdgpu_gfx_rlc_init_microcode_v2_4(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_4 *rlc_hdr; + struct amdgpu_firmware_info *info; + + rlc_hdr = (const struct rlc_firmware_header_v2_4 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.global_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->global_tap_delays_ucode_size_bytes); + adev->gfx.rlc.global_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->global_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se0_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se0_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se1_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se1_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se2_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se2_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_offset_bytes); + adev->gfx.rlc.se3_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_size_bytes); + adev->gfx.rlc.se3_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_offset_bytes); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + + if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS]; + info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE); + } + } +} + +int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev, + uint16_t version_major, + uint16_t version_minor) +{ + int err; + + if (version_major < 2) { + /* only support rlc_hdr v2.x and onwards */ + dev_err(adev->dev, "unsupported rlc fw hdr\n"); + return -EINVAL; + } + + /* is_rlc_v2_1 is still used in APU code path */ + if (version_major == 2 && version_minor == 1) + adev->gfx.rlc.is_rlc_v2_1 = true; + + if (version_minor >= 0) { + err = amdgpu_gfx_rlc_init_microcode_v2_0(adev); + if (err) { + dev_err(adev->dev, "fail to init rlc v2_0 microcode\n"); + return err; + } + } + if (version_minor >= 1) + amdgpu_gfx_rlc_init_microcode_v2_1(adev); + if (version_minor >= 2) + amdgpu_gfx_rlc_init_microcode_v2_2(adev); + if (version_minor == 3) + amdgpu_gfx_rlc_init_microcode_v2_3(adev); + if (version_minor == 4) + amdgpu_gfx_rlc_init_microcode_v2_4(adev); + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index 03ac36b2c2cf..23f060db9255 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -267,5 +267,7 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev); int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev); void amdgpu_gfx_rlc_setup_cp_table(struct amdgpu_device *adev); void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev); - +int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev, + uint16_t version_major, + uint16_t version_minor); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 96b6cf4c4d54..59edf32f775e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -260,8 +260,12 @@ struct rlc_firmware_header_v2_2 { /* version_major=2, version_minor=3 */ struct rlc_firmware_header_v2_3 { struct rlc_firmware_header_v2_2 v2_2; + uint32_t rlcp_ucode_version; + uint32_t rlcp_ucode_feature_version; uint32_t rlcp_ucode_size_bytes; uint32_t rlcp_ucode_offset_bytes; + uint32_t rlcv_ucode_version; + uint32_t rlcv_ucode_feature_version; uint32_t rlcv_ucode_size_bytes; uint32_t rlcv_ucode_offset_bytes; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f36e4f08db6d..0b52af415b28 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -191,7 +191,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) fw_name = FIRMWARE_VCN4_0_2; if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = false; + adev->vcn.indirect_sram = true; break; case IP_VERSION(4, 0, 4): fw_name = FIRMWARE_VCN4_0_4; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f6b1bb40e503..daf8ba8235cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -474,49 +474,6 @@ static void gfx_v11_0_free_microcode(struct amdgpu_device *adev) kfree(adev->gfx.rlc.register_list_format); } -static void gfx_v11_0_init_rlc_ext_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_1 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver); - adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver); - adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes); - adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes); - adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver); - adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver); - adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes); - adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes); - adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver); - adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver); - adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes); - adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes); - adev->gfx.rlc.reg_list_format_direct_reg_list_length = - le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); -} - -static void gfx_v11_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_2 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); - adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); - adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); - adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); -} - -static void gfx_v11_0_init_rlcp_rlcv_microcode(struct amdgpu_device *adev) -{ - const struct rlc_firmware_header_v2_3 *rlc_hdr; - - rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data; - adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes); - adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes); - adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes); - adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes); -} - static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) { char fw_name[40]; @@ -527,8 +484,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) const struct gfx_firmware_header_v1_0 *cp_hdr; const struct gfx_firmware_header_v2_0 *cp_hdr_v2_0; const struct rlc_firmware_header_v2_0 *rlc_hdr; - unsigned int *tmp = NULL; - unsigned int i = 0; uint16_t version_major; uint16_t version_minor; @@ -583,58 +538,14 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) if (err) goto out; err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + if (err) + goto out; rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); - - adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); - adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); - adev->gfx.rlc.save_and_restore_offset = - le32_to_cpu(rlc_hdr->save_and_restore_offset); - adev->gfx.rlc.clear_state_descriptor_offset = - le32_to_cpu(rlc_hdr->clear_state_descriptor_offset); - adev->gfx.rlc.avail_scratch_ram_locations = - le32_to_cpu(rlc_hdr->avail_scratch_ram_locations); - adev->gfx.rlc.reg_restore_list_size = - le32_to_cpu(rlc_hdr->reg_restore_list_size); - adev->gfx.rlc.reg_list_format_start = - le32_to_cpu(rlc_hdr->reg_list_format_start); - adev->gfx.rlc.reg_list_format_separate_start = - le32_to_cpu(rlc_hdr->reg_list_format_separate_start); - adev->gfx.rlc.starting_offsets_start = - le32_to_cpu(rlc_hdr->starting_offsets_start); - adev->gfx.rlc.reg_list_format_size_bytes = - le32_to_cpu(rlc_hdr->reg_list_format_size_bytes); - adev->gfx.rlc.reg_list_size_bytes = - le32_to_cpu(rlc_hdr->reg_list_size_bytes); - adev->gfx.rlc.register_list_format = - kmalloc(adev->gfx.rlc.reg_list_format_size_bytes + - adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL); - if (!adev->gfx.rlc.register_list_format) { - err = -ENOMEM; + err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor); + if (err) goto out; - } - - tmp = (unsigned int *)((uintptr_t)rlc_hdr + - le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes)); - for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++) - adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]); - - adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i; - - tmp = (unsigned int *)((uintptr_t)rlc_hdr + - le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes)); - for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) - adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); - - if (version_major == 2) { - if (version_minor >= 1) - gfx_v11_0_init_rlc_ext_microcode(adev); - if (version_minor >= 2) - gfx_v11_0_init_rlc_iram_dram_microcode(adev); - if (version_minor == 3) - gfx_v11_0_init_rlcp_rlcv_microcode(adev); - } } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix); @@ -769,60 +680,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) adev->firmware.fw_size += ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE); } - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_G; - info->fw = adev->gfx.rlc_fw; - if (info->fw) { - header = (const struct common_firmware_header *)info->fw->data; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); - } - if (adev->gfx.rlc.save_restore_list_gpm_size_bytes && - adev->gfx.rlc.save_restore_list_srm_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlc_iram_ucode_size_bytes && - adev->gfx.rlc.rlc_dram_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlcp_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_P; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE); - } - - if (adev->gfx.rlc.rlcv_ucode_size_bytes) { - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V]; - info->ucode_id = AMDGPU_UCODE_ID_RLC_V; - info->fw = adev->gfx.rlc_fw; - adev->firmware.fw_size += - ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE); - } } out: @@ -5260,6 +5117,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { u32 reg, data; + amdgpu_gfx_off_ctrl(adev, false); + reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); if (amdgpu_sriov_is_pp_one_vf(adev)) data = RREG32_NO_KIQ(reg); @@ -5273,6 +5132,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data); else WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data); + + amdgpu_gfx_off_ctrl(adev, true); } static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fc9c1043244c..037af8352677 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -5597,7 +5597,7 @@ static void gfx_v9_0_ring_emit_patch_cond_exec(struct amdgpu_ring *ring, unsigne BUG_ON(offset > ring->buf_mask); BUG_ON(ring->ring[offset] != 0x55aa55aa); - cur = (ring->wptr & ring->buf_mask) - 1; + cur = (ring->wptr - 1) & ring->buf_mask; if (likely(cur > offset)) ring->ring[offset] = cur - offset; else diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index cc3fdbbcd314..f92744b8d79d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -185,6 +185,10 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; mes_add_queue_pkt.trap_en = 1; + /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ + mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; + mes_add_queue_pkt.gds_size = input->queue_size; + return mes_v11_0_submit_pkt_and_poll_completion(mes, &mes_add_queue_pkt, sizeof(mes_add_queue_pkt), offsetof(union MESAPI__ADD_QUEUE, api_status)); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 2e50db3b761e..6e564b549b9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -625,6 +625,7 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; adev->external_rev_id = adev->rev_id + 0x1; break; 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 e83725a28106..007a3db69df1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -205,6 +205,8 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, } queue_input.is_kfd_process = 1; + queue_input.is_aql_queue = (q->properties.format == KFD_QUEUE_FORMAT_AQL); + queue_input.queue_size = q->properties.queue_size >> 2; queue_input.paging = false; queue_input.tba_addr = qpd->tba_addr; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index a6fcbeeb7428..0d53f6067422 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -350,11 +350,11 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev, print_sq_intr_info_inst(context_id0, context_id1); sq_int_priv = REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, PRIV); - if (sq_int_priv /*&& (kfd_set_dbg_ev_from_interrupt(dev, pasid, + /*if (sq_int_priv && (kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_CTXID0_TRAP_CODE(context_id0), - NULL, 0))*/) - return; + NULL, 0))) + return;*/ break; case SQ_INTERRUPT_WORD_ENCODING_ERROR: print_sq_intr_info_error(context_id0, context_id1); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index b8e14c2cc295..3ae350220d42 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -126,6 +126,10 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF; m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF; m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se4 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se5 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se6 = 0xFFFFFFFF; + m->compute_static_thread_mgmt_se7 = 0xFFFFFFFF; m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index c8da18e45b0e..8ca10ab3dfc1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -170,7 +170,13 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) &stream, 1, ¶ms); - power_opt |= psr_power_opt_z10_static_screen; + /* + * Only enable static-screen optimizations for PSR1. For PSR SU, this + * causes vstartup interrupt issues, used by amdgpu_dm to send vblank + * events. + */ + if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1) + power_opt |= psr_power_opt_z10_static_screen; return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 8559dcd80af0..4a15aa7a375f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -130,11 +130,20 @@ static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { + struct stream_encoder *stream_enc = pipe->stream_res.stream_enc; + if (disable) { + if (stream_enc && stream_enc->funcs->disable_fifo) + pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc); + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); reset_sync_context_for_pipe(dc, context, i); - } else + } else { pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); + + if (stream_enc && stream_enc->funcs->enable_fifo) + pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc); + } } } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index c6785969eb1a..f0f3f66629cc 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -156,12 +156,14 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); unsigned int num_levels; + unsigned int num_dcfclk_levels, num_dtbclk_levels, num_dispclk_levels; memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks)); clk_mgr_base->clks.p_state_change_support = true; clk_mgr_base->clks.prev_p_state_change_support = true; clk_mgr_base->clks.fclk_prev_p_state_change_support = true; clk_mgr->smu_present = false; + clk_mgr->dpm_present = false; if (!clk_mgr_base->bw_params) return; @@ -179,6 +181,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) dcn32_init_single_clock(clk_mgr, PPCLK_DCFCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz, &num_levels); + num_dcfclk_levels = num_levels; /* SOCCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_SOCCLK, @@ -189,11 +192,16 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) dcn32_init_single_clock(clk_mgr, PPCLK_DTBCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz, &num_levels); + num_dtbclk_levels = num_levels; /* DISPCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DISPCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz, &num_levels); + num_dispclk_levels = num_levels; + + if (num_dcfclk_levels && num_dtbclk_levels && num_dispclk_levels) + clk_mgr->dpm_present = true; if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) { unsigned int i; @@ -658,6 +666,12 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) &num_levels); clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1; + if (clk_mgr->dpm_present && !num_levels) + clk_mgr->dpm_present = false; + + if (!clk_mgr->dpm_present) + dcn32_patch_dpm_table(clk_mgr_base->bw_params); + DC_FP_START(); /* Refresh bounding box */ clk_mgr_base->ctx->dc->res_pool->funcs->update_bw_bounding_box( diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index aea49334021c..38a67051d470 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2164,8 +2164,7 @@ static void dce110_setup_audio_dto( continue; if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A) continue; - if (pipe_ctx->stream_res.audio != NULL && - pipe_ctx->stream_res.audio->enabled == false) { + if (pipe_ctx->stream_res.audio != NULL) { struct audio_output audio_output; build_audio_output(context, pipe_ctx, &audio_output); @@ -2205,8 +2204,7 @@ static void dce110_setup_audio_dto( if (!dc_is_dp_signal(pipe_ctx->stream->signal)) continue; - if (pipe_ctx->stream_res.audio != NULL && - pipe_ctx->stream_res.audio->enabled == false) { + if (pipe_ctx->stream_res.audio != NULL) { struct audio_output audio_output; build_audio_output(context, pipe_ctx, &audio_output); diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 232cc15979dd..fb729674953b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -45,6 +45,48 @@ #define DC_LOGGER \ dccg->ctx->logger +static void dccg314_get_pixel_rate_div( + struct dccg *dccg, + uint32_t otg_inst, + enum pixel_rate_div *k1, + enum pixel_rate_div *k2) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA; + + *k1 = PIXEL_RATE_DIV_NA; + *k2 = PIXEL_RATE_DIV_NA; + + switch (otg_inst) { + case 0: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG0_PIXEL_RATE_DIVK1, &val_k1, + OTG0_PIXEL_RATE_DIVK2, &val_k2); + break; + case 1: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG1_PIXEL_RATE_DIVK1, &val_k1, + OTG1_PIXEL_RATE_DIVK2, &val_k2); + break; + case 2: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG2_PIXEL_RATE_DIVK1, &val_k1, + OTG2_PIXEL_RATE_DIVK2, &val_k2); + break; + case 3: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG3_PIXEL_RATE_DIVK1, &val_k1, + OTG3_PIXEL_RATE_DIVK2, &val_k2); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } + + *k1 = (enum pixel_rate_div)val_k1; + *k2 = (enum pixel_rate_div)val_k2; +} + static void dccg314_set_pixel_rate_div( struct dccg *dccg, uint32_t otg_inst, @@ -52,6 +94,11 @@ static void dccg314_set_pixel_rate_div( enum pixel_rate_div k2) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + + dccg314_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA || (k1 == cur_k1 && k2 == cur_k2)) + return; switch (otg_inst) { case 0: diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index 06d8638db696..8c0ab013764e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -56,7 +56,8 @@ static void enc314_enable_fifo(struct stream_encoder *enc) /* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */ REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000); - REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000); @@ -261,6 +262,16 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } +void enc314_stream_encoder_dp_blank( + struct dc_link *link, + struct stream_encoder *enc) +{ + /* New to DCN314 - disable the FIFO before VID stream disable. */ + enc314_disable_fifo(enc); + + enc1_stream_encoder_dp_blank(link, enc); +} + static void enc314_stream_encoder_dp_unblank( struct dc_link *link, struct stream_encoder *enc, @@ -316,15 +327,11 @@ static void enc314_stream_encoder_dp_unblank( /* switch DP encoder to CRTC data, but reset it the fifo first. It may happen * that it overflows during mode transition, and sometimes doesn't recover. */ - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 1); udelay(10); REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0); - /* DIG Resync FIFO now needs to be explicitly enabled. */ - enc314_enable_fifo(enc); - /* wait 100us for DIG/DP logic to prime * (i.e. a few video lines) */ @@ -340,6 +347,12 @@ static void enc314_stream_encoder_dp_unblank( REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, true); + /* + * DIG Resync FIFO now needs to be explicitly enabled. + * This should come after DP_VID_STREAM_ENABLE per HW docs. + */ + enc314_enable_fifo(enc); + dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_DP_VID_STREAM); } @@ -408,7 +421,7 @@ static const struct stream_encoder_funcs dcn314_str_enc_funcs = { .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, .dp_blank = - enc1_stream_encoder_dp_blank, + enc314_stream_encoder_dp_blank, .dp_unblank = enc314_stream_encoder_dp_unblank, .audio_mute_control = enc3_audio_mute_control, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index 0d5e8a441512..6640d0ac4304 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -42,6 +42,48 @@ #define DC_LOGGER \ dccg->ctx->logger +static void dccg32_get_pixel_rate_div( + struct dccg *dccg, + uint32_t otg_inst, + enum pixel_rate_div *k1, + enum pixel_rate_div *k2) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA; + + *k1 = PIXEL_RATE_DIV_NA; + *k2 = PIXEL_RATE_DIV_NA; + + switch (otg_inst) { + case 0: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG0_PIXEL_RATE_DIVK1, &val_k1, + OTG0_PIXEL_RATE_DIVK2, &val_k2); + break; + case 1: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG1_PIXEL_RATE_DIVK1, &val_k1, + OTG1_PIXEL_RATE_DIVK2, &val_k2); + break; + case 2: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG2_PIXEL_RATE_DIVK1, &val_k1, + OTG2_PIXEL_RATE_DIVK2, &val_k2); + break; + case 3: + REG_GET_2(OTG_PIXEL_RATE_DIV, + OTG3_PIXEL_RATE_DIVK1, &val_k1, + OTG3_PIXEL_RATE_DIVK2, &val_k2); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } + + *k1 = (enum pixel_rate_div)val_k1; + *k2 = (enum pixel_rate_div)val_k2; +} + static void dccg32_set_pixel_rate_div( struct dccg *dccg, uint32_t otg_inst, @@ -50,6 +92,17 @@ static void dccg32_set_pixel_rate_div( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA; + + // Don't program 0xF into the register field. Not valid since + // K1 / K2 field is only 1 / 2 bits wide + if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA) + return; + + dccg32_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2); + if (k1 == cur_k1 && k2 == cur_k2) + return; + switch (otg_inst) { case 0: REG_UPDATE_2(OTG_PIXEL_RATE_DIV, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c index 99eb239bbc7b..9aebc1be2f59 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c @@ -98,9 +98,13 @@ static void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigne default: break; } - /* Should never be hit, if it is we have an erroneous hw config*/ - ASSERT(hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size - + hubbub2->det3_size + hubbub2->compbuf_size_segments <= hubbub2->crb_size_segs); + if (hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size + + hubbub2->det3_size + hubbub2->compbuf_size_segments > hubbub2->crb_size_segs) { + /* This may happen during seamless transition from ODM 2:1 to ODM4:1 */ + DC_LOG_WARNING("CRB Config Warning: DET size (%d,%d,%d,%d) + Compbuf size (%d) > CRB segments (%d)\n", + hubbub2->det0_size, hubbub2->det1_size, hubbub2->det2_size, hubbub2->det3_size, + hubbub2->compbuf_size_segments, hubbub2->crb_size_segs); + } } static void dcn32_program_compbuf_size(struct hubbub *hubbub, unsigned int compbuf_size_kb, bool safe_to_increase) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index f43686997917..e573e706430d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -121,8 +121,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { }, }, .num_states = 1, - .sr_exit_time_us = 20.16, - .sr_enter_plus_exit_time_us = 27.13, + .sr_exit_time_us = 42.97, + .sr_enter_plus_exit_time_us = 49.94, .sr_exit_z8_time_us = 285.0, .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, @@ -1926,6 +1926,45 @@ static void remove_entry_from_table_at_index(struct _vcs_dpi_voltage_scaling_st memset(&table[--(*num_entries)], 0, sizeof(struct _vcs_dpi_voltage_scaling_st)); } +void dcn32_patch_dpm_table(struct clk_bw_params *bw_params) +{ + int i; + unsigned int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, + max_phyclk_mhz = 0, max_dtbclk_mhz = 0, max_fclk_mhz = 0, max_uclk_mhz = 0; + + for (i = 0; i < MAX_NUM_DPM_LVL; i++) { + if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz) + max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz; + if (bw_params->clk_table.entries[i].fclk_mhz > max_fclk_mhz) + max_fclk_mhz = bw_params->clk_table.entries[i].fclk_mhz; + if (bw_params->clk_table.entries[i].memclk_mhz > max_uclk_mhz) + max_uclk_mhz = bw_params->clk_table.entries[i].memclk_mhz; + if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz) + max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz; + if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz) + max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz; + if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz) + max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz; + if (bw_params->clk_table.entries[i].dtbclk_mhz > max_dtbclk_mhz) + max_dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz; + } + + /* Scan through clock values we currently have and if they are 0, + * then populate it with dcn3_2_soc.clock_limits[] value. + * + * Do it for DCFCLK, DISPCLK, DTBCLK and UCLK as any of those being + * 0, will cause it to skip building the clock table. + */ + if (max_dcfclk_mhz == 0) + bw_params->clk_table.entries[0].dcfclk_mhz = dcn3_2_soc.clock_limits[0].dcfclk_mhz; + if (max_dispclk_mhz == 0) + bw_params->clk_table.entries[0].dispclk_mhz = dcn3_2_soc.clock_limits[0].dispclk_mhz; + if (max_dtbclk_mhz == 0) + bw_params->clk_table.entries[0].dtbclk_mhz = dcn3_2_soc.clock_limits[0].dtbclk_mhz; + if (max_uclk_mhz == 0) + bw_params->clk_table.entries[0].memclk_mhz = dcn3_2_soc.clock_limits[0].dram_speed_mts / 16; +} + static int build_synthetic_soc_states(struct clk_bw_params *bw_params, struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h index 6ce221098979..e1b79e2aab8c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h @@ -77,4 +77,6 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, int pipe_cnt, int vlevel); +void dcn32_patch_dpm_table(struct clk_bw_params *bw_params); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h index 68c2ed434d2c..cff5fd55a0ad 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h @@ -340,6 +340,8 @@ struct clk_mgr_internal { bool smu_present; void *wm_range_table; long long wm_range_table_addr; + + bool dpm_present; }; struct clk_mgr_internal_funcs { diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h index 50bfa513cb35..7e85cdc5bd34 100644 --- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h +++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h @@ -269,7 +269,8 @@ union MESAPI__ADD_QUEUE { uint32_t map_kiq_utility_queue : 1; uint32_t is_kfd_process : 1; uint32_t trap_en : 1; - uint32_t reserved : 21; + uint32_t is_aql_queue : 1; + uint32_t reserved : 20; }; struct MES_API_STATUS api_status; uint64_t tma_addr; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 096327513dd0..1d454485e0d9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -239,82 +239,47 @@ smu_v13_0_0_get_allowed_feature_mask(struct smu_context *smu, uint32_t *feature_mask, uint32_t num) { struct amdgpu_device *adev = smu->adev; + u32 smu_version; if (num > 2) return -EINVAL; - memset(feature_mask, 0, sizeof(uint32_t) * num); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DATA_READ_BIT); + memset(feature_mask, 0xff, sizeof(uint32_t) * num); - if (adev->pm.pp_feature & PP_SCLK_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_IMU_BIT); + if (!(adev->pm.pp_feature & PP_SCLK_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_IMU_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MM_DPM_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_VCN_BIT); - - if ((adev->pg_flags & AMD_PG_SUPPORT_ATHUB) && - (adev->pg_flags & AMD_PG_SUPPORT_MMHUB)) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT); + if (!(adev->pg_flags & AMD_PG_SUPPORT_ATHUB) || + !(adev->pg_flags & AMD_PG_SUPPORT_MMHUB)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT); - if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); - -#if 0 - if (adev->pm.pp_feature & PP_GFXOFF_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFXOFF_BIT); -#endif + if (!(adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_THROTTLERS_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FAN_CONTROL_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DF_CSTATE_BIT); - - if (adev->pm.pp_feature & PP_MCLK_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT); + /* PMFW 78.58 contains a critical fix for gfxoff feature */ + smu_cmn_get_smc_version(smu, NULL, &smu_version); + if ((smu_version < 0x004e3a00) || + !(adev->pm.pp_feature & PP_GFXOFF_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFXOFF_BIT); + + if (!(adev->pm.pp_feature & PP_MCLK_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_UCLK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MEM_TEMP_READ_BIT); - - if (adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_SOCCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_MPCLK_DS_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_MPCLK_DS_BIT); + if (!(adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_GFXCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_FCLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCN_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_DCFCLK_BIT); - - if (adev->pm.pp_feature & PP_PCIE_DPM_MASK) { - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_LINK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_LCLK_BIT); + if (!(adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_LINK_BIT); + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_LCLK_BIT); } - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DSTATE_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT); - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_CG_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_FCLK_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_CTF_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_UCLK_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VR0HOT_BIT); - - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT); - - if (adev->pm.pp_feature & PP_ULV_MASK) - *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT); + if (!(adev->pm.pp_feature & PP_ULV_MASK)) + *(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_ULV_BIT); return 0; } diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 8aadcc0aa90b..df9370e0ff23 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1864,12 +1864,6 @@ EXPORT_SYMBOL_GPL(analogix_dp_remove); int analogix_dp_suspend(struct analogix_dp_device *dp) { clk_disable_unprepare(dp->clock); - - if (dp->plat_data->panel) { - if (drm_panel_unprepare(dp->plat_data->panel)) - DRM_ERROR("failed to turnoff the panel\n"); - } - return 0; } EXPORT_SYMBOL_GPL(analogix_dp_suspend); @@ -1884,13 +1878,6 @@ int analogix_dp_resume(struct analogix_dp_device *dp) return ret; } - if (dp->plat_data->panel) { - if (drm_panel_prepare(dp->plat_data->panel)) { - DRM_ERROR("failed to setup the panel\n"); - return -EBUSY; - } - } - return 0; } EXPORT_SYMBOL_GPL(analogix_dp_resume); diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 28bad30dc4e5..5968f4af190b 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -188,7 +188,7 @@ static int lt8912_write_lvds_config(struct lt8912 *lt) {0x03, 0xff}, }; - return regmap_multi_reg_write(lt->regmap[I2C_CEC_DSI], seq, ARRAY_SIZE(seq)); + return regmap_multi_reg_write(lt->regmap[I2C_MAIN], seq, ARRAY_SIZE(seq)); }; static inline struct lt8912 *bridge_to_lt8912(struct drm_bridge *b) @@ -268,7 +268,7 @@ static int lt8912_video_setup(struct lt8912 *lt) u32 hactive, h_total, hpw, hfp, hbp; u32 vactive, v_total, vpw, vfp, vbp; u8 settle = 0x08; - int ret; + int ret, hsync_activehigh, vsync_activehigh; if (!lt) return -EINVAL; @@ -278,12 +278,14 @@ static int lt8912_video_setup(struct lt8912 *lt) hpw = lt->mode.hsync_len; hbp = lt->mode.hback_porch; h_total = hactive + hfp + hpw + hbp; + hsync_activehigh = lt->mode.flags & DISPLAY_FLAGS_HSYNC_HIGH; vactive = lt->mode.vactive; vfp = lt->mode.vfront_porch; vpw = lt->mode.vsync_len; vbp = lt->mode.vback_porch; v_total = vactive + vfp + vpw + vbp; + vsync_activehigh = lt->mode.flags & DISPLAY_FLAGS_VSYNC_HIGH; if (vactive <= 600) settle = 0x04; @@ -317,6 +319,13 @@ static int lt8912_video_setup(struct lt8912 *lt) ret |= regmap_write(lt->regmap[I2C_CEC_DSI], 0x3e, hfp & 0xff); ret |= regmap_write(lt->regmap[I2C_CEC_DSI], 0x3f, hfp >> 8); + ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xab, BIT(0), + vsync_activehigh ? BIT(0) : 0); + ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xab, BIT(1), + hsync_activehigh ? BIT(1) : 0); + ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xb2, BIT(0), + lt->connector.display_info.is_hdmi ? BIT(0) : 0); + return ret; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 633a7e5dba3b..6b5d4ea22b67 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -166,6 +166,21 @@ struct intel_engine_execlists { struct timer_list preempt; /** + * @preempt_target: active request at the time of the preemption request + * + * We force a preemption to occur if the pending contexts have not + * been promoted to active upon receipt of the CS ack event within + * the timeout. This timeout maybe chosen based on the target, + * using a very short timeout if the context is no longer schedulable. + * That short timeout may not be applicable to other contexts, so + * if a context switch should happen within before the preemption + * timeout, we may shoot early at an innocent context. To prevent this, + * we record which context was active at the time of the preemption + * request and only reset that context upon the timeout. + */ + const struct i915_request *preempt_target; + + /** * @ccid: identifier for contexts submitted to this engine */ u32 ccid; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 4b909cb88cdf..c718e6dc40b5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -1241,6 +1241,9 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, if (!rq) return 0; + /* Only allow ourselves to force reset the currently active context */ + engine->execlists.preempt_target = rq; + /* Force a fast reset for terminated contexts (ignoring sysfs!) */ if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq))) return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS; @@ -2427,8 +2430,24 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) GEM_BUG_ON(inactive - post > ARRAY_SIZE(post)); if (unlikely(preempt_timeout(engine))) { + const struct i915_request *rq = *engine->execlists.active; + + /* + * If after the preempt-timeout expired, we are still on the + * same active request/context as before we initiated the + * preemption, reset the engine. + * + * However, if we have processed a CS event to switch contexts, + * but not yet processed the CS event for the pending + * preemption, reset the timer allowing the new context to + * gracefully exit. + */ cancel_timer(&engine->execlists.preempt); - engine->execlists.error_interrupt |= ERROR_PREEMPT; + if (rq == engine->execlists.preempt_target) + engine->execlists.error_interrupt |= ERROR_PREEMPT; + else + set_timer_ms(&engine->execlists.preempt, + active_preempt_timeout(engine, rq)); } if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index 73a8b46e0234..d09a0e845d09 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -545,8 +545,7 @@ static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK); -static const struct attribute *freq_attrs[] = { - &dev_attr_punit_req_freq_mhz.attr, +static const struct attribute *throttle_reason_attrs[] = { &attr_throttle_reason_status.attr, &attr_throttle_reason_pl1.attr, &attr_throttle_reason_pl2.attr, @@ -763,12 +762,20 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) if (!is_object_gt(kobj)) return; - ret = sysfs_create_files(kobj, freq_attrs); + ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr); if (ret) drm_warn(>->i915->drm, - "failed to create gt%u throttle sysfs files (%pe)", + "failed to create gt%u punit_req_freq_mhz sysfs (%pe)", gt->info.id, ERR_PTR(ret)); + if (GRAPHICS_VER(gt->i915) >= 11) { + ret = sysfs_create_files(kobj, throttle_reason_attrs); + if (ret) + drm_warn(>->i915->drm, + "failed to create gt%u throttle sysfs files (%pe)", + gt->info.id, ERR_PTR(ret)); + } + if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(>->uc)) { ret = sysfs_create_files(kobj, media_perf_power_attrs); if (ret) diff --git a/drivers/input/keyboard/iqs62x-keys.c b/drivers/input/keyboard/iqs62x-keys.c index 93446b21f98f..db793a550c25 100644 --- a/drivers/input/keyboard/iqs62x-keys.c +++ b/drivers/input/keyboard/iqs62x-keys.c @@ -77,6 +77,7 @@ static int iqs62x_keys_parse_prop(struct platform_device *pdev, if (ret) { dev_err(&pdev->dev, "Failed to read switch code: %d\n", ret); + fwnode_handle_put(child); return ret; } iqs62x_keys->switches[i].code = val; @@ -90,6 +91,8 @@ static int iqs62x_keys_parse_prop(struct platform_device *pdev, iqs62x_keys->switches[i].flag = (i == IQS62X_SW_HALL_N ? IQS62X_EVENT_HALL_N_T : IQS62X_EVENT_HALL_S_T); + + fwnode_handle_put(child); } return 0; diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c index 65286762b02a..ad8660be0127 100644 --- a/drivers/input/keyboard/snvs_pwrkey.c +++ b/drivers/input/keyboard/snvs_pwrkey.c @@ -20,7 +20,7 @@ #include <linux/mfd/syscon.h> #include <linux/regmap.h> -#define SNVS_HPVIDR1_REG 0xF8 +#define SNVS_HPVIDR1_REG 0xBF8 #define SNVS_LPSR_REG 0x4C /* LP Status Register */ #define SNVS_LPCR_REG 0x38 /* LP Control Register */ #define SNVS_HPSR_REG 0x14 diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 434d48ae4b12..ffad142801b3 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -186,7 +186,6 @@ static const char * const smbus_pnp_ids[] = { "LEN2044", /* L470 */ "LEN2054", /* E480 */ "LEN2055", /* E580 */ - "LEN2064", /* T14 Gen 1 AMD / P14s Gen 1 AMD */ "LEN2068", /* T14 Gen 1 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c index 2745bf1aee38..83f4be05e27b 100644 --- a/drivers/input/touchscreen/melfas_mip4.c +++ b/drivers/input/touchscreen/melfas_mip4.c @@ -1453,7 +1453,7 @@ static int mip4_probe(struct i2c_client *client, const struct i2c_device_id *id) "ce", GPIOD_OUT_LOW); if (IS_ERR(ts->gpio_ce)) { error = PTR_ERR(ts->gpio_ce); - if (error != EPROBE_DEFER) + if (error != -EPROBE_DEFER) dev_err(&client->dev, "Failed to get gpio: %d\n", error); return error; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 66b9fa408bf2..eb5ea5b69cfa 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -561,6 +561,11 @@ config IRQ_LOONGARCH_CPU select GENERIC_IRQ_CHIP select IRQ_DOMAIN select GENERIC_IRQ_EFFECTIVE_AFF_MASK + select LOONGSON_LIOINTC + select LOONGSON_EIOINTC + select LOONGSON_PCH_PIC + select LOONGSON_PCH_MSI + select LOONGSON_PCH_LPC help Support for the LoongArch CPU Interrupt Controller. For details of irq chip hierarchy on LoongArch platforms please read the document @@ -623,8 +628,9 @@ config LOONGSON_PCH_MSI config LOONGSON_PCH_LPC bool "Loongson PCH LPC Controller" + depends on LOONGARCH depends on MACH_LOONGSON64 - default (MACH_LOONGSON64 && LOONGARCH) + default MACH_LOONGSON64 select IRQ_DOMAIN_HIERARCHY help Support for the Loongson PCH LPC Controller. diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 5ff09de6c48f..beead1a0191c 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1574,13 +1574,15 @@ static int its_select_cpu(struct irq_data *d, const struct cpumask *aff_mask) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); - cpumask_var_t tmpmask; + static DEFINE_RAW_SPINLOCK(tmpmask_lock); + static struct cpumask __tmpmask; + struct cpumask *tmpmask; + unsigned long flags; int cpu, node; - - if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC)) - return -ENOMEM; - node = its_dev->its->numa_node; + tmpmask = &__tmpmask; + + raw_spin_lock_irqsave(&tmpmask_lock, flags); if (!irqd_affinity_is_managed(d)) { /* First try the NUMA node */ @@ -1634,7 +1636,7 @@ static int its_select_cpu(struct irq_data *d, cpu = cpumask_pick_least_loaded(d, tmpmask); } out: - free_cpumask_var(tmpmask); + raw_spin_unlock_irqrestore(&tmpmask_lock, flags); pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu); return cpu; diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index a73763d475f0..6a3f7498ea8e 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -716,7 +716,7 @@ static int stm32_exti_h_domain_alloc(struct irq_domain *dm, irq_domain_set_hwirq_and_chip(dm, virq, hwirq, chip, chip_data); - if (!host_data->drv_data || !host_data->drv_data->desc_irqs) + if (!host_data->drv_data->desc_irqs) return -EINVAL; desc_irq = host_data->drv_data->desc_irqs[hwirq]; diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c index a1bd6d9c9223..909df82fed33 100644 --- a/drivers/media/dvb-core/dvb_vb2.c +++ b/drivers/media/dvb-core/dvb_vb2.c @@ -354,6 +354,12 @@ int dvb_vb2_reqbufs(struct dvb_vb2_ctx *ctx, struct dmx_requestbuffers *req) int dvb_vb2_querybuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b) { + struct vb2_queue *q = &ctx->vb_q; + + if (b->index >= q->num_buffers) { + dprintk(1, "[%s] buffer index out of range\n", ctx->name); + return -EINVAL; + } vb2_core_querybuf(&ctx->vb_q, b->index, b); dprintk(3, "[%s] index=%d\n", ctx->name, b->index); return 0; @@ -378,8 +384,13 @@ int dvb_vb2_expbuf(struct dvb_vb2_ctx *ctx, struct dmx_exportbuffer *exp) int dvb_vb2_qbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b) { + struct vb2_queue *q = &ctx->vb_q; int ret; + if (b->index >= q->num_buffers) { + dprintk(1, "[%s] buffer index out of range\n", ctx->name); + return -EINVAL; + } ret = vb2_core_qbuf(&ctx->vb_q, b->index, b, NULL); if (ret) { dprintk(1, "[%s] index=%d errno=%d\n", ctx->name, diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c index 95e8c29ccc65..d2f5f30582a9 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c @@ -228,7 +228,6 @@ static int mtk_vcodec_probe(struct platform_device *pdev) { struct mtk_vcodec_dev *dev; struct video_device *vfd_enc; - struct resource *res; phandle rproc_phandle; enum mtk_vcodec_fw_type fw_type; int ret; @@ -272,14 +271,12 @@ static int mtk_vcodec_probe(struct platform_device *pdev) goto err_res; } - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (res == NULL) { - dev_err(&pdev->dev, "failed to get irq resource"); - ret = -ENOENT; + dev->enc_irq = platform_get_irq(pdev, 0); + if (dev->enc_irq < 0) { + ret = dev->enc_irq; goto err_res; } - dev->enc_irq = platform_get_irq(pdev, 0); irq_set_status_flags(dev->enc_irq, IRQ_NOAUTOEN); ret = devm_request_irq(&pdev->dev, dev->enc_irq, mtk_vcodec_enc_irq_handler, diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 9c05776f11d1..d509a4a2f08e 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2740,7 +2740,7 @@ static const struct usb_device_id uvc_ids[] = { .idProduct = 0x4034, .bInterfaceClass = USB_CLASS_VIDEO, .bInterfaceSubClass = 1, - .bInterfaceProtocol = 0, + .bInterfaceProtocol = UVC_PC_PROTOCOL_15, .driver_info = (kernel_ulong_t)&uvc_ctrl_power_line_limited }, /* LogiLink Wireless Webcam */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 0f3d6b5667b0..55c26e7d370e 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -1040,6 +1040,8 @@ int v4l2_compat_get_array_args(struct file *file, void *mbuf, { int err = 0; + memset(mbuf, 0, array_size); + switch (cmd) { case VIDIOC_G_FMT32: case VIDIOC_S_FMT32: diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index c314025d977e..e6fd355a2e92 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2872,9 +2872,9 @@ static const struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO(VIDIOC_S_PRIORITY, v4l_s_priority, v4l_print_u32, INFO_FL_PRIO), IOCTL_INFO(VIDIOC_G_SLICED_VBI_CAP, v4l_g_sliced_vbi_cap, v4l_print_sliced_vbi_cap, INFO_FL_CLEAR(v4l2_sliced_vbi_cap, type)), IOCTL_INFO(VIDIOC_LOG_STATUS, v4l_log_status, v4l_print_newline, 0), - IOCTL_INFO(VIDIOC_G_EXT_CTRLS, v4l_g_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL), - IOCTL_INFO(VIDIOC_S_EXT_CTRLS, v4l_s_ext_ctrls, v4l_print_ext_controls, INFO_FL_PRIO | INFO_FL_CTRL), - IOCTL_INFO(VIDIOC_TRY_EXT_CTRLS, v4l_try_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL), + IOCTL_INFO(VIDIOC_G_EXT_CTRLS, v4l_g_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL | INFO_FL_ALWAYS_COPY), + IOCTL_INFO(VIDIOC_S_EXT_CTRLS, v4l_s_ext_ctrls, v4l_print_ext_controls, INFO_FL_PRIO | INFO_FL_CTRL | INFO_FL_ALWAYS_COPY), + IOCTL_INFO(VIDIOC_TRY_EXT_CTRLS, v4l_try_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL | INFO_FL_ALWAYS_COPY), IOCTL_INFO(VIDIOC_ENUM_FRAMESIZES, v4l_stub_enum_framesizes, v4l_print_frmsizeenum, INFO_FL_CLEAR(v4l2_frmsizeenum, pixel_format)), IOCTL_INFO(VIDIOC_ENUM_FRAMEINTERVALS, v4l_stub_enum_frameintervals, v4l_print_frmivalenum, INFO_FL_CLEAR(v4l2_frmivalenum, height)), IOCTL_INFO(VIDIOC_G_ENC_INDEX, v4l_stub_g_enc_index, v4l_print_enc_idx, 0), @@ -3367,8 +3367,7 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg, array_buf = kvmalloc(array_size, GFP_KERNEL); err = -ENOMEM; if (array_buf == NULL) - goto out_array_args; - err = -EFAULT; + goto out; if (in_compat_syscall()) err = v4l2_compat_get_array_args(file, array_buf, user_ptr, array_size, @@ -3377,7 +3376,7 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg, err = copy_from_user(array_buf, user_ptr, array_size) ? -EFAULT : 0; if (err) - goto out_array_args; + goto out; *kernel_ptr = array_buf; } @@ -3395,6 +3394,13 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg, trace_v4l2_qbuf(video_devdata(file)->minor, parg); } + /* + * Some ioctls can return an error, but still have valid + * results that must be returned. + */ + if (err < 0 && !always_copy) + goto out; + if (has_array_args) { *kernel_ptr = (void __force *)user_ptr; if (in_compat_syscall()) { @@ -3409,16 +3415,8 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg, } else if (copy_to_user(user_ptr, array_buf, array_size)) { err = -EFAULT; } - goto out_array_args; } - /* - * Some ioctls can return an error, but still have valid - * results that must be returned. - */ - if (err < 0 && !always_copy) - goto out; -out_array_args: if (video_put_user((void __user *)arg, parg, cmd, orig_cmd)) err = -EFAULT; out: diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 06aa62ce0ed1..3662bf5320ce 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -870,7 +870,8 @@ try_again: * the CCS bit is set as well. We deliberately deviate from the spec in * regards to this, which allows UHS-I to be supported for SDSC cards. */ - if (!mmc_host_is_spi(host) && rocr && (*rocr & SD_ROCR_S18A)) { + if (!mmc_host_is_spi(host) && (ocr & SD_OCR_S18R) && + rocr && (*rocr & SD_ROCR_S18A)) { err = mmc_set_uhs_voltage(host, pocr); if (err == -EAGAIN) { retries--; diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c index a5e05ed0fda3..9d35453e7371 100644 --- a/drivers/mmc/host/mmc_hsq.c +++ b/drivers/mmc/host/mmc_hsq.c @@ -34,7 +34,7 @@ static void mmc_hsq_pump_requests(struct mmc_hsq *hsq) spin_lock_irqsave(&hsq->lock, flags); /* Make sure we are not already running a request now */ - if (hsq->mrq) { + if (hsq->mrq || hsq->recovery_halt) { spin_unlock_irqrestore(&hsq->lock, flags); return; } diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index b6eb75f4bbfc..dfc3ffd5b1f8 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -111,8 +111,8 @@ #define CLK_DIV_MASK 0x7f /* REG_BUS_WIDTH */ -#define BUS_WIDTH_8 BIT(2) -#define BUS_WIDTH_4 BIT(1) +#define BUS_WIDTH_4_SUPPORT BIT(3) +#define BUS_WIDTH_4 BIT(2) #define BUS_WIDTH_1 BIT(0) #define MMC_VDD_360 23 @@ -524,9 +524,6 @@ static void moxart_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_BUS_WIDTH_4: writel(BUS_WIDTH_4, host->base + REG_BUS_WIDTH); break; - case MMC_BUS_WIDTH_8: - writel(BUS_WIDTH_8, host->base + REG_BUS_WIDTH); - break; default: writel(BUS_WIDTH_1, host->base + REG_BUS_WIDTH); break; @@ -651,16 +648,8 @@ static int moxart_probe(struct platform_device *pdev) dmaengine_slave_config(host->dma_chan_rx, &cfg); } - switch ((readl(host->base + REG_BUS_WIDTH) >> 3) & 3) { - case 1: + if (readl(host->base + REG_BUS_WIDTH) & BUS_WIDTH_4_SUPPORT) mmc->caps |= MMC_CAP_4_BIT_DATA; - break; - case 2: - mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA; - break; - default: - break; - } writel(0, host->base + REG_INTERRUPT_MASK); diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 7689ffec5ad1..251172890af7 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -3928,7 +3928,7 @@ bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error, if (intmask & (SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC)) { *cmd_error = -EILSEQ; - if (!mmc_op_tuning(host->cmd->opcode)) + if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)))) sdhci_err_stats_inc(host, CMD_CRC); } else if (intmask & SDHCI_INT_TIMEOUT) { *cmd_error = -ETIMEDOUT; @@ -3938,7 +3938,7 @@ bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error, if (intmask & (SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC)) { *data_error = -EILSEQ; - if (!mmc_op_tuning(host->cmd->opcode)) + if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)))) sdhci_err_stats_inc(host, DAT_CRC); } else if (intmask & SDHCI_INT_DATA_TIMEOUT) { *data_error = -ETIMEDOUT; diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index f23a03300a81..029cd8194ed5 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -235,9 +235,22 @@ static inline u8 c_can_get_tx_tail(const struct c_can_tx_ring *ring) return ring->tail & (ring->obj_num - 1); } -static inline u8 c_can_get_tx_free(const struct c_can_tx_ring *ring) +static inline u8 c_can_get_tx_free(const struct c_can_priv *priv, + const struct c_can_tx_ring *ring) { - return ring->obj_num - (ring->head - ring->tail); + u8 head = c_can_get_tx_head(ring); + u8 tail = c_can_get_tx_tail(ring); + + if (priv->type == BOSCH_D_CAN) + return ring->obj_num - (ring->head - ring->tail); + + /* This is not a FIFO. C/D_CAN sends out the buffers + * prioritized. The lowest buffer number wins. + */ + if (head < tail) + return 0; + + return ring->obj_num - head; } #endif /* C_CAN_H */ diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index dc8132862f33..d6605dbb7737 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -429,7 +429,7 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface, static bool c_can_tx_busy(const struct c_can_priv *priv, const struct c_can_tx_ring *tx_ring) { - if (c_can_get_tx_free(tx_ring) > 0) + if (c_can_get_tx_free(priv, tx_ring) > 0) return false; netif_stop_queue(priv->dev); @@ -437,7 +437,7 @@ static bool c_can_tx_busy(const struct c_can_priv *priv, /* Memory barrier before checking tx_free (head and tail) */ smp_mb(); - if (c_can_get_tx_free(tx_ring) == 0) { + if (c_can_get_tx_free(priv, tx_ring) == 0) { netdev_dbg(priv->dev, "Stopping tx-queue (tx_head=0x%08x, tx_tail=0x%08x, len=%d).\n", tx_ring->head, tx_ring->tail, @@ -465,7 +465,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb, idx = c_can_get_tx_head(tx_ring); tx_ring->head++; - if (c_can_get_tx_free(tx_ring) == 0) + if (c_can_get_tx_free(priv, tx_ring) == 0) netif_stop_queue(dev); if (idx < c_can_get_tx_tail(tx_ring)) @@ -748,7 +748,7 @@ static void c_can_do_tx(struct net_device *dev) return; tx_ring->tail += pkts; - if (c_can_get_tx_free(tx_ring)) { + if (c_can_get_tx_free(priv, tx_ring)) { /* Make sure that anybody stopping the queue after * this sees the new tx_ring->tail. */ @@ -760,8 +760,7 @@ static void c_can_do_tx(struct net_device *dev) stats->tx_packets += pkts; tail = c_can_get_tx_tail(tx_ring); - - if (tail == 0) { + if (priv->type == BOSCH_D_CAN && tail == 0) { u8 head = c_can_get_tx_head(tx_ring); /* Start transmission for all cached messages */ diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 835807911be0..409d5c3d76ea 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -506,14 +506,19 @@ static bool mt7531_dual_sgmii_supported(struct mt7530_priv *priv) static int mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface) { - struct mt7530_priv *priv = ds->priv; + return 0; +} + +static void +mt7531_pll_setup(struct mt7530_priv *priv) +{ u32 top_sig; u32 hwstrap; u32 xtal; u32 val; if (mt7531_dual_sgmii_supported(priv)) - return 0; + return; val = mt7530_read(priv, MT7531_CREV); top_sig = mt7530_read(priv, MT7531_TOP_SIG_SR); @@ -592,8 +597,6 @@ mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface) val |= EN_COREPLL; mt7530_write(priv, MT7531_PLLGP_EN, val); usleep_range(25, 35); - - return 0; } static void @@ -2326,11 +2329,17 @@ mt7531_setup(struct dsa_switch *ds) return -ENODEV; } + /* all MACs must be forced link-down before sw reset */ + for (i = 0; i < MT7530_NUM_PORTS; i++) + mt7530_write(priv, MT7530_PMCR_P(i), MT7531_FORCE_LNK); + /* Reset the switch through internal reset */ mt7530_write(priv, MT7530_SYS_CTRL, SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST | SYS_CTRL_REG_RST); + mt7531_pll_setup(priv); + if (mt7531_dual_sgmii_supported(priv)) { priv->p5_intf_sel = P5_INTF_SEL_GMAC5_SGMII; @@ -2887,8 +2896,6 @@ mt7531_cpu_port_config(struct dsa_switch *ds, int port) case 6: interface = PHY_INTERFACE_MODE_2500BASEX; - mt7531_pad_setup(ds, interface); - priv->p6_interface = interface; break; default: diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66c7d08d376a..a2897549f9c4 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5109,6 +5109,7 @@ static int __maybe_unused macb_suspend(struct device *dev) if (!(bp->wol & MACB_WOL_ENABLED)) { rtnl_lock(); phylink_stop(bp->phylink); + phy_exit(bp->sgmii_phy); rtnl_unlock(); spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); @@ -5198,6 +5199,9 @@ static int __maybe_unused macb_resume(struct device *dev) macb_set_rx_mode(netdev); macb_restore_features(bp); rtnl_lock(); + if (!device_may_wakeup(&bp->dev->dev)) + phy_init(bp->sgmii_phy); + phylink_start(bp->phylink); rtnl_unlock(); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index a7f291c89702..557c591a6ce3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -14,6 +14,7 @@ #include "cudbg_entity.h" #include "cudbg_lib.h" #include "cudbg_zlib.h" +#include "cxgb4_tc_mqprio.h" static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = { {0x7e40, 0x7e44, 0x020, 28}, /* t6_tp_pio_regs_20_to_3b */ @@ -3458,7 +3459,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, for (i = 0; i < utxq->ntxq; i++) QDESC_GET_TXQ(&utxq->uldtxq[i].q, cudbg_uld_txq_to_qtype(j), - out_unlock); + out_unlock_uld); } } @@ -3475,7 +3476,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, for (i = 0; i < urxq->nrxq; i++) QDESC_GET_RXQ(&urxq->uldrxq[i].rspq, cudbg_uld_rxq_to_qtype(j), - out_unlock); + out_unlock_uld); } /* ULD FLQ */ @@ -3487,7 +3488,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, for (i = 0; i < urxq->nrxq; i++) QDESC_GET_FLQ(&urxq->uldrxq[i].fl, cudbg_uld_flq_to_qtype(j), - out_unlock); + out_unlock_uld); } /* ULD CIQ */ @@ -3500,29 +3501,34 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, for (i = 0; i < urxq->nciq; i++) QDESC_GET_RXQ(&urxq->uldrxq[base + i].rspq, cudbg_uld_ciq_to_qtype(j), - out_unlock); + out_unlock_uld); } } + mutex_unlock(&uld_mutex); + + if (!padap->tc_mqprio) + goto out; + mutex_lock(&padap->tc_mqprio->mqprio_mutex); /* ETHOFLD TXQ */ if (s->eohw_txq) for (i = 0; i < s->eoqsets; i++) QDESC_GET_TXQ(&s->eohw_txq[i].q, - CUDBG_QTYPE_ETHOFLD_TXQ, out); + CUDBG_QTYPE_ETHOFLD_TXQ, out_unlock_mqprio); /* ETHOFLD RXQ and FLQ */ if (s->eohw_rxq) { for (i = 0; i < s->eoqsets; i++) QDESC_GET_RXQ(&s->eohw_rxq[i].rspq, - CUDBG_QTYPE_ETHOFLD_RXQ, out); + CUDBG_QTYPE_ETHOFLD_RXQ, out_unlock_mqprio); for (i = 0; i < s->eoqsets; i++) QDESC_GET_FLQ(&s->eohw_rxq[i].fl, - CUDBG_QTYPE_ETHOFLD_FLQ, out); + CUDBG_QTYPE_ETHOFLD_FLQ, out_unlock_mqprio); } -out_unlock: - mutex_unlock(&uld_mutex); +out_unlock_mqprio: + mutex_unlock(&padap->tc_mqprio->mqprio_mutex); out: qdesc_info->qdesc_entry_size = sizeof(*qdesc_entry); @@ -3559,6 +3565,10 @@ out_free: #undef QDESC_GET return rc; + +out_unlock_uld: + mutex_unlock(&uld_mutex); + goto out; } int cudbg_collect_flash(struct cudbg_init *pdbg_init, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 97453d1dfafe..dd2285d4bef4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1467,7 +1467,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) bool wd; if (tx_ring->xsk_pool) - wd = ice_xmit_zc(tx_ring, ICE_DESC_UNUSED(tx_ring), budget); + wd = ice_xmit_zc(tx_ring); else if (ice_ring_is_xdp(tx_ring)) wd = true; else diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 03ce85f6e6df..056c904b83cc 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -392,13 +392,6 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) goto failure; } - if (!is_power_of_2(vsi->rx_rings[qid]->count) || - !is_power_of_2(vsi->tx_rings[qid]->count)) { - netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n"); - pool_failure = -EINVAL; - goto failure; - } - if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); if (if_running) { @@ -534,11 +527,10 @@ exit: bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { u16 rx_thresh = ICE_RING_QUARTER(rx_ring); - u16 batched, leftover, i, tail_bumps; + u16 leftover, i, tail_bumps; - batched = ALIGN_DOWN(count, rx_thresh); - tail_bumps = batched / rx_thresh; - leftover = count & (rx_thresh - 1); + tail_bumps = count / rx_thresh; + leftover = count - (tail_bumps * rx_thresh); for (i = 0; i < tail_bumps; i++) if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) @@ -788,69 +780,57 @@ ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) } /** - * ice_clean_xdp_irq_zc - Reclaim resources after transmit completes on XDP ring - * @xdp_ring: XDP ring to clean - * @napi_budget: amount of descriptors that NAPI allows us to clean - * - * Returns count of cleaned descriptors + * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ + * @xdp_ring: XDP Tx ring */ -static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget) +static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); - int budget = napi_budget / tx_thresh; - u16 next_dd = xdp_ring->next_dd; - u16 ntc, cleared_dds = 0; - - do { - struct ice_tx_desc *next_dd_desc; - u16 desc_cnt = xdp_ring->count; - struct ice_tx_buf *tx_buf; - u32 xsk_frames; - u16 i; - - next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd); - if (!(next_dd_desc->cmd_type_offset_bsz & - cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) - break; + u16 ntc = xdp_ring->next_to_clean; + struct ice_tx_desc *tx_desc; + u16 cnt = xdp_ring->count; + struct ice_tx_buf *tx_buf; + u16 xsk_frames = 0; + u16 last_rs; + int i; - cleared_dds++; - xsk_frames = 0; - if (likely(!xdp_ring->xdp_tx_active)) { - xsk_frames = tx_thresh; - goto skip; - } + last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1; + tx_desc = ICE_TX_DESC(xdp_ring, last_rs); + if ((tx_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) { + if (last_rs >= ntc) + xsk_frames = last_rs - ntc + 1; + else + xsk_frames = last_rs + cnt - ntc + 1; + } - ntc = xdp_ring->next_to_clean; + if (!xsk_frames) + return; - for (i = 0; i < tx_thresh; i++) { - tx_buf = &xdp_ring->tx_buf[ntc]; + if (likely(!xdp_ring->xdp_tx_active)) + goto skip; - if (tx_buf->raw_buf) { - ice_clean_xdp_tx_buf(xdp_ring, tx_buf); - tx_buf->raw_buf = NULL; - } else { - xsk_frames++; - } + ntc = xdp_ring->next_to_clean; + for (i = 0; i < xsk_frames; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; - ntc++; - if (ntc >= xdp_ring->count) - ntc = 0; + if (tx_buf->raw_buf) { + ice_clean_xdp_tx_buf(xdp_ring, tx_buf); + tx_buf->raw_buf = NULL; + } else { + xsk_frames++; } + + ntc++; + if (ntc >= xdp_ring->count) + ntc = 0; + } skip: - xdp_ring->next_to_clean += tx_thresh; - if (xdp_ring->next_to_clean >= desc_cnt) - xdp_ring->next_to_clean -= desc_cnt; - if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); - next_dd_desc->cmd_type_offset_bsz = 0; - next_dd = next_dd + tx_thresh; - if (next_dd >= desc_cnt) - next_dd = tx_thresh - 1; - } while (--budget); - - xdp_ring->next_dd = next_dd; - - return cleared_dds * tx_thresh; + tx_desc->cmd_type_offset_bsz = 0; + xdp_ring->next_to_clean += xsk_frames; + if (xdp_ring->next_to_clean >= cnt) + xdp_ring->next_to_clean -= cnt; + if (xsk_frames) + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); } /** @@ -885,7 +865,6 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, unsigned int *total_bytes) { - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u16 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; u32 i; @@ -905,13 +884,6 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de } xdp_ring->next_to_use = ntu; - - if (xdp_ring->next_to_use > xdp_ring->next_rs) { - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs += tx_thresh; - } } /** @@ -924,7 +896,6 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, u32 nb_pkts, unsigned int *total_bytes) { - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u32 batched, leftover, i; batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); @@ -933,54 +904,54 @@ static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *d ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); for (; i < batched + leftover; i++) ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); +} - if (xdp_ring->next_to_use > xdp_ring->next_rs) { - struct ice_tx_desc *tx_desc; +/** + * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU) + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + */ +static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring) +{ + u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1; + struct ice_tx_desc *tx_desc; - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs += tx_thresh; - } + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); } /** * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on - * @budget: number of free descriptors on HW Tx ring that can be used - * @napi_budget: amount of descriptors that NAPI allows us to clean * * Returns true if there is no more work that needs to be done, false otherwise */ -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget) +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) { struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u32 nb_pkts, nb_processed = 0; unsigned int total_bytes = 0; + int budget; + + ice_clean_xdp_irq_zc(xdp_ring); - if (budget < tx_thresh) - budget += ice_clean_xdp_irq_zc(xdp_ring, napi_budget); + budget = ICE_DESC_UNUSED(xdp_ring); + budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); if (!nb_pkts) return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { - struct ice_tx_desc *tx_desc; - nb_processed = xdp_ring->count - xdp_ring->next_to_use; ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs = tx_thresh - 1; xdp_ring->next_to_use = 0; } ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, &total_bytes); + ice_set_rs_bit(xdp_ring); ice_xdp_ring_update_tail(xdp_ring); ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); @@ -1058,14 +1029,16 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) */ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { - u16 count_mask = rx_ring->count - 1; u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; - for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) { + while (ntc != ntu) { struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); xsk_buff_free(xdp); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; } } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 4edbe81eb646..6fa181f080ef 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -26,13 +26,10 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); -bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring); int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else -static inline bool -ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, - u32 __always_unused budget, - int __always_unused napi_budget) +static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring) { return false; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c index 0eec05d905eb..4a3baa7e0142 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -700,10 +700,10 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *priv) void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) { - static struct dentry *mvpp2_root; - struct dentry *mvpp2_dir; + struct dentry *mvpp2_dir, *mvpp2_root; int ret, i; + mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index ecf85e9ed824..0f9668a4079d 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -319,8 +319,8 @@ #define MTK_RXD5_PPE_CPU_REASON GENMASK(22, 18) #define MTK_RXD5_SRC_PORT GENMASK(29, 26) -#define RX_DMA_GET_SPORT(x) (((x) >> 19) & 0xf) -#define RX_DMA_GET_SPORT_V2(x) (((x) >> 26) & 0x7) +#define RX_DMA_GET_SPORT(x) (((x) >> 19) & 0x7) +#define RX_DMA_GET_SPORT_V2(x) (((x) >> 26) & 0xf) /* PDMA V2 descriptor rxd3 */ #define RX_DMA_VTAG_V2 BIT(0) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c index 4aeb927c3715..aa780b1614a3 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -246,8 +246,8 @@ int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) } priv->clk_io = devm_ioremap(dev, res->start, resource_size(res)); - if (IS_ERR(priv->clk_io)) - return PTR_ERR(priv->clk_io); + if (!priv->clk_io) + return -ENOMEM; mlxbf_gige_mdio_cfg(priv); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 306026e6aa11..8f8005bc6eea 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -290,6 +290,13 @@ static int ocelot_port_num_untagged_vlans(struct ocelot *ocelot, int port) if (!(vlan->portmask & BIT(port))) continue; + /* Ignore the VLAN added by ocelot_add_vlan_unaware_pvid(), + * because this is never active in hardware at the same time as + * the bridge VLANs, which only matter in VLAN-aware mode. + */ + if (vlan->vid >= OCELOT_RSV_VLAN_RANGE_START) + continue; + if (vlan->untagged & BIT(port)) num_untagged++; } diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index ee734b69150f..d1e1aa19a68e 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -4213,7 +4213,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .ev_test_generate = efx_ef10_ev_test_generate, .filter_table_probe = efx_ef10_filter_table_probe, .filter_table_restore = efx_mcdi_filter_table_restore, - .filter_table_remove = efx_mcdi_filter_table_remove, + .filter_table_remove = efx_ef10_filter_table_remove, .filter_update_rx_scatter = efx_mcdi_update_rx_scatter, .filter_insert = efx_mcdi_filter_insert, .filter_remove_safe = efx_mcdi_filter_remove_safe, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 592d29abcb1c..9083159b93f1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3801,6 +3801,15 @@ static int __stmmac_open(struct net_device *dev, stmmac_reset_queues_param(priv); + if (priv->plat->serdes_powerup) { + ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv); + if (ret < 0) { + netdev_err(priv->dev, "%s: Serdes powerup failed\n", + __func__); + goto init_error; + } + } + ret = stmmac_hw_setup(dev, true); if (ret < 0) { netdev_err(priv->dev, "%s: Hw setup failed\n", __func__); @@ -3904,6 +3913,10 @@ static int stmmac_release(struct net_device *dev) /* Disable the MAC Rx/Tx */ stmmac_mac_set(priv, priv->ioaddr, false); + /* Powerdown Serdes if there is */ + if (priv->plat->serdes_powerdown) + priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv); + netif_carrier_off(dev); stmmac_release_ptp(priv); @@ -7293,14 +7306,6 @@ int stmmac_dvr_probe(struct device *device, goto error_netdev_register; } - if (priv->plat->serdes_powerup) { - ret = priv->plat->serdes_powerup(ndev, - priv->plat->bsp_priv); - - if (ret < 0) - goto error_serdes_powerup; - } - #ifdef CONFIG_DEBUG_FS stmmac_init_fs(ndev); #endif @@ -7315,8 +7320,6 @@ int stmmac_dvr_probe(struct device *device, return ret; -error_serdes_powerup: - unregister_netdev(ndev); error_netdev_register: phylink_destroy(priv->phylink); error_xpcs_setup: diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 74e845fa2e07..aa8f828a0ae7 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -213,6 +213,7 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_iounmap(pdev, rrpriv->regs); if (pdev) pci_release_regions(pdev); + pci_disable_device(pdev); out2: free_netdev(dev); out3: diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 12ff276b80ae..4df8c337221b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -316,11 +316,13 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev) phydev->suspended_by_mdio_bus = 0; - /* If we manged to get here with the PHY state machine in a state neither - * PHY_HALTED nor PHY_READY this is an indication that something went wrong - * and we should most likely be using MAC managed PM and we are not. + /* If we managed to get here with the PHY state machine in a state + * neither PHY_HALTED, PHY_READY nor PHY_UP, this is an indication + * that something went wrong and we should most likely be using + * MAC managed PM, but we are not. */ - WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY); + WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY && + phydev->state != PHY_UP); ret = phy_init_hw(phydev); if (ret < 0) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 259b2b84b2b3..db736b944016 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2828,7 +2828,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) rcu_assign_pointer(tfile->tun, tun); } - netif_carrier_on(tun->dev); + if (ifr->ifr_flags & IFF_NO_CARRIER) + netif_carrier_off(tun->dev); + else + netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. @@ -3056,8 +3059,8 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, * This is needed because we never checked for invalid flags on * TUNSETIFF. */ - return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES, - (unsigned int __user*)argp); + return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER | + TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 0cb187def5bc..26c34a7c21bd 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1402,6 +1402,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81c2, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81cc, 8)}, /* Dell Wireless 5816e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index aaa89b4cfd50..e368b0780753 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1598,6 +1598,7 @@ void usbnet_disconnect (struct usb_interface *intf) struct usbnet *dev; struct usb_device *xdev; struct net_device *net; + struct urb *urb; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); @@ -1614,7 +1615,11 @@ void usbnet_disconnect (struct usb_interface *intf) net = dev->net; unregister_netdev (net); - usb_scuttle_anchored_urbs(&dev->deferred); + while ((urb = usb_get_from_anchor(&dev->deferred))) { + dev_kfree_skb(urb->context); + kfree(urb->sg); + usb_free_urb(urb); + } if (dev->driver_info->unbind) dev->driver_info->unbind(dev, intf); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 66446f1e06cf..8d5a7ae19844 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2162,14 +2162,14 @@ static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new, static int nvme_pr_clear(struct block_device *bdev, u64 key) { - u32 cdw10 = 1 | (key ? 1 << 3 : 0); + u32 cdw10 = 1 | (key ? 0 : 1 << 3); - return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register); + return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { - u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0); + u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3); return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 98864b853eef..67d3335e9cc8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3470,6 +3470,10 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN | NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1987, 0x5019), /* phison E19 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x1987, 0x5021), /* Phison E21 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1b4b, 0x1092), /* Lexar 256 GB SSD */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, diff --git a/drivers/reset/reset-imx7.c b/drivers/reset/reset-imx7.c index 185a333df66c..d2408725eb2c 100644 --- a/drivers/reset/reset-imx7.c +++ b/drivers/reset/reset-imx7.c @@ -329,6 +329,7 @@ static int imx8mp_reset_set(struct reset_controller_dev *rcdev, break; case IMX8MP_RESET_PCIE_CTRL_APPS_EN: + case IMX8MP_RESET_PCIEPHY_PERST: value = assert ? 0 : bit; break; } diff --git a/drivers/reset/reset-microchip-sparx5.c b/drivers/reset/reset-microchip-sparx5.c index 00b612a0effa..f3528dd1d084 100644 --- a/drivers/reset/reset-microchip-sparx5.c +++ b/drivers/reset/reset-microchip-sparx5.c @@ -33,11 +33,8 @@ static struct regmap_config sparx5_reset_regmap_config = { .reg_stride = 4, }; -static int sparx5_switch_reset(struct reset_controller_dev *rcdev, - unsigned long id) +static int sparx5_switch_reset(struct mchp_reset_context *ctx) { - struct mchp_reset_context *ctx = - container_of(rcdev, struct mchp_reset_context, rcdev); u32 val; /* Make sure the core is PROTECTED from reset */ @@ -54,8 +51,14 @@ static int sparx5_switch_reset(struct reset_controller_dev *rcdev, 1, 100); } +static int sparx5_reset_noop(struct reset_controller_dev *rcdev, + unsigned long id) +{ + return 0; +} + static const struct reset_control_ops sparx5_reset_ops = { - .reset = sparx5_switch_reset, + .reset = sparx5_reset_noop, }; static int mchp_sparx5_map_syscon(struct platform_device *pdev, char *name, @@ -122,6 +125,11 @@ static int mchp_sparx5_reset_probe(struct platform_device *pdev) ctx->rcdev.of_node = dn; ctx->props = device_get_match_data(&pdev->dev); + /* Issue the reset very early, our actual reset callback is a noop. */ + err = sparx5_switch_reset(ctx); + if (err) + return err; + return devm_reset_controller_register(&pdev->dev, &ctx->rcdev); } @@ -163,6 +171,10 @@ static int __init mchp_sparx5_reset_init(void) return platform_driver_register(&mchp_sparx5_reset_driver); } +/* + * Because this is a global reset, keep this postcore_initcall() to issue the + * reset as early as possible during the kernel startup. + */ postcore_initcall(mchp_sparx5_reset_init); MODULE_DESCRIPTION("Microchip Sparx5 switch reset driver"); diff --git a/drivers/reset/reset-npcm.c b/drivers/reset/reset-npcm.c index 24c55efa98e5..f2333506b0a6 100644 --- a/drivers/reset/reset-npcm.c +++ b/drivers/reset/reset-npcm.c @@ -291,7 +291,7 @@ static void npcm_usb_reset_npcm8xx(struct npcm_rc_data *rc) iprst2 |= ipsrst2_bits; iprst3 |= (ipsrst3_bits | NPCM_IPSRST3_USBPHY1 | NPCM_IPSRST3_USBPHY2); - iprst2 |= ipsrst4_bits; + iprst4 |= ipsrst4_bits; writel(iprst1, rc->base + NPCM_IPSRST1); writel(iprst2, rc->base + NPCM_IPSRST2); diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 9c82e5dc4fcc..a36fa1c128a8 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -872,7 +872,8 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth) struct domain_device *dev = sdev_to_domain_dev(sdev); if (dev_is_sata(dev)) - return __ata_change_queue_depth(dev->sata_dev.ap, sdev, depth); + return ata_change_queue_depth(dev->sata_dev.ap, + sas_to_ata_dev(dev), sdev, depth); if (!sdev->tagged_supported) depth = 1; diff --git a/drivers/soc/bcm/brcmstb/biuctrl.c b/drivers/soc/bcm/brcmstb/biuctrl.c index 1467bbd59690..e1d7b4543248 100644 --- a/drivers/soc/bcm/brcmstb/biuctrl.c +++ b/drivers/soc/bcm/brcmstb/biuctrl.c @@ -288,7 +288,6 @@ static int __init setup_hifcpubiuctrl_regs(struct device_node *np) if (BRCM_ID(family_id) == 0x7260 && BRCM_REV(family_id) == 0) cpubiuctrl_regs = b53_cpubiuctrl_no_wb_regs; out: - of_node_put(np); return ret; } diff --git a/drivers/soc/sunxi/sunxi_sram.c b/drivers/soc/sunxi/sunxi_sram.c index a8f3876963a0..09754cd1d57d 100644 --- a/drivers/soc/sunxi/sunxi_sram.c +++ b/drivers/soc/sunxi/sunxi_sram.c @@ -78,8 +78,8 @@ static struct sunxi_sram_desc sun4i_a10_sram_d = { static struct sunxi_sram_desc sun50i_a64_sram_c = { .data = SUNXI_SRAM_DATA("C", 0x4, 24, 1, - SUNXI_SRAM_MAP(0, 1, "cpu"), - SUNXI_SRAM_MAP(1, 0, "de2")), + SUNXI_SRAM_MAP(1, 0, "cpu"), + SUNXI_SRAM_MAP(0, 1, "de2")), }; static const struct of_device_id sunxi_sram_dt_ids[] = { @@ -254,6 +254,7 @@ int sunxi_sram_claim(struct device *dev) writel(val | ((device << sram_data->offset) & mask), base + sram_data->reg); + sram_desc->claimed = true; spin_unlock(&sram_lock); return 0; @@ -329,11 +330,11 @@ static struct regmap_config sunxi_sram_emac_clock_regmap = { .writeable_reg = sunxi_sram_regmap_accessible_reg, }; -static int sunxi_sram_probe(struct platform_device *pdev) +static int __init sunxi_sram_probe(struct platform_device *pdev) { - struct dentry *d; struct regmap *emac_clock; const struct sunxi_sramc_variant *variant; + struct device *dev = &pdev->dev; sram_dev = &pdev->dev; @@ -345,13 +346,6 @@ static int sunxi_sram_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev); - - d = debugfs_create_file("sram", S_IRUGO, NULL, NULL, - &sunxi_sram_fops); - if (!d) - return -ENOMEM; - if (variant->num_emac_clocks > 0) { emac_clock = devm_regmap_init_mmio(&pdev->dev, base, &sunxi_sram_emac_clock_regmap); @@ -360,6 +354,10 @@ static int sunxi_sram_probe(struct platform_device *pdev) return PTR_ERR(emac_clock); } + of_platform_populate(dev->of_node, NULL, NULL, dev); + + debugfs_create_file("sram", 0444, NULL, NULL, &sunxi_sram_fops); + return 0; } @@ -409,9 +407,8 @@ static struct platform_driver sunxi_sram_driver = { .name = "sunxi-sram", .of_match_table = sunxi_sram_dt_match, }, - .probe = sunxi_sram_probe, }; -module_platform_driver(sunxi_sram_driver); +builtin_platform_driver_probe(sunxi_sram_driver, sunxi_sram_probe); MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>"); MODULE_DESCRIPTION("Allwinner sunXi SRAM Controller Driver"); diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c index 4af5a831bde0..4fc167b42cf0 100644 --- a/drivers/staging/media/rkvdec/rkvdec-h264.c +++ b/drivers/staging/media/rkvdec/rkvdec-h264.c @@ -1162,8 +1162,8 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx) schedule_delayed_work(&rkvdec->watchdog_work, msecs_to_jiffies(2000)); - writel(0xffffffff, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN); - writel(0xffffffff, rkvdec->regs + RKVDEC_REG_H264_ERR_E); + writel(0, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN); + writel(0, rkvdec->regs + RKVDEC_REG_H264_ERR_E); writel(1, rkvdec->regs + RKVDEC_REG_PREF_LUMA_CACHE_COMMAND); writel(1, rkvdec->regs + RKVDEC_REG_PREF_CHR_CACHE_COMMAND); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index c63c1f4ff9dc..77d7f07ca075 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2413,6 +2413,7 @@ int tb_switch_configure(struct tb_switch *sw) * additional capabilities. */ sw->config.cmuv = USB4_VERSION_1_0; + sw->config.plug_events_delay = 0xa; /* Enumerate the switch */ ret = tb_sw_write(sw, (u32 *)&sw->config + 1, TB_CFG_SWITCH, diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c index 166b5bde45cb..6c14a79279f9 100644 --- a/drivers/usb/dwc3/dwc3-st.c +++ b/drivers/usb/dwc3/dwc3-st.c @@ -251,7 +251,7 @@ static int st_dwc3_probe(struct platform_device *pdev) /* Manage SoftReset */ reset_control_deassert(dwc3_data->rstc_rst); - child = of_get_child_by_name(node, "dwc3"); + child = of_get_child_by_name(node, "usb"); if (!child) { dev_err(&pdev->dev, "failed to find dwc3 core node\n"); ret = -ENODEV; diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 23ab3b048d9b..251778d14e2d 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -52,6 +52,13 @@ UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME), +/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */ +UNUSUAL_DEV(0x090c, 0x2000, 0x0000, 0x9999, + "Hiksemi", + "External HDD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? @@ -76,6 +83,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_REPORT_LUNS), +/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */ +UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999, + "Hiksemi", + "External HDD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */ UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, "Initio Corporation", @@ -118,6 +132,13 @@ UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X), +/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */ +UNUSUAL_DEV(0x17ef, 0x3899, 0x0000, 0x9999, + "Thinkplus", + "External HDD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* Reported-by: Hans de Goede <hdegoede@redhat.com> */ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, "VIA", diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 7f2624f42724..6364f0d467ea 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -588,8 +588,6 @@ static int ucsi_get_pdos(struct ucsi_connector *con, int is_partner, num_pdos * sizeof(u32)); if (ret < 0 && ret != -ETIMEDOUT) dev_err(ucsi->dev, "UCSI_GET_PDOS failed (%d)\n", ret); - if (ret == 0 && offset == 0) - dev_warn(ucsi->dev, "UCSI_GET_PDOS returned 0 bytes\n"); return ret; } diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index 75a703b803a2..3e4486bfa0b7 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -323,7 +323,7 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) u32 q_pair_id; ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; - q_pair_id = qid / hw->nr_vring; + q_pair_id = qid / 2; avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; last_avail_idx = vp_ioread16(avail_idx_addr); @@ -337,7 +337,7 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num) u32 q_pair_id; ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; - q_pair_id = qid / hw->nr_vring; + q_pair_id = qid / 2; avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; hw->vring[qid].last_avail_idx = num; vp_iowrite16(num, avail_idx_addr); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index ed100a35e596..90913365def4 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1320,6 +1320,8 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue * static int create_rqt(struct mlx5_vdpa_net *ndev) { + int rqt_table_size = roundup_pow_of_two(ndev->rqt_size); + int act_sz = roundup_pow_of_two(ndev->cur_num_vqs / 2); __be32 *list; void *rqtc; int inlen; @@ -1327,7 +1329,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) int i, j; int err; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + rqt_table_size * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1336,12 +1338,12 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); - MLX5_SET(rqtc, rqtc, rqt_max_size, ndev->rqt_size); + MLX5_SET(rqtc, rqtc, rqt_max_size, rqt_table_size); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) + for (i = 0, j = 0; i < act_sz; i++, j += 2) list[i] = cpu_to_be32(ndev->vqs[j % ndev->cur_num_vqs].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); + MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz); err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); kfree(in); if (err) @@ -1354,6 +1356,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) { + int act_sz = roundup_pow_of_two(num / 2); __be32 *list; void *rqtc; int inlen; @@ -1361,7 +1364,7 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) int i, j; int err; - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + act_sz * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1372,10 +1375,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) + for (i = 0, j = 0; i < act_sz; i++, j = j + 2) list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); + MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz); err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn); kfree(in); if (err) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 41c0b29739f1..35dceee3ed56 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -673,10 +673,15 @@ static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset, { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - if (offset > dev->config_size || - len > dev->config_size - offset) + /* Initialize the buffer in case of partial copy. */ + memset(buf, 0, len); + + if (offset > dev->config_size) return; + if (len > dev->config_size - offset) + len = dev->config_size - offset; + memcpy(buf, dev->config + offset, len); } diff --git a/fs/coredump.c b/fs/coredump.c index 9f4aae202109..1ab4f5b76a1e 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -832,6 +832,38 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) } } +static int dump_emit_page(struct coredump_params *cprm, struct page *page) +{ + struct bio_vec bvec = { + .bv_page = page, + .bv_offset = 0, + .bv_len = PAGE_SIZE, + }; + struct iov_iter iter; + struct file *file = cprm->file; + loff_t pos = file->f_pos; + ssize_t n; + + if (cprm->to_skip) { + if (!__dump_skip(cprm, cprm->to_skip)) + return 0; + cprm->to_skip = 0; + } + if (cprm->written + PAGE_SIZE > cprm->limit) + return 0; + if (dump_interrupted()) + return 0; + iov_iter_bvec(&iter, WRITE, &bvec, 1, PAGE_SIZE); + n = __kernel_write_iter(cprm->file, &iter, &pos); + if (n != PAGE_SIZE) + return 0; + file->f_pos = pos; + cprm->written += PAGE_SIZE; + cprm->pos += PAGE_SIZE; + + return 1; +} + int dump_emit(struct coredump_params *cprm, const void *addr, int nr) { if (cprm->to_skip) { @@ -863,7 +895,6 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page; - int stop; /* * To avoid having to allocate page tables for virtual address @@ -874,10 +905,7 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, */ page = get_dump_page(addr); if (page) { - void *kaddr = kmap_local_page(page); - - stop = !dump_emit(cprm, kaddr, PAGE_SIZE); - kunmap_local(kaddr); + int stop = !dump_emit_page(cprm, page); put_page(page); if (stop) return 0; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 71f5b67d7f28..9dad93059945 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -910,7 +910,7 @@ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, int *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - struct ext4_group_info *grp, *iter; + struct ext4_group_info *grp = NULL, *iter; int i; if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { @@ -927,7 +927,6 @@ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); continue; } - grp = NULL; list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], bb_avg_fragment_size_node) { if (sbi->s_mb_stats) diff --git a/fs/internal.h b/fs/internal.h index 87e96b9024ce..3e206d3e317c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -16,6 +16,7 @@ struct shrink_control; struct fs_context; struct user_namespace; struct pipe_inode_info; +struct iov_iter; /* * block/bdev.c @@ -221,3 +222,5 @@ ssize_t do_getxattr(struct user_namespace *mnt_userns, int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct xattr_ctx *ctx); + +ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 5ae8de09b271..001f4e053c85 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2092,7 +2092,8 @@ get_ctx_vol_failed: // TODO: Initialize security. /* Get the extended system files' directory inode. */ vol->extend_ino = ntfs_iget(sb, FILE_Extend); - if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino)) { + if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) || + !S_ISDIR(vol->extend_ino->i_mode)) { if (!IS_ERR(vol->extend_ino)) iput(vol->extend_ino); ntfs_error(sb, "Failed to load $Extend."); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b2fd3c20e7c2..0c034ea39954 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -28,14 +28,11 @@ #include <linux/crypto.h> #include <linux/string.h> #include <linux/timer.h> -#include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/jiffies.h> #include <linux/workqueue.h> -#include <crypto/acompress.h> - #include "internal.h" /* @@ -93,8 +90,7 @@ module_param(compress, charp, 0444); MODULE_PARM_DESC(compress, "compression to use"); /* Compression parameters */ -static struct crypto_acomp *tfm; -static struct acomp_req *creq; +static struct crypto_comp *tfm; struct pstore_zbackend { int (*zbufsize)(size_t size); @@ -272,21 +268,12 @@ static const struct pstore_zbackend zbackends[] = { static int pstore_compress(const void *in, void *out, unsigned int inlen, unsigned int outlen) { - struct scatterlist src, dst; int ret; if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS)) return -EINVAL; - sg_init_table(&src, 1); - sg_set_buf(&src, in, inlen); - - sg_init_table(&dst, 1); - sg_set_buf(&dst, out, outlen); - - acomp_request_set_params(creq, &src, &dst, inlen, outlen); - - ret = crypto_acomp_compress(creq); + ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); if (ret) { pr_err("crypto_comp_compress failed, ret = %d!\n", ret); return ret; @@ -297,7 +284,7 @@ static int pstore_compress(const void *in, void *out, static void allocate_buf_for_compression(void) { - struct crypto_acomp *acomp; + struct crypto_comp *ctx; int size; char *buf; @@ -309,7 +296,7 @@ static void allocate_buf_for_compression(void) if (!psinfo || tfm) return; - if (!crypto_has_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC)) { + if (!crypto_has_comp(zbackend->name, 0, 0)) { pr_err("Unknown compression: %s\n", zbackend->name); return; } @@ -328,24 +315,16 @@ static void allocate_buf_for_compression(void) return; } - acomp = crypto_alloc_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(acomp)) { + ctx = crypto_alloc_comp(zbackend->name, 0, 0); + if (IS_ERR_OR_NULL(ctx)) { kfree(buf); pr_err("crypto_alloc_comp('%s') failed: %ld\n", zbackend->name, - PTR_ERR(acomp)); - return; - } - - creq = acomp_request_alloc(acomp); - if (!creq) { - crypto_free_acomp(acomp); - kfree(buf); - pr_err("acomp_request_alloc('%s') failed\n", zbackend->name); + PTR_ERR(ctx)); return; } /* A non-NULL big_oops_buf indicates compression is available. */ - tfm = acomp; + tfm = ctx; big_oops_buf_sz = size; big_oops_buf = buf; @@ -355,8 +334,7 @@ static void allocate_buf_for_compression(void) static void free_buf_for_compression(void) { if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) { - acomp_request_free(creq); - crypto_free_acomp(tfm); + crypto_free_comp(tfm); tfm = NULL; } kfree(big_oops_buf); @@ -693,8 +671,6 @@ static void decompress_record(struct pstore_record *record) int ret; int unzipped_len; char *unzipped, *workspace; - struct acomp_req *dreq; - struct scatterlist src, dst; if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed) return; @@ -718,30 +694,16 @@ static void decompress_record(struct pstore_record *record) if (!workspace) return; - dreq = acomp_request_alloc(tfm); - if (!dreq) { - kfree(workspace); - return; - } - - sg_init_table(&src, 1); - sg_set_buf(&src, record->buf, record->size); - - sg_init_table(&dst, 1); - sg_set_buf(&dst, workspace, unzipped_len); - - acomp_request_set_params(dreq, &src, &dst, record->size, unzipped_len); - /* After decompression "unzipped_len" is almost certainly smaller. */ - ret = crypto_acomp_decompress(dreq); + ret = crypto_comp_decompress(tfm, record->buf, record->size, + workspace, &unzipped_len); if (ret) { - pr_err("crypto_acomp_decompress failed, ret = %d!\n", ret); + pr_err("crypto_comp_decompress failed, ret = %d!\n", ret); kfree(workspace); return; } /* Append ECC notice to decompressed buffer. */ - unzipped_len = dreq->dlen; memcpy(workspace + unzipped_len, record->buf + record->size, record->ecc_notice_size); @@ -749,7 +711,6 @@ static void decompress_record(struct pstore_record *record) unzipped = kmemdup(workspace, unzipped_len + record->ecc_notice_size, GFP_KERNEL); kfree(workspace); - acomp_request_free(dreq); if (!unzipped) return; diff --git a/fs/read_write.c b/fs/read_write.c index 1a261dcf1778..328ce8cf9a85 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -496,14 +496,9 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t } /* caller is responsible for file_start_write/file_end_write */ -ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) +ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { - struct kvec iov = { - .iov_base = (void *)buf, - .iov_len = min_t(size_t, count, MAX_RW_COUNT), - }; struct kiocb kiocb; - struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) @@ -519,8 +514,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; - iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); - ret = file->f_op->write_iter(&kiocb, &iter); + ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; @@ -530,6 +524,18 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t inc_syscw(current); return ret; } + +/* caller is responsible for file_start_write/file_end_write */ +ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) +{ + struct kvec iov = { + .iov_base = (void *)buf, + .iov_len = min_t(size_t, count, MAX_RW_COUNT), + }; + struct iov_iter iter; + iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); + return __kernel_write_iter(file, &iter, pos); +} /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 69d9c83ea4b2..5b1f9a24ed59 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -175,13 +175,13 @@ xfs_dax_notify_failure( u64 ddev_start; u64 ddev_end; - if (!(mp->m_sb.sb_flags & SB_BORN)) { + if (!(mp->m_super->s_flags & SB_BORN)) { xfs_warn(mp, "filesystem is not ready for notify_failure()!"); return -EIO; } if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { - xfs_warn(mp, + xfs_debug(mp, "notify_failure() not supported on realtime device!"); return -EOPNOTSUPP; } @@ -194,7 +194,7 @@ xfs_dax_notify_failure( } if (!xfs_has_rmapbt(mp)) { - xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); return -EOPNOTSUPP; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 698032e5ef2d..20765d1c5f80 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1136,8 +1136,8 @@ extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); -extern int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, - int queue_depth); +extern int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev, + struct scsi_device *sdev, int queue_depth); extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6257867fbf95..567f12323f55 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1788,42 +1788,6 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_unlock(); } -/** - * get_mem_cgroup_from_obj - get a memcg associated with passed kernel object. - * @p: pointer to object from which memcg should be extracted. It can be NULL. - * - * Retrieves the memory group into which the memory of the pointed kernel - * object is accounted. If memcg is found, its reference is taken. - * If a passed kernel object is uncharged, or if proper memcg cannot be found, - * as well as if mem_cgroup is disabled, NULL is returned. - * - * Return: valid memcg pointer with taken reference or NULL. - */ -static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p) -{ - struct mem_cgroup *memcg; - - rcu_read_lock(); - do { - memcg = mem_cgroup_from_obj(p); - } while (memcg && !css_tryget(&memcg->css)); - rcu_read_unlock(); - return memcg; -} - -/** - * mem_cgroup_or_root - always returns a pointer to a valid memory cgroup. - * @memcg: pointer to a valid memory cgroup or NULL. - * - * If passed argument is not NULL, returns it without any additional checks - * and changes. Otherwise, root_mem_cgroup is returned. - * - * NOTE: root_mem_cgroup can be NULL during early boot. - */ -static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg) -{ - return memcg ? memcg : root_mem_cgroup; -} #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1880,15 +1844,6 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { } -static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p) -{ - return NULL; -} - -static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg) -{ - return NULL; -} #endif /* CONFIG_MEMCG_KMEM */ #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 19010491a603..c3b4cc84877b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -139,6 +139,11 @@ struct dev_pagemap { }; }; +static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) +{ + return pgmap->ops && pgmap->ops->memory_failure; +} + static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 2ec07de1d73b..b6d7b868f290 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -67,6 +67,8 @@ #define IFF_TAP 0x0002 #define IFF_NAPI 0x0010 #define IFF_NAPI_FRAGS 0x0020 +/* Used in TUNSETIFF to bring up tun/tap without carrier */ +#define IFF_NO_CARRIER 0x0040 #define IFF_NO_PI 0x1000 /* This flag has no real effect */ #define IFF_ONE_QUEUE 0x2000 diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2965b354efc8..242d896c00f3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3357,6 +3357,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, goto err; } + if (ctx->flags & IORING_SETUP_SINGLE_ISSUER + && !(ctx->flags & IORING_SETUP_R_DISABLED)) + ctx->submitter_task = get_task_struct(current); + file = io_uring_get_file(ctx); if (IS_ERR(file)) { ret = PTR_ERR(file); @@ -3548,6 +3552,9 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) if (!(ctx->flags & IORING_SETUP_R_DISABLED)) return -EBADFD; + if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) + ctx->submitter_task = get_task_struct(current); + if (ctx->restrictions.registered) ctx->restricted = 1; diff --git a/io_uring/poll.c b/io_uring/poll.c index d5bad0bea6e4..0d9f49c575e0 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -857,7 +857,7 @@ int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); - if (flags & ~(IORING_POLL_ADD_MULTI|IORING_POLL_ADD_LEVEL)) + if (flags & ~IORING_POLL_ADD_MULTI) return -EINVAL; if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP)) return -EINVAL; diff --git a/kernel/events/core.c b/kernel/events/core.c index 2621fd24ad26..ff4bffc502c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6893,9 +6893,16 @@ static void perf_output_read_group(struct perf_output_handle *handle, { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; + unsigned long flags; u64 values[6]; int n = 0; + /* + * Disabling interrupts avoids all counter scheduling + * (context switches, timer based rotation and IPIs). + */ + local_irq_save(flags); + values[n++] = 1 + leader->nr_siblings; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -6931,6 +6938,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, __output_copy(handle, values, n * sizeof(u64)); } + + local_irq_restore(flags); } #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index cfdf63132d5a..4e51466c4e74 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -884,6 +884,7 @@ static int dbgfs_rm_context(char *name) struct dentry *root, *dir, **new_dirs; struct damon_ctx **new_ctxs; int i, j; + int ret = 0; if (damon_nr_running_ctxs()) return -EBUSY; @@ -898,14 +899,16 @@ static int dbgfs_rm_context(char *name) new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs), GFP_KERNEL); - if (!new_dirs) - return -ENOMEM; + if (!new_dirs) { + ret = -ENOMEM; + goto out_dput; + } new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs), GFP_KERNEL); if (!new_ctxs) { - kfree(new_dirs); - return -ENOMEM; + ret = -ENOMEM; + goto out_new_dirs; } for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) { @@ -925,7 +928,13 @@ static int dbgfs_rm_context(char *name) dbgfs_ctxs = new_ctxs; dbgfs_nr_ctxs--; - return 0; + goto out_dput; + +out_new_dirs: + kfree(new_dirs); +out_dput: + dput(dir); + return ret; } static ssize_t dbgfs_rm_context_write(struct file *file, diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 7488e27c87c3..bdef9682d0a0 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -2182,12 +2182,12 @@ static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target, if (!t) return -ENOMEM; + damon_add_target(ctx, t); if (damon_target_has_pid(ctx)) { t->pid = find_get_pid(sys_target->pid); if (!t->pid) goto destroy_targets_out; } - damon_add_target(ctx, t); err = damon_sysfs_set_regions(t, sys_target->regions); if (err) goto destroy_targets_out; diff --git a/mm/frontswap.c b/mm/frontswap.c index 1a97610308cb..279e55b4ed87 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -125,6 +125,9 @@ void frontswap_init(unsigned type, unsigned long *map) * p->frontswap set to something valid to work properly. */ frontswap_map_set(sis, map); + + if (!frontswap_enabled()) + return; frontswap_ops->init(type); } @@ -2345,8 +2345,28 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +/* + * Fast-gup relies on pte change detection to avoid concurrent pgtable + * operations. + * + * To pin the page, fast-gup needs to do below in order: + * (1) pin the page (by prefetching pte), then (2) check pte not changed. + * + * For the rest of pgtable operations where pgtable updates can be racy + * with fast-gup, we need to do (1) clear pte, then (2) check whether page + * is pinned. + * + * Above will work for all pte-level operations, including THP split. + * + * For THP collapse, it's a bit more complicated because fast-gup may be + * walking a pgtable page that is being freed (pte is still valid but pmd + * can be cleared already). To avoid race in such condition, we need to + * also check pmd here to make sure pmd doesn't change (corresponds to + * pmdp_collapse_flush() in the THP collapse code path). + */ +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; @@ -2392,7 +2412,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, goto pte_unmap; } - if (unlikely(pte_val(pte) != pte_val(*ptep))) { + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || + unlikely(pte_val(pte) != pte_val(*ptep))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } @@ -2439,8 +2460,9 @@ pte_unmap: * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_huge_pmd even if we can't operate on ptes. */ -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { return 0; } @@ -2764,7 +2786,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, PMD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pte_range(pmd, addr, next, flags, pages, nr)) + } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e9414ee57c5b..f42bb51e023a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2894,11 +2894,9 @@ static void split_huge_pages_all(void) max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { int nr_pages; - if (!pfn_valid(pfn)) - continue; - page = pfn_to_page(pfn); - if (!get_page_unless_zero(page)) + page = pfn_to_online_page(pfn); + if (!page || !get_page_unless_zero(page)) continue; if (zone != page_zone(page)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e070b8593b37..0bdfc7e1c933 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3420,6 +3420,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) { int i, nid = page_to_nid(page); struct hstate *target_hstate; + struct page *subpage; int rc = 0; target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); @@ -3453,15 +3454,16 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) mutex_lock(&target_hstate->resize_lock); for (i = 0; i < pages_per_huge_page(h); i += pages_per_huge_page(target_hstate)) { + subpage = nth_page(page, i); if (hstate_is_gigantic(target_hstate)) - prep_compound_gigantic_page_for_demote(page + i, + prep_compound_gigantic_page_for_demote(subpage, target_hstate->order); else - prep_compound_page(page + i, target_hstate->order); - set_page_private(page + i, 0); - set_page_refcounted(page + i); - prep_new_huge_page(target_hstate, page + i, nid); - put_page(page + i); + prep_compound_page(subpage, target_hstate->order); + set_page_private(subpage, 0); + set_page_refcounted(subpage); + prep_new_huge_page(target_hstate, subpage, nid); + put_page(subpage); } mutex_unlock(&target_hstate->resize_lock); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 01f71786d530..70b7ac66411c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1083,10 +1083,12 @@ static void collapse_huge_page(struct mm_struct *mm, pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* - * After this gup_fast can't run anymore. This also removes - * any huge TLB entry from the CPU so we won't allow - * huge and small TLB entries for the same virtual address - * to avoid the risk of CPU bugs in that area. + * This removes any huge TLB entry from the CPU so we won't allow + * huge and small TLB entries for the same virtual address to + * avoid the risk of CPU bugs in that area. + * + * Parallel fast GUP is fine since fast GUP will back off when + * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); diff --git a/mm/madvise.c b/mm/madvise.c index 5f0f0948a50e..9ff51650f4f0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -451,8 +451,11 @@ regular_page: continue; } - /* Do not interfere with other mappings of this page */ - if (page_mapcount(page) != 1) + /* + * Do not interfere with other mappings of this page and + * non-LRU page. + */ + if (!PageLRU(page) || page_mapcount(page) != 1) continue; VM_BUG_ON_PAGE(PageTransCompound(page), page); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 14439806b5ef..e7ac570dda75 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -345,13 +345,17 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, * not much we can do. We just print a message and ignore otherwise. */ +#define FSDAX_INVALID_PGOFF ULONG_MAX + /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. * - * Notice: @fsdax_pgoff is used only when @p is a fsdax page. - * In other cases, such as anonymous and file-backend page, the address to be - * killed can be caculated by @p itself. + * Note: @fsdax_pgoff is used only when @p is a fsdax page and a + * filesystem with a memory failure handler has claimed the + * memory_failure event. In all other cases, page->index and + * page->mapping are sufficient for mapping the page back to its + * corresponding user virtual address. */ static void add_to_kill(struct task_struct *tsk, struct page *p, pgoff_t fsdax_pgoff, struct vm_area_struct *vma, @@ -367,11 +371,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, tk->addr = page_address_in_vma(p, vma); if (is_zone_device_page(p)) { - /* - * Since page->mapping is not used for fsdax, we need - * calculate the address based on the vma. - */ - if (p->pgmap->type == MEMORY_DEVICE_FS_DAX) + if (fsdax_pgoff != FSDAX_INVALID_PGOFF) tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma); tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); } else @@ -523,7 +523,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == t->mm) - add_to_kill(t, page, 0, vma, to_kill); + add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, + to_kill); } } read_unlock(&tasklist_lock); @@ -559,7 +560,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) - add_to_kill(t, page, 0, vma, to_kill); + add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, + to_kill); } } read_unlock(&tasklist_lock); @@ -743,6 +745,9 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn, }; priv.tk.tsk = p; + if (!p->mm) + return -EFAULT; + mmap_read_lock(p->mm); ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops, (void *)&priv); @@ -1928,7 +1933,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * Call driver's implementation to handle the memory failure, otherwise * fall back to generic handler. */ - if (pgmap->ops->memory_failure) { + if (pgmap_has_memory_failure(pgmap)) { rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags); /* * Fall back to generic handler too if operation is not diff --git a/mm/memory.c b/mm/memory.c index 4ba73f5aa8bb..a78814413ac0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4386,14 +4386,20 @@ vm_fault_t finish_fault(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - ret = 0; + /* Re-check under ptl */ - if (likely(!vmf_pte_changed(vmf))) + if (likely(!vmf_pte_changed(vmf))) { do_set_pte(vmf, page, vmf->address); - else + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, vmf->address, vmf->pte); + + ret = 0; + } else { + update_mmu_tlb(vma, vmf->address, vmf->pte); ret = VM_FAULT_NOPAGE; + } - update_mmu_tlb(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 27fb37d65476..dbf6c7a7a7c9 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <linux/memremap.h> #include <linux/migrate.h> +#include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/oom.h> @@ -193,10 +194,10 @@ again: bool anon_exclusive; pte_t swp_pte; + flush_cache_page(vma, addr, pte_pfn(*ptep)); anon_exclusive = PageAnon(page) && PageAnonExclusive(page); if (anon_exclusive) { - flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush(vma, addr, ptep); + pte = ptep_clear_flush(vma, addr, ptep); if (page_try_share_anon_rmap(page)) { set_pte_at(mm, addr, ptep, pte); @@ -206,11 +207,15 @@ again: goto next; } } else { - ptep_get_and_clear(mm, addr, ptep); + pte = ptep_get_and_clear(mm, addr, ptep); } migrate->cpages++; + /* Set the dirty flag on the folio now the pte is gone. */ + if (pte_dirty(pte)) + folio_mark_dirty(page_folio(page)); + /* Setup special migration page table entry */ if (mpfn & MIGRATE_PFN_WRITE) entry = make_writable_migration_entry( @@ -254,13 +259,14 @@ next: migrate->dst[migrate->npages] = 0; migrate->src[migrate->npages++] = mpfn; } - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(ptep - 1, ptl); /* Only flush the TLB if we actually modified any entries */ if (unmapped) flush_tlb_range(walk->vma, start, end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(ptep - 1, ptl); + return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e5486d47406e..d04211f0ef0b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4708,6 +4708,30 @@ void fs_reclaim_release(gfp_t gfp_mask) EXPORT_SYMBOL_GPL(fs_reclaim_release); #endif +/* + * Zonelists may change due to hotplug during allocation. Detect when zonelists + * have been rebuilt so allocation retries. Reader side does not lock and + * retries the allocation if zonelist changes. Writer side is protected by the + * embedded spin_lock. + */ +static DEFINE_SEQLOCK(zonelist_update_seq); + +static unsigned int zonelist_iter_begin(void) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqbegin(&zonelist_update_seq); + + return 0; +} + +static unsigned int check_retry_zonelist(unsigned int seq) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqretry(&zonelist_update_seq, seq); + + return seq; +} + /* Perform direct synchronous page reclaim */ static unsigned long __perform_reclaim(gfp_t gfp_mask, unsigned int order, @@ -5001,6 +5025,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int compaction_retries; int no_progress_loops; unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; int reserve_flags; /* @@ -5011,11 +5036,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; -retry_cpuset: +restart: compaction_retries = 0; no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); /* * The fast path uses conservative alloc_flags to succeed only until @@ -5187,9 +5213,13 @@ retry: goto retry; - /* Deal with possible cpuset update races before we start OOM killing */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); @@ -5209,9 +5239,13 @@ retry: } nopage: - /* Deal with possible cpuset update races before we fail */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure @@ -5706,6 +5740,18 @@ refill: /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } } nc->pagecnt_bias--; @@ -6514,9 +6560,8 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; - static DEFINE_SPINLOCK(lock); - spin_lock(&lock); + write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); @@ -6553,7 +6598,7 @@ static void __build_all_zonelists(void *data) #endif } - spin_unlock(&lock); + write_sequnlock(&zonelist_update_seq); } static noinline void __init diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 9d73dc38e3d7..eb3a68ca92ad 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -288,6 +288,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * @isolate_before: isolate the pageblock before the boundary_pfn * @skip_isolation: the flag to skip the pageblock isolation in second * isolate_single_pageblock() + * @migratetype: migrate type to set in error recovery. * * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one * pageblock. When not all pageblocks within a page are isolated at the same @@ -302,9 +303,9 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * the in-use page then splitting the free page. */ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, - gfp_t gfp_flags, bool isolate_before, bool skip_isolation) + gfp_t gfp_flags, bool isolate_before, bool skip_isolation, + int migratetype) { - unsigned char saved_mt; unsigned long start_pfn; unsigned long isolate_pageblock; unsigned long pfn; @@ -328,13 +329,13 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, start_pfn = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES), zone->zone_start_pfn); - saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock)); + if (skip_isolation) { + int mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock)); - if (skip_isolation) - VM_BUG_ON(!is_migrate_isolate(saved_mt)); - else { - ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt, flags, - isolate_pageblock, isolate_pageblock + pageblock_nr_pages); + VM_BUG_ON(!is_migrate_isolate(mt)); + } else { + ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype, + flags, isolate_pageblock, isolate_pageblock + pageblock_nr_pages); if (ret) return ret; @@ -475,7 +476,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, failed: /* restore the original migratetype */ if (!skip_isolation) - unset_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt); + unset_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype); return -EBUSY; } @@ -537,7 +538,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, bool skip_isolation = false; /* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */ - ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false, skip_isolation); + ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false, + skip_isolation, migratetype); if (ret) return ret; @@ -545,7 +547,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, skip_isolation = true; /* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */ - ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true, skip_isolation); + ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true, + skip_isolation, migratetype); if (ret) { unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype); return ret; diff --git a/mm/secretmem.c b/mm/secretmem.c index e3e9590c6fb3..3f7154099795 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -285,7 +285,7 @@ static int secretmem_init(void) secretmem_mnt = kern_mount(&secretmem_fs); if (IS_ERR(secretmem_mnt)) - ret = PTR_ERR(secretmem_mnt); + return PTR_ERR(secretmem_mnt); /* prevent secretmem mappings from ever getting PROT_EXEC */ secretmem_mnt->mnt_flags |= MNT_NOEXEC; diff --git a/mm/swap_state.c b/mm/swap_state.c index e166051566f4..41afa6d45b23 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -151,7 +151,7 @@ void __delete_from_swap_cache(struct folio *folio, for (i = 0; i < nr; i++) { void *entry = xas_store(&xas, shadow); - VM_BUG_ON_FOLIO(entry != folio, folio); + VM_BUG_ON_PAGE(entry != folio, entry); set_page_private(folio_page(folio, i), 0); xas_next(&xas); } diff --git a/mm/util.c b/mm/util.c index c9439c66d8cf..346e40177bc6 100644 --- a/mm/util.c +++ b/mm/util.c @@ -619,6 +619,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (ret || size <= PAGE_SIZE) return ret; + /* non-sleeping allocations are not supported by vmalloc */ + if (!gfpflags_allow_blocking(flags)) + return NULL; + /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); diff --git a/mm/vmscan.c b/mm/vmscan.c index b2b1431352dc..382dbe97329f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2550,8 +2550,8 @@ static void shrink_active_list(unsigned long nr_to_scan, } if (unlikely(buffer_heads_over_limit)) { - if (folio_get_private(folio) && folio_trylock(folio)) { - if (folio_get_private(folio)) + if (folio_test_private(folio) && folio_trylock(folio)) { + if (folio_test_private(folio)) filemap_release_folio(folio, 0); folio_unlock(folio); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6b9f19122ec1..0ec2f5906a27 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -18,7 +18,6 @@ #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> -#include <linux/sched/mm.h> #include <linux/uidgid.h> #include <linux/cookie.h> @@ -1144,13 +1143,7 @@ static int __register_pernet_operations(struct list_head *list, * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { - struct mem_cgroup *old, *memcg; - - memcg = mem_cgroup_or_root(get_mem_cgroup_from_obj(net)); - old = set_active_memcg(memcg); error = ops_init(ops, net); - set_active_memcg(old); - mem_cgroup_put(memcg); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5265d2b6db12..fc764984d687 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4040,7 +4040,6 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, if (!(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && (!elems->he_cap || !elems->he_operation)) { - mutex_unlock(&sdata->local->sta_mtx); sdata_info(sdata, "HE AP is missing HE capability/operation\n"); ret = false; @@ -5589,12 +5588,16 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); - if (WARN_ON(!sta)) + if (WARN_ON(!sta)) { + mutex_unlock(&local->sta_mtx); goto free; + } link_sta = rcu_dereference_protected(sta->link[link->link_id], lockdep_is_held(&local->sta_mtx)); - if (WARN_ON(!link_sta)) + if (WARN_ON(!link_sta)) { + mutex_unlock(&local->sta_mtx); goto free; + } changed |= ieee80211_recalc_twt_req(link, link_sta, elems); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 5f27e6746762..788a82f9c74d 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -10,6 +10,7 @@ #include <linux/random.h> #include <linux/moduleparam.h> #include <linux/ieee80211.h> +#include <linux/minmax.h> #include <net/mac80211.h> #include "rate.h" #include "sta_info.h" @@ -1550,6 +1551,7 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct ieee80211_sta_rates *rates; int i = 0; + int max_rates = min_t(int, mp->hw->max_rates, IEEE80211_TX_RATE_TABLE_SIZE); rates = kzalloc(sizeof(*rates), GFP_ATOMIC); if (!rates) @@ -1559,10 +1561,10 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_tp_rate[0]); /* Fill up remaining, keep one entry for max_probe_rate */ - for (; i < (mp->hw->max_rates - 1); i++) + for (; i < (max_rates - 1); i++) minstrel_ht_set_rate(mp, mi, rates, i, mi->max_tp_rate[i]); - if (i < mp->hw->max_rates) + if (i < max_rates) minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_prob_rate); if (i < IEEE80211_TX_RATE_TABLE_SIZE) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 8e77fd2e9fdf..3f9ddd7f04b6 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -729,7 +729,7 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, if (!sdata) { skb->dev = NULL; - } else { + } else if (!dropped) { unsigned int hdr_size = ieee80211_hdrlen(hdr->frame_control); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index bf7fe6cd9dfc..13249e97a069 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5878,6 +5878,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_reset_network_header(skb); skb_reset_mac_header(skb); + if (local->hw.queues < IEEE80211_NUM_ACS) + goto start_xmit; + /* update QoS header to prioritize control port frames if possible, * priorization also happens for control port frames send over * AF_PACKET @@ -5905,6 +5908,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, } rcu_read_unlock(); +start_xmit: /* mutex lock is only needed for incrementing the cookie counter */ mutex_lock(&local->mtx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 53826c663723..efcefb2dd882 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -301,14 +301,14 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) local_bh_disable(); spin_lock(&fq->lock); + sdata->vif.txqs_stopped[ac] = false; + if (!test_bit(SDATA_STATE_RUNNING, &sdata->state)) goto out; if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; - sdata->vif.txqs_stopped[ac] = false; - list_for_each_entry_rcu(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 969b33a9dd64..f8897a70c11d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2662,7 +2662,7 @@ static void __mptcp_clear_xmit(struct sock *sk) dfrag_clear(sk, dfrag); } -static void mptcp_cancel_work(struct sock *sk) +void mptcp_cancel_work(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -2802,13 +2802,12 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } -static void mptcp_close(struct sock *sk, long timeout) +bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; - lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { @@ -2850,6 +2849,17 @@ cleanup: } else { mptcp_reset_timeout(msk, 0); } + + return do_cancel_work; +} + +static void mptcp_close(struct sock *sk, long timeout) +{ + bool do_cancel_work; + + lock_sock(sk); + + do_cancel_work = __mptcp_close(sk, timeout); release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 132d50833df1..8f372b8f059c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -612,6 +612,8 @@ void mptcp_subflow_reset(struct sock *ssk); void mptcp_subflow_queue_clean(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); +bool __mptcp_close(struct sock *sk, long timeout); +void mptcp_cancel_work(struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c7d49fb6e7bd..07dd23d0fe04 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -602,30 +602,6 @@ static bool subflow_hmac_valid(const struct request_sock *req, return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN); } -static void mptcp_sock_destruct(struct sock *sk) -{ - /* if new mptcp socket isn't accepted, it is free'd - * from the tcp listener sockets request queue, linked - * from req->sk. The tcp socket is released. - * This calls the ULP release function which will - * also remove the mptcp socket, via - * sock_put(ctx->conn). - * - * Problem is that the mptcp socket will be in - * ESTABLISHED state and will not have the SOCK_DEAD flag. - * Both result in warnings from inet_sock_destruct. - */ - if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { - sk->sk_state = TCP_CLOSE; - WARN_ON_ONCE(sk->sk_socket); - sock_orphan(sk); - } - - /* We don't need to clear msk->subflow, as it's still NULL at this point */ - mptcp_destroy_common(mptcp_sk(sk), 0); - inet_sock_destruct(sk); -} - static void mptcp_force_close(struct sock *sk) { /* the msk is not yet exposed to user-space */ @@ -768,7 +744,6 @@ create_child: /* new mpc subflow takes ownership of the newly * created mptcp socket */ - new_msk->sk_destruct = mptcp_sock_destruct; mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); @@ -1763,13 +1738,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk) for (msk = head; msk; msk = next) { struct sock *sk = (struct sock *)msk; - bool slow; + bool slow, do_cancel_work; + sock_hold(sk); slow = lock_sock_fast_nested(sk); next = msk->dl_next; msk->first = NULL; msk->dl_next = NULL; + + do_cancel_work = __mptcp_close(sk, 0); unlock_sock_fast(sk, slow); + if (do_cancel_work) + mptcp_cancel_work(sk); + sock_put(sk); } /* we are still under the listener msk socket lock */ diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index d55afb8d14be..5950974ae8f6 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1394,7 +1394,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, err = tcf_ct_flow_table_get(net, params); if (err) - goto cleanup; + goto cleanup_params; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -1409,6 +1409,9 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return res; +cleanup_params: + if (params->tmpl) + nf_ct_put(params->tmpl); cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); diff --git a/net/wireless/util.c b/net/wireless/util.c index 2c127951764a..775836f6785a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1361,7 +1361,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ - 11769, /* 1.851851... */ + 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ @@ -1444,7 +1444,7 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ - 11769, /* 1.851851... */ + 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index d84ffdf47210..5a478649f338 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -450,6 +450,16 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x51cb, }, + /* RaptorLake-M */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51ce, + }, + /* RaptorLake-PX */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cf, + }, #endif }; diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index 15596452ca37..4f19fd9b65d1 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -901,7 +901,10 @@ static void nau8824_jdet_work(struct work_struct *work) NAU8824_IRQ_KEY_RELEASE_DIS | NAU8824_IRQ_KEY_SHORT_PRESS_DIS, 0); - nau8824_sema_release(nau8824); + if (nau8824->resume_lock) { + nau8824_sema_release(nau8824); + nau8824->resume_lock = false; + } } static void nau8824_setup_auto_irq(struct nau8824 *nau8824) @@ -966,7 +969,10 @@ static irqreturn_t nau8824_interrupt(int irq, void *data) /* release semaphore held after resume, * and cancel jack detection */ - nau8824_sema_release(nau8824); + if (nau8824->resume_lock) { + nau8824_sema_release(nau8824); + nau8824->resume_lock = false; + } cancel_work_sync(&nau8824->jdet_work); } else if (active_irq & NAU8824_KEY_SHORT_PRESS_IRQ) { int key_status, button_pressed; @@ -1524,6 +1530,7 @@ static int __maybe_unused nau8824_suspend(struct snd_soc_component *component) static int __maybe_unused nau8824_resume(struct snd_soc_component *component) { struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component); + int ret; regcache_cache_only(nau8824->regmap, false); regcache_sync(nau8824->regmap); @@ -1531,7 +1538,10 @@ static int __maybe_unused nau8824_resume(struct snd_soc_component *component) /* Hold semaphore to postpone playback happening * until jack detection done. */ - nau8824_sema_acquire(nau8824, 0); + nau8824->resume_lock = true; + ret = nau8824_sema_acquire(nau8824, 0); + if (ret) + nau8824->resume_lock = false; enable_irq(nau8824->irq); } @@ -1940,6 +1950,7 @@ static int nau8824_i2c_probe(struct i2c_client *i2c) nau8824->regmap = devm_regmap_init_i2c(i2c, &nau8824_regmap_config); if (IS_ERR(nau8824->regmap)) return PTR_ERR(nau8824->regmap); + nau8824->resume_lock = false; nau8824->dev = dev; nau8824->irq = i2c->irq; sema_init(&nau8824->jd_sem, 1); diff --git a/sound/soc/codecs/nau8824.h b/sound/soc/codecs/nau8824.h index de4bae8281d0..5fcfc43dfc85 100644 --- a/sound/soc/codecs/nau8824.h +++ b/sound/soc/codecs/nau8824.h @@ -436,6 +436,7 @@ struct nau8824 { struct semaphore jd_sem; int fs; int irq; + int resume_lock; int micbias_voltage; int vref_impedance; int jkdet_polarity; diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 5a844329800f..0f8e6dd214b0 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2494,7 +2494,7 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component, /* Select JD-source */ snd_soc_component_update_bits(component, RT5640_JD_CTRL, - RT5640_JD_MASK, rt5640->jd_src); + RT5640_JD_MASK, rt5640->jd_src << RT5640_JD_SFT); /* Selecting GPIO01 as an interrupt */ snd_soc_component_update_bits(component, RT5640_GPIO_CTRL1, @@ -2504,12 +2504,8 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component, snd_soc_component_update_bits(component, RT5640_GPIO_CTRL3, RT5640_GP1_PF_MASK, RT5640_GP1_PF_OUT); - /* Enabling jd2 in general control 1 */ snd_soc_component_write(component, RT5640_DUMMY1, 0x3f41); - /* Enabling jd2 in general control 2 */ - snd_soc_component_write(component, RT5640_DUMMY2, 0x4001); - rt5640_set_ovcd_params(component); /* @@ -2518,12 +2514,25 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component, * pin 0/1 instead of it being stuck to 1. So we invert the JD polarity * on systems where the hardware does not already do this. */ - if (rt5640->jd_inverted) - snd_soc_component_write(component, RT5640_IRQ_CTRL1, - RT5640_IRQ_JD_NOR); - else - snd_soc_component_write(component, RT5640_IRQ_CTRL1, - RT5640_IRQ_JD_NOR | RT5640_JD_P_INV); + if (rt5640->jd_inverted) { + if (rt5640->jd_src == RT5640_JD_SRC_JD1_IN4P) + snd_soc_component_write(component, RT5640_IRQ_CTRL1, + RT5640_IRQ_JD_NOR); + else if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N) + snd_soc_component_update_bits(component, RT5640_DUMMY2, + RT5640_IRQ_JD2_MASK | RT5640_JD2_MASK, + RT5640_IRQ_JD2_NOR | RT5640_JD2_EN); + } else { + if (rt5640->jd_src == RT5640_JD_SRC_JD1_IN4P) + snd_soc_component_write(component, RT5640_IRQ_CTRL1, + RT5640_IRQ_JD_NOR | RT5640_JD_P_INV); + else if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N) + snd_soc_component_update_bits(component, RT5640_DUMMY2, + RT5640_IRQ_JD2_MASK | RT5640_JD2_P_MASK | + RT5640_JD2_MASK, + RT5640_IRQ_JD2_NOR | RT5640_JD2_P_INV | + RT5640_JD2_EN); + } rt5640->jack = jack; if (rt5640->jack->status & SND_JACK_MICROPHONE) { @@ -2725,10 +2734,8 @@ static int rt5640_probe(struct snd_soc_component *component) if (device_property_read_u32(component->dev, "realtek,jack-detect-source", &val) == 0) { - if (val <= RT5640_JD_SRC_GPIO4) - rt5640->jd_src = val << RT5640_JD_SFT; - else if (val == RT5640_JD_SRC_HDA_HEADER) - rt5640->jd_src = RT5640_JD_SRC_HDA_HEADER; + if (val <= RT5640_JD_SRC_HDA_HEADER) + rt5640->jd_src = val; else dev_warn(component->dev, "Warning: Invalid jack-detect-source value: %d, leaving jack-detect disabled\n", val); @@ -2809,12 +2816,31 @@ static int rt5640_resume(struct snd_soc_component *component) regcache_sync(rt5640->regmap); if (rt5640->jack) { - if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) + if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) { snd_soc_component_update_bits(component, RT5640_DUMMY2, 0x1100, 0x1100); - else - snd_soc_component_write(component, RT5640_DUMMY2, - 0x4001); + } else { + if (rt5640->jd_inverted) { + if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N) + snd_soc_component_update_bits( + component, RT5640_DUMMY2, + RT5640_IRQ_JD2_MASK | + RT5640_JD2_MASK, + RT5640_IRQ_JD2_NOR | + RT5640_JD2_EN); + + } else { + if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N) + snd_soc_component_update_bits( + component, RT5640_DUMMY2, + RT5640_IRQ_JD2_MASK | + RT5640_JD2_P_MASK | + RT5640_JD2_MASK, + RT5640_IRQ_JD2_NOR | + RT5640_JD2_P_INV | + RT5640_JD2_EN); + } + } queue_delayed_work(system_long_wq, &rt5640->jack_work, 0); } diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h index 505c93514051..f58b88e3325b 100644 --- a/sound/soc/codecs/rt5640.h +++ b/sound/soc/codecs/rt5640.h @@ -1984,6 +1984,20 @@ #define RT5640_M_MONO_ADC_R_SFT 12 #define RT5640_MCLK_DET (0x1 << 11) +/* General Control 1 (0xfb) */ +#define RT5640_IRQ_JD2_MASK (0x1 << 12) +#define RT5640_IRQ_JD2_SFT 12 +#define RT5640_IRQ_JD2_BP (0x0 << 12) +#define RT5640_IRQ_JD2_NOR (0x1 << 12) +#define RT5640_JD2_P_MASK (0x1 << 10) +#define RT5640_JD2_P_SFT 10 +#define RT5640_JD2_P_NOR (0x0 << 10) +#define RT5640_JD2_P_INV (0x1 << 10) +#define RT5640_JD2_MASK (0x1 << 8) +#define RT5640_JD2_SFT 8 +#define RT5640_JD2_DIS (0x0 << 8) +#define RT5640_JD2_EN (0x1 << 8) + /* Codec Private Register definition */ /* MIC Over current threshold scale factor (0x15) */ diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index bb653b664146..b6765235a4b3 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -495,6 +495,8 @@ static struct snd_soc_dai_driver tas2770_dai_driver[] = { }, }; +static const struct regmap_config tas2770_i2c_regmap; + static int tas2770_codec_probe(struct snd_soc_component *component) { struct tas2770_priv *tas2770 = @@ -508,6 +510,7 @@ static int tas2770_codec_probe(struct snd_soc_component *component) } tas2770_reset(tas2770); + regmap_reinit_cache(tas2770->regmap, &tas2770_i2c_regmap); return 0; } diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 14be29530fb5..3f128ced4180 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -698,6 +698,10 @@ static int imx_card_parse_of(struct imx_card_data *data) of_node_put(cpu); of_node_put(codec); of_node_put(platform); + + cpu = NULL; + codec = NULL; + platform = NULL; } return 0; diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index a49bfaab6b21..2ff30b40a1e4 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -270,6 +270,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0AFF") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2 | + SOF_SDW_FOUR_SPK), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B00") }, .driver_data = (void *)(SOF_SDW_TGL_HDMI | diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h index b238dbc9eb85..6a10ff5f5be9 100644 --- a/tools/include/linux/gfp.h +++ b/tools/include/linux/gfp.h @@ -3,26 +3,7 @@ #define _TOOLS_INCLUDE_LINUX_GFP_H #include <linux/types.h> - -#define __GFP_BITS_SHIFT 26 -#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -#define __GFP_HIGH 0x20u -#define __GFP_IO 0x40u -#define __GFP_FS 0x80u -#define __GFP_NOWARN 0x200u -#define __GFP_ZERO 0x8000u -#define __GFP_ATOMIC 0x80000u -#define __GFP_ACCOUNT 0x100000u -#define __GFP_DIRECT_RECLAIM 0x400000u -#define __GFP_KSWAPD_RECLAIM 0x2000000u - -#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM) - -#define GFP_ZONEMASK 0x0fu -#define GFP_ATOMIC (__GFP_HIGH | __GFP_ATOMIC | __GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#include <linux/gfp_types.h> static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h new file mode 100644 index 000000000000..5f9f1ed190a0 --- /dev/null +++ b/tools/include/linux/gfp_types.h @@ -0,0 +1 @@ +#include "../../../include/linux/gfp_types.h" diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index dfb6173b2a82..9e9a2b67de19 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest for (i = 0; i < nsyscalls; ++i) for (j = 0; j < expected_nr_events[i]; ++j) { - int foo = syscalls[i](); - ++foo; + syscalls[i](); } md = &evlist->mmap[0]; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 6a001fcfed68..4952abe716f3 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -332,7 +332,7 @@ out_delete_evlist: out: if (err == -EACCES) return TEST_SKIP; - if (err < 0) + if (err < 0 || errs != 0) return TEST_FAIL; return TEST_OK; } diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index 00c7285ce1ac..301f95427159 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -61,7 +61,7 @@ test_register_capture() { echo "Register capture test [Skipped missing registers]" return fi - if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \ + if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \ -c 1000 --per-thread true 2> /dev/null \ | perf script -F ip,sym,iregs -i - 2> /dev/null \ | egrep -q "DI:" diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index c644f94a6500..ec801cffae6b 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then fi # skip the test if the hardware doesn't support branch stack sampling -perf record -b -o- -B true > /dev/null 2>&1 || exit 2 +# and if the architecture doesn't support filter types: any,save_type,u +perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 4fd8d703ff19..8ab035b55875 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type) /* Symbol names that begin with the following are ignored.*/ static const char * const ignored_prefixes[] = { "$", /* local symbols for ARM, MIPS, etc. */ - ".LASANPC", /* s390 kasan local symbols */ + ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */ "__crc_", /* modversions */ "__efistub_", /* arm64 EFI stub namespace */ - "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */ + "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */ "__AArch64ADRPThunk_", /* arm64 lld */ "__ARMV5PILongThunk_", /* arm lld */ "__ARMV7PILongThunk_", diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 9dfae1bda9cc..485e1a343165 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -269,7 +269,7 @@ CFLAGS_expr-flex.o += $(flex_flags) bison_flags := -DYYENABLE_NLS=0 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35) ifeq ($(BISON_GE_35),1) - bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum + bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option else bison_flags += -w endif diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 22dcfe07e886..906476a839e1 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -498,7 +498,7 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr) { union perf_mem_data_src data_src = { 0 }; - bool is_neoverse = is_midr_in_range(midr, neoverse_spe); + bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe); if (record->op == ARM_SPE_LD) data_src.mem_op = PERF_MEM_OP_LOAD; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index c72f8ad96f75..9aa8cdd93de4 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -48,6 +48,7 @@ const volatile __u32 num_cpus = 1; int enabled = 0; int use_cgroup_v2 = 0; +int perf_subsys_id = -1; static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) { @@ -58,7 +59,15 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) int level; int cnt; - cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup); + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup); level = BPF_CORE_READ(cgrp, level); for (cnt = 0; i < MAX_LEVELS; i++) { diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index c4ba2bcf179f..38e3b287dbb2 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -94,6 +94,8 @@ const volatile bool has_prev_state = false; const volatile bool needs_cgroup = false; const volatile bool uses_cgroup_v1 = false; +int perf_subsys_id = -1; + /* * Old kernel used to call it task_struct->state and now it's '__state'. * Use BPF CO-RE "ignored suffix rule" to deal with it like below: @@ -119,11 +121,19 @@ static inline __u64 get_cgroup_id(struct task_struct *t) { struct cgroup *cgrp; - if (uses_cgroup_v1) - cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup); - else - cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp); + if (!uses_cgroup_v1) + return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id); + + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup); return BPF_CORE_READ(cgrp, kn, id); } diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c index 284f8eabd3b9..7c9f9150bad5 100644 --- a/tools/perf/util/parse-events-hybrid.c +++ b/tools/perf/util/parse-events-hybrid.c @@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr, * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. */ attr->type = type; - attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); + attr->config = (attr->config & PERF_HW_EVENT_MASK) | + ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); } static int create_event_hybrid(__u32 config_type, int *idx, @@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx, __u64 config = attr->config; config_hybrid_attr(attr, config_type, pmu->type); + + /* + * Some hybrid hardware cache events are only available on one CPU + * PMU. For example, the 'L1-dcache-load-misses' is only available + * on cpu_core, while the 'L1-icache-loads' is only available on + * cpu_atom. We need to remove "not supported" hybrid cache events. + */ + if (attr->type == PERF_TYPE_HW_CACHE + && !is_event_supported(attr->type, attr->config)) + return 0; + evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, pmu, config_terms); - if (evsel) + if (evsel) { evsel->pmu_name = strdup(pmu->name); - else + if (!evsel->pmu_name) + return -ENOMEM; + } else return -ENOMEM; - attr->type = type; attr->config = config; return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f05e15acd33f..f3b2c2a87456 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -28,6 +28,7 @@ #include "util/parse-events-hybrid.h" #include "util/pmu-hybrid.h" #include "tracepoint.h" +#include "thread_map.h" #define MAX_NAME_LEN 100 @@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) +bool is_event_supported(u8 type, u64 config) +{ + bool ret = true; + int open_return; + struct evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + }; + struct perf_thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; + + evsel = evsel__new(&attr); + if (evsel) { + open_return = evsel__open(evsel, NULL, tmap); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; + } + evsel__delete(evsel); + } + + perf_thread_map__put(tmap); + return ret; +} + const char *event_type(int type) { switch (type) { diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 7e6a601d9cd0..07df7bb7b042 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -19,6 +19,7 @@ struct option; struct perf_pmu; bool have_tracepoints(struct list_head *evlist); +bool is_event_supported(u8 type, u64 config); const char *event_type(int type); diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index ba1ab5134685..c4d5d87fae2f 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -22,7 +22,6 @@ #include "probe-file.h" #include "string2.h" #include "strlist.h" -#include "thread_map.h" #include "tracepoint.h" #include "pfm.h" #include "pmu-hybrid.h" @@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, strlist__delete(sdtlist); } -static bool is_event_supported(u8 type, unsigned int config) -{ - bool ret = true; - int open_return; - struct evsel *evsel; - struct perf_event_attr attr = { - .type = type, - .config = config, - .disabled = 1, - }; - struct perf_thread_map *tmap = thread_map__new_by_tid(0); - - if (tmap == NULL) - return false; - - evsel = evsel__new(&attr); - if (evsel) { - open_return = evsel__open(evsel, NULL, tmap); - ret = open_return >= 0; - - if (open_return == -EACCES) { - /* - * This happens if the paranoid value - * /proc/sys/kernel/perf_event_paranoid is set to 2 - * Re-run with exclude_kernel set; we don't do that - * by default as some ARM machines do not support it. - * - */ - evsel->core.attr.exclude_kernel = 1; - ret = evsel__open(evsel, NULL, tmap) >= 0; - } - evsel__delete(evsel); - } - - perf_thread_map__put(tmap); - return ret; -} - int print_hwcache_events(const char *event_glob, bool name_only) { unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0; diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index c92326c2233a..0f5ba28339cf 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -3,4 +3,4 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum -CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations +CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 4c122f1b1737..6448cb9f710f 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -48,6 +48,8 @@ LIBKVM += lib/rbtree.c LIBKVM += lib/sparsebit.c LIBKVM += lib/test_util.c +LIBKVM_STRING += lib/string_override.c + LIBKVM_x86_64 += lib/x86_64/apic.c LIBKVM_x86_64 += lib/x86_64/handlers.S LIBKVM_x86_64 += lib/x86_64/perf_test_util.c @@ -220,7 +222,8 @@ LIBKVM_C := $(filter %.c,$(LIBKVM)) LIBKVM_S := $(filter %.S,$(LIBKVM)) LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) -LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.* @@ -231,6 +234,12 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ +# Compile the string overrides as freestanding to prevent the compiler from +# generating self-referential code, e.g. without "freestanding" the compiler may +# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion. +$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ + x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) $(TEST_GEN_PROGS): $(LIBKVM_OBJS) $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 1c2749b1481a..76c583a07ea2 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -31,8 +31,9 @@ * These limitations are worked around in this test by using a large enough * region of memory for each vCPU such that the number of translations cached in * the TLB and the number of pages held in pagevecs are a small fraction of the - * overall workload. And if either of those conditions are not true this test - * will fail rather than silently passing. + * overall workload. And if either of those conditions are not true (for example + * in nesting, where TLB size is unlimited) this test will print a warning + * rather than silently passing. */ #include <inttypes.h> #include <limits.h> @@ -172,17 +173,23 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, vcpu_idx, no_pfn, pages); /* - * Test that at least 90% of memory has been marked idle (the rest might - * not be marked idle because the pages have not yet made it to an LRU - * list or the translations are still cached in the TLB). 90% is + * Check that at least 90% of memory has been marked idle (the rest + * might not be marked idle because the pages have not yet made it to an + * LRU list or the translations are still cached in the TLB). 90% is * arbitrary; high enough that we ensure most memory access went through * access tracking but low enough as to not make the test too brittle * over time and across architectures. + * + * Note that when run in nested virtualization, this check will trigger + * much more frequently because TLB size is unlimited and since no flush + * happens, much more pages are cached there and guest won't see the + * "idle" bit cleared. */ - TEST_ASSERT(still_idle < pages / 10, - "vCPU%d: Too many pages still idle (%"PRIu64 " out of %" - PRIu64 ").\n", - vcpu_idx, still_idle, pages); + if (still_idle < pages / 10) + printf("WARNING: vCPU%d: Too many pages still idle (%" PRIu64 + "out of %" PRIu64 "), this will affect performance results" + ".\n", + vcpu_idx, still_idle, pages); close(page_idle_fd); close(pagemap_fd); diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 99fa1410964c..790c6d1ecb34 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -617,6 +617,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t memslot); void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t addr, uint64_t size); +bool kvm_vm_has_ept(struct kvm_vm *vm); void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot); void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm); diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index 71ade6100fd3..2bd25b191d15 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -22,7 +22,7 @@ static void test_dump_stack(void) * Build and run this command: * * addr2line -s -e /proc/$PPID/exe -fpai {backtrace addresses} | \ - * grep -v test_dump_stack | cat -n 1>&2 + * cat -n 1>&2 * * Note that the spacing is different and there's no newline. */ @@ -36,18 +36,24 @@ static void test_dump_stack(void) n * (((sizeof(void *)) * 2) + 1) + /* Null terminator: */ 1]; - char *c; + char *c = cmd; n = backtrace(stack, n); - c = &cmd[0]; - c += sprintf(c, "%s", addr2line); /* - * Skip the first 3 frames: backtrace, test_dump_stack, and - * test_assert. We hope that backtrace isn't inlined and the other two - * we've declared noinline. + * Skip the first 2 frames, which should be test_dump_stack() and + * test_assert(); both of which are declared noinline. Bail if the + * resulting stack trace would be empty. Otherwise, addr2line will block + * waiting for addresses to be passed in via stdin. */ + if (n <= 2) { + fputs(" (stack trace empty)\n", stderr); + return; + } + + c += sprintf(c, "%s", addr2line); for (i = 2; i < n; i++) c += sprintf(c, " %lx", ((unsigned long) stack[i]) - 1); + c += sprintf(c, "%s", pipeline); #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wunused-result" diff --git a/tools/testing/selftests/kvm/lib/string_override.c b/tools/testing/selftests/kvm/lib/string_override.c new file mode 100644 index 000000000000..632398adc229 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/string_override.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> + +/* + * Override the "basic" built-in string helpers so that they can be used in + * guest code. KVM selftests don't support dynamic loading in guest code and + * will jump into the weeds if the compiler decides to insert an out-of-line + * call via the PLT. + */ +int memcmp(const void *cs, const void *ct, size_t count) +{ + const unsigned char *su1, *su2; + int res = 0; + + for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--) { + if ((res = *su1 - *su2) != 0) + break; + } + return res; +} + +void *memcpy(void *dest, const void *src, size_t count) +{ + char *tmp = dest; + const char *s = src; + + while (count--) + *tmp++ = *s++; + return dest; +} + +void *memset(void *s, int c, size_t count) +{ + char *xs = s; + + while (count--) + *xs++ = c; + return s; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 80a568c439b8..d21049c38fc5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -5,6 +5,8 @@ * Copyright (C) 2018, Google LLC. */ +#include <asm/msr-index.h> + #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -542,9 +544,27 @@ void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, __nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G); } +bool kvm_vm_has_ept(struct kvm_vm *vm) +{ + struct kvm_vcpu *vcpu; + uint64_t ctrl; + + vcpu = list_first_entry(&vm->vcpus, struct kvm_vcpu, list); + TEST_ASSERT(vcpu, "Cannot determine EPT support without vCPUs.\n"); + + ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32; + if (!(ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) + return false; + + ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2) >> 32; + return ctrl & SECONDARY_EXEC_ENABLE_EPT; +} + void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot) { + TEST_REQUIRE(kvm_vm_has_ept(vm)); + vmx->eptp = (void *)vm_vaddr_alloc_page(vm); vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp); diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index b1905d280ef5..e0004bd26536 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -14,6 +14,9 @@ #include "kvm_util.h" #include "processor.h" +/* VMCALL and VMMCALL are both 3-byte opcodes. */ +#define HYPERCALL_INSN_SIZE 3 + static bool ud_expected; static void guest_ud_handler(struct ex_regs *regs) @@ -22,7 +25,7 @@ static void guest_ud_handler(struct ex_regs *regs) GUEST_DONE(); } -extern unsigned char svm_hypercall_insn; +extern uint8_t svm_hypercall_insn[HYPERCALL_INSN_SIZE]; static uint64_t svm_do_sched_yield(uint8_t apic_id) { uint64_t ret; @@ -39,7 +42,7 @@ static uint64_t svm_do_sched_yield(uint8_t apic_id) return ret; } -extern unsigned char vmx_hypercall_insn; +extern uint8_t vmx_hypercall_insn[HYPERCALL_INSN_SIZE]; static uint64_t vmx_do_sched_yield(uint8_t apic_id) { uint64_t ret; @@ -56,30 +59,20 @@ static uint64_t vmx_do_sched_yield(uint8_t apic_id) return ret; } -static void assert_hypercall_insn(unsigned char *exp_insn, unsigned char *obs_insn) -{ - uint32_t exp = 0, obs = 0; - - memcpy(&exp, exp_insn, sizeof(exp)); - memcpy(&obs, obs_insn, sizeof(obs)); - - GUEST_ASSERT_EQ(exp, obs); -} - static void guest_main(void) { - unsigned char *native_hypercall_insn, *hypercall_insn; + uint8_t *native_hypercall_insn, *hypercall_insn; uint8_t apic_id; apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID)); if (is_intel_cpu()) { - native_hypercall_insn = &vmx_hypercall_insn; - hypercall_insn = &svm_hypercall_insn; + native_hypercall_insn = vmx_hypercall_insn; + hypercall_insn = svm_hypercall_insn; svm_do_sched_yield(apic_id); } else if (is_amd_cpu()) { - native_hypercall_insn = &svm_hypercall_insn; - hypercall_insn = &vmx_hypercall_insn; + native_hypercall_insn = svm_hypercall_insn; + hypercall_insn = vmx_hypercall_insn; vmx_do_sched_yield(apic_id); } else { GUEST_ASSERT(0); @@ -87,8 +80,13 @@ static void guest_main(void) return; } + /* + * The hypercall didn't #UD (guest_ud_handler() signals "done" if a #UD + * occurs). Verify that a #UD is NOT expected and that KVM patched in + * the native hypercall. + */ GUEST_ASSERT(!ud_expected); - assert_hypercall_insn(native_hypercall_insn, hypercall_insn); + GUEST_ASSERT(!memcmp(native_hypercall_insn, hypercall_insn, HYPERCALL_INSN_SIZE)); GUEST_DONE(); } diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c index 072d709c96b4..65aea27d761c 100644 --- a/tools/testing/selftests/net/reuseport_bpf.c +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -328,7 +328,7 @@ static void test_extra_filter(const struct test_params p) if (bind(fd1, addr, sockaddr_size())) error(1, errno, "failed to bind recv socket 1"); - if (!bind(fd2, addr, sockaddr_size()) && errno != EADDRINUSE) + if (!bind(fd2, addr, sockaddr_size()) || errno != EADDRINUSE) error(1, errno, "bind socket 2 should fail with EADDRINUSE"); free(addr); diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 363b98228301..5d3440f474dd 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -14,6 +14,7 @@ struct virtio_device { u64 features; struct list_head vqs; spinlock_t vqs_list_lock; + const struct virtio_config_ops *config; }; struct virtqueue { @@ -23,7 +24,9 @@ struct virtqueue { struct virtio_device *vdev; unsigned int index; unsigned int num_free; + unsigned int num_max; void *priv; + bool reset; }; /* Interfaces exported by virtio_ring. */ diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index f2640e505c4e..2a8a70e2a950 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -3,6 +3,11 @@ #include <linux/virtio.h> #include <uapi/linux/virtio_config.h> +struct virtio_config_ops { + int (*disable_vq_and_reset)(struct virtqueue *vq); + int (*enable_vq_after_reset)(struct virtqueue *vq); +}; + /* * __virtio_test_bit - helper to test feature bits. For use by transports. * Devices should normally use virtio_has_feature, |