diff options
156 files changed, 1938 insertions, 804 deletions
@@ -207,6 +207,7 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> +Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org> Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com> David Brownell <david-b@pacbell.net> David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org> @@ -794,6 +795,7 @@ Sven Eckelmann <sven@narfation.org> <sven.eckelmann@open-mesh.com> Sven Eckelmann <sven@narfation.org> <sven.eckelmann@openmesh.com> Sven Eckelmann <sven@narfation.org> <sven@open-mesh.com> Sven Peter <sven@kernel.org> <sven@svenpeter.dev> +Szymon Wilczek <swilczek.lx@gmail.com> <szymonwilczek@gmx.com> Takashi YOSHII <takashi.yoshii.zj@renesas.com> Tamizh Chelvam Raja <quic_tamizhr@quicinc.com> <tamizhr@codeaurora.org> Taniya Das <quic_tdas@quicinc.com> <tdas@codeaurora.org> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a8d0afde7f85..1058f2a6d6a8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2917,6 +2917,41 @@ Kernel parameters for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" are exclusive, so you cannot specify multiple forms. + kfence.burst= [MM,KFENCE] The number of additional successive + allocations to be attempted through KFENCE for each + sample interval. + Format: <unsigned integer> + Default: 0 + + kfence.check_on_panic= + [MM,KFENCE] Whether to check all KFENCE-managed objects' + canaries on panic. + Format: <bool> + Default: false + + kfence.deferrable= + [MM,KFENCE] Whether to use a deferrable timer to trigger + allocations. This avoids forcing CPU wake-ups if the + system is idle, at the risk of a less predictable + sample interval. + Format: <bool> + Default: CONFIG_KFENCE_DEFERRABLE + + kfence.sample_interval= + [MM,KFENCE] KFENCE's sample interval in milliseconds. + Format: <unsigned integer> + 0 - Disable KFENCE. + >0 - Enabled KFENCE with given sample interval. + Default: CONFIG_KFENCE_SAMPLE_INTERVAL + + kfence.skip_covered_thresh= + [MM,KFENCE] If pool utilization reaches this threshold + (pool usage%), KFENCE limits currently covered + allocations of the same source from further filling + up the pool. + Format: <unsigned integer> + Default: 75 + kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. Format: <Controller#>[,poll interval] The controller # is the number of the ehci usb debug diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 369a738a6819..91fa4ccd326c 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -303,6 +303,14 @@ netdev_max_backlog Maximum number of packets, queued on the INPUT side, when the interface receives packets faster than kernel can process them. +qdisc_max_burst +------------------ + +Maximum number of packets that can be temporarily stored before +reaching qdisc. + +Default: 1000 + netdev_rss_key -------------- diff --git a/Documentation/devicetree/bindings/sound/everest,es8316.yaml b/Documentation/devicetree/bindings/sound/everest,es8316.yaml index 81a0215050e0..fe5d938ca310 100644 --- a/Documentation/devicetree/bindings/sound/everest,es8316.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es8316.yaml @@ -49,6 +49,10 @@ properties: items: - const: mclk + interrupts: + maxItems: 1 + description: Headphone detect interrupt + port: $ref: audio-graph-port.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml index 3f4f59287c1c..2eb631950963 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml @@ -47,6 +47,12 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + + clock-names: + const: mclk + interrupts: maxItems: 1 description: The CODEC's interrupt output. @@ -98,6 +104,7 @@ properties: - 4 # Use GPIO2 for jack-detect - 5 # Use GPIO3 for jack-detect - 6 # Use GPIO4 for jack-detect + - 7 # Use HDA header for jack-detect realtek,jack-detect-not-inverted: description: @@ -121,6 +128,10 @@ properties: - 2 # Scale current by 1.0 - 3 # Scale current by 1.5 + port: + $ref: audio-graph-port.yaml# + unevaluatedProperties: false + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml index 32dea7392e8d..56c755c22945 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml @@ -70,6 +70,9 @@ properties: "#sound-dai-cells": const: 0 + port: + $ref: /schemas/graph.yaml#/properties/port + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/ufs/ufs-common.yaml b/Documentation/devicetree/bindings/ufs/ufs-common.yaml index 9f04f34d8c5a..ed97f5682509 100644 --- a/Documentation/devicetree/bindings/ufs/ufs-common.yaml +++ b/Documentation/devicetree/bindings/ufs/ufs-common.yaml @@ -48,8 +48,8 @@ properties: enum: [1, 2] default: 2 description: - Number of lanes available per direction. Note that it is assume same - number of lanes is used both directions at once. + Number of lanes available per direction. Note that it is assumed that + the same number of lanes are used in both directions at once. vdd-hba-supply: description: diff --git a/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst b/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst index 696e0a645a7e..f8029bcb5282 100644 --- a/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst +++ b/Documentation/userspace-api/media/v4l/metafmt-arm-mali-c55.rst @@ -44,7 +44,7 @@ member and userspace must populate the type member with a value from struct v4l2_isp_params_buffer *params = (struct v4l2_isp_params_buffer *)buffer; - params->version = MALI_C55_PARAM_BUFFER_V1; + params->version = V4L2_ISP_PARAMS_VERSION_V1; params->data_size = 0; void *data = (void *)params->data; diff --git a/MAINTAINERS b/MAINTAINERS index d0ea96323ba0..41ace5aeecbe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -314,6 +314,7 @@ R: Mauro Carvalho Chehab <mchehab@kernel.org> R: Shuai Xue <xueshuai@linux.alibaba.com> L: linux-acpi@vger.kernel.org F: drivers/acpi/apei/ +F: drivers/firmware/efi/cper* ACPI COMPONENT ARCHITECTURE (ACPICA) M: "Rafael J. Wysocki" <rafael@kernel.org> @@ -9516,6 +9517,7 @@ F: arch/arm/boot/compressed/efi-header.S F: arch/x86/platform/efi/ F: drivers/firmware/efi/ F: include/linux/efi*.h +X: drivers/firmware/efi/cper* EXTERNAL CONNECTOR SUBSYSTEM (EXTCON) M: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -14880,6 +14882,7 @@ LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Sathya Prakash <sathya.prakash@broadcom.com> M: Sreekanth Reddy <sreekanth.reddy@broadcom.com> M: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com> +M: Ranjan Kumar <ranjan.kumar@broadcom.com> L: MPT-FusionLinux.pdl@broadcom.com L: linux-scsi@vger.kernel.org S: Supported @@ -18423,9 +18426,11 @@ M: Jakub Kicinski <kuba@kernel.org> M: Sabrina Dubroca <sd@queasysnail.net> L: netdev@vger.kernel.org S: Maintained +F: Documentation/networking/tls* F: include/net/tls.h F: include/uapi/linux/tls.h -F: net/tls/* +F: net/tls/ +F: tools/testing/selftests/net/tls.c NETWORKING [SOCKETS] M: Eric Dumazet <edumazet@google.com> diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index a673d3d68254..8986048f9b11 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,6 +425,28 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif +static inline void __init highmem_init(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + /* + * If CPU cannot support HIGHMEM discard the memory above highstart_pfn + */ + if (cpu_has_dc_aliases) { + memblock_remove(PFN_PHYS(highstart_pfn), -1); + return; + } + + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { + struct page *page = pfn_to_page(tmp); + + if (!memblock_is_memory(PFN_PHYS(tmp))) + SetPageReserved(page); + } +#endif +} + void __init arch_mm_preinit(void) { /* @@ -435,6 +457,7 @@ void __init arch_mm_preinit(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ + highmem_init(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2429cb1c7baa..764001deb060 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/processor.h> #include <linux/smp.h> +#include <linux/sys_info.h> #include <asm/interrupt.h> #include <asm/paca.h> @@ -235,7 +236,11 @@ static void watchdog_smp_panic(int cpu) pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000); - if (!sysctl_hardlockup_all_cpu_backtrace) { + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) { + trigger_allbutcpu_cpu_backtrace(cpu); + cpumask_clear(&wd_smp_cpus_ipi); + } else { /* * Try to trigger the stuck CPUs, unless we are going to * get a backtrace on all of them anyway. @@ -244,11 +249,9 @@ static void watchdog_smp_panic(int cpu) smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } - } else { - trigger_allbutcpu_cpu_backtrace(cpu); - cpumask_clear(&wd_smp_cpus_ipi); } + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); @@ -415,9 +418,11 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi - if (sysctl_hardlockup_all_cpu_backtrace) + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) trigger_allbutcpu_cpu_backtrace(cpu); + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 5f9457e910e8..37888abee70c 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1133,10 +1133,6 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, store_args(nr_arg_slots, args_off, ctx); - /* skip to actual body of traced function */ - if (flags & BPF_TRAMP_F_ORIG_STACK) - orig_call += RV_FENTRY_NINSNS * 4; - if (flags & BPF_TRAMP_F_CALL_ORIG) { emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); @@ -1171,6 +1167,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* skip to actual body of traced function */ + orig_call += RV_FENTRY_NINSNS * 4; restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); restore_stack_args(nr_arg_slots - RV_MAX_REG_ARGS, args_off, stk_arg_off, ctx); ret = emit_call((const u64)orig_call, true, ctx); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index da233f20ae6f..608983806fd7 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -319,10 +319,29 @@ EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { + struct fpstate *fpstate = guest_fpu->fpstate; + fpregs_lock(); - guest_fpu->fpstate->xfd = xfd; - if (guest_fpu->fpstate->in_use) - xfd_update_state(guest_fpu->fpstate); + + /* + * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the + * save state to its initial configuration. Likewise, KVM_GET_XSAVE does + * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1. + * + * If the guest's FPU state is in hardware, just update XFD: the XSAVE + * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1. + * + * If however the guest's FPU state is NOT resident in hardware, clear + * disabled components in XSTATE_BV now, or a subsequent XRSTOR will + * attempt to load disabled components and generate #NM _in the host_. + */ + if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD)) + fpstate->regs.xsave.header.xfeatures &= ~xfd; + + fpstate->xfd = xfd; + if (fpstate->in_use) + xfd_update_state(fpstate); + fpregs_unlock(); } EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd); @@ -431,6 +450,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, return -EINVAL; /* + * Disabled features must be in their initial state, otherwise XRSTOR + * causes an exception. + */ + if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd)) + return -EINVAL; + + /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this * case (all other components are eventually re-initialized). diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index df78ddee0abb..37dc8465e0f5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -89,6 +89,7 @@ struct kvm_task_sleep_node { struct swait_queue_head wq; u32 token; int cpu; + bool dummy; }; static struct kvm_task_sleep_head { @@ -120,15 +121,26 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { - /* dummy entry exist -> wake up was delivered ahead of PF */ - hlist_del(&e->link); + struct kvm_task_sleep_node *dummy = NULL; + + /* + * The entry can either be a 'dummy' entry (which is put on the + * list when wake-up happens ahead of APF handling completion) + * or a token from another task which should not be touched. + */ + if (e->dummy) { + hlist_del(&e->link); + dummy = e; + } + raw_spin_unlock(&b->lock); - kfree(e); + kfree(dummy); return false; } n->token = token; n->cpu = smp_processor_id(); + n->dummy = false; init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); @@ -231,6 +243,7 @@ again: } dummy->token = token; dummy->cpu = smp_processor_id(); + dummy->dummy = true; init_swait_queue_head(&dummy->wq); hlist_add_head(&dummy->link, &b->list); dummy = NULL; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ff8812f3a129..63afdb6bb078 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5807,9 +5807,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { + union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + /* + * For backwards compatibility, do not expect disabled features to be in + * their initial state. XSTATE_BV[i] must still be cleared whenever + * XFD[i]=1, or XRSTOR would cause a #NM. + */ + xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd; + return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, kvm_caps.supported_xcr0, diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 6d4d06236f61..cc3c83e4cc23 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -28,6 +28,10 @@ static bool sleep_no_lps0 __read_mostly; module_param(sleep_no_lps0, bool, 0644); MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface"); +static bool check_lps0_constraints __read_mostly; +module_param(check_lps0_constraints, bool, 0644); +MODULE_PARM_DESC(check_lps0_constraints, "Check LPS0 device constraints"); + static const struct acpi_device_id lps0_device_ids[] = { {"PNP0D80", }, {"", }, @@ -515,7 +519,8 @@ static struct acpi_scan_handler lps0_handler = { static int acpi_s2idle_begin_lps0(void) { - if (pm_debug_messages_on && !lpi_constraints_table) { + if (lps0_device_handle && !sleep_no_lps0 && check_lps0_constraints && + !lpi_constraints_table) { if (acpi_s2idle_vendor_amd()) lpi_device_get_constraints_amd(); else @@ -539,7 +544,7 @@ static int acpi_s2idle_prepare_late_lps0(void) if (!lps0_device_handle || sleep_no_lps0) return 0; - if (pm_debug_messages_on) + if (check_lps0_constraints) lpi_check_constraints(); /* Screen off */ diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 0867115aeef2..c6ae27c982f4 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -67,14 +67,16 @@ struct dev_dax_range { /** * struct dev_dax - instance data for a subdivision of a dax region, and * data while the device is activated in the driver. - * @region - parent region - * @dax_dev - core dax functionality + * @region: parent region + * @dax_dev: core dax functionality + * @align: alignment of this instance * @target_node: effective numa node if dev_dax memory range is onlined * @dyn_id: is this a dynamic or statically created instance * @id: ida allocated id when the dax_region is not static * @ida: mapping id allocator - * @dev - device core - * @pgmap - pgmap for memmap setup / lifetime (driver owned) + * @dev: device core + * @pgmap: pgmap for memmap setup / lifetime (driver owned) + * @memmap_on_memory: allow kmem to put the memmap in the memory * @nr_range: size of @ranges * @ranges: range tuples of memory used */ diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 0232bd040f61..bd99802cb0ca 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -162,7 +162,7 @@ int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, len -= size; str += size; } - return len - buf_size; + return buf_size - len; } EXPORT_SYMBOL_GPL(cper_bits_to_str); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 55452e61af31..f5ff6e84a9b7 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -819,6 +819,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, if (tbl) { phys_initrd_start = tbl->base; phys_initrd_size = tbl->size; + tbl->base = tbl->size = 0; early_memunmap(tbl, sizeof(*tbl)); } } diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 538f27209ce7..97780f27ce5b 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -6,6 +6,7 @@ * Copyright (c) 2007, MontaVista Software, Inc. <source@mvista.com> */ +#include <linux/cleanup.h> #include <linux/gpio/driver.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -109,6 +110,22 @@ davinci_direction_out(struct gpio_chip *chip, unsigned offset, int value) return __davinci_direction(chip, offset, true, value); } +static int davinci_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct davinci_gpio_controller *d = gpiochip_get_data(chip); + struct davinci_gpio_regs __iomem *g; + u32 mask = __gpio_mask(offset), val; + int bank = offset / 32; + + g = d->regs[bank]; + + guard(spinlock_irqsave)(&d->lock); + + val = readl_relaxed(&g->dir); + + return (val & mask) ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; +} + /* * Read the pin's value (works even if it's set up as output); * returns zero/nonzero. @@ -203,6 +220,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.get = davinci_gpio_get; chips->chip.direction_output = davinci_direction_out; chips->chip.set = davinci_gpio_set; + chips->chip.get_direction = davinci_get_direction; chips->chip.ngpio = ngpio; chips->chip.base = -1; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index dcf427d3cf43..fe2d107b0a84 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -468,9 +468,6 @@ int gpiod_get_direction(struct gpio_desc *desc) test_bit(GPIOD_FLAG_IS_OUT, &flags)) return 0; - if (!guard.gc->get_direction) - return -ENOTSUPP; - ret = gpiochip_get_direction(guard.gc, offset); if (ret < 0) return ret; diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c index 58027b23c206..63f09bb5136e 100644 --- a/drivers/hv/mshv_common.c +++ b/drivers/hv/mshv_common.c @@ -142,6 +142,7 @@ int hv_call_get_partition_property(u64 partition_id, } EXPORT_SYMBOL_GPL(hv_call_get_partition_property); +#ifdef CONFIG_X86 /* * Corresponding sleep states have to be initialized in order for a subsequent * HVCALL_ENTER_SLEEP_STATE call to succeed. Currently only S5 state as per @@ -237,3 +238,4 @@ void hv_machine_power_off(void) BUG(); } +#endif diff --git a/drivers/hv/mshv_regions.c b/drivers/hv/mshv_regions.c index 202b9d551e39..30bacba6aec3 100644 --- a/drivers/hv/mshv_regions.c +++ b/drivers/hv/mshv_regions.c @@ -58,7 +58,7 @@ static long mshv_region_process_chunk(struct mshv_mem_region *region, page_order = folio_order(page_folio(page)); /* The hypervisor only supports 4K and 2M page sizes */ - if (page_order && page_order != HPAGE_PMD_ORDER) + if (page_order && page_order != PMD_ORDER) return -EINVAL; stride = 1 << page_order; @@ -494,13 +494,6 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, unsigned long mstart, mend; int ret = -EPERM; - if (mmu_notifier_range_blockable(range)) - mutex_lock(®ion->mutex); - else if (!mutex_trylock(®ion->mutex)) - goto out_fail; - - mmu_interval_set_seq(mni, cur_seq); - mstart = max(range->start, region->start_uaddr); mend = min(range->end, region->start_uaddr + (region->nr_pages << HV_HYP_PAGE_SHIFT)); @@ -508,10 +501,17 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, page_offset = HVPFN_DOWN(mstart - region->start_uaddr); page_count = HVPFN_DOWN(mend - mstart); + if (mmu_notifier_range_blockable(range)) + mutex_lock(®ion->mutex); + else if (!mutex_trylock(®ion->mutex)) + goto out_fail; + + mmu_interval_set_seq(mni, cur_seq); + ret = mshv_region_remap_pages(region, HV_MAP_GPA_NO_ACCESS, page_offset, page_count); if (ret) - goto out_fail; + goto out_unlock; mshv_region_invalidate_pages(region, page_offset, page_count); @@ -519,6 +519,8 @@ static bool mshv_region_interval_invalidate(struct mmu_interval_notifier *mni, return true; +out_unlock: + mutex_unlock(®ion->mutex); out_fail: WARN_ONCE(ret, "Failed to invalidate region %#llx-%#llx (range %#lx-%#lx, event: %u, pages %#llx-%#llx, mm: %#llx): %d\n", diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index d236aef80a8d..e1e63c2be82b 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -3,6 +3,7 @@ * Helpers for IOMMU drivers implementing SVA */ #include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> #include <linux/mutex.h> #include <linux/sched/mm.h> #include <linux/iommu.h> diff --git a/drivers/media/i2c/ov02c10.c b/drivers/media/i2c/ov02c10.c index b1e540eb8326..cf93d36032e1 100644 --- a/drivers/media/i2c/ov02c10.c +++ b/drivers/media/i2c/ov02c10.c @@ -165,16 +165,12 @@ static const struct reg_sequence sensor_1928x1092_30fps_setting[] = { {0x3809, 0x88}, {0x380a, 0x04}, {0x380b, 0x44}, - {0x3810, 0x00}, - {0x3811, 0x02}, - {0x3812, 0x00}, - {0x3813, 0x02}, {0x3814, 0x01}, {0x3815, 0x01}, {0x3816, 0x01}, {0x3817, 0x01}, - {0x3820, 0xa0}, + {0x3820, 0xa8}, {0x3821, 0x00}, {0x3822, 0x80}, {0x3823, 0x08}, @@ -385,8 +381,6 @@ struct ov02c10 { struct v4l2_ctrl *vblank; struct v4l2_ctrl *hblank; struct v4l2_ctrl *exposure; - struct v4l2_ctrl *hflip; - struct v4l2_ctrl *vflip; struct clk *img_clk; struct gpio_desc *reset; @@ -465,13 +459,17 @@ static int ov02c10_set_ctrl(struct v4l2_ctrl *ctrl) break; case V4L2_CID_HFLIP: + cci_write(ov02c10->regmap, OV02C10_ISP_X_WIN_CONTROL, + ctrl->val ? 2 : 1, &ret); cci_update_bits(ov02c10->regmap, OV02C10_ROTATE_CONTROL, - BIT(3), ov02c10->hflip->val << 3, &ret); + BIT(3), ctrl->val ? 0 : BIT(3), &ret); break; case V4L2_CID_VFLIP: + cci_write(ov02c10->regmap, OV02C10_ISP_Y_WIN_CONTROL, + ctrl->val ? 2 : 1, &ret); cci_update_bits(ov02c10->regmap, OV02C10_ROTATE_CONTROL, - BIT(4), ov02c10->vflip->val << 4, &ret); + BIT(4), ctrl->val << 4, &ret); break; default: @@ -549,15 +547,11 @@ static int ov02c10_init_controls(struct ov02c10 *ov02c10) OV02C10_EXPOSURE_STEP, exposure_max); - ov02c10->hflip = v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, - V4L2_CID_HFLIP, 0, 1, 1, 0); - if (ov02c10->hflip) - ov02c10->hflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; + v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_HFLIP, + 0, 1, 1, 0); - ov02c10->vflip = v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, - V4L2_CID_VFLIP, 0, 1, 1, 0); - if (ov02c10->vflip) - ov02c10->vflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; + v4l2_ctrl_new_std(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_VFLIP, + 0, 1, 1, 0); v4l2_ctrl_new_std_menu_items(ctrl_hdlr, &ov02c10_ctrl_ops, V4L2_CID_TEST_PATTERN, diff --git a/drivers/media/pci/intel/Kconfig b/drivers/media/pci/intel/Kconfig index d9fcddce028b..3f14ca110d06 100644 --- a/drivers/media/pci/intel/Kconfig +++ b/drivers/media/pci/intel/Kconfig @@ -6,7 +6,7 @@ source "drivers/media/pci/intel/ivsc/Kconfig" config IPU_BRIDGE tristate "Intel IPU Bridge" - depends on ACPI || COMPILE_TEST + depends on ACPI depends on I2C help The IPU bridge is a helper library for Intel IPU drivers to diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index c9827e9fe6ff..b2b710094914 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -5,6 +5,7 @@ #include <acpi/acpi_bus.h> #include <linux/cleanup.h> #include <linux/device.h> +#include <linux/dmi.h> #include <linux/i2c.h> #include <linux/mei_cl_bus.h> #include <linux/platform_device.h> @@ -98,6 +99,28 @@ static const struct ipu_sensor_config ipu_supported_sensors[] = { IPU_SENSOR_CONFIG("XMCC0003", 1, 321468000), }; +/* + * DMI matches for laptops which have their sensor mounted upside-down + * without reporting a rotation of 180° in neither the SSDB nor the _PLD. + */ +static const struct dmi_system_id upside_down_sensor_dmi_ids[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 13 9350"), + }, + .driver_data = "OVTI02C1", + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "XPS 16 9640"), + }, + .driver_data = "OVTI02C1", + }, + {} /* Terminating entry */ +}; + static const struct ipu_property_names prop_names = { .clock_frequency = "clock-frequency", .rotation = "rotation", @@ -248,6 +271,12 @@ out_free_buff: static u32 ipu_bridge_parse_rotation(struct acpi_device *adev, struct ipu_sensor_ssdb *ssdb) { + const struct dmi_system_id *dmi_id; + + dmi_id = dmi_first_match(upside_down_sensor_dmi_ids); + if (dmi_id && acpi_dev_hid_match(adev, dmi_id->driver_data)) + return 180; + switch (ssdb->degree) { case IPU_SENSOR_ROTATION_NORMAL: return 0; diff --git a/drivers/media/platform/arm/mali-c55/mali-c55-params.c b/drivers/media/platform/arm/mali-c55/mali-c55-params.c index 082cda4f4f63..be0e909bcf29 100644 --- a/drivers/media/platform/arm/mali-c55/mali-c55-params.c +++ b/drivers/media/platform/arm/mali-c55/mali-c55-params.c @@ -582,13 +582,6 @@ static int mali_c55_params_buf_prepare(struct vb2_buffer *vb) struct mali_c55 *mali_c55 = params->mali_c55; int ret; - if (config->version != MALI_C55_PARAM_BUFFER_V1) { - dev_dbg(mali_c55->dev, - "Unsupported extensible format version: %u\n", - config->version); - return -EINVAL; - } - ret = v4l2_isp_params_validate_buffer_size(mali_c55->dev, vb, v4l2_isp_params_buffer_size(MALI_C55_PARAMS_MAX_SIZE)); if (ret) diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c index 0fbdae280fdc..6dc4b53607b4 100644 --- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c +++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c @@ -96,13 +96,6 @@ #define VSRSTS_RETRIES 20 -#define RZG2L_CSI2_MIN_WIDTH 320 -#define RZG2L_CSI2_MIN_HEIGHT 240 -#define RZG2L_CSI2_MAX_WIDTH 2800 -#define RZG2L_CSI2_MAX_HEIGHT 4095 - -#define RZG2L_CSI2_DEFAULT_WIDTH RZG2L_CSI2_MIN_WIDTH -#define RZG2L_CSI2_DEFAULT_HEIGHT RZG2L_CSI2_MIN_HEIGHT #define RZG2L_CSI2_DEFAULT_FMT MEDIA_BUS_FMT_UYVY8_1X16 enum rzg2l_csi2_pads { @@ -137,6 +130,10 @@ struct rzg2l_csi2_info { int (*dphy_enable)(struct rzg2l_csi2 *csi2); int (*dphy_disable)(struct rzg2l_csi2 *csi2); bool has_system_clk; + unsigned int min_width; + unsigned int min_height; + unsigned int max_width; + unsigned int max_height; }; struct rzg2l_csi2_timings { @@ -418,6 +415,10 @@ static const struct rzg2l_csi2_info rzg2l_csi2_info = { .dphy_enable = rzg2l_csi2_dphy_enable, .dphy_disable = rzg2l_csi2_dphy_disable, .has_system_clk = true, + .min_width = 320, + .min_height = 240, + .max_width = 2800, + .max_height = 4095, }; static int rzg2l_csi2_dphy_setting(struct v4l2_subdev *sd, bool on) @@ -542,6 +543,10 @@ static const struct rzg2l_csi2_info rzv2h_csi2_info = { .dphy_enable = rzv2h_csi2_dphy_enable, .dphy_disable = rzv2h_csi2_dphy_disable, .has_system_clk = false, + .min_width = 320, + .min_height = 240, + .max_width = 4096, + .max_height = 4096, }; static int rzg2l_csi2_mipi_link_setting(struct v4l2_subdev *sd, bool on) @@ -631,6 +636,7 @@ static int rzg2l_csi2_set_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, struct v4l2_subdev_format *fmt) { + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); struct v4l2_mbus_framefmt *src_format; struct v4l2_mbus_framefmt *sink_format; @@ -653,9 +659,11 @@ static int rzg2l_csi2_set_format(struct v4l2_subdev *sd, sink_format->ycbcr_enc = fmt->format.ycbcr_enc; sink_format->quantization = fmt->format.quantization; sink_format->width = clamp_t(u32, fmt->format.width, - RZG2L_CSI2_MIN_WIDTH, RZG2L_CSI2_MAX_WIDTH); + csi2->info->min_width, + csi2->info->max_width); sink_format->height = clamp_t(u32, fmt->format.height, - RZG2L_CSI2_MIN_HEIGHT, RZG2L_CSI2_MAX_HEIGHT); + csi2->info->min_height, + csi2->info->max_height); fmt->format = *sink_format; /* propagate format to source pad */ @@ -668,9 +676,10 @@ static int rzg2l_csi2_init_state(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state) { struct v4l2_subdev_format fmt = { .pad = RZG2L_CSI2_SINK, }; + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); - fmt.format.width = RZG2L_CSI2_DEFAULT_WIDTH; - fmt.format.height = RZG2L_CSI2_DEFAULT_HEIGHT; + fmt.format.width = csi2->info->min_width; + fmt.format.height = csi2->info->min_height; fmt.format.field = V4L2_FIELD_NONE; fmt.format.code = RZG2L_CSI2_DEFAULT_FMT; fmt.format.colorspace = V4L2_COLORSPACE_SRGB; @@ -697,16 +706,18 @@ static int rzg2l_csi2_enum_frame_size(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state, struct v4l2_subdev_frame_size_enum *fse) { + struct rzg2l_csi2 *csi2 = sd_to_csi2(sd); + if (fse->index != 0) return -EINVAL; if (!rzg2l_csi2_code_to_fmt(fse->code)) return -EINVAL; - fse->min_width = RZG2L_CSI2_MIN_WIDTH; - fse->min_height = RZG2L_CSI2_MIN_HEIGHT; - fse->max_width = RZG2L_CSI2_MAX_WIDTH; - fse->max_height = RZG2L_CSI2_MAX_HEIGHT; + fse->min_width = csi2->info->min_width; + fse->min_height = csi2->info->min_height; + fse->max_width = csi2->info->max_width; + fse->max_height = csi2->info->max_height; return 0; } diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index cfaea6178a71..e15e320db476 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig CAN_DEV - bool "CAN Device Drivers" + tristate "CAN Device Drivers" default y depends on CAN help @@ -17,7 +17,10 @@ menuconfig CAN_DEV virtual ones. If you own such devices or plan to use the virtual CAN interfaces to develop applications, say Y here. -if CAN_DEV && CAN + To compile as a module, choose M here: the module will be called + can-dev. + +if CAN_DEV config CAN_VCAN tristate "Virtual Local CAN Interface (vcan)" diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 37e2f1a2faec..d7bc10a6b8ea 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_CAN_VCAN) += vcan.o obj-$(CONFIG_CAN_VXCAN) += vxcan.o obj-$(CONFIG_CAN_SLCAN) += slcan/ -obj-$(CONFIG_CAN_DEV) += dev/ +obj-y += dev/ obj-y += esd/ obj-y += rcar/ obj-y += rockchip/ diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 1e6b9e3dc2fe..0ea1ff28dfce 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -310,7 +310,7 @@ static int ctucan_set_secondary_sample_point(struct net_device *ndev) } ssp_cfg = FIELD_PREP(REG_TRV_DELAY_SSP_OFFSET, ssp_offset); - ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x1); + ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x0); } ctucan_write32(priv, CTUCANFD_TRV_DELAY, ssp_cfg); diff --git a/drivers/net/can/dev/Makefile b/drivers/net/can/dev/Makefile index 64226acf0f3d..633687d6b6c0 100644 --- a/drivers/net/can/dev/Makefile +++ b/drivers/net/can/dev/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_CAN) += can-dev.o +obj-$(CONFIG_CAN_DEV) += can-dev.o + +can-dev-y += skb.o -can-dev-$(CONFIG_CAN_DEV) += skb.o can-dev-$(CONFIG_CAN_CALC_BITTIMING) += calc_bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += dev.o diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 091f30e94c61..7ab9578f5b89 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -375,6 +375,32 @@ void can_set_default_mtu(struct net_device *dev) } } +void can_set_cap_info(struct net_device *dev) +{ + struct can_priv *priv = netdev_priv(dev); + u32 can_cap; + + if (can_dev_in_xl_only_mode(priv)) { + /* XL only mode => no CC/FD capability */ + can_cap = CAN_CAP_XL; + } else { + /* mixed mode => CC + FD/XL capability */ + can_cap = CAN_CAP_CC; + + if (priv->ctrlmode & CAN_CTRLMODE_FD) + can_cap |= CAN_CAP_FD; + + if (priv->ctrlmode & CAN_CTRLMODE_XL) + can_cap |= CAN_CAP_XL; + } + + if (priv->ctrlmode & (CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_RESTRICTED)) + can_cap |= CAN_CAP_RO; + + can_set_cap(dev, can_cap); +} + /* helper to define static CAN controller features at device creation time */ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) { @@ -390,6 +416,7 @@ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) /* override MTU which was set by default in can_setup()? */ can_set_default_mtu(dev); + can_set_cap_info(dev); return 0; } diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index d6b0e686fb11..0498198a4696 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -377,6 +377,7 @@ static int can_ctrlmode_changelink(struct net_device *dev, } can_set_default_mtu(dev); + can_set_cap_info(dev); return 0; } diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index f799233c2b72..2d248deb69dc 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1736,7 +1736,7 @@ static int es58x_alloc_rx_urbs(struct es58x_device *es58x_dev) dev_dbg(dev, "%s: Allocated %d rx URBs each of size %u\n", __func__, i, rx_buf_len); - return ret; + return 0; } /** diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index a0233e550a5a..d093babbc320 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -751,6 +751,8 @@ resubmit_urb: hf, parent->hf_size_rx, gs_usb_receive_bulk_callback, parent); + usb_anchor_urb(urb, &parent->rx_submitted); + rc = usb_submit_urb(urb, GFP_ATOMIC); /* USB failure take down all interfaces */ diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index fdc662aea279..76e6b7b5c6a1 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -130,6 +130,19 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static void vcan_set_cap_info(struct net_device *dev) +{ + u32 can_cap = CAN_CAP_CC; + + if (dev->mtu > CAN_MTU) + can_cap |= CAN_CAP_FD; + + if (dev->mtu >= CANXL_MIN_MTU) + can_cap |= CAN_CAP_XL; + + can_set_cap(dev, can_cap); +} + static int vcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ @@ -141,6 +154,7 @@ static int vcan_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); + vcan_set_cap_info(dev); return 0; } @@ -162,6 +176,7 @@ static void vcan_setup(struct net_device *dev) dev->tx_queue_len = 0; dev->flags = IFF_NOARP; can_set_ml_priv(dev, netdev_priv(dev)); + vcan_set_cap_info(dev); /* set flags according to driver capabilities */ if (echo) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index b2c19f8c5f8e..f14c6f02b662 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -125,6 +125,19 @@ static int vxcan_get_iflink(const struct net_device *dev) return iflink; } +static void vxcan_set_cap_info(struct net_device *dev) +{ + u32 can_cap = CAN_CAP_CC; + + if (dev->mtu > CAN_MTU) + can_cap |= CAN_CAP_FD; + + if (dev->mtu >= CANXL_MIN_MTU) + can_cap |= CAN_CAP_XL; + + can_set_cap(dev, can_cap); +} + static int vxcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ @@ -136,6 +149,7 @@ static int vxcan_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); + vxcan_set_cap_info(dev); return 0; } @@ -167,6 +181,7 @@ static void vxcan_setup(struct net_device *dev) can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); + vxcan_set_cap_info(dev); } /* forward declaration for rtnl_create_link() */ diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 420c3f4cf741..1d9760b4b8f4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -218,7 +218,7 @@ static int octep_vf_request_irqs(struct octep_vf_device *oct) ioq_irq_err: while (i) { --i; - free_irq(oct->msix_entries[i].vector, oct); + free_irq(oct->msix_entries[i].vector, oct->ioq_vector[i]); } return -1; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 262dc032e276..ff4ab4691baf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -962,7 +962,7 @@ struct mlx5e_priv { }; struct mlx5e_dev { - struct mlx5e_priv *priv; + struct net_device *netdev; struct devlink_port dl_port; }; @@ -1242,10 +1242,13 @@ struct net_device * mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); -void mlx5e_destroy_netdev(struct mlx5e_priv *priv); -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv); -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv); +void mlx5e_destroy_netdev(struct net_device *netdev); +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv); +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 07fc4d2c8fad..9042c8a388e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6325,6 +6325,7 @@ err_free_cpumask: void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { + bool destroying = test_bit(MLX5E_STATE_DESTROYING, &priv->state); int i; /* bail if change profile failed and also rollback failed */ @@ -6352,6 +6353,8 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) } memset(priv, 0, sizeof(*priv)); + if (destroying) /* restore destroying bit, to allow unload */ + set_bit(MLX5E_STATE_DESTROYING, &priv->state); } static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev, @@ -6584,19 +6587,28 @@ profile_cleanup: return err; } -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv) +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv) { - const struct mlx5e_profile *orig_profile = priv->profile; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; - void *orig_ppriv = priv->ppriv; + struct mlx5e_priv *priv = netdev_priv(netdev); + const struct mlx5e_profile *orig_profile; int err, rollback_err; + void *orig_ppriv; - /* cleanup old profile */ - mlx5e_detach_netdev(priv); - priv->profile->cleanup(priv); - mlx5e_priv_cleanup(priv); + orig_profile = priv->profile; + orig_ppriv = priv->ppriv; + + /* NULL could happen if previous change_profile failed to rollback */ + if (priv->profile) { + WARN_ON_ONCE(priv->mdev != mdev); + /* cleanup old profile */ + mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); + mlx5e_priv_cleanup(priv); + } + /* priv members are not valid from this point ... */ if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); @@ -6613,23 +6625,33 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, return 0; rollback: + if (!orig_profile) { + netdev_warn(netdev, "no original profile to rollback to\n"); + priv->profile = NULL; + return err; + } + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); - if (rollback_err) - netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", - __func__, rollback_err); + if (rollback_err) { + netdev_err(netdev, "failed to rollback to orig profile, %d\n", + rollback_err); + priv->profile = NULL; + } return err; } -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv) +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev) { - mlx5e_netdev_change_profile(priv, &mlx5e_nic_profile, NULL); + mlx5e_netdev_change_profile(netdev, mdev, &mlx5e_nic_profile, NULL); } -void mlx5e_destroy_netdev(struct mlx5e_priv *priv) +void mlx5e_destroy_netdev(struct net_device *netdev) { - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); - mlx5e_priv_cleanup(priv); + if (priv->profile) + mlx5e_priv_cleanup(priv); free_netdev(netdev); } @@ -6637,8 +6659,8 @@ static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos, *to; int err, i; @@ -6684,10 +6706,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos; int i; @@ -6748,11 +6771,11 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_devlink_port_unregister; } SET_NETDEV_DEVLINK_PORT(netdev, &mlx5e_dev->dl_port); + mlx5e_dev->netdev = netdev; mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; @@ -6785,7 +6808,7 @@ err_resume: err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); err_devlink_unregister: @@ -6815,17 +6838,20 @@ static void _mlx5e_remove(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = edev->mdev; mlx5_core_uplink_netdev_set(mdev, NULL); - mlx5e_dcbnl_delete_app(priv); + + if (priv->profile) + mlx5e_dcbnl_delete_app(priv); /* When unload driver, the netdev is in registered state * if it's from legacy mode. If from switchdev mode, it * is already unregistered before changing to NIC profile. */ - if (priv->netdev->reg_state == NETREG_REGISTERED) { - unregister_netdev(priv->netdev); + if (netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(netdev); _mlx5e_suspend(adev, false); } else { struct mlx5_core_dev *pos; @@ -6840,7 +6866,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev) /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ee9595109649..6eec88fa6d10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1508,17 +1508,16 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev; - struct mlx5e_priv *priv; int err; netdev = mlx5_uplink_netdev_get(dev); if (!netdev) return 0; - priv = netdev_priv(netdev); - rpriv->netdev = priv->netdev; - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + /* must not use netdev_priv(netdev), it might not be initialized yet */ + rpriv->netdev = netdev; + err = mlx5e_netdev_change_profile(netdev, dev, + &mlx5e_uplink_rep_profile, rpriv); mlx5_uplink_netdev_put(dev, netdev); return err; } @@ -1546,7 +1545,7 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) unregister_netdev(netdev); - mlx5e_netdev_attach_nic_profile(priv); + mlx5e_netdev_attach_nic_profile(netdev, priv->mdev); } static int @@ -1612,7 +1611,7 @@ err_cleanup_profile: priv->profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev); return err; } @@ -1667,7 +1666,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); free_ppriv: kvfree(ppriv); /* mlx5e_rep_priv */ } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3d47d749ef9f..cbd52cb79268 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1750,6 +1750,9 @@ static int netvsc_set_rxfh(struct net_device *dev, rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (!ndc->rx_table_sz) + return -EOPNOTSUPP; + rndis_dev = ndev->extension; if (rxfh->indir) { for (i = 0; i < ndc->rx_table_sz; i++) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 7966545512cf..b4df7e184791 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -59,7 +59,7 @@ struct macvlan_port { struct macvlan_source_entry { struct hlist_node hlist; - struct macvlan_dev *vlan; + struct macvlan_dev __rcu *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; @@ -146,7 +146,7 @@ static struct macvlan_source_entry *macvlan_hash_lookup_source( hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && - entry->vlan == vlan) + rcu_access_pointer(entry->vlan) == vlan) return entry; } return NULL; @@ -168,7 +168,7 @@ static int macvlan_hash_add_source(struct macvlan_dev *vlan, return -ENOMEM; ether_addr_copy(entry->addr, addr); - entry->vlan = vlan; + RCU_INIT_POINTER(entry->vlan, vlan); h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; @@ -187,6 +187,7 @@ static void macvlan_hash_add(struct macvlan_dev *vlan) static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { + RCU_INIT_POINTER(entry->vlan, NULL); hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } @@ -390,7 +391,7 @@ static void macvlan_flush_sources(struct macvlan_port *port, int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) - if (entry->vlan == vlan) + if (rcu_access_pointer(entry->vlan) == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; @@ -433,9 +434,14 @@ static bool macvlan_forward_source(struct sk_buff *skb, hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { - if (entry->vlan->flags & MACVLAN_FLAG_NODST) + struct macvlan_dev *vlan = rcu_dereference(entry->vlan); + + if (!vlan) + continue; + + if (vlan->flags & MACVLAN_FLAG_NODST) consume = true; - macvlan_forward_source_one(skb, entry->vlan); + macvlan_forward_source_one(skb, vlan); } } @@ -1680,7 +1686,7 @@ static int macvlan_fill_info_macaddr(struct sk_buff *skb, struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { - if (entry->vlan != vlan) + if (rcu_access_pointer(entry->vlan) != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index 89b5b19a9bd2..42d46b5758fc 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -1741,10 +1741,10 @@ static int yt8521_led_hw_control_set(struct phy_device *phydev, u8 index, val |= YT8521_LED_1000_ON_EN; if (test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &rules)) - val |= YT8521_LED_HDX_ON_EN; + val |= YT8521_LED_FDX_ON_EN; if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &rules)) - val |= YT8521_LED_FDX_ON_EN; + val |= YT8521_LED_HDX_ON_EN; if (test_bit(TRIGGER_NETDEV_TX, &rules) || test_bit(TRIGGER_NETDEV_RX, &rules)) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 22d894101c01..db88dcaefb20 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -425,9 +425,6 @@ struct virtnet_info { u16 rss_indir_table_size; u32 rss_hash_types_supported; u32 rss_hash_types_saved; - struct virtio_net_rss_config_hdr *rss_hdr; - struct virtio_net_rss_config_trailer rss_trailer; - u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; /* Has control virtqueue */ bool has_cvq; @@ -441,9 +438,6 @@ struct virtnet_info { /* Packet virtio header size */ u8 hdr_len; - /* Work struct for delayed refilling if we run low on memory. */ - struct delayed_work refill; - /* UDP tunnel support */ bool tx_tnl; @@ -451,12 +445,6 @@ struct virtnet_info { bool rx_tnl_csum; - /* Is delayed refill enabled? */ - bool refill_enabled; - - /* The lock to synchronize the access to refill_enabled */ - spinlock_t refill_lock; - /* Work struct for config space updates */ struct work_struct config_work; @@ -493,7 +481,16 @@ struct virtnet_info { struct failover *failover; u64 device_stats_cap; + + struct virtio_net_rss_config_hdr *rss_hdr; + + /* Must be last as it ends in a flexible-array member. */ + TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data, + u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; + ); }; +static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) == + offsetof(struct virtnet_info, rss_hash_key_data)); struct padded_vnet_hdr { struct virtio_net_hdr_v1_hash hdr; @@ -720,20 +717,6 @@ static void virtnet_rq_free_buf(struct virtnet_info *vi, put_page(virt_to_head_page(buf)); } -static void enable_delayed_refill(struct virtnet_info *vi) -{ - spin_lock_bh(&vi->refill_lock); - vi->refill_enabled = true; - spin_unlock_bh(&vi->refill_lock); -} - -static void disable_delayed_refill(struct virtnet_info *vi) -{ - spin_lock_bh(&vi->refill_lock); - vi->refill_enabled = false; - spin_unlock_bh(&vi->refill_lock); -} - static void enable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); @@ -2948,42 +2931,6 @@ static void virtnet_napi_disable(struct receive_queue *rq) napi_disable(napi); } -static void refill_work(struct work_struct *work) -{ - struct virtnet_info *vi = - container_of(work, struct virtnet_info, refill.work); - bool still_empty; - int i; - - for (i = 0; i < vi->curr_queue_pairs; i++) { - struct receive_queue *rq = &vi->rq[i]; - - /* - * When queue API support is added in the future and the call - * below becomes napi_disable_locked, this driver will need to - * be refactored. - * - * One possible solution would be to: - * - cancel refill_work with cancel_delayed_work (note: - * non-sync) - * - cancel refill_work with cancel_delayed_work_sync in - * virtnet_remove after the netdev is unregistered - * - wrap all of the work in a lock (perhaps the netdev - * instance lock) - * - check netif_running() and return early to avoid a race - */ - napi_disable(&rq->napi); - still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); - virtnet_napi_do_enable(rq->vq, &rq->napi); - - /* In theory, this can happen: if we don't get any buffers in - * we will *never* try to fill again. - */ - if (still_empty) - schedule_delayed_work(&vi->refill, HZ/2); - } -} - static int virtnet_receive_xsk_bufs(struct virtnet_info *vi, struct receive_queue *rq, int budget, @@ -3046,16 +2993,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget, else packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats); + u64_stats_set(&stats.packets, packets); if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { - if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { - spin_lock(&vi->refill_lock); - if (vi->refill_enabled) - schedule_delayed_work(&vi->refill, 0); - spin_unlock(&vi->refill_lock); - } + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) + /* We need to retry refilling in the next NAPI poll so + * we must return budget to make sure the NAPI is + * repolled. + */ + packets = budget; } - u64_stats_set(&stats.packets, packets); u64_stats_update_begin(&rq->stats.syncp); for (i = 0; i < ARRAY_SIZE(virtnet_rq_stats_desc); i++) { size_t offset = virtnet_rq_stats_desc[i].offset; @@ -3226,13 +3173,12 @@ static int virtnet_open(struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int i, err; - enable_delayed_refill(vi); - for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) - /* Make sure we have some buffers: if oom use wq. */ - if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) - schedule_delayed_work(&vi->refill, 0); + /* Pre-fill rq agressively, to make sure we are ready to + * get packets immediately. + */ + try_fill_recv(vi, &vi->rq[i], GFP_KERNEL); err = virtnet_enable_queue_pair(vi, i); if (err < 0) @@ -3251,9 +3197,6 @@ static int virtnet_open(struct net_device *dev) return 0; err_enable_qp: - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); - for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); @@ -3432,8 +3375,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void __virtnet_rx_pause(struct virtnet_info *vi, - struct receive_queue *rq) +static void virtnet_rx_pause(struct virtnet_info *vi, + struct receive_queue *rq) { bool running = netif_running(vi->dev); @@ -3447,62 +3390,37 @@ static void virtnet_rx_pause_all(struct virtnet_info *vi) { int i; - /* - * Make sure refill_work does not run concurrently to - * avoid napi_disable race which leads to deadlock. - */ - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) - __virtnet_rx_pause(vi, &vi->rq[i]); + virtnet_rx_pause(vi, &vi->rq[i]); } -static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +static void virtnet_rx_resume(struct virtnet_info *vi, + struct receive_queue *rq, + bool refill) { - /* - * Make sure refill_work does not run concurrently to - * avoid napi_disable race which leads to deadlock. - */ - disable_delayed_refill(vi); - cancel_delayed_work_sync(&vi->refill); - __virtnet_rx_pause(vi, rq); -} - -static void __virtnet_rx_resume(struct virtnet_info *vi, - struct receive_queue *rq, - bool refill) -{ - bool running = netif_running(vi->dev); - bool schedule_refill = false; + if (netif_running(vi->dev)) { + /* Pre-fill rq agressively, to make sure we are ready to get + * packets immediately. + */ + if (refill) + try_fill_recv(vi, rq, GFP_KERNEL); - if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) - schedule_refill = true; - if (running) virtnet_napi_enable(rq); - - if (schedule_refill) - schedule_delayed_work(&vi->refill, 0); + } } static void virtnet_rx_resume_all(struct virtnet_info *vi) { int i; - enable_delayed_refill(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) - __virtnet_rx_resume(vi, &vi->rq[i], true); + virtnet_rx_resume(vi, &vi->rq[i], true); else - __virtnet_rx_resume(vi, &vi->rq[i], false); + virtnet_rx_resume(vi, &vi->rq[i], false); } } -static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) -{ - enable_delayed_refill(vi); - __virtnet_rx_resume(vi, rq, true); -} - static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { @@ -3516,7 +3434,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); - virtnet_rx_resume(vi, rq); + virtnet_rx_resume(vi, rq, true); return err; } @@ -3829,11 +3747,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) } succ: vi->curr_queue_pairs = queue_pairs; - /* virtnet_open() will refill when device is going to up. */ - spin_lock_bh(&vi->refill_lock); - if (dev->flags & IFF_UP && vi->refill_enabled) - schedule_delayed_work(&vi->refill, 0); - spin_unlock_bh(&vi->refill_lock); + if (dev->flags & IFF_UP) { + local_bh_disable(); + for (int i = 0; i < vi->curr_queue_pairs; ++i) + virtqueue_napi_schedule(&vi->rq[i].napi, vi->rq[i].vq); + local_bh_enable(); + } return 0; } @@ -3843,10 +3762,6 @@ static int virtnet_close(struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int i; - /* Make sure NAPI doesn't schedule refill work */ - disable_delayed_refill(vi); - /* Make sure refill_work doesn't re-enable napi! */ - cancel_delayed_work_sync(&vi->refill); /* Prevent the config change callback from changing carrier * after close */ @@ -5802,7 +5717,6 @@ static int virtnet_restore_up(struct virtio_device *vdev) virtio_device_ready(vdev); - enable_delayed_refill(vi); enable_rx_mode_work(vi); if (netif_running(vi->dev)) { @@ -5892,7 +5806,7 @@ static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queu rq->xsk_pool = pool; - virtnet_rx_resume(vi, rq); + virtnet_rx_resume(vi, rq, true); if (pool) return 0; @@ -6559,7 +6473,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) if (!vi->rq) goto err_rq; - INIT_DELAYED_WORK(&vi->refill, refill_work); for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].pages = NULL; netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll, @@ -6901,7 +6814,6 @@ static int virtnet_probe(struct virtio_device *vdev) INIT_WORK(&vi->config_work, virtnet_config_changed_work); INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); - spin_lock_init(&vi->refill_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; @@ -7165,7 +7077,6 @@ free_failover: net_failover_destroy(vi->failover); free_vqs: virtio_reset_device(vdev); - cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); free: diff --git a/drivers/scsi/bfa/bfa_fcs.c b/drivers/scsi/bfa/bfa_fcs.c index e52ce9b01f49..9b57312f43f5 100644 --- a/drivers/scsi/bfa/bfa_fcs.c +++ b/drivers/scsi/bfa/bfa_fcs.c @@ -1169,7 +1169,7 @@ bfa_fcs_fabric_vport_lookup(struct bfa_fcs_fabric_s *fabric, wwn_t pwwn) * This function should be used only if there is any requirement * to check for FOS version below 6.3. * To check if the attached fabric is a brocade fabric, use - * bfa_lps_is_brcd_fabric() which works for FOS versions 6.3 + * fabric->lps->brcd_switch which works for FOS versions 6.3 * or above only. */ diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index f869108fd969..eebca96c1fc1 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1063,6 +1063,9 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, unsigned char *cmnd, int cmnd_size, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif /* * We need saved copies of a number of fields - this is because @@ -1115,6 +1118,18 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, (sdev->lun << 5 & 0xe0); /* + * Encryption must be disabled for the commands submitted by the error handler. + * Hence, clear the encryption context information. + */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + ses->rq_crypt_keyslot = rq->crypt_keyslot; + ses->rq_crypt_ctx = rq->crypt_ctx; + + rq->crypt_keyslot = NULL; + rq->crypt_ctx = NULL; +#endif + + /* * Zero the sense buffer. The scsi spec mandates that any * untransferred sense data should be interpreted as being zero. */ @@ -1131,6 +1146,10 @@ EXPORT_SYMBOL(scsi_eh_prep_cmnd); */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif + /* * Restore original data */ @@ -1143,6 +1162,11 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + rq->crypt_keyslot = ses->rq_crypt_keyslot; + rq->crypt_ctx = ses->rq_crypt_ctx; +#endif } EXPORT_SYMBOL(scsi_eh_restore_cmnd); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 93031326ac3e..c7d6b76c86d2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2459,7 +2459,7 @@ EXPORT_SYMBOL(scsi_mode_sense); * @retries: number of retries before failing * @sshdr: outpout pointer for decoded sense information. * - * Returns zero if unsuccessful or an error if TUR failed. For + * Returns zero if successful or an error if TUR failed. For * removable media, UNIT_ATTENTION sets ->changed flag. **/ int diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index 3d4d00188c26..d933cebad52b 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -23,6 +23,7 @@ const struct device_type sdw_slave_type = { .release = sdw_slave_release, .uevent = sdw_slave_uevent, }; +EXPORT_SYMBOL_GPL(sdw_slave_type); int sdw_slave_add(struct sdw_bus *bus, struct sdw_slave_id *id, struct fwnode_handle *fwnode) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0babb7035200..604043a7533d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10736,9 +10736,7 @@ static int ufshcd_add_scsi_host(struct ufs_hba *hba) if (is_mcq_supported(hba)) { ufshcd_mcq_enable(hba); err = ufshcd_alloc_mcq(hba); - if (!err) { - ufshcd_config_mcq(hba); - } else { + if (err) { /* Continue with SDB mode */ ufshcd_mcq_disable(hba); use_mcq_mode = false; @@ -11011,6 +11009,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) if (err) goto out_disable; + if (hba->mcq_enabled) + ufshcd_config_mcq(hba); + if (hba->quirks & UFSHCD_QUIRK_SKIP_PH_CONFIGURATION) goto initialized; diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index ecbbf52bf734..66b11cc0703b 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -1112,7 +1112,7 @@ static void ufs_mtk_setup_clk_gating(struct ufs_hba *hba) unsigned long flags; u32 ah_ms = 10; u32 ah_scale, ah_timer; - u32 scale_us[] = {1, 10, 100, 1000, 10000, 100000}; + static const u32 scale_us[] = {1, 10, 100, 1000, 10000, 100000}; if (ufshcd_is_clkgating_allowed(hba)) { if (ufshcd_is_auto_hibern8_supported(hba) && hba->ahit) { diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 97ebe457c00a..d27a0b1080a9 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -484,7 +484,7 @@ static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs) new = bio_alloc(prev->bi_bdev, nr_iovecs, prev->bi_opf, GFP_NOIO); bio_clone_blkg_association(new, prev); new->bi_iter.bi_sector = bio_end_sector(prev); - bio_chain(prev, new); + bio_chain(new, prev); submit_bio(prev); return new; } diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index ab76120705e2..134d7f760a33 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -417,8 +417,10 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; - if (d->len == 0) - return -ENODEV; + if (d->len == 0) { + error = -ENODEV; + goto out_blkdev_put; + } ops = bdev->bd_disk->fops->pr_ops; if (!ops) { diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2248e3ad089a..8a3857a49d84 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -149,7 +149,7 @@ static int nfs4_do_check_delegation(struct inode *inode, fmode_t type, int nfs4_have_delegation(struct inode *inode, fmode_t type, int flags) { if (S_ISDIR(inode->i_mode) && !directory_delegations) - nfs_inode_evict_delegation(inode); + nfs4_inode_set_return_delegation_on_close(inode); return nfs4_do_check_delegation(inode, type, flags, true); } @@ -581,6 +581,10 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation if (delegation == NULL) return 0; + /* Directory delegations don't require any state recovery */ + if (!S_ISREG(inode->i_mode)) + goto out_return; + if (!issync) mode |= O_NONBLOCK; /* Recall of any remaining application leases */ @@ -604,6 +608,7 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation goto out; } +out_return: err = nfs_do_return_delegation(inode, delegation, issync); out: /* Refcount matched in nfs_start_delegation_return_locked() */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 23a78a742b61..8f9ea79b7882 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1440,7 +1440,8 @@ static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) if (!dir || !nfs_verify_change_attribute(dir, verf)) return; - if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + if (NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0) || + (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0))) nfs_set_verifier_delegated(&verf); dentry->d_time = verf; } @@ -1465,6 +1466,49 @@ void nfs_set_verifier(struct dentry *dentry, unsigned long verf) EXPORT_SYMBOL_GPL(nfs_set_verifier); #if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_clear_verifier_file(struct inode *inode) +{ + struct dentry *alias; + struct inode *dir; + + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + spin_lock(&alias->d_lock); + dir = d_inode_rcu(alias->d_parent); + if (!dir || + !NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0)) + nfs_unset_verifier_delegated(&alias->d_time); + spin_unlock(&alias->d_lock); + } +} + +static void nfs_clear_verifier_directory(struct inode *dir) +{ + struct dentry *this_parent; + struct dentry *dentry; + struct inode *inode; + + if (hlist_empty(&dir->i_dentry)) + return; + this_parent = + hlist_entry(dir->i_dentry.first, struct dentry, d_u.d_alias); + + spin_lock(&this_parent->d_lock); + nfs_unset_verifier_delegated(&this_parent->d_time); + dentry = d_first_child(this_parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + inode = d_inode_rcu(dentry); + if (inode && + NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + nfs_unset_verifier_delegated(&dentry->d_time); + spin_unlock(&dentry->d_lock); + } + spin_unlock(&this_parent->d_lock); +} + /** * nfs_clear_verifier_delegated - clear the dir verifier delegation tag * @inode: pointer to inode @@ -1477,16 +1521,13 @@ EXPORT_SYMBOL_GPL(nfs_set_verifier); */ void nfs_clear_verifier_delegated(struct inode *inode) { - struct dentry *alias; - if (!inode) return; spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - spin_lock(&alias->d_lock); - nfs_unset_verifier_delegated(&alias->d_time); - spin_unlock(&alias->d_lock); - } + if (S_ISREG(inode->i_mode)) + nfs_clear_verifier_file(inode); + else if (S_ISDIR(inode->i_mode)) + nfs_clear_verifier_directory(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); @@ -1516,14 +1557,6 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (!nfs_dentry_verify_change(dir, dentry)) return 0; - /* - * If we have a directory delegation then we don't need to revalidate - * the directory. The delegation will either get recalled or we will - * receive a notification when it changes. - */ - if (nfs_have_directory_delegation(dir)) - return 0; - /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { if (rcu_walk) @@ -2217,13 +2250,6 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs_lookup_revalidate_delegated_parent(struct inode *dir, struct dentry *dentry, - struct inode *inode) -{ - return nfs_lookup_revalidate_done(dir, dentry, inode, 1); -} - -static int nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { @@ -2247,12 +2273,10 @@ nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, if (inode == NULL) goto full_reval; - if (nfs_verifier_is_delegated(dentry)) + if (nfs_verifier_is_delegated(dentry) || + nfs_have_directory_delegation(inode)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); - if (nfs_have_directory_delegation(dir)) - return nfs_lookup_revalidate_delegated_parent(dir, dentry, inode); - /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto full_reval; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d020aab40c64..d1c138a416cf 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -511,7 +511,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio->mapping->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c55ea8fa3bfa..c2d8a13a9dbd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -103,7 +103,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, sizeof(struct nfs4_ff_ds_version), gfp_flags); if (!ds_versions) - goto out_scratch; + goto out_err_drain_dsaddrs; for (i = 0; i < version_count; i++) { /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 84049f3cd340..de2cce1d08f4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,7 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int error = 0; kuid_t task_uid = current_fsuid(); kuid_t owner_uid = inode->i_uid; @@ -727,6 +727,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; + if (S_ISREG(inode->i_mode)) + nfs_file_block_o_direct(NFS_I(inode)); + + oldsize = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); @@ -774,10 +778,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) { - nfs_file_block_o_direct(NFS_I(inode)); + if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/io.c b/fs/nfs/io.c index d275b0a250bf..8337f0ae852d 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -84,6 +84,7 @@ nfs_start_io_write(struct inode *inode) nfs_file_block_o_direct(NFS_I(inode)); return err; } +EXPORT_SYMBOL_GPL(nfs_start_io_write); /** * nfs_end_io_write - declare that the buffered write operation is done @@ -97,6 +98,7 @@ nfs_end_io_write(struct inode *inode) { up_write(&inode->i_rwsem); } +EXPORT_SYMBOL_GPL(nfs_end_io_write); /* Call with exclusively locked inode->i_rwsem */ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index a113bfdacfd6..41fbcb3f9167 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -461,6 +461,8 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) v = 0; total = hdr->args.count; base = hdr->args.pgbase; + pagevec += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; while (total && v < hdr->page_array.npages) { len = min_t(size_t, total, PAGE_SIZE - base); bvec_set_page(&iocb->bvec[v], *pagevec, len, base); @@ -618,7 +620,6 @@ static void nfs_local_call_read(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; - bool force_done = false; ssize_t status; int n_iters; @@ -637,13 +638,13 @@ static void nfs_local_call_read(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial read */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_read_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short reads */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_read_iocb_done(iocb); + break; } } } @@ -821,7 +822,6 @@ static void nfs_local_call_write(struct work_struct *work) container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; unsigned long old_flags = current->flags; - bool force_done = false; ssize_t status; int n_iters; @@ -843,13 +843,13 @@ static void nfs_local_call_write(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial write */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_write_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short writes */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_write_iocb_done(iocb); + break; } } file_end_write(filp); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d537fb0c230e..c08520828708 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,7 +114,6 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; - nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -138,13 +137,17 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); @@ -155,7 +158,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -170,7 +173,9 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) @@ -179,7 +184,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -189,14 +194,17 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) { nfs_truncate_last_folio(inode->i_mapping, oldsize, @@ -205,7 +213,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -416,7 +424,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; - loff_t oldsize_dst = i_size_read(dst_inode); + loff_t oldsize_dst; size_t count = args->count; ssize_t status; @@ -461,6 +469,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); + oldsize_dst = i_size_read(dst_inode); status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec1ce593dea2..a0885ae55abc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3894,8 +3894,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -4494,6 +4494,25 @@ static bool should_request_dir_deleg(struct inode *inode) } #endif /* CONFIG_NFS_V4_1 */ +static void nfs4_call_getattr_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server->nfs_client, data->seq_args, + data->seq_res, task); +} + +static void nfs4_call_getattr_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + + nfs4_sequence_process(task, data->seq_res); +} + +static const struct rpc_call_ops nfs4_call_getattr_ops = { + .rpc_call_prepare = nfs4_call_getattr_prepare, + .rpc_call_done = nfs4_call_getattr_done, +}; + static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode) { @@ -4511,16 +4530,26 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_call_getattr_ops, + .callback_data = &data, + }; struct nfs4_gdd_res gdd_res; - unsigned short task_flags = 0; int status; if (nfs4_has_session(server->nfs_client)) - task_flags = RPC_TASK_MOVEABLE; + task_setup.flags = RPC_TASK_MOVEABLE; /* Is this is an attribute revalidation, subject to softreval? */ if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) - task_flags |= RPC_TASK_TIMEOUT; + task_setup.flags |= RPC_TASK_TIMEOUT; args.get_dir_deleg = should_request_dir_deleg(inode); if (args.get_dir_deleg) @@ -4530,22 +4559,24 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); - status = nfs4_do_call_sync(server->client, server, &msg, - &args.seq_args, &res.seq_res, task_flags); + status = nfs4_call_sync_custom(&task_setup); + if (args.get_dir_deleg) { switch (status) { case 0: if (gdd_res.status != GDD4_OK) break; - status = nfs_inode_set_delegation( - inode, current_cred(), FMODE_READ, - &gdd_res.deleg, 0, NFS4_OPEN_DELEGATE_READ); + nfs_inode_set_delegation(inode, current_cred(), + FMODE_READ, &gdd_res.deleg, 0, + NFS4_OPEN_DELEGATE_READ); break; case -ENOTSUPP: case -EOPNOTSUPP: server->caps &= ~NFS_CAP_DIR_DELEG; } } + + nfs4_sequence_free_slot(&res.seq_res); return status; } @@ -7005,7 +7036,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 01179f7de322..dba51c622cf3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1445,6 +1445,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode, struct nfs4_state *state; bool found = false; + if (!S_ISREG(inode->i_mode)) + goto out; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; @@ -1466,7 +1468,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, found = true; } rcu_read_unlock(); - +out: nfs_inode_find_delegation_state_and_recover(inode, stateid); if (found) nfs4_schedule_state_manager(clp); @@ -1478,6 +1480,8 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; + if (!S_ISREG(inode->i_mode)) + return; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 6ce55e8e6b67..9f9ce4a565ea 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1062,6 +1062,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b72d7cc36766..cff225721d1c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1533,10 +1533,9 @@ static int pnfs_layout_return_on_reboot(struct pnfs_layout_hdr *lo) PNFS_FL_LAYOUTRETURN_PRIVILEGED); } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1547,7 +1546,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1560,20 +1559,14 @@ retry: lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1582,12 +1575,43 @@ retry: if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1627,7 +1651,7 @@ retry: out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 91ff877185c8..3db8f13d8fe4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -303,10 +303,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -773,12 +772,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 336c510f3750..bf412455e8ed 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2025,6 +2025,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) } /** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + +/** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page * @folio: pointer to folio diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d97295eaebe6..c19d6d713780 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -848,15 +848,16 @@ sparse_alloc: * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * - * Set min agbno to the first aligned, non-zero agbno and max to - * the last aligned agbno that is at least one full chunk from - * the end of the AG. + * Set min agbno to the first chunk aligned, non-zero agbno and + * max to one less than the last chunk aligned agbno from the + * end of the AG. We subtract 1 from max so that the cluster + * allocation alignment takes over and allows allocation within + * the last full inode chunk in the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(xfs_ag_block_count(args.mp, pag_agno(pag)), - args.mp->m_sb.sb_inoalignmt) - - igeo->ialloc_blks; + args.mp->m_sb.sb_inoalignmt) - 1; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 9186c58e83d5..be16efaa6925 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -48,6 +48,31 @@ xfs_rtgroup_min_block( return 0; } +/* Compute the number of rt extents in this realtime group. */ +static xfs_rtxnum_t +__xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + ASSERT(rgno < rgcount); + if (rgno == rgcount - 1) + return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); + + ASSERT(xfs_has_rtgroups(mp)); + return mp->m_sb.sb_rgextents; +} + +xfs_rtxnum_t +xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, + mp->m_sb.sb_rextents); +} + /* Precompute this group's geometry */ void xfs_rtgroup_calc_geometry( @@ -58,7 +83,8 @@ xfs_rtgroup_calc_geometry( xfs_rtbxlen_t rextents) { rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); - rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + rtg_group(rtg)->xg_block_count = + rtg->rtg_extents * mp->m_sb.sb_rextsize; rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); } @@ -136,31 +162,6 @@ out_unwind_new_rtgs: return error; } -/* Compute the number of rt extents in this realtime group. */ -xfs_rtxnum_t -__xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, - xfs_rtbxlen_t rextents) -{ - ASSERT(rgno < rgcount); - if (rgno == rgcount - 1) - return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); - - ASSERT(xfs_has_rtgroups(mp)); - return mp->m_sb.sb_rgextents; -} - -xfs_rtxnum_t -xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno) -{ - return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, - mp->m_sb.sb_rextents); -} - /* * Update the rt extent count of the previous tail rtgroup if it changed during * recovery (i.e. recovery of a growfs). diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 03f1e2493334..73cace4d25c7 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -285,8 +285,6 @@ void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents); -xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno); void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a311385b23d8..d4544ccafea5 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1180,9 +1180,11 @@ xfs_log_cover( int error = 0; bool need_covered; - ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && - !xfs_ail_min_lsn(mp->m_log->l_ailp)) || - xlog_is_shutdown(mp->m_log)); + if (!xlog_is_shutdown(mp->m_log)) { + ASSERT(xlog_cil_empty(mp->m_log)); + ASSERT(xlog_iclogs_empty(mp->m_log)); + ASSERT(!xfs_ail_min_lsn(mp->m_log->l_ailp)); + } if (!xfs_log_writable(mp)) return 0; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index e063f4f2f2e6..a12ffed12391 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -126,7 +126,7 @@ xfs_rtcopy_summary( error = 0; out: xfs_rtbuf_cache_relse(oargs); - return 0; + return error; } /* * Mark an extent specified by start and len allocated. @@ -1265,7 +1265,7 @@ xfs_growfs_check_rtgeom( uint32_t rem; if (rextsize != 1) - return -EINVAL; + goto out_inval; div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, @@ -1326,7 +1326,7 @@ xfs_grow_last_rtg( return true; if (mp->m_sb.sb_rgcount == 0) return false; - return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <= + return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) < mp->m_sb.sb_rgextents; } diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h index 04b18d0e37af..30fbbde81c5c 100644 --- a/include/hyperv/hvgdk_mini.h +++ b/include/hyperv/hvgdk_mini.h @@ -578,9 +578,12 @@ struct hv_tlb_flush { /* HV_INPUT_FLUSH_VIRTUAL_ADDRESS_LIST */ struct hv_tlb_flush_ex { u64 address_space; u64 flags; - struct hv_vpset hv_vp_set; - u64 gva_list[]; + __TRAILING_OVERLAP(struct hv_vpset, hv_vp_set, bank_contents, __packed, + u64 gva_list[]; + ); } __packed; +static_assert(offsetof(struct hv_tlb_flush_ex, hv_vp_set.bank_contents) == + offsetof(struct hv_tlb_flush_ex, gva_list)); struct ms_hyperv_tsc_page { /* HV_REFERENCE_TSC_PAGE */ volatile u32 tsc_sequence; diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 8afa92d15a66..1e99fda2b380 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -46,6 +46,12 @@ #include <linux/list.h> #include <linux/netdevice.h> +/* exposed CAN device capabilities for network layer */ +#define CAN_CAP_CC BIT(0) /* CAN CC aka Classical CAN */ +#define CAN_CAP_FD BIT(1) /* CAN FD */ +#define CAN_CAP_XL BIT(2) /* CAN XL */ +#define CAN_CAP_RO BIT(3) /* read-only mode (LISTEN/RESTRICTED) */ + #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) @@ -64,6 +70,7 @@ struct can_ml_priv { #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif + u32 can_cap; }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) @@ -77,4 +84,21 @@ static inline void can_set_ml_priv(struct net_device *dev, netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } +static inline bool can_cap_enabled(struct net_device *dev, u32 cap) +{ + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (!can_ml) + return false; + + return (can_ml->can_cap & cap); +} + +static inline void can_set_cap(struct net_device *dev, u32 cap) +{ + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + can_ml->can_cap = cap; +} + #endif /* CAN_ML_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index f6416a56e95d..6d0710d6f571 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -111,18 +111,12 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, void free_candev(struct net_device *dev); /* a candev safe wrapper around netdev_priv */ -#if IS_ENABLED(CONFIG_CAN_NETLINK) struct can_priv *safe_candev_priv(struct net_device *dev); -#else -static inline struct can_priv *safe_candev_priv(struct net_device *dev) -{ - return NULL; -} -#endif int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); void can_set_default_mtu(struct net_device *dev); +void can_set_cap_info(struct net_device *dev); int __must_check can_set_static_ctrlmode(struct net_device *dev, u32 static_mode); int can_hwtstamp_get(struct net_device *netdev, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index b760a3c470a5..f7cc60de0058 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -626,7 +626,13 @@ struct cgroup { #endif /* All ancestors including self */ - struct cgroup *ancestors[]; + union { + DECLARE_FLEX_ARRAY(struct cgroup *, ancestors); + struct { + struct cgroup *_root_ancestor; + DECLARE_FLEX_ARRAY(struct cgroup *, _low_ancestors); + }; + }; }; /* @@ -647,16 +653,6 @@ struct cgroup_root { struct list_head root_list; struct rcu_head rcu; /* Must be near the top */ - /* - * The root cgroup. The containing cgroup_root will be destroyed on its - * release. cgrp->ancestors[0] will be used overflowing into the - * following field. cgrp_ancestor_storage must immediately follow. - */ - struct cgroup cgrp; - - /* must follow cgrp for cgrp->ancestors[0], see above */ - struct cgroup *cgrp_ancestor_storage; - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; @@ -668,6 +664,13 @@ struct cgroup_root { /* The name for this hierarchy - may be empty */ char name[MAX_CGROUP_ROOT_NAMELEN]; + + /* + * The root cgroup. The containing cgroup_root will be destroyed on its + * release. This must be embedded last due to flexible array at the end + * of struct cgroup. + */ + struct cgroup cgrp; }; /* diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 0ad1ddbb8b99..e5822f6e7f27 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -211,6 +211,7 @@ struct kmem_obj_info; * __kfence_obj_info() - fill kmem_obj_info struct * @kpp: kmem_obj_info to be filled * @object: the object + * @slab: the slab * * Return: * * false - not a KFENCE object diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a6624edb7226..8dd79a3f3d66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -637,6 +637,7 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); +extern int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index cf3c6ab408aa..207156f2143c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -83,6 +83,7 @@ static inline void reset_hung_task_detector(void) { } #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); extern unsigned int hardlockup_panic; +extern unsigned long hardlockup_si_mask; #else static inline void hardlockup_detector_disable(void) {} #endif diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0e1d73955fa5..95d0040df584 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -325,6 +325,7 @@ static inline void might_alloc(gfp_t gfp_mask) /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index ab64ecdf39a0..d01ef4a6b3d7 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -52,8 +52,8 @@ static inline void airoha_ppe_put_dev(struct airoha_ppe_dev *dev) { } -static inline int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, - void *type_data) +static inline int airoha_ppe_dev_setup_tc_block_cb(struct airoha_ppe_dev *dev, + void *type_data) { return -EOPNOTSUPP; } diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 6673e4d4ac2e..4933777404d6 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -35,6 +35,7 @@ struct ts_state * @get_pattern: return head of pattern * @get_pattern_len: return length of pattern * @owner: module reference to algorithm + * @list: list to search */ struct ts_ops { diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 58d91ccc56e0..a7b7abd66e21 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -67,6 +67,7 @@ FN(TC_EGRESS) \ FN(SECURITY_HOOK) \ FN(QDISC_DROP) \ + FN(QDISC_BURST_DROP) \ FN(QDISC_OVERLIMIT) \ FN(QDISC_CONGESTED) \ FN(CAKE_FLOOD) \ @@ -375,6 +376,11 @@ enum skb_drop_reason { */ SKB_DROP_REASON_QDISC_DROP, /** + * @SKB_DROP_REASON_QDISC_BURST_DROP: dropped when net.core.qdisc_max_burst + * limit is hit. + */ + SKB_DROP_REASON_QDISC_BURST_DROP, + /** * @SKB_DROP_REASON_QDISC_OVERLIMIT: dropped by qdisc when a qdisc * instance exceeds its total buffer size limit. */ diff --git a/include/net/hotdata.h b/include/net/hotdata.h index 4acec191c54a..6632b1aa7584 100644 --- a/include/net/hotdata.h +++ b/include/net/hotdata.h @@ -42,6 +42,7 @@ struct net_hotdata { int netdev_budget_usecs; int tstamp_prequeue; int max_backlog; + int qdisc_max_burst; int dev_tx_weight; int dev_rx_weight; int sysctl_max_skb_frags; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ecae35512b9b..4021e6a73e32 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -19,6 +19,7 @@ #include <net/rtnetlink.h> #include <net/lwtunnel.h> #include <net/dst_cache.h> +#include <net/netdev_lock.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -372,7 +373,17 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, fl4->flowi4_flags = flow_flags; } -int ip_tunnel_init(struct net_device *dev); +int __ip_tunnel_init(struct net_device *dev); +#define ip_tunnel_init(DEV) \ +({ \ + struct net_device *__dev = (DEV); \ + int __res = __ip_tunnel_init(__dev); \ + \ + if (!__res) \ + netdev_lockdep_set_classes(__dev);\ + __res; \ +}) + void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 1ae08e81339f..15679be90c5c 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -41,6 +41,12 @@ struct scsi_eh_save { unsigned char cmnd[32]; struct scsi_data_buffer sdb; struct scatterlist sense_sgl; + + /* struct request fields */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *rq_crypt_ctx; + struct blk_crypto_keyslot *rq_crypt_keyslot; +#endif }; extern void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 58fd6e84f961..a7860c047503 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1402,7 +1402,7 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h index 109082c5694f..3d335f950eeb 100644 --- a/include/uapi/linux/media/arm/mali-c55-config.h +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -195,15 +195,6 @@ struct mali_c55_stats_buffer { } __attribute__((packed)); /** - * enum mali_c55_param_buffer_version - Mali-C55 parameters block versioning - * - * @MALI_C55_PARAM_BUFFER_V1: First version of Mali-C55 parameters block - */ -enum mali_c55_param_buffer_version { - MALI_C55_PARAM_BUFFER_V1, -}; - -/** * enum mali_c55_param_block_type - Enumeration of Mali-C55 parameter blocks * * This enumeration defines the types of Mali-C55 parameters block. Each block diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0ca69f888fa..3135643d5695 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9609,6 +9609,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env, if (reg->type != PTR_TO_MAP_VALUE) return -EINVAL; + if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { + verbose(env, "R%d points to insn_array map which cannot be used as const string\n", regno); + return -EACCES; + } + if (!bpf_map_is_rdonly(map)) { verbose(env, "R%d does not point to a readonly map'\n", regno); return -EACCES; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e717208cfb18..554a02ee298b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5847,7 +5847,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ - cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); + cgrp = kzalloc(struct_size(cgrp, _low_ancestors, level), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 9dc51fab604f..d4482b6e3cae 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -460,27 +460,23 @@ static void __init deserialize_bitmap(unsigned int order, } } -/* Return true if memory was deserizlied */ -static bool __init kho_mem_deserialize(const void *fdt) +/* Returns physical address of the preserved memory map from FDT */ +static phys_addr_t __init kho_get_mem_map_phys(const void *fdt) { - struct khoser_mem_chunk *chunk; const void *mem_ptr; - u64 mem; int len; mem_ptr = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len); if (!mem_ptr || len != sizeof(u64)) { pr_err("failed to get preserved memory bitmaps\n"); - return false; + return 0; } - mem = get_unaligned((const u64 *)mem_ptr); - chunk = mem ? phys_to_virt(mem) : NULL; - - /* No preserved physical pages were passed, no deserialization */ - if (!chunk) - return false; + return get_unaligned((const u64 *)mem_ptr); +} +static void __init kho_mem_deserialize(struct khoser_mem_chunk *chunk) +{ while (chunk) { unsigned int i; @@ -489,8 +485,6 @@ static bool __init kho_mem_deserialize(const void *fdt) &chunk->bitmaps[i]); chunk = KHOSER_LOAD_PTR(chunk->hdr.next); } - - return true; } /* @@ -1253,6 +1247,7 @@ bool kho_finalized(void) struct kho_in { phys_addr_t fdt_phys; phys_addr_t scratch_phys; + phys_addr_t mem_map_phys; struct kho_debugfs dbg; }; @@ -1434,12 +1429,10 @@ static void __init kho_release_scratch(void) void __init kho_memory_init(void) { - if (kho_in.scratch_phys) { + if (kho_in.mem_map_phys) { kho_scratch = phys_to_virt(kho_in.scratch_phys); kho_release_scratch(); - - if (!kho_mem_deserialize(kho_get_fdt())) - kho_in.fdt_phys = 0; + kho_mem_deserialize(phys_to_virt(kho_in.mem_map_phys)); } else { kho_reserve_scratch(); } @@ -1448,8 +1441,9 @@ void __init kho_memory_init(void) void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, u64 scratch_len) { - void *fdt = NULL; struct kho_scratch *scratch = NULL; + phys_addr_t mem_map_phys; + void *fdt = NULL; int err = 0; unsigned int scratch_cnt = scratch_len / sizeof(*kho_scratch); @@ -1475,6 +1469,12 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, goto out; } + mem_map_phys = kho_get_mem_map_phys(fdt); + if (!mem_map_phys) { + err = -ENOENT; + goto out; + } + scratch = early_memremap(scratch_phys, scratch_len); if (!scratch) { pr_warn("setup: failed to memremap scratch (phys=0x%llx, len=%lld)\n", @@ -1515,6 +1515,7 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, kho_in.fdt_phys = fdt_phys; kho_in.scratch_phys = scratch_phys; + kho_in.mem_map_phys = mem_map_phys; kho_scratch_cnt = scratch_cnt; pr_info("found kexec handover data.\n"); diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c index 25f253812512..a25dccdf7aa7 100644 --- a/kernel/module/kmod.c +++ b/kernel/module/kmod.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kmod - the kernel module loader * diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 3fa403f9831f..32fc12e53675 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1557,18 +1557,27 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) ctxt->allow_unsafe_takeover = nbcon_allow_unsafe_takeover(); while (nbcon_seq_read(con) < stop_seq) { - if (!nbcon_context_try_acquire(ctxt, false)) - return -EPERM; - /* - * nbcon_emit_next_record() returns false when the console was - * handed over or taken over. In both cases the context is no - * longer valid. + * Atomic flushing does not use console driver synchronization + * (i.e. it does not hold the port lock for uart consoles). + * Therefore IRQs must be disabled to avoid being interrupted + * and then calling into a driver that will deadlock trying + * to acquire console ownership. */ - if (!nbcon_emit_next_record(&wctxt, true)) - return -EAGAIN; + scoped_guard(irqsave) { + if (!nbcon_context_try_acquire(ctxt, false)) + return -EPERM; - nbcon_context_release(ctxt); + /* + * nbcon_emit_next_record() returns false when + * the console was handed over or taken over. + * In both cases the context is no longer valid. + */ + if (!nbcon_emit_next_record(&wctxt, true)) + return -EAGAIN; + + nbcon_context_release(ctxt); + } if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ @@ -1595,22 +1604,11 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) { struct console_flush_type ft; - unsigned long flags; int err; again: - /* - * Atomic flushing does not use console driver synchronization (i.e. - * it does not hold the port lock for uart consoles). Therefore IRQs - * must be disabled to avoid being interrupted and then calling into - * a driver that will deadlock trying to acquire console ownership. - */ - local_irq_save(flags); - err = __nbcon_atomic_flush_pending_con(con, stop_seq); - local_irq_restore(flags); - /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ef2d5dca6f70..aa758efc3731 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1148,7 +1148,6 @@ struct ftrace_page { }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) -#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; @@ -3834,7 +3833,8 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) return 0; } -static int ftrace_allocate_records(struct ftrace_page *pg, int count) +static int ftrace_allocate_records(struct ftrace_page *pg, int count, + unsigned long *num_pages) { int order; int pages; @@ -3844,7 +3844,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return -EINVAL; /* We want to fill as much as possible, with no empty pages */ - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); + pages = DIV_ROUND_UP(count * ENTRY_SIZE, PAGE_SIZE); order = fls(pages) - 1; again: @@ -3859,6 +3859,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) } ftrace_number_of_pages += 1 << order; + *num_pages += 1 << order; ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; @@ -3887,12 +3888,14 @@ static void ftrace_free_pages(struct ftrace_page *pages) } static struct ftrace_page * -ftrace_allocate_pages(unsigned long num_to_init) +ftrace_allocate_pages(unsigned long num_to_init, unsigned long *num_pages) { struct ftrace_page *start_pg; struct ftrace_page *pg; int cnt; + *num_pages = 0; + if (!num_to_init) return NULL; @@ -3906,7 +3909,7 @@ ftrace_allocate_pages(unsigned long num_to_init) * waste as little space as possible. */ for (;;) { - cnt = ftrace_allocate_records(pg, num_to_init); + cnt = ftrace_allocate_records(pg, num_to_init, num_pages); if (cnt < 0) goto free_pages; @@ -7192,8 +7195,6 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); - /* * Sorting mcount in vmlinux at build time depend on * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in @@ -7206,7 +7207,7 @@ static int ftrace_process_locs(struct module *mod, test_is_sorted(start, count); } - start_pg = ftrace_allocate_pages(count); + start_pg = ftrace_allocate_pages(count, &pages); if (!start_pg) return -ENOMEM; @@ -7305,27 +7306,27 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { unsigned long pg_remaining, remaining = 0; - unsigned long skip; + long skip; /* Count the number of entries unused and compare it to skipped. */ - pg_remaining = (ENTRIES_PER_PAGE << pg->order) - pg->index; + pg_remaining = (PAGE_SIZE << pg->order) / ENTRY_SIZE - pg->index; if (!WARN(skipped < pg_remaining, "Extra allocated pages for ftrace")) { skip = skipped - pg_remaining; - for (pg = pg_unuse; pg; pg = pg->next) + for (pg = pg_unuse; pg && skip > 0; pg = pg->next) { remaining += 1 << pg->order; + skip -= (PAGE_SIZE << pg->order) / ENTRY_SIZE; + } pages -= remaining; - skip = DIV_ROUND_UP(skip, ENTRIES_PER_PAGE); - /* * Check to see if the number of pages remaining would * just fit the number of entries skipped. */ - WARN(skip != remaining, "Extra allocated pages for ftrace: %lu with %lu skipped", + WARN(pg || skip > 0, "Extra allocated pages for ftrace: %lu with %lu skipped", remaining, skipped); } /* Need to synchronize with ftrace_location_range() */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0685e3a8aa0a..366122f4a0f8 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -71,7 +71,7 @@ unsigned int __read_mostly hardlockup_panic = * hard lockup is detected, it could be task, memory, lock etc. * Refer include/linux/sys_info.h for detailed bit definition. */ -static unsigned long hardlockup_si_mask; +unsigned long hardlockup_si_mask; #ifdef CONFIG_SYSFS diff --git a/lib/buildid.c b/lib/buildid.c index aaf61dfc0919..818331051afe 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,6 +5,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/pagemap.h> +#include <linux/fs.h> #include <linux/secretmem.h> #define BUILD_ID 3 @@ -46,20 +47,9 @@ static int freader_get_folio(struct freader *r, loff_t file_off) freader_put_folio(r); - /* reject secretmem folios created with memfd_secret() */ - if (secretmem_mapping(r->file->f_mapping)) - return -EFAULT; - + /* only use page cache lookup - fail if not already cached */ r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); - /* if sleeping is allowed, wait for the page, if necessary */ - if (r->may_fault && (IS_ERR(r->folio) || !folio_test_uptodate(r->folio))) { - filemap_invalidate_lock_shared(r->file->f_mapping); - r->folio = read_cache_folio(r->file->f_mapping, file_off >> PAGE_SHIFT, - NULL, r->file); - filemap_invalidate_unlock_shared(r->file->f_mapping); - } - if (IS_ERR(r->folio) || !folio_test_uptodate(r->folio)) { if (!IS_ERR(r->folio)) folio_put(r->folio); @@ -97,6 +87,24 @@ const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz) return r->data + file_off; } + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) { + r->err = -EFAULT; + return NULL; + } + + /* use __kernel_read() for sleepable context */ + if (r->may_fault) { + ssize_t ret; + + ret = __kernel_read(r->file, r->buf, sz, &file_off); + if (ret != sz) { + r->err = (ret < 0) ? ret : -EIO; + return NULL; + } + return r->buf; + } + /* fetch or reuse folio for given file offset */ r->err = freader_get_folio(r, file_off); if (r->err) diff --git a/mm/damon/core.c b/mm/damon/core.c index f9fc0375890a..84f80a20f233 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1431,6 +1431,35 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/* + * damon_call_handle_inactive_ctx() - handle DAMON call request that added to + * an inactive context. + * @ctx: The inactive DAMON context. + * @control: Control variable of the call request. + * + * This function is called in a case that @control is added to @ctx but @ctx is + * not running (inactive). See if @ctx handled @control or not, and cleanup + * @control if it was not handled. + * + * Returns 0 if @control was handled by @ctx, negative error code otherwise. + */ +static int damon_call_handle_inactive_ctx( + struct damon_ctx *ctx, struct damon_call_control *control) +{ + struct damon_call_control *c; + + mutex_lock(&ctx->call_controls_lock); + list_for_each_entry(c, &ctx->call_controls, list) { + if (c == control) { + list_del(&control->list); + mutex_unlock(&ctx->call_controls_lock); + return -EINVAL; + } + } + mutex_unlock(&ctx->call_controls_lock); + return 0; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. @@ -1461,7 +1490,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) - return -EINVAL; + return damon_call_handle_inactive_ctx(ctx, control); if (control->repeat) return 0; wait_for_completion(&control->completion); @@ -2051,13 +2080,15 @@ static unsigned long damos_get_node_memcg_used_bp( rcu_read_lock(); memcg = mem_cgroup_from_id(goal->memcg_id); - rcu_read_unlock(); - if (!memcg) { + if (!memcg || !mem_cgroup_tryget(memcg)) { + rcu_read_unlock(); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) return 0; else /* DAMOS_QUOTA_NODE_MEMCG_FREE_BP */ return 10000; } + rcu_read_unlock(); + mem_cgroup_flush_stats(memcg); lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(goal->nid)); used_pages = lruvec_page_state(lruvec, NR_ACTIVE_ANON); @@ -2065,6 +2096,8 @@ static unsigned long damos_get_node_memcg_used_bp( used_pages += lruvec_page_state(lruvec, NR_ACTIVE_FILE); used_pages += lruvec_page_state(lruvec, NR_INACTIVE_FILE); + mem_cgroup_put(memcg); + si_meminfo_node(&i, goal->nid); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) numerator = used_pages; @@ -2751,13 +2784,13 @@ done: if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); kfree(ctx->regions_score_histogram); + kdamond_call(ctx, true); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); - kdamond_call(ctx, true); damos_walk_cancel(ctx); mutex_lock(&damon_lock); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 30d20f5b3192..3a699dcd5a7f 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2152,13 +2152,13 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) return err; err = damos_sysfs_set_dests(scheme); if (err) - goto put_access_pattern_out; + goto rmdir_put_access_pattern_out; err = damon_sysfs_scheme_set_quotas(scheme); if (err) goto put_dests_out; err = damon_sysfs_scheme_set_watermarks(scheme); if (err) - goto put_quotas_access_pattern_out; + goto rmdir_put_quotas_access_pattern_out; err = damos_sysfs_set_filter_dirs(scheme); if (err) goto put_watermarks_quotas_access_pattern_out; @@ -2183,13 +2183,15 @@ put_filters_watermarks_quotas_access_pattern_out: put_watermarks_quotas_access_pattern_out: kobject_put(&scheme->watermarks->kobj); scheme->watermarks = NULL; -put_quotas_access_pattern_out: +rmdir_put_quotas_access_pattern_out: + damon_sysfs_quotas_rm_dirs(scheme->quotas); kobject_put(&scheme->quotas->kobj); scheme->quotas = NULL; put_dests_out: kobject_put(&scheme->dests->kobj); scheme->dests = NULL; -put_access_pattern_out: +rmdir_put_access_pattern_out: + damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); kobject_put(&scheme->access_pattern->kobj); scheme->access_pattern = NULL; return err; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index e2bd2d7becdd..95fd9375a7d8 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -792,7 +792,7 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) nr_regions_range = damon_sysfs_ul_range_alloc(10, 1000); if (!nr_regions_range) { err = -ENOMEM; - goto put_intervals_out; + goto rmdir_put_intervals_out; } err = kobject_init_and_add(&nr_regions_range->kobj, @@ -806,6 +806,8 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) put_nr_regions_intervals_out: kobject_put(&nr_regions_range->kobj); attrs->nr_regions_range = NULL; +rmdir_put_intervals_out: + damon_sysfs_intervals_rm_dirs(intervals); put_intervals_out: kobject_put(&intervals->kobj); attrs->intervals = NULL; @@ -948,7 +950,7 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) err = damon_sysfs_context_set_targets(context); if (err) - goto put_attrs_out; + goto rmdir_put_attrs_out; err = damon_sysfs_context_set_schemes(context); if (err) @@ -958,7 +960,8 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) put_targets_attrs_out: kobject_put(&context->targets->kobj); context->targets = NULL; -put_attrs_out: +rmdir_put_attrs_out: + damon_sysfs_attrs_rm_dirs(context->attrs); kobject_put(&context->attrs->kobj); context->attrs = NULL; return err; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 51273baec9e5..e0ab14020513 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4286,6 +4286,11 @@ static int __init hugepages_setup(char *s) unsigned long tmp; char *p = s; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepages=%s cmdline\n", s); + return 0; + } + if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; @@ -4366,6 +4371,11 @@ static int __init hugepagesz_setup(char *s) unsigned long size; struct hstate *h; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepagesz=%s cmdline\n", s); + return 0; + } + parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); @@ -4414,6 +4424,12 @@ static int __init default_hugepagesz_setup(char *s) unsigned long size; int i; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring default_hugepagesz=%s cmdline\n", + s); + return 0; + } + parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index e7f554a31bb4..9e1c5f2b7a41 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -207,7 +207,7 @@ void kmsan_free_page(struct page *page, unsigned int order) if (!kmsan_enabled || kmsan_in_runtime()) return; kmsan_enter_runtime(); - kmsan_internal_poison_memory(page_address(page), page_size(page), + kmsan_internal_poison_memory(page_address(page), PAGE_SIZE << order, GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 5b009a9cd8b4..8f5735fda0a2 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,6 +7,8 @@ #include <linux/numa.h> #include <linux/numa_memblks.h> +#include <asm/numa.h> + int numa_distance_cnt; static u8 *numa_distance; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c380f063e8b7..f65c4edf199d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -167,6 +167,33 @@ static inline void __pcp_trylock_noop(unsigned long *flags) { } pcp_trylock_finish(UP_flags); \ }) +/* + * With the UP spinlock implementation, when we spin_lock(&pcp->lock) (for i.e. + * a potentially remote cpu drain) and get interrupted by an operation that + * attempts pcp_spin_trylock(), we can't rely on the trylock failure due to UP + * spinlock assumptions making the trylock a no-op. So we have to turn that + * spin_lock() to a spin_lock_irqsave(). This works because on UP there are no + * remote cpu's so we can only be locking the only existing local one. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +static inline void __flags_noop(unsigned long *flags) { } +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ +({ \ + __flags_noop(&(flags)); \ + spin_lock(&(ptr)->lock); \ +}) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ +({ \ + spin_unlock(&(ptr)->lock); \ + __flags_noop(&(flags)); \ +}) +#else +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ + spin_lock_irqsave(&(ptr)->lock, flags) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ + spin_unlock_irqrestore(&(ptr)->lock, flags) +#endif + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -2556,6 +2583,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) { int high_min, to_drain, to_drain_batched, batch; + unsigned long UP_flags; bool todo = false; high_min = READ_ONCE(pcp->high_min); @@ -2575,9 +2603,9 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) to_drain = pcp->count - pcp->high; while (to_drain > 0) { to_drain_batched = min(to_drain, batch); - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain_batched, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); todo = true; to_drain -= to_drain_batched; @@ -2594,14 +2622,15 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { + unsigned long UP_flags; int to_drain, batch; batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } } #endif @@ -2612,10 +2641,11 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + unsigned long UP_flags; int count; do { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); count = pcp->count; if (count) { int to_drain = min(count, @@ -2624,7 +2654,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) free_pcppages_bulk(zone, to_drain, pcp, 0); count -= to_drain; } - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } while (count); } @@ -6109,6 +6139,7 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) { struct per_cpu_pages *pcp; struct cpu_cacheinfo *cci; + unsigned long UP_flags; pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); cci = get_cpu_cacheinfo(cpu); @@ -6119,12 +6150,12 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) * This can reduce zone lock contention without hurting * cache-hot pages sharing. */ - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) pcp->flags |= PCPF_FREE_HIGH_BATCH; else pcp->flags &= ~PCPF_FREE_HIGH_BATCH; - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } void setup_pcp_cacheinfo(unsigned int cpu) @@ -6667,11 +6698,19 @@ static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table * int old_percpu_pagelist_high_fraction; int ret; + /* + * Avoid using pcp_batch_high_lock for reads as the value is read + * atomically and a race with offlining is harmless. + */ + + if (!write) + return proc_dointvec_minmax(table, write, buffer, length, ppos); + mutex_lock(&pcp_batch_high_lock); old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || ret < 0) + if (ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ @@ -67,18 +67,13 @@ struct mmap_state { .state = VMA_MERGE_START, \ } -/* - * If, at any point, the VMA had unCoW'd mappings from parents, it will maintain - * more than one anon_vma_chain connecting it to more than one anon_vma. A merge - * would mean a wider range of folios sharing the root anon_vma lock, and thus - * potential lock contention, we do not wish to encourage merging such that this - * scales to a problem. - */ -static bool vma_had_uncowed_parents(struct vm_area_struct *vma) +/* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */ +static bool vma_is_fork_child(struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. + * parents. This can improve scalability caused by the anon_vma root + * lock. */ return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); } @@ -115,11 +110,19 @@ static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) VM_WARN_ON(src && src_anon != src->anon_vma); /* Case 1 - we will dup_anon_vma() from src into tgt. */ - if (!tgt_anon && src_anon) - return !vma_had_uncowed_parents(src); + if (!tgt_anon && src_anon) { + struct vm_area_struct *copied_from = vmg->copied_from; + + if (vma_is_fork_child(src)) + return false; + if (vma_is_fork_child(copied_from)) + return false; + + return true; + } /* Case 2 - we will simply use tgt's anon_vma. */ if (tgt_anon && !src_anon) - return !vma_had_uncowed_parents(tgt); + return !vma_is_fork_child(tgt); /* Case 3 - the anon_vma's are already shared. */ return src_anon == tgt_anon; } @@ -829,6 +832,8 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); + /* An existing merge can never be used by the mremap() logic. */ + VM_WARN_ON_VMG(vmg->copied_from, vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -1099,6 +1104,33 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) } /* + * vma_merge_copied_range - Attempt to merge a VMA that is being copied by + * mremap() + * + * @vmg: Describes the VMA we are adding, in the copied-to range @vmg->start to + * @vmg->end (exclusive), which we try to merge with any adjacent VMAs if + * possible. + * + * vmg->prev, next, start, end, pgoff should all be relative to the COPIED TO + * range, i.e. the target range for the VMA. + * + * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer + * to the VMA we expanded. + * + * ASSUMPTIONS: Same as vma_merge_new_range(), except vmg->middle must contain + * the copied-from VMA. + */ +static struct vm_area_struct *vma_merge_copied_range(struct vma_merge_struct *vmg) +{ + /* We must have a copied-from VMA. */ + VM_WARN_ON_VMG(!vmg->middle, vmg); + + vmg->copied_from = vmg->middle; + vmg->middle = NULL; + return vma_merge_new_range(vmg); +} + +/* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. @@ -1117,46 +1149,52 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; - bool remove_next = false; struct vm_area_struct *target = vmg->target; struct vm_area_struct *next = vmg->next; + bool remove_next = false; vm_flags_t sticky_flags; - - sticky_flags = vmg->vm_flags & VM_STICKY; - sticky_flags |= target->vm_flags & VM_STICKY; - - VM_WARN_ON_VMG(!target, vmg); + int ret = 0; mmap_assert_write_locked(vmg->mm); - vma_start_write(target); - if (next && (target != next) && (vmg->end == next->vm_end)) { - int ret; - sticky_flags |= next->vm_flags & VM_STICKY; + if (next && target != next && vmg->end == next->vm_end) remove_next = true; - /* This should already have been checked by this point. */ - VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); - vma_start_write(next); - /* - * In this case we don't report OOM, so vmg->give_up_on_mm is - * safe. - */ - ret = dup_anon_vma(target, next, &anon_dup); - if (ret) - return ret; - } + /* We must have a target. */ + VM_WARN_ON_VMG(!target, vmg); + /* This should have already been checked by this point. */ + VM_WARN_ON_VMG(remove_next && !can_merge_remove_vma(next), vmg); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != target && vmg->end > next->vm_start, vmg); - /* Only handles expanding */ + /* Only handles expanding. */ VM_WARN_ON_VMG(target->vm_start < vmg->start || target->vm_end > vmg->end, vmg); + sticky_flags = vmg->vm_flags & VM_STICKY; + sticky_flags |= target->vm_flags & VM_STICKY; if (remove_next) - vmg->__remove_next = true; + sticky_flags |= next->vm_flags & VM_STICKY; + + /* + * If we are removing the next VMA or copying from a VMA + * (e.g. mremap()'ing), we must propagate anon_vma state. + * + * Note that, by convention, callers ignore OOM for this case, so + * we don't need to account for vmg->give_up_on_mm here. + */ + if (remove_next) + ret = dup_anon_vma(target, next, &anon_dup); + if (!ret && vmg->copied_from) + ret = dup_anon_vma(target, vmg->copied_from, &anon_dup); + if (ret) + return ret; + if (remove_next) { + vma_start_write(next); + vmg->__remove_next = true; + } if (commit_merge(vmg)) goto nomem; @@ -1828,10 +1866,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - vmg.middle = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); - new_vma = vma_merge_new_range(&vmg); + new_vma = vma_merge_copied_range(&vmg); if (new_vma) { /* @@ -106,6 +106,9 @@ struct vma_merge_struct { struct anon_vma_name *anon_name; enum vma_merge_state state; + /* If copied from (i.e. mremap()'d) the VMA from which we are copying. */ + struct vm_area_struct *copied_from; + /* Flags which callers can use to modify merge behaviour: */ /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 41dd01e8430c..628f96e83b11 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4248,7 +4248,7 @@ void *vzalloc_node_noprof(unsigned long size, int node) EXPORT_SYMBOL(vzalloc_node_noprof); /** - * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents + * vrealloc_node_align - reallocate virtually contiguous memory; contents * remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate diff --git a/mm/zswap.c b/mm/zswap.c index 5d0f8b13a958..ac9b7a60736b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -787,7 +787,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) return 0; fail: - if (acomp) + if (!IS_ERR_OR_NULL(acomp)) crypto_free_acomp(acomp); kfree(buffer); return ret; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a9f5b1a68356..cbc3a75d7326 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4420,6 +4420,7 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (bis_capable(hdev)) { events[1] |= 0x20; /* LE PA Report */ events[1] |= 0x40; /* LE PA Sync Established */ + events[1] |= 0x80; /* LE PA Sync Lost */ events[3] |= 0x04; /* LE Create BIG Complete */ events[3] |= 0x08; /* LE Terminate BIG Complete */ events[3] |= 0x10; /* LE BIG Sync Established */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 655efac6f133..26cfcfdc45eb 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1294,8 +1294,6 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, batch_size = NAPI_POLL_WEIGHT; else if (batch_size > TEST_XDP_MAX_BATCH) return -E2BIG; - - headroom += sizeof(struct xdp_page_head); } else if (batch_size) { return -EINVAL; } @@ -1308,16 +1306,26 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, /* There can't be user provided data before the meta data */ if (ctx->data_meta || ctx->data_end > kattr->test.data_size_in || ctx->data > ctx->data_end || - unlikely(xdp_metalen_invalid(ctx->data)) || (do_live && (kattr->test.data_out || kattr->test.ctx_out))) goto free_ctx; - /* Meta data is allocated from the headroom */ - headroom -= ctx->data; meta_sz = ctx->data; + if (xdp_metalen_invalid(meta_sz) || meta_sz > headroom - sizeof(struct xdp_frame)) + goto free_ctx; + + /* Meta data is allocated from the headroom */ + headroom -= meta_sz; linear_sz = ctx->data_end; } + /* The xdp_page_head structure takes up space in each page, limiting the + * size of the packet data; add the extra size to headroom here to make + * sure it's accounted in the length checks below, but not in the + * metadata size check above. + */ + if (do_live) + headroom += sizeof(struct xdp_page_head); + max_linear_sz = PAGE_SIZE - headroom - tailroom; linear_sz = min_t(u32, linear_sz, max_linear_sz); @@ -1355,13 +1363,13 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (sinfo->nr_frags == MAX_SKB_FRAGS) { ret = -ENOMEM; - goto out; + goto out_put_dev; } page = alloc_page(GFP_KERNEL); if (!page) { ret = -ENOMEM; - goto out; + goto out_put_dev; } frag = &sinfo->frags[sinfo->nr_frags++]; @@ -1373,7 +1381,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (copy_from_user(page_address(page), data_in + size, data_len)) { ret = -EFAULT; - goto out; + goto out_put_dev; } sinfo->xdp_frags_size += data_len; size += data_len; @@ -1388,6 +1396,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, ret = bpf_test_run_xdp_live(prog, &xdp, repeat, batch_size, &duration); else ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); +out_put_dev: /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented * even if the test run failed. diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 58d22e2b85fc..0501ffcb8a3d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -70,7 +70,7 @@ static inline int has_expired(const struct net_bridge *br, { return !test_bit(BR_FDB_STATIC, &fdb->flags) && !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) && - time_before_eq(fdb->updated + hold_time(br), jiffies); + time_before_eq(READ_ONCE(fdb->updated) + hold_time(br), jiffies); } static int fdb_to_nud(const struct net_bridge *br, @@ -126,9 +126,9 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) goto nla_put_failure; - ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; - ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; @@ -551,7 +551,7 @@ void br_fdb_cleanup(struct work_struct *work) */ rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { - unsigned long this_timer = f->updated + delay; + unsigned long this_timer = READ_ONCE(f->updated) + delay; if (test_bit(BR_FDB_STATIC, &f->flags) || test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags)) { @@ -924,6 +924,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct net_bridge_fdb_entry *f; struct __fdb_entry *fe = buf; + unsigned long delta; int num = 0; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); @@ -953,8 +954,11 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->port_hi = f->dst->port_no >> 8; fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags); - if (!test_bit(BR_FDB_STATIC, &f->flags)) - fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); + if (!test_bit(BR_FDB_STATIC, &f->flags)) { + delta = jiffies - READ_ONCE(f->updated); + fe->ageing_timer_value = + jiffies_delta_to_clock_t(delta); + } ++fe; ++num; } @@ -1002,8 +1006,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; bool fdb_modified = false; - if (now != fdb->updated) { - fdb->updated = now; + if (now != READ_ONCE(fdb->updated)) { + WRITE_ONCE(fdb->updated, now); fdb_modified = __fdb_mark_active(fdb); } @@ -1242,10 +1246,10 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, if (fdb_handle_notify(fdb, notify)) modified = true; - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); if (modified) { if (refresh) - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); fdb_notify(br, fdb, RTM_NEWNEIGH, true); } @@ -1556,7 +1560,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, goto err_unlock; } - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); if (READ_ONCE(fdb->dst) != p) { WRITE_ONCE(fdb->dst, p); @@ -1565,7 +1569,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); } else { modified = true; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 777fa869c1a1..e355a15bf5ab 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -221,8 +221,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (test_bit(BR_FDB_LOCAL, &dst->flags)) return br_pass_frame_up(skb, false); - if (now != dst->used) - dst->used = now; + if (now != READ_ONCE(dst->used)) + WRITE_ONCE(dst->used, now); br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 613a911dda10..8656ab388c83 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1695,8 +1695,16 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); - if (session->transmission) + if (session->transmission) { j1939_session_deactivate_activate_next(session); + } else if (session->state == J1939_SESSION_WAITING_ABORT) { + /* Force deactivation for the receiver. + * If we rely on the timer starting in j1939_session_cancel, + * a second RTS call here will cancel that timer and fail + * to restart it because the state is already WAITING_ABORT. + */ + j1939_session_deactivate_activate_next(session); + } return -EBUSY; } diff --git a/net/can/raw.c b/net/can/raw.c index be1ef7cf4204..12293363413c 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -49,8 +49,8 @@ #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> +#include <linux/can/can-ml.h> #include <linux/can/core.h> -#include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */ #include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> @@ -892,58 +892,21 @@ static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) } } -static inline bool raw_dev_cc_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* The CANXL-only mode disables error-signalling on the CAN bus - * which is needed to send CAN CC/FD frames - */ - if (priv) - return !can_dev_in_xl_only_mode(priv); - - /* virtual CAN interfaces always support CAN CC */ - return true; -} - -static inline bool raw_dev_fd_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* check FD ctrlmode on real CAN interfaces */ - if (priv) - return (priv->ctrlmode & CAN_CTRLMODE_FD); - - /* check MTU for virtual CAN FD interfaces */ - return (READ_ONCE(dev->mtu) >= CANFD_MTU); -} - -static inline bool raw_dev_xl_enabled(struct net_device *dev, - struct can_priv *priv) -{ - /* check XL ctrlmode on real CAN interfaces */ - if (priv) - return (priv->ctrlmode & CAN_CTRLMODE_XL); - - /* check MTU for virtual CAN XL interfaces */ - return can_is_canxl_dev_mtu(READ_ONCE(dev->mtu)); -} - static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, struct net_device *dev) { - struct can_priv *priv = safe_candev_priv(dev); - /* Classical CAN */ - if (can_is_can_skb(skb) && raw_dev_cc_enabled(dev, priv)) + if (can_is_can_skb(skb) && can_cap_enabled(dev, CAN_CAP_CC)) return CAN_MTU; /* CAN FD */ if (ro->fd_frames && can_is_canfd_skb(skb) && - raw_dev_fd_enabled(dev, priv)) + can_cap_enabled(dev, CAN_CAP_FD)) return CANFD_MTU; /* CAN XL */ if (ro->xl_frames && can_is_canxl_skb(skb) && - raw_dev_xl_enabled(dev, priv)) + can_cap_enabled(dev, CAN_CAP_XL)) return CANXL_MTU; return 0; @@ -982,6 +945,12 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (!dev) return -ENXIO; + /* no sending on a CAN device in read-only mode */ + if (can_cap_enabled(dev, CAN_CAP_RO)) { + err = -EACCES; + goto put_dev; + } + skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) diff --git a/net/core/dev.c b/net/core/dev.c index 36dc5199037e..ccef685023c2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -478,15 +478,21 @@ static const unsigned short netdev_lock_type[] = { ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, + ARPHRD_CAN, ARPHRD_MCTP, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, + ARPHRD_RAWHDLC, ARPHRD_RAWIP, + ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; + ARPHRD_IEEE80211_RADIOTAP, + ARPHRD_IEEE802154, ARPHRD_IEEE802154_MONITOR, + ARPHRD_PHONET, ARPHRD_PHONET_PIPE, + ARPHRD_CAIF, ARPHRD_IP6GRE, ARPHRD_NETLINK, ARPHRD_6LOWPAN, + ARPHRD_VSOCKMON, + ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -495,15 +501,21 @@ static const char *const netdev_lock_name[] = { "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_CAN", "_xmit_MCTP", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_RAWHDLC", "_xmit_RAWIP", + "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; + "_xmit_IEEE80211_RADIOTAP", + "_xmit_IEEE802154", "_xmit_IEEE802154_MONITOR", + "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_CAIF", "_xmit_IP6GRE", "_xmit_NETLINK", "_xmit_6LOWPAN", + "_xmit_VSOCKMON", + "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -516,6 +528,7 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ + WARN_ONCE(1, "netdev_lock_pos() could not find dev_type=%u\n", dev_type); return ARRAY_SIZE(netdev_lock_type) - 1; } @@ -4190,8 +4203,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, do { if (first_n && !defer_count) { defer_count = atomic_long_inc_return(&q->defer_count); - if (unlikely(defer_count > READ_ONCE(q->limit))) { - kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP); + if (unlikely(defer_count > READ_ONCE(net_hotdata.qdisc_max_burst))) { + kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_BURST_DROP); return NET_XMIT_DROP; } } @@ -4209,7 +4222,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, ll_list = llist_del_all(&q->defer_list); /* There is a small race because we clear defer_count not atomically * with the prior llist_del_all(). This means defer_list could grow - * over q->limit. + * over qdisc_max_burst. */ atomic_long_set(&q->defer_count, 0); diff --git a/net/core/dst.c b/net/core/dst.c index e9d35f49c9e7..1dae26c51ebe 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -68,6 +68,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->lwtstate = NULL; rcuref_init(&dst->__rcuref, 1); INIT_LIST_HEAD(&dst->rt_uncached); + dst->rt_uncached_list = NULL; dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; diff --git a/net/core/hotdata.c b/net/core/hotdata.c index dddd5c287cf0..a6db36580817 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -17,6 +17,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .tstamp_prequeue = 1, .max_backlog = 1000, + .qdisc_max_burst = 1000, .dev_tx_weight = 64, .dev_rx_weight = 64, .sysctl_max_skb_frags = MAX_SKB_FRAGS, diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8d4decb2606f..05dd55cf8b58 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -430,6 +430,13 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { + .procname = "qdisc_max_burst", + .data = &net_hotdata.qdisc_max_burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "netdev_rss_key", .data = &netdev_rss_key, .maxlen = sizeof(int), diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 05828d4cb6cd..abd77162f5e7 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,8 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8178c44a3cdd..e13244729ad8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -891,10 +891,17 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); - struct iphdr *iph; struct gre_base_hdr *greh; + struct iphdr *iph; + int needed; + + needed = t->hlen + sizeof(*iph); + if (skb_headroom(skb) < needed && + pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -needed; - iph = skb_push(skb, t->hlen + sizeof(*iph)); + iph = skb_push(skb, needed); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 158a30ae7c5f..50d0f5fe4e4c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1281,7 +1281,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); -int ip_tunnel_init(struct net_device *dev) +int __ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1308,10 +1308,9 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); - netdev_lockdep_set_classes(dev); return 0; } -EXPORT_SYMBOL_GPL(ip_tunnel_init); +EXPORT_SYMBOL_GPL(__ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b549d6a57307..11d990703d31 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1537,9 +1537,9 @@ void rt_add_uncached_list(struct rtable *rt) void rt_del_uncached_list(struct rtable *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b66217d1b2f8..27ab9d7adc64 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3112,12 +3112,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); - ipv6_del_addr(ifp); - if (!(ifp->flags & IFA_F_TEMPORARY) && (ifp->flags & IFA_F_MANAGETEMPADDR)) delete_tempaddrs(idev, ifp); + ipv6_del_addr(ifp); + addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 22410243ebe8..22895521a57d 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,8 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) : htons(ETH_P_IPV6); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6405072050e0..c1f39735a236 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -844,7 +844,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_network_header(skb); - if (!pskb_inet_may_pull(skb)) { + if (skb_vlan_inet_prepare(skb, true)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a3e051dc66ee..e3a260a5564b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -148,9 +148,9 @@ void rt6_uncached_list_add(struct rt6_info *rt) void rt6_uncached_list_del(struct rt6_info *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f4013b547438..9d59090bbe93 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -529,8 +529,10 @@ set_change_agg: return 0; destroy_class: - qdisc_put(cl->qdisc); - kfree(cl); + if (!existing) { + qdisc_put(cl->qdisc); + kfree(cl); + } return err; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9e14e453b55c..98b362d51836 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3151,6 +3151,7 @@ int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) int err; if (family == AF_INET && + (!x->dir || x->dir == XFRM_SA_DIR_OUT) && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; diff --git a/rust/helpers/bitops.c b/rust/helpers/bitops.c index 5d0861d29d3f..e79ef9e6d98f 100644 --- a/rust/helpers/bitops.c +++ b/rust/helpers/bitops.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> +#include <linux/find.h> void rust_helper___set_bit(unsigned long nr, unsigned long *addr) { @@ -21,3 +22,44 @@ void rust_helper_clear_bit(unsigned long nr, volatile unsigned long *addr) { clear_bit(nr, addr); } + +/* + * The rust_helper_ prefix is intentionally omitted below so that the + * declarations in include/linux/find.h are compatible with these helpers. + * + * Note that the below #ifdefs mean that the helper is only created if C does + * not provide a definition. + */ +#ifdef find_first_zero_bit +__rust_helper +unsigned long _find_first_zero_bit(const unsigned long *p, unsigned long size) +{ + return find_first_zero_bit(p, size); +} +#endif /* find_first_zero_bit */ + +#ifdef find_next_zero_bit +__rust_helper +unsigned long _find_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} +#endif /* find_next_zero_bit */ + +#ifdef find_first_bit +__rust_helper +unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) +{ + return find_first_bit(addr, size); +} +#endif /* find_first_bit */ + +#ifdef find_next_bit +__rust_helper +unsigned long _find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} +#endif /* find_next_bit */ diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index a82dd155e1d3..b12df5b5ddfc 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1074,7 +1074,9 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - snd_pcm_runtime_buffer_set_silence(runtime); + err = snd_pcm_runtime_buffer_set_silence(runtime); + if (err < 0) + goto failure; runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 68bee40c9ada..932a9bf98cbc 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -730,13 +730,18 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) } /* fill the PCM buffer with the current silence format; called from pcm_oss.c */ -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) { - snd_pcm_buffer_access_lock(runtime); + int err; + + err = snd_pcm_buffer_access_lock(runtime); + if (err < 0) + return err; if (runtime->dma_area) snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); snd_pcm_buffer_access_unlock(runtime); + return 0; } EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 61c7372e6307..29469e549791 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6613,6 +6613,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a2e, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -6817,6 +6818,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8f42, "HP ZBook 8 G2a 14W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8f57, "HP Trekker G7JC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8f62, "HP ZBook 8 G2a 16W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), + SND_PCI_QUIRK(0x1043, 0x1024, "ASUS Zephyrus G14 2025", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c index 3cca750857b6..dc35932b6b22 100644 --- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c +++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c @@ -103,6 +103,7 @@ static int cirrus_scodec_test_gpio_probe(struct platform_device *pdev) /* GPIO core modifies our struct gpio_chip so use a copy */ gpio_priv->chip = cirrus_scodec_test_gpio_chip; + gpio_priv->chip.parent = &pdev->dev; ret = devm_gpiochip_add_data(&pdev->dev, &gpio_priv->chip, gpio_priv); if (ret) return dev_err_probe(&pdev->dev, ret, "Failed to add gpiochip\n"); @@ -319,7 +320,7 @@ static struct kunit_case cirrus_scodec_test_cases[] = { }; static struct kunit_suite cirrus_scodec_test_suite = { - .name = "snd-hda-scodec-cs35l56-test", + .name = "snd-hda-cirrus-scodec-test", .init = cirrus_scodec_test_case_init, .test_cases = cirrus_scodec_test_cases, }; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index f7a7f216d586..624a822341bb 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -2,7 +2,7 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 - 2025 Texas Instruments, Inc. +// Copyright 2023 - 2026 Texas Instruments, Inc. // // Author: Shenghao Ding <shenghao-ding@ti.com> // Current maintainer: Baojun Xu <baojun.xu@ti.com> @@ -60,6 +60,7 @@ struct tas2781_hda_i2c_priv { int (*save_calibration)(struct tas2781_hda *h); int hda_chip_id; + bool skip_calibration; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -491,7 +492,8 @@ static void tasdevice_dspfw_init(void *context) /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - hda_priv->save_calibration(tas_hda); + if (!hda_priv->skip_calibration) + hda_priv->save_calibration(tas_hda); } static void tasdev_fw_ready(const struct firmware *fmw, void *context) @@ -548,6 +550,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_component_parent *parent = master_data; struct hda_component *comp; struct hda_codec *codec; @@ -568,11 +571,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, case 0x1028: tas_hda->catlog_id = DELL; break; + case 0x103C: + tas_hda->catlog_id = HP; + break; default: tas_hda->catlog_id = LENOVO; break; } + /* + * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data + * causes audio dropouts during playback, use fallback data + * from DSP firmware as a workaround. + */ + if (codec->core.subsystem_id == 0x10431384) + hda_priv->skip_calibration = true; + pm_runtime_get_sync(dev); comp->dev = dev; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index bf4d9d336561..0294177acc66 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -420,6 +420,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RE"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "M6501RM"), } }, diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 443cf59cb71a..fdf4a9add852 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -23,7 +23,6 @@ #include "tlv320adcx140.h" struct adcx140_priv { - struct snd_soc_component *component; struct regulator *supply_areg; struct gpio_desc *gpio_reset; struct regmap *regmap; @@ -338,7 +337,7 @@ static const struct snd_kcontrol_new adcx140_dapm_ch4_dre_en_switch = SOC_DAPM_SINGLE("Switch", ADCX140_CH4_CFG0, 0, 1, 0); static const struct snd_kcontrol_new adcx140_dapm_dre_en_switch = - SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 0); + SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 1); /* Output Mixer */ static const struct snd_kcontrol_new adcx140_output_mixer_controls[] = { @@ -699,7 +698,6 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) { int pwr_ctrl = 0; int ret = 0; - struct snd_soc_component *component = adcx140->component; if (power_state) pwr_ctrl = ADCX140_PWR_CFG_ADC_PDZ | ADCX140_PWR_CFG_PLL_PDZ; @@ -711,7 +709,7 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) ret = regmap_write(adcx140->regmap, ADCX140_PHASE_CALIB, adcx140->phase_calib_on ? 0x00 : 0x40); if (ret) - dev_err(component->dev, "%s: register write error %d\n", + dev_err(adcx140->dev, "%s: register write error %d\n", __func__, ret); } @@ -727,7 +725,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, struct adcx140_priv *adcx140 = snd_soc_component_get_drvdata(component); u8 data = 0; - switch (params_width(params)) { + switch (params_physical_width(params)) { case 16: data = ADCX140_16_BIT_WORD; break; @@ -742,7 +740,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, break; default: dev_err(component->dev, "%s: Unsupported width %d\n", - __func__, params_width(params)); + __func__, params_physical_width(params)); return -EINVAL; } @@ -1156,6 +1154,9 @@ static int adcx140_i2c_probe(struct i2c_client *i2c) adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(adcx140->gpio_reset)) + return dev_err_probe(&i2c->dev, PTR_ERR(adcx140->gpio_reset), + "Failed to get Reset GPIO\n"); + if (!adcx140->gpio_reset) dev_info(&i2c->dev, "Reset GPIO not defined\n"); adcx140->supply_areg = devm_regulator_get_optional(adcx140->dev, diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index d7aca6567c2d..2fc234adca5f 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -678,6 +678,7 @@ struct wsa881x_priv { */ unsigned int sd_n_val; int active_ports; + bool hw_init; bool port_prepared[WSA881X_MAX_SWR_PORTS]; bool port_enable[WSA881X_MAX_SWR_PORTS]; }; @@ -687,6 +688,9 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) struct regmap *rm = wsa881x->regmap; unsigned int val = 0; + if (wsa881x->hw_init) + return; + regmap_register_patch(wsa881x->regmap, wsa881x_rev_2_0, ARRAY_SIZE(wsa881x_rev_2_0)); @@ -724,6 +728,8 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) regmap_update_bits(rm, WSA881X_OTP_REG_28, 0x3F, 0x3A); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG1, 0xFF, 0xB2); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG2, 0xFF, 0x05); + + wsa881x->hw_init = true; } static int wsa881x_component_probe(struct snd_soc_component *comp) @@ -1067,6 +1073,9 @@ static int wsa881x_update_status(struct sdw_slave *slave, { struct wsa881x_priv *wsa881x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa881x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) wsa881x_init(wsa881x); diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index c3046e260cb9..468d2b38a22a 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -475,6 +475,7 @@ struct wsa883x_priv { int active_ports; int dev_mode; int comp_offset; + bool hw_init; /* * Protects temperature reading code (related to speaker protection) and * fields: temperature and pa_on. @@ -1043,6 +1044,9 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) struct regmap *regmap = wsa883x->regmap; int variant, version, ret; + if (wsa883x->hw_init) + return 0; + ret = regmap_read(regmap, WSA883X_OTP_REG_0, &variant); if (ret) return ret; @@ -1054,22 +1058,23 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) switch (variant) { case WSA8830: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", + version); break; case WSA8835: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", + version); break; case WSA8832: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", + version); break; case WSA8835_V2: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", + version); break; default: + dev_warn(wsa883x->dev, "unknown variant: %d\n", variant); break; } @@ -1085,6 +1090,8 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) wsa883x->comp_offset); } + wsa883x->hw_init = true; + return 0; } @@ -1093,6 +1100,9 @@ static int wsa883x_update_status(struct sdw_slave *slave, { struct wsa883x_priv *wsa883x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa883x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) return wsa883x_init(wsa883x); diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c index 887edd2be705..6c6b497657d0 100644 --- a/sound/soc/codecs/wsa884x.c +++ b/sound/soc/codecs/wsa884x.c @@ -1534,7 +1534,7 @@ static void wsa884x_init(struct wsa884x_priv *wsa884x) wsa884x_set_gain_parameters(wsa884x); - wsa884x->hw_init = false; + wsa884x->hw_init = true; } static int wsa884x_update_status(struct sdw_slave *slave, @@ -2109,7 +2109,6 @@ static int wsa884x_probe(struct sdw_slave *pdev, /* Start in cache-only until device is enumerated */ regcache_cache_only(wsa884x->regmap, true); - wsa884x->hw_init = true; if (IS_REACHABLE(CONFIG_HWMON)) { struct device *hwmon; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 355f7ec8943c..bdc02e85b089 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1179,9 +1179,9 @@ void graph_util_parse_link_direction(struct device_node *np, bool is_playback_only = of_property_read_bool(np, "playback-only"); bool is_capture_only = of_property_read_bool(np, "capture-only"); - if (playback_only) + if (np && playback_only) *playback_only = is_playback_only; - if (capture_only) + if (np && capture_only) *capture_only = is_capture_only; } EXPORT_SYMBOL_GPL(graph_util_parse_link_direction); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 2c1001148d54..8721a098d53f 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -767,6 +767,14 @@ 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, "0DD6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_ptlrvp"), }, .driver_data = (void *)(SOC_SDW_PCH_DMIC), diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c index 4c954501e500..2685ff4f0932 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c +++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c @@ -44,7 +44,7 @@ static const struct snd_soc_dapm_route cs42l43_dmic_map[] = { static struct snd_soc_jack_pin soc_jack_pins[] = { { .pin = "Headphone", - .mask = SND_JACK_HEADPHONE, + .mask = SND_JACK_HEADPHONE | SND_JACK_LINEOUT, }, { .pin = "Headset Mic", diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index bf382aa07e92..ccf149f949e8 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -841,6 +841,19 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_part(const u64 adr) } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_part, "SND_SOC_SDW_UTILS"); +static struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_sdw_id(const struct sdw_slave_id *id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) + if (id->part_id == codec_info_list[i].part_id && + (!codec_info_list[i].version_id || + id->sdw_version == codec_info_list[i].version_id)) + return &codec_info_list[i]; + + return NULL; +} + struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_acpi(const u8 *acpi_id) { int i; @@ -873,22 +886,46 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_dai(const char *dai_name, i } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_dai, "SND_SOC_SDW_UTILS"); +static int asoc_sdw_find_codec_info_dai_index(const struct asoc_sdw_codec_info *codec_info, + const char *dai_name) +{ + int i; + + for (i = 0; i < codec_info->dai_num; i++) { + if (!strcmp(codec_info->dais[i].dai_name, dai_name)) + return i; + } + + return -ENOENT; +} + int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_card *card = rtd->card; struct snd_soc_dapm_context *dapm = snd_soc_card_to_dapm(card); struct asoc_sdw_codec_info *codec_info; struct snd_soc_dai *dai; + struct sdw_slave *sdw_peripheral; const char *spk_components=""; int dai_index; int ret; int i; for_each_rtd_codec_dais(rtd, i, dai) { - codec_info = asoc_sdw_find_codec_info_dai(dai->name, &dai_index); + if (is_sdw_slave(dai->component->dev)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev); + else if (dai->component->dev->parent && is_sdw_slave(dai->component->dev->parent)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev->parent); + else + continue; + + codec_info = asoc_sdw_find_codec_info_sdw_id(&sdw_peripheral->id); if (!codec_info) return -EINVAL; + dai_index = asoc_sdw_find_codec_info_dai_index(codec_info, dai->name); + WARN_ON(dai_index < 0); + /* * A codec dai can be connected to different dai links for capture and playback, * but we only need to call the rtd_init function once. @@ -898,6 +935,10 @@ int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) if (codec_info->dais[dai_index].rtd_init_done) continue; + dev_dbg(card->dev, "%#x/%s initializing for %s/%s\n", + codec_info->part_id, codec_info->dais[dai_index].dai_name, + dai->component->name, dai->name); + /* * Add card controls and dapm widgets for the first codec dai. * The controls and widgets will be used for all codec dais. diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 624e9269fc25..ba42939d5f01 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -543,11 +543,11 @@ int snd_soc_bytes_get(struct snd_kcontrol *kcontrol, ucontrol->value.bytes.data[0] &= ~params->mask; break; case 2: - ((u16 *)(&ucontrol->value.bytes.data))[0] + ((__be16 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be16(~params->mask); break; case 4: - ((u32 *)(&ucontrol->value.bytes.data))[0] + ((__be32 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be32(~params->mask); break; default: diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 261d9067d27b..e795907a3963 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -2077,7 +2077,7 @@ static const struct regmap_config tegra210_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA210_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra186_ahub_regmap_config = { @@ -2085,7 +2085,7 @@ static const struct regmap_config tegra186_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA186_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra264_ahub_regmap_config = { @@ -2094,7 +2094,7 @@ static const struct regmap_config tegra264_ahub_regmap_config = { .reg_stride = 4, .writeable_reg = tegra264_ahub_wr_reg, .max_register = TEGRA264_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct tegra_ahub_soc_data soc_data_tegra210 = { diff --git a/sound/soc/ti/davinci-evm.c b/sound/soc/ti/davinci-evm.c index 3848766d96c3..ad514c2e5a25 100644 --- a/sound/soc/ti/davinci-evm.c +++ b/sound/soc/ti/davinci-evm.c @@ -194,27 +194,32 @@ static int davinci_evm_probe(struct platform_device *pdev) return -EINVAL; dai->cpus->of_node = of_parse_phandle(np, "ti,mcasp-controller", 0); - if (!dai->cpus->of_node) - return -EINVAL; + if (!dai->cpus->of_node) { + ret = -EINVAL; + goto err_put; + } dai->platforms->of_node = dai->cpus->of_node; evm_soc_card.dev = &pdev->dev; ret = snd_soc_of_parse_card_name(&evm_soc_card, "ti,model"); if (ret) - return ret; + goto err_put; mclk = devm_clk_get(&pdev->dev, "mclk"); if (PTR_ERR(mclk) == -EPROBE_DEFER) { - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto err_put; } else if (IS_ERR(mclk)) { dev_dbg(&pdev->dev, "mclk not found.\n"); mclk = NULL; } drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; + if (!drvdata) { + ret = -ENOMEM; + goto err_put; + } drvdata->mclk = mclk; @@ -224,7 +229,8 @@ static int davinci_evm_probe(struct platform_device *pdev) if (!drvdata->mclk) { dev_err(&pdev->dev, "No clock or clock rate defined.\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put; } drvdata->sysclk = clk_get_rate(drvdata->mclk); } else if (drvdata->mclk) { @@ -240,8 +246,25 @@ static int davinci_evm_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(&evm_soc_card, drvdata); ret = devm_snd_soc_register_card(&pdev->dev, &evm_soc_card); - if (ret) + if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); + goto err_put; + } + + return ret; + +err_put: + dai->platforms->of_node = NULL; + + if (dai->cpus->of_node) { + of_node_put(dai->cpus->of_node); + dai->cpus->of_node = NULL; + } + + if (dai->codecs->of_node) { + of_node_put(dai->codecs->of_node); + dai->codecs->of_node = NULL; + } return ret; } diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 54d01dfd820f..263abb36bb2d 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1553,7 +1553,7 @@ static int prepare_playback_urb(struct snd_usb_substream *subs, for (i = 0; i < ctx->packets; i++) { counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, avail); - if (counts < 0) + if (counts < 0 || frames + counts >= ep->max_urb_frames) break; /* set up descriptor */ urb->iso_frame_desc[i].offset = frames * stride; diff --git a/tools/net/ynl/pyynl/lib/doc_generator.py b/tools/net/ynl/pyynl/lib/doc_generator.py index 3a16b8eb01ca..8b922d8f89e8 100644 --- a/tools/net/ynl/pyynl/lib/doc_generator.py +++ b/tools/net/ynl/pyynl/lib/doc_generator.py @@ -166,13 +166,13 @@ class YnlDocGenerator: continue lines.append(self.fmt.rst_paragraph(self.fmt.bold(key), level + 1)) if key in ['request', 'reply']: - lines.append(self.parse_do_attributes(do_dict[key], level + 1) + "\n") + lines.append(self.parse_op_attributes(do_dict[key], level + 1) + "\n") else: lines.append(self.fmt.headroom(level + 2) + do_dict[key] + "\n") return "\n".join(lines) - def parse_do_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: + def parse_op_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: """Parse 'attributes' section""" if "attributes" not in attrs: return "" @@ -184,7 +184,7 @@ class YnlDocGenerator: def parse_operations(self, operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" - preprocessed = ["name", "doc", "title", "do", "dump", "flags"] + preprocessed = ["name", "doc", "title", "do", "dump", "flags", "event"] linkable = ["fixed-header", "attribute-set"] lines = [] @@ -217,6 +217,9 @@ class YnlDocGenerator: if "dump" in operation: lines.append(self.fmt.rst_paragraph(":dump:", 0)) lines.append(self.parse_do(operation["dump"], 0)) + if "event" in operation: + lines.append(self.fmt.rst_paragraph(":event:", 0)) + lines.append(self.parse_op_attributes(operation["event"], 0)) # New line after fields lines.append("\n") diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index ee94c281888a..26159e0499c7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -47,6 +47,7 @@ void test_xdp_context_test_run(void) struct test_xdp_context_test_run *skel = NULL; char data[sizeof(pkt_v4) + sizeof(__u32)]; char bad_ctx[sizeof(struct xdp_md) + 1]; + char large_data[256]; struct xdp_md ctx_in, ctx_out; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, @@ -94,9 +95,6 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data), 0, 0, 0); - /* Meta data must be 255 bytes or smaller */ - test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0); - /* Total size of data must be data_end - data_meta or larger */ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data) + 1, 0, 0, 0); @@ -116,6 +114,16 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data), 0, 0, 1); + /* Meta data must be 216 bytes or smaller (256 - sizeof(struct + * xdp_frame)). Test both nearest invalid size and nearest invalid + * 4-byte-aligned size, and make sure data_in is large enough that we + * actually hit the check on metadata length + */ + opts.data_in = large_data; + opts.data_size_in = sizeof(large_data); + test_xdp_context_error(prog_fd, opts, 0, 217, sizeof(large_data), 0, 0, 0); + test_xdp_context_error(prog_fd, opts, 0, 220, sizeof(large_data), 0, 0, 0); + test_xdp_context_test_run__destroy(skel); } diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index d23b3b0c20a3..285bb17df9c2 100644 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -485,8 +485,8 @@ static void parse_rps_bitmap(const char *arg) bitmap = strtoul(arg, NULL, 0); - if (bitmap & ~(RPS_MAX_CPUS - 1)) - error(1, 0, "rps bitmap 0x%lx out of bounds 0..%lu", + if (bitmap & ~((1UL << RPS_MAX_CPUS) - 1)) + error(1, 0, "rps bitmap 0x%lx out of bounds, max cpu %lu", bitmap, RPS_MAX_CPUS - 1); for (i = 0; i < RPS_MAX_CPUS; i++) diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index d2db5ee9e358..d288c57894f6 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -94,12 +94,14 @@ def _configure_rps(cfg, rps_cpus): mask = 0 for cpu in rps_cpus: mask |= (1 << cpu) - mask = hex(mask)[2:] + + mask = hex(mask) # Set RPS bitmap for all rx queues for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): with open(rps_file, "w", encoding="utf-8") as fp: - fp.write(mask) + # sysfs expects hex without '0x' prefix, toeplitz.c needs the prefix + fp.write(mask[2:]) return mask diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7d..37b166260ee3 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -69,6 +69,12 @@ static inline void __tileloadd(void *tile) : : "a"(tile), "d"(0)); } +static inline int tileloadd_safe(void *tile) +{ + return kvm_asm_safe(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10", + "a"(tile), "d"(0)); +} + static inline void __tilerelease(void) { asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); @@ -124,27 +130,52 @@ static void set_tilecfg(struct tile_config *cfg) } } +enum { + /* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */ + TEST_SAVE_TILEDATA = 1, + + /* Check TMM0 against tiledata */ + TEST_COMPARE_TILEDATA = 2, + + /* Restore TMM0 from earlier save */ + TEST_RESTORE_TILEDATA = 4, + + /* Full VM save/restore */ + TEST_SAVE_RESTORE = 8, +}; + static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, struct xstate *xstate) { + int vector; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) && this_cpu_has(X86_FEATURE_OSXSAVE)); check_xtile_info(); - GUEST_SYNC(1); + GUEST_SYNC(TEST_SAVE_RESTORE); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(2); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - GUEST_SYNC(3); + GUEST_SYNC(TEST_SAVE_RESTORE); /* Check save/restore when trap to userspace */ __tileloadd(tiledata); - GUEST_SYNC(4); + GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* host tries setting tiledata while guest XFD is set */ + GUEST_SYNC(TEST_RESTORE_TILEDATA); + GUEST_SYNC(TEST_SAVE_RESTORE); + + wrmsr(MSR_IA32_XFD, 0); __tilerelease(); - GUEST_SYNC(5); + GUEST_SYNC(TEST_SAVE_RESTORE); /* * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. @@ -154,6 +185,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); + /* #NM test */ + /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); @@ -166,32 +199,33 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); - GUEST_SYNC(6); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - /* Trigger #NM exception */ - __tileloadd(tiledata); - GUEST_SYNC(10); - GUEST_DONE(); -} + /* Trigger #NM exception */ + vector = tileloadd_safe(tiledata); + __GUEST_ASSERT(vector == NM_VECTOR, + "Wanted #NM on tileloadd with XFD[18]=1, got %s", + ex_str(vector)); -void guest_nm_handler(struct ex_regs *regs) -{ - /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ - GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); - GUEST_SYNC(8); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(9); + GUEST_SYNC(TEST_SAVE_RESTORE); + + __tileloadd(tiledata); + GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -200,10 +234,10 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_x86_state *state; + struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; - u32 amx_offset; int ret; /* @@ -228,9 +262,6 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); - /* Register #NM handler */ - vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); - /* amx cfg for guest_code */ amx_cfg = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); @@ -244,6 +275,7 @@ int main(int argc, char *argv[]) memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); + int iter = 0; for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); @@ -253,37 +285,47 @@ int main(int argc, char *argv[]) REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: - switch (uc.args[1]) { - case 1: - case 2: - case 3: - case 5: - case 6: - case 7: - case 8: - fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); - break; - case 4: - case 10: - fprintf(stderr, - "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + ++iter; + if (uc.args[1] & TEST_SAVE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter); + tile_state = vcpu_save_state(vcpu); + } + if (uc.args[1] & TEST_COMPARE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter); /* Compacted mode, get amx offset by xsave area * size subtract 8K amx size. */ - amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; - state = vcpu_save_state(vcpu); - void *amx_start = (void *)state->xsave + amx_offset; + u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + void *amx_start = (void *)tile_state->xsave + amx_offset; void *tiles_data = (void *)addr_gva2hva(vm, tiledata); /* Only check TMM0 register, 1 tile */ ret = memcmp(amx_start, tiles_data, TILE_SIZE); TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret); + } + if (uc.args[1] & TEST_RESTORE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter); + vcpu_xsave_set(vcpu, tile_state->xsave); + fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter); + } + if (uc.args[1] & TEST_SAVE_RESTORE) { + fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter); + state = vcpu_save_state(vcpu); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vcpu, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); kvm_x86_state_cleanup(state); - break; - case 9: - fprintf(stderr, - "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); - break; + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vcpu, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); } break; case UCALL_DONE: @@ -293,22 +335,6 @@ int main(int argc, char *argv[]) TEST_FAIL("Unknown ucall %lu", uc.cmd); } - state = vcpu_save_state(vcpu); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vcpu, ®s1); - - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - vcpu = vm_recreate_with_one_vcpu(vm); - vcpu_load_state(vcpu, state); - kvm_x86_state_cleanup(state); - - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vcpu, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); } done: kvm_vm_free(vm); diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 6279893a0adc..f61150d28eb2 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -179,7 +179,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) if (rw && shared && fs_is_unknown(fs_type)) { ksft_print_msg("Unknown filesystem\n"); result = KSFT_SKIP; - return; + break; } /* * R/O pinning or pinning in a private mapping is always diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index 363c1033cc7d..10b686102b79 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -22,12 +22,37 @@ FIXTURE(merge) struct procmap_fd procmap; }; +static char *map_carveout(unsigned int page_size) +{ + return mmap(NULL, 30 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); +} + +static pid_t do_fork(struct procmap_fd *procmap) +{ + pid_t pid = fork(); + + if (pid == -1) + return -1; + if (pid != 0) { + wait(NULL); + return pid; + } + + /* Reopen for child. */ + if (close_procmap(procmap)) + return -1; + if (open_self_procmap(procmap)) + return -1; + + return 0; +} + FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, - MAP_ANON | MAP_PRIVATE, -1, 0); + self->carveout = map_carveout(self->page_size); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ ASSERT_EQ(open_self_procmap(&self->procmap), 0); @@ -36,7 +61,8 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); - ASSERT_EQ(close_procmap(&self->procmap), 0); + /* May fail for parent of forked process. */ + close_procmap(&self->procmap); /* * Clear unconditionally, as some tests set this. It is no issue if this * fails (KSM may be disabled for instance). @@ -44,6 +70,44 @@ FIXTURE_TEARDOWN(merge) prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); } +FIXTURE(merge_with_fork) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_VARIANT(merge_with_fork) +{ + bool forked; +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, forked) +{ + .forked = true, +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, unforked) +{ + .forked = false, +}; + +FIXTURE_SETUP(merge_with_fork) +{ + self->page_size = psize(); + self->carveout = map_carveout(self->page_size); + ASSERT_NE(self->carveout, MAP_FAILED); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge_with_fork) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* See above. */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + TEST_F(merge, mprotect_unfaulted_left) { unsigned int page_size = self->page_size; @@ -322,8 +386,8 @@ TEST_F(merge, forked_target_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -344,19 +408,10 @@ TEST_F(merge, forked_target_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -386,8 +441,8 @@ TEST_F(merge, forked_source_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -408,19 +463,10 @@ TEST_F(merge, forked_source_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -1171,4 +1217,288 @@ TEST_F(merge, mremap_correct_placed_faulted) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); } +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |------------| + * | \ | + * |-----------| | / |---------| + * | unfaulted | v \ | faulted | + * |-----------| / |---------| + * B \ A + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |---------------------------| + * | \ | + * | |-----------| / |---------| + * v | unfaulted | \ | faulted | + * |-----------| / |---------| + * B \ A + * + * Then unmap VMA A to trigger the bug. + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b, *ptr_c; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | unfaulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + /* Fault it in. */ + ptr_b[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMAs A, C in position, + * unfaulted. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA C into place. */ + ptr_c = mmap(&self->carveout[page_size + 3 * page_size + 3 * page_size], + 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_c, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 9 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); + + /* If forked, B and C should also not have merged. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 3 * page_size); + } +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_faulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + char *ptr_a, *ptr_b, *ptr_bc; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | faulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* + * Map VMA B and C into place. We have to map them together so their + * anon_vma is the same and the vma->vm_pgoff's are correctly aligned. + */ + ptr_bc = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_bc, MAP_FAILED); + + /* Fault it in. */ + ptr_bc[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move VMA B out the way (splitting VMA BC) so we can place VMA A + * in position, unfaulted, and leave the remainder of the VMA we just + * moved in place, faulted, as VMA C. + */ + ptr_b = mremap(ptr_bc, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged. A,B,C if unforked, B, C if forked. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 6 * page_size); + } else { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + 9 * page_size); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index d843643ced6b..9430ef5b8bc3 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -511,6 +511,18 @@ void run_tests(const struct test_case *test_cases, printf("ok\n"); } + + printf("All tests have been executed. Waiting other peer..."); + fflush(stdout); + + /* + * Final full barrier, to ensure that all tests have been run and + * that even the last one has been successful on both sides. + */ + control_writeln("COMPLETED"); + control_expectln("COMPLETED"); + + printf("ok\n"); } void list_tests(const struct test_case *test_cases) |