diff options
203 files changed, 2729 insertions, 1460 deletions
diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml index 7735e08d35ba..beef193aaaeb 100644 --- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml +++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml @@ -102,21 +102,21 @@ properties: default: 2 interrupts: - anyOf: - - minItems: 1 - items: - - description: TX interrupt - - description: RX interrupt - - items: - - description: common/combined interrupt + minItems: 1 + maxItems: 2 interrupt-names: oneOf: - - minItems: 1 + - description: TX interrupt + const: tx + - description: RX interrupt + const: rx + - description: TX and RX interrupts items: - const: tx - const: rx - - const: common + - description: Common/combined interrupt + const: common fck_parent: $ref: /schemas/types.yaml#/definitions/string @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 58 +SUBLEVEL = 59 EXTRAVERSION = NAME = Pinguïn Aangedreven diff --git a/arch/arm/boot/dts/broadcom/bcm2837-rpi-cm3-io3.dts b/arch/arm/boot/dts/broadcom/bcm2837-rpi-cm3-io3.dts index 72d26d130efa..85f54fa595aa 100644 --- a/arch/arm/boot/dts/broadcom/bcm2837-rpi-cm3-io3.dts +++ b/arch/arm/boot/dts/broadcom/bcm2837-rpi-cm3-io3.dts @@ -77,7 +77,7 @@ }; &hdmi { - hpd-gpios = <&expgpio 1 GPIO_ACTIVE_LOW>; + hpd-gpios = <&expgpio 0 GPIO_ACTIVE_LOW>; power-domains = <&power RPI_POWER_DOMAIN_HDMI>; status = "okay"; }; diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 9a2d3723cd0f..11782860717f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X --pic-veneer ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 685cc436146a..18413d869cca 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -777,6 +777,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) + return -EIO; + if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) kvm_vcpu_sleep(vcpu); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b233a64df295..370a1a7bd369 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1708,7 +1708,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) * one cache line. */ if (kvm_has_mte(vcpu->kvm)) - clidr |= 2 << CLIDR_TTYPE_SHIFT(loc); + clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc); __vcpu_sys_reg(vcpu, r->reg) = clidr; diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index a2b439ad387c..b7306c588d9d 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -494,10 +494,10 @@ int kvm_vgic_map_resources(struct kvm *kvm) out: mutex_unlock(&kvm->arch.config_lock); out_slots: - mutex_unlock(&kvm->slots_lock); - if (ret) - kvm_vgic_destroy(kvm); + kvm_vm_dead(kvm); + + mutex_unlock(&kvm->slots_lock); return ret; } diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h index c60796869b2b..d2317fa6a766 100644 --- a/arch/loongarch/include/asm/bootinfo.h +++ b/arch/loongarch/include/asm/bootinfo.h @@ -24,6 +24,10 @@ struct loongson_board_info { const char *board_vendor; }; +/* + * The "core" of cores_per_node and cores_per_package stands for a + * logical core, which means in a SMT system it stands for a thread. + */ struct loongson_system_configuration { int nr_cpus; int nr_nodes; diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index cd6084f4e153..c6bce5fbff57 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -16,7 +16,7 @@ #define XRANGE_SHIFT (48) /* Valid address length */ -#define XRANGE_SHADOW_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) +#define XRANGE_SHADOW_SHIFT min(cpu_vabits, VA_BITS) /* Used for taking out the valid address */ #define XRANGE_SHADOW_MASK GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0) /* One segment whole address space size */ diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index f2ff8b5d591e..6e58f65455c7 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -293,13 +293,15 @@ unsigned long stack_top(void) { unsigned long top = TASK_SIZE & PAGE_MASK; - /* Space for the VDSO & data page */ - top -= PAGE_ALIGN(current->thread.vdso->size); - top -= VVAR_SIZE; - - /* Space to randomize the VDSO base */ - if (current->flags & PF_RANDOMIZE) - top -= VDSO_RANDOMIZE_SIZE; + if (current->thread.vdso) { + /* Space for the VDSO & data page */ + top -= PAGE_ALIGN(current->thread.vdso->size); + top -= VVAR_SIZE; + + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + } return top; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 6748d7f3f221..065f2db57c09 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -55,6 +55,7 @@ #define SMBIOS_FREQHIGH_OFFSET 0x17 #define SMBIOS_FREQLOW_MASK 0xFF #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 +#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25 #define LOONGSON_EFI_ENABLE (1 << 3) #ifdef CONFIG_EFI @@ -129,7 +130,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm) cpu_clock_freq = freq_temp * 1000000; loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]); - loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET); + loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); pr_info("CpuClock = %llu\n", cpu_clock_freq); } diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index aebfc3733a76..d59052c03d9b 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -529,6 +529,9 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs) #else unsigned int *pc; + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_enable(); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); /* @@ -553,6 +556,8 @@ sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); out: + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_disable(); #endif irqentry_exit(regs, state); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 2f041b5cea97..26eeb3973631 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -555,8 +555,8 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, rv_lr_w(r0, 0, rd, 0, 0), ctx); jmp_offset = ninsns_rvoff(8); emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx); - emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) : - rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx); + emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) : + rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); emit(rv_fence(0x3, 0x3), ctx); diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 9917e2717b2b..66aff768f815 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -73,6 +73,7 @@ struct perf_sf_sde_regs { #define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE) #define perf_arch_fetch_caller_regs(regs, __ip) do { \ + (regs)->psw.mask = 0; \ (regs)->psw.addr = (__ip); \ (regs)->gprs[15] = (unsigned long)__builtin_frame_address(0) - \ offsetof(struct stack_frame, back_chain); \ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b9324ca2eb94..b3961f1016ea 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -272,18 +272,19 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) goto no_pdev; switch (ccdf->pec) { - case 0x003a: /* Service Action or Error Recovery Successful */ + case 0x002a: /* Error event concerns FMB */ + case 0x002b: + case 0x002c: + break; + case 0x0040: /* Service Action or Error Recovery Failed */ + case 0x003b: + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: /* PCI function left in the error state attempt to recover */ ers_res = zpci_event_attempt_error_recovery(pdev); if (ers_res != PCI_ERS_RESULT_RECOVERED) zpci_event_io_failure(pdev, pci_channel_io_perm_failure); break; - default: - /* - * Mark as frozen not permanently failed because the device - * could be subsequently recovered by the platform. - */ - zpci_event_io_failure(pdev, pci_channel_io_frozen); - break; } pci_dev_put(pdev); no_pdev: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 82d12c93feab..05c82fd5d0f6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2217,6 +2217,7 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING config ADDRESS_MASKING bool "Linear Address Masking support" depends on X86_64 + depends on COMPILE_TEST || !CPU_MITIGATIONS # wait for LASS help Linear Address Masking (LAM) modifies the checking that is applied to 64-bit linear addresses, allowing software to use of the diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index b44c487727d4..a701e7921ea5 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -27,10 +27,10 @@ * hardware. The allocated bandwidth percentage is rounded to the next * control step available on the hardware. */ -static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) { - unsigned long bw; int ret; + u32 bw; /* * Only linear delay values is supported for current Intel SKUs. @@ -40,16 +40,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - ret = kstrtoul(buf, 10, &bw); + ret = kstrtou32(buf, 10, &bw); if (ret) { - rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); + rdt_last_cmd_printf("Invalid MB value %s\n", buf); return false; } - if ((bw < r->membw.min_bw || bw > r->default_ctrl) && - !is_mba_sc(r)) { - rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, - r->membw.min_bw, r->default_ctrl); + /* Nothing else to do if software controller is enabled. */ + if (is_mba_sc(r)) { + *data = bw; + return true; + } + + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", + bw, r->membw.min_bw, r->default_ctrl); return false; } @@ -63,7 +68,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; - unsigned long bw_val; + u32 bw_val; cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 60891b9ce25f..acf22bd99efc 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -63,8 +63,12 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; + /* + * Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores + * nCR3[4:0] when loading PDPTEs from memory. + */ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + (cr3 & GENMASK(11, 5)) + index * 8, 8); if (ret) return 0; return pdpte; diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 388abd40024b..f3db3fa91dd5 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -496,7 +496,7 @@ static int encode_addr_size_pairs(struct dma_xfer *xfer, struct wrapper_list *wr nents = sgt->nents; nents_dma = nents; *size = QAIC_MANAGE_EXT_MSG_LENGTH - msg_hdr_len - sizeof(**out_trans); - for_each_sgtable_sg(sgt, sg, i) { + for_each_sgtable_dma_sg(sgt, sg, i) { *size -= sizeof(*asp); /* Save 1K for possible follow-up transactions. */ if (*size < SZ_1K) { diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index ed1a5af434f2..d2f8c70a77a5 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -177,7 +177,7 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl nents = 0; size = size ? size : PAGE_SIZE; - for (sg = sgt_in->sgl; sg; sg = sg_next(sg)) { + for_each_sgtable_dma_sg(sgt_in, sg, j) { len = sg_dma_len(sg); if (!len) @@ -214,7 +214,7 @@ static int clone_range_of_sgt_for_slice(struct qaic_device *qdev, struct sg_tabl /* copy relevant sg node and fix page and length */ sgn = sgf; - for_each_sgtable_sg(sgt, sg, j) { + for_each_sgtable_dma_sg(sgt, sg, j) { memcpy(sg, sgn, sizeof(*sg)); if (sgn == sgf) { sg_dma_address(sg) += offf; @@ -294,7 +294,7 @@ static int encode_reqs(struct qaic_device *qdev, struct bo_slice *slice, * fence. */ dev_addr = req->dev_addr; - for_each_sgtable_sg(slice->sgt, sg, i) { + for_each_sgtable_dma_sg(slice->sgt, sg, i) { slice->reqs[i].cmd = cmd; slice->reqs[i].src_addr = cpu_to_le64(slice->dir == DMA_TO_DEVICE ? sg_dma_address(sg) : dev_addr); diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 1e76a64cce0a..906a7bfa448b 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -130,6 +130,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = { }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, + { + /* + * Samsung galaxybook2 ,initial _LID device notification returns + * lid closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "750XED"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, {} }; diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 7aced0b9bad7..5df417626fd1 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -39,6 +39,9 @@ #include <linux/rwsem.h> #include <linux/wait.h> #include <linux/topology.h> +#include <linux/dmi.h> +#include <linux/units.h> +#include <asm/unaligned.h> #include <acpi/cppc_acpi.h> @@ -1858,3 +1861,116 @@ unsigned int cppc_get_transition_latency(int cpu_num) return latency_ns; } EXPORT_SYMBOL_GPL(cppc_get_transition_latency); + +/* Minimum struct length needed for the DMI processor entry we want */ +#define DMI_ENTRY_PROCESSOR_MIN_LENGTH 48 + +/* Offset in the DMI processor structure for the max frequency */ +#define DMI_PROCESSOR_MAX_SPEED 0x14 + +/* Callback function used to retrieve the max frequency from DMI */ +static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) +{ + const u8 *dmi_data = (const u8 *)dm; + u16 *mhz = (u16 *)private; + + if (dm->type == DMI_ENTRY_PROCESSOR && + dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) { + u16 val = (u16)get_unaligned((const u16 *) + (dmi_data + DMI_PROCESSOR_MAX_SPEED)); + *mhz = val > *mhz ? val : *mhz; + } +} + +/* Look up the max frequency in DMI */ +static u64 cppc_get_dmi_max_khz(void) +{ + u16 mhz = 0; + + dmi_walk(cppc_find_dmi_mhz, &mhz); + + /* + * Real stupid fallback value, just in case there is no + * actual value set. + */ + mhz = mhz ? mhz : 1; + + return KHZ_PER_MHZ * mhz; +} + +/* + * If CPPC lowest_freq and nominal_freq registers are exposed then we can + * use them to convert perf to freq and vice versa. The conversion is + * extrapolated as an affine function passing by the 2 points: + * - (Low perf, Low freq) + * - (Nominal perf, Nominal freq) + */ +unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf) +{ + s64 retval, offset = 0; + static u64 max_khz; + u64 mul, div; + + if (caps->lowest_freq && caps->nominal_freq) { + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_freq; + div = caps->nominal_perf; + } else { + mul = caps->nominal_freq - caps->lowest_freq; + div = caps->nominal_perf - caps->lowest_perf; + } + mul *= KHZ_PER_MHZ; + offset = caps->nominal_freq * KHZ_PER_MHZ - + div64_u64(caps->nominal_perf * mul, div); + } else { + if (!max_khz) + max_khz = cppc_get_dmi_max_khz(); + mul = max_khz; + div = caps->highest_perf; + } + + retval = offset + div64_u64(perf * mul, div); + if (retval >= 0) + return retval; + return 0; +} +EXPORT_SYMBOL_GPL(cppc_perf_to_khz); + +unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq) +{ + s64 retval, offset = 0; + static u64 max_khz; + u64 mul, div; + + if (caps->lowest_freq && caps->nominal_freq) { + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_perf; + div = caps->nominal_freq; + } else { + mul = caps->nominal_perf - caps->lowest_perf; + div = caps->nominal_freq - caps->lowest_freq; + } + /* + * We don't need to convert to kHz for computing offset and can + * directly use nominal_freq and lowest_freq as the div64_u64 + * will remove the frequency unit. + */ + offset = caps->nominal_perf - + div64_u64(caps->nominal_freq * mul, div); + /* But we need it for computing the perf level. */ + div *= KHZ_PER_MHZ; + } else { + if (!max_khz) + max_khz = cppc_get_dmi_max_khz(); + mul = caps->highest_perf; + div = max_khz; + } + + retval = offset + div64_u64(freq * mul, div); + if (retval >= 0) + return retval; + return 0; +} +EXPORT_SYMBOL_GPL(cppc_khz_to_perf); diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index 7020584096bf..8b391f12853b 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -52,7 +52,7 @@ struct prm_context_buffer { static LIST_HEAD(prm_module_list); struct prm_handler_info { - guid_t guid; + efi_guid_t guid; efi_status_t (__efiapi *handler_addr)(u64, void *); u64 static_data_buffer_addr; u64 acpi_param_buffer_addr; @@ -72,17 +72,21 @@ struct prm_module_info { struct prm_handler_info handlers[]; }; -static u64 efi_pa_va_lookup(u64 pa) +static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa) { efi_memory_desc_t *md; u64 pa_offset = pa & ~PAGE_MASK; u64 page = pa & PAGE_MASK; for_each_efi_memory_desc(md) { - if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages) + if ((md->attribute & EFI_MEMORY_RUNTIME) && + (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) { return pa_offset + md->virt_addr + page - md->phys_addr; + } } + pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa); + return 0; } @@ -148,9 +152,15 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end) th = &tm->handlers[cur_handler]; guid_copy(&th->guid, (guid_t *)handler_info->handler_guid); - th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address); - th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address); - th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address); + th->handler_addr = + (void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address); + + th->static_data_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address); + + th->acpi_param_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address); + } while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info))); return 0; @@ -253,6 +263,13 @@ static acpi_status acpi_platformrt_space_handler(u32 function, if (!handler || !module) goto invalid_guid; + if (!handler->handler_addr || + !handler->static_data_buffer_addr || + !handler->acpi_param_buffer_addr) { + buffer->prm_status = PRM_HANDLER_ERROR; + return AE_OK; + } + ACPI_COPY_NAMESEG(context.signature, "PRMC"); context.revision = 0x0; context.reserved = 0x0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 95233b413c1a..d3d776d4fb5a 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -498,6 +498,13 @@ static const struct dmi_system_id tongfang_gm_rg[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), }, }, + { + /* LG Electronics 16T90SP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "16T90SP"), + }, + }, { } }; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index a96566e1b2b8..9cc022522184 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -636,6 +636,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, /* the scmd has an associated qc */ if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ + set_host_byte(scmd, DID_TIME_OUT); qc->err_mask |= AC_ERR_TIMEOUT; qc->flags |= ATA_QCFLAG_EH; nr_timedout++; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 01f46caf1f88..54b80911f3e2 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2313,7 +2313,7 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, return -EINVAL; /* Prevent arg from speculatively bypassing the length check */ - barrier_nospec(); + arg = array_index_nospec(arg, cdi->capacity); info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index f461f99eb040..8c16d67b98bf 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1061,11 +1061,21 @@ static int amd_pstate_register_driver(int mode) return -EINVAL; cppc_state = mode; + + ret = amd_pstate_enable(true); + if (ret) { + pr_err("failed to enable cppc during amd-pstate driver registration, return %d\n", + ret); + amd_pstate_driver_cleanup(); + return ret; + } + ret = cpufreq_register_driver(current_pstate_driver); if (ret) { amd_pstate_driver_cleanup(); return ret; } + return 0; } diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 1ba3943be8a3..15f1d41920a3 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -16,7 +16,6 @@ #include <linux/delay.h> #include <linux/cpu.h> #include <linux/cpufreq.h> -#include <linux/dmi.h> #include <linux/irq_work.h> #include <linux/kthread.h> #include <linux/time.h> @@ -27,12 +26,6 @@ #include <acpi/cppc_acpi.h> -/* Minimum struct length needed for the DMI processor entry we want */ -#define DMI_ENTRY_PROCESSOR_MIN_LENGTH 48 - -/* Offset in the DMI processor structure for the max frequency */ -#define DMI_PROCESSOR_MAX_SPEED 0x14 - /* * This list contains information parsed from per CPU ACPI _CPC and _PSD * structures: e.g. the highest and lowest supported performance, capabilities, @@ -291,97 +284,9 @@ static inline void cppc_freq_invariance_exit(void) } #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */ -/* Callback function used to retrieve the max frequency from DMI */ -static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) -{ - const u8 *dmi_data = (const u8 *)dm; - u16 *mhz = (u16 *)private; - - if (dm->type == DMI_ENTRY_PROCESSOR && - dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) { - u16 val = (u16)get_unaligned((const u16 *) - (dmi_data + DMI_PROCESSOR_MAX_SPEED)); - *mhz = val > *mhz ? val : *mhz; - } -} - -/* Look up the max frequency in DMI */ -static u64 cppc_get_dmi_max_khz(void) -{ - u16 mhz = 0; - - dmi_walk(cppc_find_dmi_mhz, &mhz); - - /* - * Real stupid fallback value, just in case there is no - * actual value set. - */ - mhz = mhz ? mhz : 1; - - return (1000 * mhz); -} - -/* - * If CPPC lowest_freq and nominal_freq registers are exposed then we can - * use them to convert perf to freq and vice versa. The conversion is - * extrapolated as an affine function passing by the 2 points: - * - (Low perf, Low freq) - * - (Nominal perf, Nominal perf) - */ -static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data, - unsigned int perf) -{ - struct cppc_perf_caps *caps = &cpu_data->perf_caps; - s64 retval, offset = 0; - static u64 max_khz; - u64 mul, div; - - if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_freq - caps->lowest_freq; - div = caps->nominal_perf - caps->lowest_perf; - offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div); - } else { - if (!max_khz) - max_khz = cppc_get_dmi_max_khz(); - mul = max_khz; - div = caps->highest_perf; - } - - retval = offset + div64_u64(perf * mul, div); - if (retval >= 0) - return retval; - return 0; -} - -static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data, - unsigned int freq) -{ - struct cppc_perf_caps *caps = &cpu_data->perf_caps; - s64 retval, offset = 0; - static u64 max_khz; - u64 mul, div; - - if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_perf - caps->lowest_perf; - div = caps->nominal_freq - caps->lowest_freq; - offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div); - } else { - if (!max_khz) - max_khz = cppc_get_dmi_max_khz(); - mul = caps->highest_perf; - div = max_khz; - } - - retval = offset + div64_u64(freq * mul, div); - if (retval >= 0) - return retval; - return 0; -} - static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) - { struct cppc_cpudata *cpu_data = policy->driver_data; unsigned int cpu = policy->cpu; @@ -389,7 +294,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, u32 desired_perf; int ret = 0; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); /* Return if it is exactly the same perf */ if (desired_perf == cpu_data->perf_ctrls.desired_perf) return ret; @@ -417,7 +322,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy, u32 desired_perf; int ret; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); cpu_data->perf_ctrls.desired_perf = desired_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -530,7 +435,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev, min_step = min_cap / CPPC_EM_CAP_STEP; max_step = max_cap / CPPC_EM_CAP_STEP; - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + perf_prev = cppc_khz_to_perf(perf_caps, *KHz); step = perf_prev / perf_step; if (step > max_step) @@ -550,8 +455,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, perf = step * perf_step; } - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; /* @@ -561,8 +466,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, */ while ((*KHz == prev_freq) || (step_check != step)) { perf++; - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; } @@ -591,7 +496,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, perf_caps = &cpu_data->perf_caps; max_cap = arch_scale_cpu_capacity(cpu_dev->id); - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz); + perf_prev = cppc_khz_to_perf(perf_caps, KHz); perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; step = perf_prev / perf_step; @@ -679,10 +584,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) goto free_mask; } - /* Convert the lowest and nominal freq from MHz to KHz */ - cpu_data->perf_caps.lowest_freq *= 1000; - cpu_data->perf_caps.nominal_freq *= 1000; - list_add(&cpu_data->node, &cpu_data_list); return cpu_data; @@ -724,20 +625,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Set min to lowest nonlinear perf to avoid any efficiency penalty (see * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ - policy->min = cppc_cpufreq_perf_to_khz(cpu_data, - caps->lowest_nonlinear_perf); - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance * available if userspace wants to use any perf between lowest & lowest * nonlinear perf */ - policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data, - caps->lowest_perf); - policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; @@ -773,7 +670,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) boost_supported = true; /* Set policy->cur to max now. The governors will adjust later. */ - policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf); + policy->cur = cppc_perf_to_khz(caps, caps->highest_perf); cpu_data->perf_ctrls.desired_perf = caps->highest_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -868,7 +765,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0, &fb_ctrs_t1); - return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); } static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) @@ -883,11 +780,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) } if (state) - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->highest_perf); + policy->max = cppc_perf_to_khz(caps, caps->highest_perf); else - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); policy->cpuinfo.max_freq = policy->max; ret = freq_qos_update_request(policy->max_freq_req, policy->max); @@ -947,7 +842,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) if (ret < 0) return -EIO; - return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf); } static void cppc_check_hisi_workaround(void) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 87383c05424b..3962683e2af9 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2603,10 +2603,8 @@ static struct scmi_debug_info *scmi_debugfs_common_setup(struct scmi_info *info) dbg->top_dentry = top_dentry; if (devm_add_action_or_reset(info->dev, - scmi_debugfs_common_cleanup, dbg)) { - scmi_debugfs_common_cleanup(dbg); + scmi_debugfs_common_cleanup, dbg)) return NULL; - } return dbg; } diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index b8d470417e8f..8e513f70b75d 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -23,6 +23,7 @@ * @chan_receiver: Optional Receiver mailbox unidirectional channel * @cinfo: SCMI channel info * @shmem: Transmit/Receive shared memory area + * @chan_lock: Lock that prevents multiple xfers from being queued */ struct scmi_mailbox { struct mbox_client cl; @@ -30,6 +31,7 @@ struct scmi_mailbox { struct mbox_chan *chan_receiver; struct scmi_chan_info *cinfo; struct scmi_shared_mem __iomem *shmem; + struct mutex chan_lock; }; #define client_to_scmi_mailbox(c) container_of(c, struct scmi_mailbox, cl) @@ -228,6 +230,7 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, cinfo->transport_info = smbox; smbox->cinfo = cinfo; + mutex_init(&smbox->chan_lock); return 0; } @@ -255,13 +258,23 @@ static int mailbox_send_message(struct scmi_chan_info *cinfo, struct scmi_mailbox *smbox = cinfo->transport_info; int ret; - ret = mbox_send_message(smbox->chan, xfer); + /* + * The mailbox layer has its own queue. However the mailbox queue + * confuses the per message SCMI timeouts since the clock starts when + * the message is submitted into the mailbox queue. So when multiple + * messages are queued up the clock starts on all messages instead of + * only the one inflight. + */ + mutex_lock(&smbox->chan_lock); - /* mbox_send_message returns non-negative value on success, so reset */ - if (ret > 0) - ret = 0; + ret = mbox_send_message(smbox->chan, xfer); + /* mbox_send_message returns non-negative value on success */ + if (ret < 0) { + mutex_unlock(&smbox->chan_lock); + return ret; + } - return ret; + return 0; } static void mailbox_mark_txdone(struct scmi_chan_info *cinfo, int ret, @@ -269,13 +282,10 @@ static void mailbox_mark_txdone(struct scmi_chan_info *cinfo, int ret, { struct scmi_mailbox *smbox = cinfo->transport_info; - /* - * NOTE: we might prefer not to need the mailbox ticker to manage the - * transfer queueing since the protocol layer queues things by itself. - * Unfortunately, we have to kick the mailbox framework after we have - * received our message. - */ mbox_client_txdone(smbox->chan, ret); + + /* Release channel */ + mutex_unlock(&smbox->chan_lock); } static void mailbox_fetch_response(struct scmi_chan_info *cinfo, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 2bca37044ad0..fac204d6e0ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, struct acpi_buffer *params) { acpi_status status; + union acpi_object *obj; union acpi_object atif_arg_elements[2]; struct acpi_object_list atif_arg; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, status = acpi_evaluate_object(atif->handle, NULL, &atif_arg, &buffer); + obj = (union acpi_object *)buffer.pointer; - /* Fail only if calling the method fails and ATIF is supported */ + /* Fail if calling the method fails and ATIF is supported */ if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n", acpi_format_exception(status)); - kfree(buffer.pointer); + kfree(obj); return NULL; } - return buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER) { + DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n", + obj->type); + kfree(obj); + return NULL; + } + + return obj; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index c5c55e132af2..5e3abdd0805b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1053,8 +1053,10 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, r = amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT, NULL); - if (r) + if (r) { + amdgpu_mes_unlock(&adev->mes); goto clean_up_memory; + } amdgpu_mes_ring_to_queue_props(adev, ring, &qprops); @@ -1087,7 +1089,6 @@ clean_up_ring: amdgpu_ring_fini(ring); clean_up_memory: kfree(ring); - amdgpu_mes_unlock(&adev->mes); return r; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 2b3d5183818a..4887a360ead4 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) isPSRSUSupported = false; else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index e238e4e8116c..ad57368dc13f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -722,12 +722,13 @@ void dpu_crtc_complete_commit(struct drm_crtc *crtc) _dpu_crtc_complete_flip(crtc); } -static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc, +static int _dpu_crtc_check_and_setup_lm_bounds(struct drm_crtc *crtc, struct drm_crtc_state *state) { struct dpu_crtc_state *cstate = to_dpu_crtc_state(state); struct drm_display_mode *adj_mode = &state->adjusted_mode; u32 crtc_split_width = adj_mode->hdisplay / cstate->num_mixers; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); int i; for (i = 0; i < cstate->num_mixers; i++) { @@ -738,7 +739,12 @@ static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc, r->y2 = adj_mode->vdisplay; trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r); + + if (drm_rect_width(r) > dpu_kms->catalog->caps->max_mixer_width) + return -E2BIG; } + + return 0; } static void _dpu_crtc_get_pcc_coeff(struct drm_crtc_state *state, @@ -814,7 +820,7 @@ static void dpu_crtc_atomic_begin(struct drm_crtc *crtc, DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id); - _dpu_crtc_setup_lm_bounds(crtc, crtc->state); + _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc->state); /* encoder will trigger pending mask now */ drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) @@ -1208,8 +1214,11 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, if (crtc_state->active_changed) crtc_state->mode_changed = true; - if (cstate->num_mixers) - _dpu_crtc_setup_lm_bounds(crtc, crtc_state); + if (cstate->num_mixers) { + rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state); + if (rc) + return rc; + } /* FIXME: move this to dpu_plane_atomic_check? */ drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 6262ec5e4020..10c68de1bf22 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1122,21 +1122,20 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - if (!dpu_enc->hw_pp[i]) { + phys->hw_pp = dpu_enc->hw_pp[i]; + if (!phys->hw_pp) { DPU_ERROR_ENC(dpu_enc, "no pp block assigned at idx: %d\n", i); return; } - if (!hw_ctl[i]) { + phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL; + if (!phys->hw_ctl) { DPU_ERROR_ENC(dpu_enc, "no ctl block assigned at idx: %d\n", i); return; } - phys->hw_pp = dpu_enc->hw_pp[i]; - phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]); - phys->cached_mode = crtc_state->adjusted_mode; if (phys->ops.atomic_mode_set) phys->ops.atomic_mode_set(phys, crtc_state, conn_state); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index daaf0e604753..20c8b9af7a21 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -280,7 +280,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine( intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); - if (phys_enc->hw_pp->merge_3d) + if (intf_cfg.mode_3d && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index add72bbc28b1..4d55e3cf570f 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -26,7 +26,7 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b end_addr = base_addr + aligned_len; if (!(*reg)) - *reg = kzalloc(len_padded, GFP_KERNEL); + *reg = kvzalloc(len_padded, GFP_KERNEL); if (*reg) dump_addr = *reg; @@ -48,20 +48,21 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b } } -static void msm_disp_state_print_regs(u32 **reg, u32 len, void __iomem *base_addr, - struct drm_printer *p) +static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, + void __iomem *base_addr, struct drm_printer *p) { int i; - u32 *dump_addr = NULL; void __iomem *addr; u32 num_rows; + if (!dump_addr) { + drm_printf(p, "Registers not stored\n"); + return; + } + addr = base_addr; num_rows = len / REG_DUMP_ALIGN; - if (*reg) - dump_addr = *reg; - for (i = 0; i < num_rows; i++) { drm_printf(p, "0x%lx : %08x %08x %08x %08x\n", (unsigned long)(addr - base_addr), @@ -89,7 +90,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p) list_for_each_entry_safe(block, tmp, &state->blocks, node) { drm_printf(p, "====================%s================\n", block->name); - msm_disp_state_print_regs(&block->state, block->size, block->base_addr, p); + msm_disp_state_print_regs(block->state, block->size, block->base_addr, p); } drm_printf(p, "===================dpu drm state================\n"); @@ -161,7 +162,7 @@ void msm_disp_state_free(void *data) list_for_each_entry_safe(block, tmp, &disp_state->blocks, node) { list_del(&block->node); - kfree(block->state); + kvfree(block->state); kfree(block); } diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 77b805eacb1b..f920329fe2e0 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -537,7 +537,7 @@ static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mo int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay; - return new_htotal * mode->vtotal * drm_mode_vrefresh(mode); + return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal); } static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode, @@ -545,7 +545,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode, { unsigned long pclk_rate; - pclk_rate = mode->clock * 1000; + pclk_rate = mode->clock * 1000u; if (dsc) pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc); diff --git a/drivers/gpu/drm/vboxvideo/hgsmi_base.c b/drivers/gpu/drm/vboxvideo/hgsmi_base.c index 8c041d7ce4f1..87dccaecc3e5 100644 --- a/drivers/gpu/drm/vboxvideo/hgsmi_base.c +++ b/drivers/gpu/drm/vboxvideo/hgsmi_base.c @@ -139,7 +139,15 @@ int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, flags |= VBOX_MOUSE_POINTER_VISIBLE; } - p = hgsmi_buffer_alloc(ctx, sizeof(*p) + pixel_len, HGSMI_CH_VBVA, + /* + * The 4 extra bytes come from switching struct vbva_mouse_pointer_shape + * from having a 4 bytes fixed array at the end to using a proper VLA + * at the end. These 4 extra bytes were not subtracted from sizeof(*p) + * before the switch to the VLA, so this way the behavior is unchanged. + * Chances are these 4 extra bytes are not necessary but they are kept + * to avoid regressions. + */ + p = hgsmi_buffer_alloc(ctx, sizeof(*p) + pixel_len + 4, HGSMI_CH_VBVA, VBVA_MOUSE_POINTER_SHAPE); if (!p) return -ENOMEM; diff --git a/drivers/gpu/drm/vboxvideo/vboxvideo.h b/drivers/gpu/drm/vboxvideo/vboxvideo.h index f60d82504da0..79ec8481de0e 100644 --- a/drivers/gpu/drm/vboxvideo/vboxvideo.h +++ b/drivers/gpu/drm/vboxvideo/vboxvideo.h @@ -351,10 +351,8 @@ struct vbva_mouse_pointer_shape { * Bytes in the gap between the AND and the XOR mask are undefined. * XOR mask scanlines have no gap between them and size of XOR mask is: * xor_len = width * 4 * height. - * - * Preallocate 4 bytes for accessing actual data as p->data. */ - u8 data[4]; + u8 data[]; } __packed; /* pointer is visible */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index b22ae25db4e1..52ea0c50c852 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -881,6 +881,10 @@ static int vmw_stdu_connector_atomic_check(struct drm_connector *conn, struct drm_crtc_state *new_crtc_state; conn_state = drm_atomic_get_connector_state(state, conn); + + if (IS_ERR(conn_state)) + return PTR_ERR(conn_state); + du = vmw_connector_to_stdu(conn); if (!conn_state->crtc) diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c index e90e2f01550a..04083b7395ab 100644 --- a/drivers/iio/accel/bma400_core.c +++ b/drivers/iio/accel/bma400_core.c @@ -1219,7 +1219,8 @@ static int bma400_activity_event_en(struct bma400_data *data, static int bma400_tap_event_en(struct bma400_data *data, enum iio_event_direction dir, int state) { - unsigned int mask, field_value; + unsigned int mask; + unsigned int field_value = 0; int ret; /* diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index e46817cb5581..6dee3b686eff 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -1335,6 +1335,8 @@ config TI_LMP92064 tristate "Texas Instruments LMP92064 ADC driver" depends on SPI select REGMAP_SPI + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to build support for the LMP92064 Precision Current and Voltage sensor. diff --git a/drivers/iio/frequency/Kconfig b/drivers/iio/frequency/Kconfig index 71de6cc4a158..036763d3e84c 100644 --- a/drivers/iio/frequency/Kconfig +++ b/drivers/iio/frequency/Kconfig @@ -82,25 +82,26 @@ config ADMV1014 module will be called admv1014. config ADMV4420 - tristate "Analog Devices ADMV4420 K Band Downconverter" - depends on SPI - help - Say yes here to build support for Analog Devices K Band - Downconverter with integrated Fractional-N PLL and VCO. + tristate "Analog Devices ADMV4420 K Band Downconverter" + depends on SPI + select REGMAP_SPI + help + Say yes here to build support for Analog Devices K Band + Downconverter with integrated Fractional-N PLL and VCO. - To compile this driver as a module, choose M here: the - module will be called admv4420. + To compile this driver as a module, choose M here: the + module will be called admv4420. config ADRF6780 - tristate "Analog Devices ADRF6780 Microwave Upconverter" - depends on SPI - depends on COMMON_CLK - help - Say yes here to build support for Analog Devices ADRF6780 - 5.9 GHz to 23.6 GHz, Wideband, Microwave Upconverter. - - To compile this driver as a module, choose M here: the - module will be called adrf6780. + tristate "Analog Devices ADRF6780 Microwave Upconverter" + depends on SPI + depends on COMMON_CLK + help + Say yes here to build support for Analog Devices ADRF6780 + 5.9 GHz to 23.6 GHz, Wideband, Microwave Upconverter. + + To compile this driver as a module, choose M here: the + module will be called adrf6780. endmenu endmenu diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index f253295795f0..fd78d678877c 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -269,6 +269,8 @@ rdma_find_ndev_for_src_ip_rcu(struct net *net, const struct sockaddr *src_in) break; #endif } + if (!ret && dev && is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); return ret ? ERR_PTR(ret) : dev; } diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c index 93572405d6fa..1e63f8091748 100644 --- a/drivers/infiniband/hw/bnxt_re/hw_counters.c +++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c @@ -366,12 +366,12 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev, goto done; } } - if (rdev->pacing.dbr_pacing) + if (rdev->pacing.dbr_pacing && bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) bnxt_re_copy_db_pacing_stats(rdev, stats); } done: - return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? + return bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ? BNXT_RE_NUM_EXT_COUNTERS : BNXT_RE_NUM_STD_COUNTERS; } @@ -381,7 +381,7 @@ struct rdma_hw_stats *bnxt_re_ib_alloc_hw_port_stats(struct ib_device *ibdev, struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); int num_counters = 0; - if (bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) num_counters = BNXT_RE_NUM_EXT_COUNTERS; else num_counters = BNXT_RE_NUM_STD_COUNTERS; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index b4d3e7dfc939..f20da108fb29 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -400,6 +400,10 @@ static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd) struct bnxt_re_fence_data *fence = &pd->fence; struct ib_mr *ib_mr = &fence->mr->ib_mr; struct bnxt_qplib_swqe *wqe = &fence->bind_wqe; + struct bnxt_re_dev *rdev = pd->rdev; + + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; memset(wqe, 0, sizeof(*wqe)); wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW; @@ -454,6 +458,9 @@ static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd) struct device *dev = &rdev->en_dev->pdev->dev; struct bnxt_re_mr *mr = fence->mr; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; + if (fence->mw) { bnxt_re_dealloc_mw(fence->mw); fence->mw = NULL; @@ -485,6 +492,9 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) struct ib_mw *mw; int rc; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return 0; + dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES, DMA_BIDIRECTIONAL); rc = dma_mapping_error(dev, dma_addr); @@ -1023,7 +1033,7 @@ static int bnxt_re_init_user_qp(struct bnxt_re_dev *rdev, struct bnxt_re_pd *pd, bytes = (qplib_qp->sq.max_wqe * qplib_qp->sq.wqe_size); /* Consider mapping PSN search memory only for RC QPs. */ if (qplib_qp->type == CMDQ_CREATE_QP_TYPE_RC) { - psn_sz = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? + psn_sz = bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ? sizeof(struct sq_psn_search_ext) : sizeof(struct sq_psn_search); psn_nume = (qplib_qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) ? @@ -1234,7 +1244,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp) qplqp = &qp->qplib_qp; dev_attr = &rdev->dev_attr; - if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) { + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { qplqp->rq.max_sge = dev_attr->max_qp_sges; if (qplqp->rq.max_sge > dev_attr->max_qp_sges) qplqp->rq.max_sge = dev_attr->max_qp_sges; @@ -1301,7 +1311,7 @@ static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp, qplqp = &qp->qplib_qp; dev_attr = &rdev->dev_attr; - if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) { + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { entries = bnxt_re_init_depth(init_attr->cap.max_send_wr + 1, uctx); qplqp->sq.max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + 1); @@ -1328,7 +1338,7 @@ static int bnxt_re_init_qp_type(struct bnxt_re_dev *rdev, goto out; } - if (bnxt_qplib_is_chip_gen_p5(chip_ctx) && + if (bnxt_qplib_is_chip_gen_p5_p7(chip_ctx) && init_attr->qp_type == IB_QPT_GSI) qptype = CMDQ_CREATE_QP_TYPE_GSI; out: @@ -1527,7 +1537,7 @@ int bnxt_re_create_qp(struct ib_qp *ib_qp, struct ib_qp_init_attr *qp_init_attr, goto fail; if (qp_init_attr->qp_type == IB_QPT_GSI && - !(bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx))) { + !(bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))) { rc = bnxt_re_create_gsi_qp(qp, pd, qp_init_attr); if (rc == -ENODEV) goto qp_destroy; @@ -2553,11 +2563,6 @@ static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; - /* Need unconditional fence for local invalidate - * opcode to work as expected. - */ - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; if (wr->send_flags & IB_SEND_SOLICITED) @@ -2580,12 +2585,6 @@ static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - /* Need unconditional fence for reg_mr - * opcode to function as expected. - */ - - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; @@ -2716,6 +2715,18 @@ bad: return rc; } +static void bnxt_re_legacy_set_uc_fence(struct bnxt_qplib_swqe *wqe) +{ + /* Need unconditional fence for non-wire memory opcode + * to work as expected. + */ + if (wqe->type == BNXT_QPLIB_SWQE_TYPE_LOCAL_INV || + wqe->type == BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_BIND_MW) + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; +} + int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { @@ -2795,8 +2806,11 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, rc = -EINVAL; goto bad; } - if (!rc) + if (!rc) { + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_re_legacy_set_uc_fence(&wqe); rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe); + } bad: if (rc) { ibdev_err(&qp->rdev->ibdev, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 039801d93ed8..0373d0e9db63 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -107,9 +107,14 @@ static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev) dev_info(rdev_to_dev(rdev), "Couldn't get DB bar size, Low latency framework is disabled\n"); /* set register offsets for both UC and WC */ - res->dpi_tbl.ucreg.offset = res->is_vf ? BNXT_QPLIB_DBR_VF_DB_OFFSET : - BNXT_QPLIB_DBR_PF_DB_OFFSET; - res->dpi_tbl.wcreg.offset = res->dpi_tbl.ucreg.offset; + if (bnxt_qplib_is_chip_gen_p7(cctx)) { + res->dpi_tbl.ucreg.offset = offset; + res->dpi_tbl.wcreg.offset = en_dev->l2_db_size; + } else { + res->dpi_tbl.ucreg.offset = res->is_vf ? BNXT_QPLIB_DBR_VF_DB_OFFSET : + BNXT_QPLIB_DBR_PF_DB_OFFSET; + res->dpi_tbl.wcreg.offset = res->dpi_tbl.ucreg.offset; + } /* If WC mapping is disabled by L2 driver then en_dev->l2_db_size * is equal to the DB-Bar actual size. This indicates that L2 @@ -128,7 +133,7 @@ static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode) struct bnxt_qplib_chip_ctx *cctx; cctx = rdev->chip_ctx; - cctx->modes.wqe_mode = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? + cctx->modes.wqe_mode = bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ? mode : BNXT_QPLIB_WQE_MODE_STATIC; if (bnxt_re_hwrm_qcaps(rdev)) dev_err(rdev_to_dev(rdev), @@ -176,8 +181,11 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) bnxt_re_set_db_offset(rdev); rc = bnxt_qplib_map_db_bar(&rdev->qplib_res); - if (rc) + if (rc) { + kfree(rdev->chip_ctx); + rdev->chip_ctx = NULL; return rc; + } if (bnxt_qplib_determine_atomics(en_dev->pdev)) ibdev_info(&rdev->ibdev, @@ -215,7 +223,7 @@ static void bnxt_re_limit_pf_res(struct bnxt_re_dev *rdev) ctx->srqc_count = min_t(u32, BNXT_RE_MAX_SRQC_COUNT, attr->max_srq); ctx->cq_count = min_t(u32, BNXT_RE_MAX_CQ_COUNT, attr->max_cq); - if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) for (i = 0; i < MAX_TQM_ALLOC_REQ; i++) rdev->qplib_ctx.tqm_ctx.qcount[i] = rdev->dev_attr.tqm_alloc_reqs[i]; @@ -264,7 +272,7 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev) memset(&rdev->qplib_ctx.vf_res, 0, sizeof(struct bnxt_qplib_vf_res)); bnxt_re_limit_pf_res(rdev); - num_vfs = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? + num_vfs = bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx) ? BNXT_RE_GEN_P5_MAX_VF : rdev->num_vfs; if (num_vfs) bnxt_re_limit_vf_res(&rdev->qplib_ctx, num_vfs); @@ -276,7 +284,7 @@ static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags)) return; rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev); - if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) { + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { bnxt_re_set_resource_limits(rdev); bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw, &rdev->qplib_ctx); @@ -1067,16 +1075,6 @@ static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq, return 0; } -#define BNXT_RE_GEN_P5_PF_NQ_DB 0x10000 -#define BNXT_RE_GEN_P5_VF_NQ_DB 0x4000 -static u32 bnxt_re_get_nqdb_offset(struct bnxt_re_dev *rdev, u16 indx) -{ - return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? - (rdev->is_virtfn ? BNXT_RE_GEN_P5_VF_NQ_DB : - BNXT_RE_GEN_P5_PF_NQ_DB) : - rdev->en_dev->msix_entries[indx].db_offset; -} - static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev) { int i; @@ -1097,7 +1095,7 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev) bnxt_qplib_init_res(&rdev->qplib_res); for (i = 1; i < rdev->num_msix ; i++) { - db_offt = bnxt_re_get_nqdb_offset(rdev, i); + db_offt = rdev->en_dev->msix_entries[i].db_offset; rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1], i - 1, rdev->en_dev->msix_entries[i].vector, db_offt, &bnxt_re_cqn_handler, @@ -1508,7 +1506,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) ibdev_err(&rdev->ibdev, "Failed to allocate CREQ: %#x\n", rc); goto free_rcfw; } - db_offt = bnxt_re_get_nqdb_offset(rdev, BNXT_RE_AEQ_IDX); + db_offt = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].db_offset; vid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].vector; rc = bnxt_qplib_enable_rcfw_channel(&rdev->rcfw, vid, db_offt, @@ -1536,7 +1534,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) bnxt_re_set_resource_limits(rdev); rc = bnxt_qplib_alloc_ctx(&rdev->qplib_res, &rdev->qplib_ctx, 0, - bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)); + bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate QPLIB context: %#x\n", rc); @@ -1659,7 +1657,7 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) return; /* Currently enabling only for GenP5 adapters */ - if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) + if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) return; if (enable) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 3b28878f6206..4ee11cb4f2bd 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -995,7 +995,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) /* SQ */ if (qp->type == CMDQ_CREATE_QP_TYPE_RC) { - psn_sz = bnxt_qplib_is_chip_gen_p5(res->cctx) ? + psn_sz = bnxt_qplib_is_chip_gen_p5_p7(res->cctx) ? sizeof(struct sq_psn_search_ext) : sizeof(struct sq_psn_search); @@ -1649,7 +1649,7 @@ static void bnxt_qplib_fill_psn_search(struct bnxt_qplib_qp *qp, flg_npsn = ((swq->next_psn << SQ_PSN_SEARCH_NEXT_PSN_SFT) & SQ_PSN_SEARCH_NEXT_PSN_MASK); - if (bnxt_qplib_is_chip_gen_p5(qp->cctx)) { + if (bnxt_qplib_is_chip_gen_p5_p7(qp->cctx)) { psns_ext->opcode_start_psn = cpu_to_le32(op_spsn); psns_ext->flags_next_psn = cpu_to_le32(flg_npsn); psns_ext->start_slot_idx = cpu_to_le16(swq->slot_idx); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index a6f38d8f12ef..56ddff96b508 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -169,7 +169,7 @@ struct bnxt_qplib_swqe { }; u32 q_key; u32 dst_qp; - u16 avid; + u32 avid; } send; /* Send Raw Ethernet and QP1 */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 5680fe8b890a..7294221b3316 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -525,7 +525,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, /* failed with status */ dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x status %#x\n", cookie, opcode, evnt->status); - rc = -EFAULT; + rc = -EIO; } return rc; @@ -852,7 +852,7 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, */ if (is_virtfn) goto skip_ctx_setup; - if (bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx)) + if (bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) goto config_vf_res; lvl = ctx->qpc_tbl.level; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index ae2bde34e785..96ceec1e8199 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -244,6 +244,8 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, sginfo.pgsize = npde * pg_size; sginfo.npages = 1; rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], &sginfo); + if (rc) + goto fail; /* Alloc PBL pages */ sginfo.npages = npbl; @@ -255,22 +257,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, dst_virt_ptr = (dma_addr_t **)hwq->pbl[PBL_LVL_0].pg_arr; src_phys_ptr = hwq->pbl[PBL_LVL_1].pg_map_arr; - if (hwq_attr->type == HWQ_TYPE_MR) { - /* For MR it is expected that we supply only 1 contigous - * page i.e only 1 entry in the PDL that will contain - * all the PBLs for the user supplied memory region - */ - for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count; - i++) - dst_virt_ptr[0][i] = src_phys_ptr[i] | - flag; - } else { - for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count; - i++) - dst_virt_ptr[PTR_PG(i)][PTR_IDX(i)] = - src_phys_ptr[i] | - PTU_PDE_VALID; - } + for (i = 0; i < hwq->pbl[PBL_LVL_1].pg_count; i++) + dst_virt_ptr[0][i] = src_phys_ptr[i] | flag; + /* Alloc or init PTEs */ rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_2], hwq_attr->sginfo); @@ -805,7 +794,7 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res, dpit = &res->dpi_tbl; reg = &dpit->wcreg; - if (!bnxt_qplib_is_chip_gen_p5(res->cctx)) { + if (!bnxt_qplib_is_chip_gen_p5_p7(res->cctx)) { /* Offest should come from L2 driver */ dbr_offset = dev_attr->l2_db_size; dpit->ucreg.offset = dbr_offset; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 534db462216a..f9e7aa3757cf 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -44,6 +44,9 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero; #define CHIP_NUM_57508 0x1750 #define CHIP_NUM_57504 0x1751 #define CHIP_NUM_57502 0x1752 +#define CHIP_NUM_58818 0xd818 +#define CHIP_NUM_57608 0x1760 + struct bnxt_qplib_drv_modes { u8 wqe_mode; @@ -296,6 +299,12 @@ struct bnxt_qplib_res { struct bnxt_qplib_db_pacing_data *pacing_data; }; +static inline bool bnxt_qplib_is_chip_gen_p7(struct bnxt_qplib_chip_ctx *cctx) +{ + return (cctx->chip_num == CHIP_NUM_58818 || + cctx->chip_num == CHIP_NUM_57608); +} + static inline bool bnxt_qplib_is_chip_gen_p5(struct bnxt_qplib_chip_ctx *cctx) { return (cctx->chip_num == CHIP_NUM_57508 || @@ -303,15 +312,20 @@ static inline bool bnxt_qplib_is_chip_gen_p5(struct bnxt_qplib_chip_ctx *cctx) cctx->chip_num == CHIP_NUM_57502); } +static inline bool bnxt_qplib_is_chip_gen_p5_p7(struct bnxt_qplib_chip_ctx *cctx) +{ + return bnxt_qplib_is_chip_gen_p5(cctx) || bnxt_qplib_is_chip_gen_p7(cctx); +} + static inline u8 bnxt_qplib_get_hwq_type(struct bnxt_qplib_res *res) { - return bnxt_qplib_is_chip_gen_p5(res->cctx) ? + return bnxt_qplib_is_chip_gen_p5_p7(res->cctx) ? HWQ_TYPE_QUEUE : HWQ_TYPE_L2_CMPL; } static inline u8 bnxt_qplib_get_ring_type(struct bnxt_qplib_chip_ctx *cctx) { - return bnxt_qplib_is_chip_gen_p5(cctx) ? + return bnxt_qplib_is_chip_gen_p5_p7(cctx) ? RING_ALLOC_REQ_RING_TYPE_NQ : RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL; } @@ -488,7 +502,7 @@ static inline void bnxt_qplib_ring_nq_db(struct bnxt_qplib_db_info *info, u32 type; type = arm ? DBC_DBC_TYPE_NQ_ARM : DBC_DBC_TYPE_NQ; - if (bnxt_qplib_is_chip_gen_p5(cctx)) + if (bnxt_qplib_is_chip_gen_p5_p7(cctx)) bnxt_qplib_ring_db(info, type); else bnxt_qplib_ring_db32(info, arm); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index a27b68515164..0b98577cd708 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -59,7 +59,7 @@ static bool bnxt_qplib_is_atomic_cap(struct bnxt_qplib_rcfw *rcfw) { u16 pcie_ctl2 = 0; - if (!bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx)) + if (!bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) return false; pcie_capability_read_word(rcfw->pdev, PCI_EXP_DEVCTL2, &pcie_ctl2); @@ -133,10 +133,12 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, * reporting the max number */ attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; - attr->max_qp_sges = bnxt_qplib_is_chip_gen_p5(rcfw->res->cctx) ? + attr->max_qp_sges = bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx) ? 6 : sb->max_sge; attr->max_cq = le32_to_cpu(sb->max_cq); attr->max_cq_wqes = le32_to_cpu(sb->max_cqe); + if (!bnxt_qplib_is_chip_gen_p7(rcfw->res->cctx)) + attr->max_cq_wqes = min_t(u32, BNXT_QPLIB_MAX_CQ_WQES, attr->max_cq_wqes); attr->max_cq_sges = attr->max_qp_sges; attr->max_mr = le32_to_cpu(sb->max_mr); attr->max_mw = le32_to_cpu(sb->max_mw); @@ -151,9 +153,17 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_srq_sges = sb->max_srq_sge; attr->max_pkey = 1; attr->max_inline_data = le32_to_cpu(sb->max_inline_data); - attr->l2_db_size = (sb->l2_db_space_size + 1) * - (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); - attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED; + if (!bnxt_qplib_is_chip_gen_p7(rcfw->res->cctx)) + attr->l2_db_size = (sb->l2_db_space_size + 1) * + (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); + /* + * Read the max gid supported by HW. + * For each entry in HW GID in HW table, we consume 2 + * GID entries in the kernel GID table. So max_gid reported + * to stack can be up to twice the value reported by the HW, up to 256 gids. + */ + attr->max_sgid = le32_to_cpu(sb->max_gid); + attr->max_sgid = min_t(u32, BNXT_QPLIB_NUM_GIDS_SUPPORTED, 2 * attr->max_sgid); attr->dev_cap_flags = le16_to_cpu(sb->dev_cap_flags); bnxt_qplib_query_version(rcfw, attr->fw_ver); @@ -934,7 +944,7 @@ int bnxt_qplib_modify_cc(struct bnxt_qplib_res *res, req->inactivity_th = cpu_to_le16(cc_param->inact_th); /* For chip gen P5 onwards fill extended cmd and header */ - if (bnxt_qplib_is_chip_gen_p5(res->cctx)) { + if (bnxt_qplib_is_chip_gen_p5_p7(res->cctx)) { struct roce_tlv *hdr; u32 payload; u32 chunks; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index d33c78b96217..755765e68eaa 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -55,6 +55,7 @@ struct bnxt_qplib_dev_attr { u32 max_qp_wqes; u32 max_qp_sges; u32 max_cq; +#define BNXT_QPLIB_MAX_CQ_WQES 0xfffff u32 max_cq_wqes; u32 max_cq_sges; u32 max_mr; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index b3757c6a0457..8d753e6e0c71 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2086,7 +2086,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip, err = -ENOMEM; if (n->dev->flags & IFF_LOOPBACK) { if (iptype == 4) - pdev = ip_dev_find(&init_net, *(__be32 *)peer_ip); + pdev = __ip_dev_find(&init_net, *(__be32 *)peer_ip, false); else if (IS_ENABLED(CONFIG_IPV6)) for_each_netdev(&init_net, pdev) { if (ipv6_chk_addr(&init_net, @@ -2101,12 +2101,12 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip, err = -ENODEV; goto out; } + if (is_vlan_dev(pdev)) + pdev = vlan_dev_real_dev(pdev); ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t, n, pdev, rt_tos2priority(tos)); - if (!ep->l2t) { - dev_put(pdev); + if (!ep->l2t) goto out; - } ep->mtu = pdev->mtu; ep->tx_chan = cxgb4_port_chan(pdev); ep->smac_idx = ((struct port_info *)netdev_priv(pdev))->smt_idx; @@ -2119,7 +2119,6 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip, ep->rss_qid = cdev->rdev.lldi.rxq_ids[ cxgb4_port_idx(pdev) * step]; set_tcp_window(ep, (struct port_info *)netdev_priv(pdev)); - dev_put(pdev); } else { pdev = get_real_dev(n->dev); ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t, diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 42d1e9771066..1916daa8c332 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3630,7 +3630,7 @@ void irdma_free_lsmm_rsrc(struct irdma_qp *iwqp) /** * irdma_accept - registered call for connection to be accepted * @cm_id: cm information for passive connection - * @conn_param: accpet parameters + * @conn_param: accept parameters */ int irdma_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) { diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 45547bf281e3..4bebc34a2929 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -68,6 +68,8 @@ MODULE_LICENSE("Dual BSD/GPL"); static u64 srpt_service_guid; static DEFINE_SPINLOCK(srpt_dev_lock); /* Protects srpt_dev_list. */ static LIST_HEAD(srpt_dev_list); /* List of srpt_device structures. */ +static DEFINE_MUTEX(srpt_mc_mutex); /* Protects srpt_memory_caches. */ +static DEFINE_XARRAY(srpt_memory_caches); /* See also srpt_memory_cache_entry */ static unsigned srp_max_req_size = DEFAULT_MAX_REQ_SIZE; module_param(srp_max_req_size, int, 0444); @@ -105,6 +107,63 @@ static void srpt_recv_done(struct ib_cq *cq, struct ib_wc *wc); static void srpt_send_done(struct ib_cq *cq, struct ib_wc *wc); static void srpt_process_wait_list(struct srpt_rdma_ch *ch); +/* Type of the entries in srpt_memory_caches. */ +struct srpt_memory_cache_entry { + refcount_t ref; + struct kmem_cache *c; +}; + +static struct kmem_cache *srpt_cache_get(unsigned int object_size) +{ + struct srpt_memory_cache_entry *e; + char name[32]; + void *res; + + guard(mutex)(&srpt_mc_mutex); + e = xa_load(&srpt_memory_caches, object_size); + if (e) { + refcount_inc(&e->ref); + return e->c; + } + snprintf(name, sizeof(name), "srpt-%u", object_size); + e = kmalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return NULL; + refcount_set(&e->ref, 1); + e->c = kmem_cache_create(name, object_size, /*align=*/512, 0, NULL); + if (!e->c) + goto free_entry; + res = xa_store(&srpt_memory_caches, object_size, e, GFP_KERNEL); + if (xa_is_err(res)) + goto destroy_cache; + return e->c; + +destroy_cache: + kmem_cache_destroy(e->c); + +free_entry: + kfree(e); + return NULL; +} + +static void srpt_cache_put(struct kmem_cache *c) +{ + struct srpt_memory_cache_entry *e = NULL; + unsigned long object_size; + + guard(mutex)(&srpt_mc_mutex); + xa_for_each(&srpt_memory_caches, object_size, e) + if (e->c == c) + break; + if (WARN_ON_ONCE(!e)) + return; + if (!refcount_dec_and_test(&e->ref)) + return; + WARN_ON_ONCE(xa_erase(&srpt_memory_caches, object_size) != e); + kmem_cache_destroy(e->c); + kfree(e); +} + /* * The only allowed channel state changes are those that change the channel * state into a state with a higher numerical value. Hence the new > prev test. @@ -2119,13 +2178,13 @@ static void srpt_release_channel_work(struct work_struct *w) ch->sport->sdev, ch->rq_size, ch->rsp_buf_cache, DMA_TO_DEVICE); - kmem_cache_destroy(ch->rsp_buf_cache); + srpt_cache_put(ch->rsp_buf_cache); srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring, sdev, ch->rq_size, ch->req_buf_cache, DMA_FROM_DEVICE); - kmem_cache_destroy(ch->req_buf_cache); + srpt_cache_put(ch->req_buf_cache); kref_put(&ch->kref, srpt_free_ch); } @@ -2245,8 +2304,7 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev, INIT_LIST_HEAD(&ch->cmd_wait_list); ch->max_rsp_size = ch->sport->port_attrib.srp_max_rsp_size; - ch->rsp_buf_cache = kmem_cache_create("srpt-rsp-buf", ch->max_rsp_size, - 512, 0, NULL); + ch->rsp_buf_cache = srpt_cache_get(ch->max_rsp_size); if (!ch->rsp_buf_cache) goto free_ch; @@ -2280,8 +2338,7 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev, alignment_offset = round_up(imm_data_offset, 512) - imm_data_offset; req_sz = alignment_offset + imm_data_offset + srp_max_req_size; - ch->req_buf_cache = kmem_cache_create("srpt-req-buf", req_sz, - 512, 0, NULL); + ch->req_buf_cache = srpt_cache_get(req_sz); if (!ch->req_buf_cache) goto free_rsp_ring; @@ -2478,7 +2535,7 @@ free_recv_ring: ch->req_buf_cache, DMA_FROM_DEVICE); free_recv_cache: - kmem_cache_destroy(ch->req_buf_cache); + srpt_cache_put(ch->req_buf_cache); free_rsp_ring: srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring, @@ -2486,7 +2543,7 @@ free_rsp_ring: ch->rsp_buf_cache, DMA_TO_DEVICE); free_rsp_cache: - kmem_cache_destroy(ch->rsp_buf_cache); + srpt_cache_put(ch->rsp_buf_cache); free_ch: if (rdma_cm_id) @@ -3055,7 +3112,7 @@ static void srpt_free_srq(struct srpt_device *sdev) srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev, sdev->srq_size, sdev->req_buf_cache, DMA_FROM_DEVICE); - kmem_cache_destroy(sdev->req_buf_cache); + srpt_cache_put(sdev->req_buf_cache); sdev->srq = NULL; } @@ -3082,8 +3139,7 @@ static int srpt_alloc_srq(struct srpt_device *sdev) pr_debug("create SRQ #wr= %d max_allow=%d dev= %s\n", sdev->srq_size, sdev->device->attrs.max_srq_wr, dev_name(&device->dev)); - sdev->req_buf_cache = kmem_cache_create("srpt-srq-req-buf", - srp_max_req_size, 0, 0, NULL); + sdev->req_buf_cache = srpt_cache_get(srp_max_req_size); if (!sdev->req_buf_cache) goto free_srq; @@ -3105,7 +3161,7 @@ static int srpt_alloc_srq(struct srpt_device *sdev) return 0; free_cache: - kmem_cache_destroy(sdev->req_buf_cache); + srpt_cache_put(sdev->req_buf_cache); free_srq: ib_destroy_srq(srq); diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index ea4b921e5e15..5a7836186fd4 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -8,6 +8,7 @@ */ #include <linux/bitfield.h> +#include <linux/cleanup.h> #include <linux/clk.h> #include <linux/err.h> #include <linux/io.h> @@ -18,6 +19,7 @@ #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/spinlock.h> +#include <linux/syscore_ops.h> #define IRQC_IRQ_START 1 #define IRQC_IRQ_COUNT 8 @@ -55,12 +57,30 @@ #define TINT_EXTRACT_HWIRQ(x) FIELD_GET(GENMASK(15, 0), (x)) #define TINT_EXTRACT_GPIOINT(x) FIELD_GET(GENMASK(31, 16), (x)) -struct rzg2l_irqc_priv { - void __iomem *base; - struct irq_fwspec fwspec[IRQC_NUM_IRQ]; - raw_spinlock_t lock; +/** + * struct rzg2l_irqc_reg_cache - registers cache (necessary for suspend/resume) + * @iitsr: IITSR register + * @titsr: TITSR registers + */ +struct rzg2l_irqc_reg_cache { + u32 iitsr; + u32 titsr[2]; }; +/** + * struct rzg2l_irqc_priv - IRQ controller private data structure + * @base: Controller's base address + * @fwspec: IRQ firmware specific data + * @lock: Lock to serialize access to hardware registers + * @cache: Registers cache for suspend/resume + */ +static struct rzg2l_irqc_priv { + void __iomem *base; + struct irq_fwspec fwspec[IRQC_NUM_IRQ]; + raw_spinlock_t lock; + struct rzg2l_irqc_reg_cache cache; +} *rzg2l_irqc_data; + static struct rzg2l_irqc_priv *irq_data_to_priv(struct irq_data *data) { return data->domain->host_data; @@ -276,6 +296,38 @@ static int rzg2l_irqc_set_type(struct irq_data *d, unsigned int type) return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH); } +static int rzg2l_irqc_irq_suspend(void) +{ + struct rzg2l_irqc_reg_cache *cache = &rzg2l_irqc_data->cache; + void __iomem *base = rzg2l_irqc_data->base; + + cache->iitsr = readl_relaxed(base + IITSR); + for (u8 i = 0; i < 2; i++) + cache->titsr[i] = readl_relaxed(base + TITSR(i)); + + return 0; +} + +static void rzg2l_irqc_irq_resume(void) +{ + struct rzg2l_irqc_reg_cache *cache = &rzg2l_irqc_data->cache; + void __iomem *base = rzg2l_irqc_data->base; + + /* + * Restore only interrupt type. TSSRx will be restored at the + * request of pin controller to avoid spurious interrupts due + * to invalid PIN states. + */ + for (u8 i = 0; i < 2; i++) + writel_relaxed(cache->titsr[i], base + TITSR(i)); + writel_relaxed(cache->iitsr, base + IITSR); +} + +static struct syscore_ops rzg2l_irqc_syscore_ops = { + .suspend = rzg2l_irqc_irq_suspend, + .resume = rzg2l_irqc_irq_resume, +}; + static const struct irq_chip irqc_chip = { .name = "rzg2l-irqc", .irq_eoi = rzg2l_irqc_eoi, @@ -357,13 +409,12 @@ static int rzg2l_irqc_parse_interrupts(struct rzg2l_irqc_priv *priv, static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent) { + struct platform_device *pdev = of_find_device_by_node(node); + struct device *dev __free(put_device) = pdev ? &pdev->dev : NULL; struct irq_domain *irq_domain, *parent_domain; - struct platform_device *pdev; struct reset_control *resetn; - struct rzg2l_irqc_priv *priv; int ret; - pdev = of_find_device_by_node(node); if (!pdev) return -ENODEV; @@ -373,15 +424,15 @@ static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent) return -ENODEV; } - priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) + rzg2l_irqc_data = devm_kzalloc(&pdev->dev, sizeof(*rzg2l_irqc_data), GFP_KERNEL); + if (!rzg2l_irqc_data) return -ENOMEM; - priv->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + rzg2l_irqc_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL); + if (IS_ERR(rzg2l_irqc_data->base)) + return PTR_ERR(rzg2l_irqc_data->base); - ret = rzg2l_irqc_parse_interrupts(priv, node); + ret = rzg2l_irqc_parse_interrupts(rzg2l_irqc_data, node); if (ret) { dev_err(&pdev->dev, "cannot parse interrupts: %d\n", ret); return ret; @@ -404,17 +455,30 @@ static int rzg2l_irqc_init(struct device_node *node, struct device_node *parent) goto pm_disable; } - raw_spin_lock_init(&priv->lock); + raw_spin_lock_init(&rzg2l_irqc_data->lock); irq_domain = irq_domain_add_hierarchy(parent_domain, 0, IRQC_NUM_IRQ, node, &rzg2l_irqc_domain_ops, - priv); + rzg2l_irqc_data); if (!irq_domain) { dev_err(&pdev->dev, "failed to add irq domain\n"); ret = -ENOMEM; goto pm_put; } + register_syscore_ops(&rzg2l_irqc_syscore_ops); + + /* + * Prevent the cleanup function from invoking put_device by assigning + * NULL to dev. + * + * make coccicheck will complain about missing put_device calls, but + * those are false positives, as dev will be automatically "put" via + * __free_put_device on the failing path. + * On the successful path we don't actually want to "put" dev. + */ + dev = NULL; + return 0; pm_put: diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 3877744193e2..062bcbe6255c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -6208,7 +6208,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .invalid_port_mask = BIT(1) | BIT(2) | BIT(8), .num_internal_phys = 5, .internal_phys_offset = 3, - .max_vid = 4095, + .max_vid = 8191, .max_sid = 63, .port_base_addr = 0x0, .phy_base_addr = 0x0, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index f48a3c0ac7f9..f02518e93b60 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -206,6 +206,7 @@ struct mv88e6xxx_gpio_ops; struct mv88e6xxx_avb_ops; struct mv88e6xxx_ptp_ops; struct mv88e6xxx_pcs_ops; +struct mv88e6xxx_cc_coeffs; struct mv88e6xxx_irq { u16 masked; @@ -397,6 +398,7 @@ struct mv88e6xxx_chip { struct cyclecounter tstamp_cc; struct timecounter tstamp_tc; struct delayed_work overflow_work; + const struct mv88e6xxx_cc_coeffs *cc_coeffs; struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_info; @@ -719,10 +721,6 @@ struct mv88e6xxx_ptp_ops { int arr1_sts_reg; int dep_sts_reg; u32 rx_filters; - u32 cc_shift; - u32 cc_mult; - u32 cc_mult_num; - u32 cc_mult_dem; }; struct mv88e6xxx_pcs_ops { diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 5394a8cf7bf1..04053fdc6489 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1713,6 +1713,7 @@ int mv88e6393x_port_set_policy(struct mv88e6xxx_chip *chip, int port, ptr = shift / 8; shift %= 8; mask >>= ptr * 8; + ptr <<= 8; err = mv88e6393x_port_policy_read(chip, port, ptr, ®); if (err) diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index ea17231dc34e..5980bb4ce43e 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -18,6 +18,13 @@ #define MV88E6XXX_MAX_ADJ_PPB 1000000 +struct mv88e6xxx_cc_coeffs { + u32 cc_shift; + u32 cc_mult; + u32 cc_mult_num; + u32 cc_mult_dem; +}; + /* Family MV88E6250: * Raw timestamps are in units of 10-ns clock periods. * @@ -25,22 +32,43 @@ * simplifies to * clkadj = scaled_ppm * 2^7 / 5^5 */ -#define MV88E6250_CC_SHIFT 28 -#define MV88E6250_CC_MULT (10 << MV88E6250_CC_SHIFT) -#define MV88E6250_CC_MULT_NUM (1 << 7) -#define MV88E6250_CC_MULT_DEM 3125ULL +#define MV88E6XXX_CC_10NS_SHIFT 28 +static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_10ns_coeffs = { + .cc_shift = MV88E6XXX_CC_10NS_SHIFT, + .cc_mult = 10 << MV88E6XXX_CC_10NS_SHIFT, + .cc_mult_num = 1 << 7, + .cc_mult_dem = 3125ULL, +}; -/* Other families: +/* Other families except MV88E6393X in internal clock mode: * Raw timestamps are in units of 8-ns clock periods. * * clkadj = scaled_ppm * 8*2^28 / (10^6 * 2^16) * simplifies to * clkadj = scaled_ppm * 2^9 / 5^6 */ -#define MV88E6XXX_CC_SHIFT 28 -#define MV88E6XXX_CC_MULT (8 << MV88E6XXX_CC_SHIFT) -#define MV88E6XXX_CC_MULT_NUM (1 << 9) -#define MV88E6XXX_CC_MULT_DEM 15625ULL +#define MV88E6XXX_CC_8NS_SHIFT 28 +static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_8ns_coeffs = { + .cc_shift = MV88E6XXX_CC_8NS_SHIFT, + .cc_mult = 8 << MV88E6XXX_CC_8NS_SHIFT, + .cc_mult_num = 1 << 9, + .cc_mult_dem = 15625ULL +}; + +/* Family MV88E6393X using internal clock: + * Raw timestamps are in units of 4-ns clock periods. + * + * clkadj = scaled_ppm * 4*2^28 / (10^6 * 2^16) + * simplifies to + * clkadj = scaled_ppm * 2^8 / 5^6 + */ +#define MV88E6XXX_CC_4NS_SHIFT 28 +static const struct mv88e6xxx_cc_coeffs mv88e6xxx_cc_4ns_coeffs = { + .cc_shift = MV88E6XXX_CC_4NS_SHIFT, + .cc_mult = 4 << MV88E6XXX_CC_4NS_SHIFT, + .cc_mult_num = 1 << 8, + .cc_mult_dem = 15625ULL +}; #define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100) @@ -83,6 +111,33 @@ static int mv88e6352_set_gpio_func(struct mv88e6xxx_chip *chip, int pin, return chip->info->ops->gpio_ops->set_pctl(chip, pin, func); } +static const struct mv88e6xxx_cc_coeffs * +mv88e6xxx_cc_coeff_get(struct mv88e6xxx_chip *chip) +{ + u16 period_ps; + int err; + + err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_CLOCK_PERIOD, &period_ps, 1); + if (err) { + dev_err(chip->dev, "failed to read cycle counter period: %d\n", + err); + return ERR_PTR(err); + } + + switch (period_ps) { + case 4000: + return &mv88e6xxx_cc_4ns_coeffs; + case 8000: + return &mv88e6xxx_cc_8ns_coeffs; + case 10000: + return &mv88e6xxx_cc_10ns_coeffs; + default: + dev_err(chip->dev, "unexpected cycle counter period of %u ps\n", + period_ps); + return ERR_PTR(-ENODEV); + } +} + static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc) { struct mv88e6xxx_chip *chip = cc_to_chip(cc); @@ -200,7 +255,6 @@ out: static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); - const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops; int neg_adj = 0; u32 diff, mult; u64 adj; @@ -210,10 +264,10 @@ static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) scaled_ppm = -scaled_ppm; } - mult = ptp_ops->cc_mult; - adj = ptp_ops->cc_mult_num; + mult = chip->cc_coeffs->cc_mult; + adj = chip->cc_coeffs->cc_mult_num; adj *= scaled_ppm; - diff = div_u64(adj, ptp_ops->cc_mult_dem); + diff = div_u64(adj, chip->cc_coeffs->cc_mult_dem); mv88e6xxx_reg_lock(chip); @@ -360,10 +414,6 @@ const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = { (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), - .cc_shift = MV88E6XXX_CC_SHIFT, - .cc_mult = MV88E6XXX_CC_MULT, - .cc_mult_num = MV88E6XXX_CC_MULT_NUM, - .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, }; const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = { @@ -387,10 +437,6 @@ const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = { (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), - .cc_shift = MV88E6250_CC_SHIFT, - .cc_mult = MV88E6250_CC_MULT, - .cc_mult_num = MV88E6250_CC_MULT_NUM, - .cc_mult_dem = MV88E6250_CC_MULT_DEM, }; const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { @@ -414,10 +460,6 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), - .cc_shift = MV88E6XXX_CC_SHIFT, - .cc_mult = MV88E6XXX_CC_MULT, - .cc_mult_num = MV88E6XXX_CC_MULT_NUM, - .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, }; const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = { @@ -442,10 +484,6 @@ const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = { (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), - .cc_shift = MV88E6XXX_CC_SHIFT, - .cc_mult = MV88E6XXX_CC_MULT, - .cc_mult_num = MV88E6XXX_CC_MULT_NUM, - .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, }; static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) @@ -458,10 +496,10 @@ static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) return 0; } -/* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3 +/* With a 250MHz input clock, the 32-bit timestamp counter overflows in ~17.2 * seconds; this task forces periodic reads so that we don't miss any. */ -#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 16) +#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 8) static void mv88e6xxx_ptp_overflow_check(struct work_struct *work) { struct delayed_work *dw = to_delayed_work(work); @@ -480,11 +518,15 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) int i; /* Set up the cycle counter */ + chip->cc_coeffs = mv88e6xxx_cc_coeff_get(chip); + if (IS_ERR(chip->cc_coeffs)) + return PTR_ERR(chip->cc_coeffs); + memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc)); chip->tstamp_cc.read = mv88e6xxx_ptp_clock_read; chip->tstamp_cc.mask = CYCLECOUNTER_MASK(32); - chip->tstamp_cc.mult = ptp_ops->cc_mult; - chip->tstamp_cc.shift = ptp_ops->cc_shift; + chip->tstamp_cc.mult = chip->cc_coeffs->cc_mult; + chip->tstamp_cc.shift = chip->cc_coeffs->cc_shift; timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, ktime_to_ns(ktime_get_real())); diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 597a02c75d52..e624d31d20d8 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -484,7 +484,7 @@ greth_start_xmit_gbit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb->len > MAX_FRAME_SIZE)) { dev->stats.tx_errors++; - goto out; + goto len_error; } /* Save skb pointer. */ @@ -575,6 +575,7 @@ frag_map_error: map_error: if (net_ratelimit()) dev_warn(greth->dev, "Could not create TX DMA mapping\n"); +len_error: dev_kfree_skb(skb); out: return err; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 6bf149d64594..f0647286c68b 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -322,6 +322,7 @@ static netdev_tx_t bcmasp_xmit(struct sk_buff *skb, struct net_device *dev) } /* Rewind so we do not have a hole */ spb_index = intf->tx_spb_index; + dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index bf1611cce974..49e890a7e04a 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1359,6 +1359,7 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, netif_err(priv, tx_err, dev, "DMA map failed at %p (len=%d)\n", skb->data, skb_len); ret = NETDEV_TX_OK; + dev_kfree_skb_any(skb); goto out; } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index ad862ed7888a..9d425ece33fd 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1381,10 +1381,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) be_get_wrb_params_from_skb(adapter, skb, &wrb_params); wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params); - if (unlikely(!wrb_cnt)) { - dev_kfree_skb_any(skb); - goto drop; - } + if (unlikely(!wrb_cnt)) + goto drop_skb; /* if os2bmc is enabled and if the pkt is destined to bmc, * enqueue the pkt a 2nd time with mgmt bit set. @@ -1393,7 +1391,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) BE_WRB_F_SET(wrb_params.features, OS2BMC, 1); wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params); if (unlikely(!wrb_cnt)) - goto drop; + goto drop_skb; else skb_get(skb); } @@ -1407,6 +1405,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) be_xmit_flush(adapter, txo); return NETDEV_TX_OK; +drop_skb: + dev_kfree_skb_any(skb); drop: tx_stats(txo)->tx_drv_drops++; /* Flush the already enqueued tx requests */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 9767586b4eb3..11da139082e1 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -197,55 +197,67 @@ static int mac_probe(struct platform_device *_of_dev) err = -EINVAL; goto _return_of_node_put; } + mac_dev->fman_dev = &of_dev->dev; /* Get the FMan cell-index */ err = of_property_read_u32(dev_node, "cell-index", &val); if (err) { dev_err(dev, "failed to read cell-index for %pOF\n", dev_node); err = -EINVAL; - goto _return_of_node_put; + goto _return_dev_put; } /* cell-index 0 => FMan id 1 */ fman_id = (u8)(val + 1); - priv->fman = fman_bind(&of_dev->dev); + priv->fman = fman_bind(mac_dev->fman_dev); if (!priv->fman) { dev_err(dev, "fman_bind(%pOF) failed\n", dev_node); err = -ENODEV; - goto _return_of_node_put; + goto _return_dev_put; } + /* Two references have been taken in of_find_device_by_node() + * and fman_bind(). Release one of them here. The second one + * will be released in mac_remove(). + */ + put_device(mac_dev->fman_dev); of_node_put(dev_node); + dev_node = NULL; /* Get the address of the memory mapped registers */ mac_dev->res = platform_get_mem_or_io(_of_dev, 0); if (!mac_dev->res) { dev_err(dev, "could not get registers\n"); - return -EINVAL; + err = -EINVAL; + goto _return_dev_put; } err = devm_request_resource(dev, fman_get_mem_region(priv->fman), mac_dev->res); if (err) { dev_err_probe(dev, err, "could not request resource\n"); - return err; + goto _return_dev_put; } mac_dev->vaddr = devm_ioremap(dev, mac_dev->res->start, resource_size(mac_dev->res)); if (!mac_dev->vaddr) { dev_err(dev, "devm_ioremap() failed\n"); - return -EIO; + err = -EIO; + goto _return_dev_put; } - if (!of_device_is_available(mac_node)) - return -ENODEV; + if (!of_device_is_available(mac_node)) { + err = -ENODEV; + goto _return_dev_put; + } /* Get the cell-index */ err = of_property_read_u32(mac_node, "cell-index", &val); if (err) { dev_err(dev, "failed to read cell-index for %pOF\n", mac_node); - return -EINVAL; + err = -EINVAL; + goto _return_dev_put; } priv->cell_index = (u8)val; @@ -259,22 +271,26 @@ static int mac_probe(struct platform_device *_of_dev) if (unlikely(nph < 0)) { dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n", mac_node); - return nph; + err = nph; + goto _return_dev_put; } if (nph != ARRAY_SIZE(mac_dev->port)) { dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n", mac_node); - return -EINVAL; + err = -EINVAL; + goto _return_dev_put; } - for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { + /* PORT_NUM determines the size of the port array */ + for (i = 0; i < PORT_NUM; i++) { /* Find the port node */ dev_node = of_parse_phandle(mac_node, "fsl,fman-ports", i); if (!dev_node) { dev_err(dev, "of_parse_phandle(%pOF, fsl,fman-ports) failed\n", mac_node); - return -EINVAL; + err = -EINVAL; + goto _return_dev_arr_put; } of_dev = of_find_device_by_node(dev_node); @@ -282,17 +298,24 @@ static int mac_probe(struct platform_device *_of_dev) dev_err(dev, "of_find_device_by_node(%pOF) failed\n", dev_node); err = -EINVAL; - goto _return_of_node_put; + goto _return_dev_arr_put; } + mac_dev->fman_port_devs[i] = &of_dev->dev; - mac_dev->port[i] = fman_port_bind(&of_dev->dev); + mac_dev->port[i] = fman_port_bind(mac_dev->fman_port_devs[i]); if (!mac_dev->port[i]) { dev_err(dev, "dev_get_drvdata(%pOF) failed\n", dev_node); err = -EINVAL; - goto _return_of_node_put; + goto _return_dev_arr_put; } + /* Two references have been taken in of_find_device_by_node() + * and fman_port_bind(). Release one of them here. The second + * one will be released in mac_remove(). + */ + put_device(mac_dev->fman_port_devs[i]); of_node_put(dev_node); + dev_node = NULL; } /* Get the PHY connection type */ @@ -312,7 +335,7 @@ static int mac_probe(struct platform_device *_of_dev) err = init(mac_dev, mac_node, ¶ms); if (err < 0) - return err; + goto _return_dev_arr_put; if (!is_zero_ether_addr(mac_dev->addr)) dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr); @@ -327,6 +350,12 @@ static int mac_probe(struct platform_device *_of_dev) return err; +_return_dev_arr_put: + /* mac_dev is kzalloc'ed */ + for (i = 0; i < PORT_NUM; i++) + put_device(mac_dev->fman_port_devs[i]); +_return_dev_put: + put_device(mac_dev->fman_dev); _return_of_node_put: of_node_put(dev_node); return err; @@ -335,6 +364,11 @@ _return_of_node_put: static void mac_remove(struct platform_device *pdev) { struct mac_device *mac_dev = platform_get_drvdata(pdev); + int i; + + for (i = 0; i < PORT_NUM; i++) + put_device(mac_dev->fman_port_devs[i]); + put_device(mac_dev->fman_dev); platform_device_unregister(mac_dev->priv->eth_dev); } diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index fe747915cc73..8b5b43d50f8e 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -19,12 +19,13 @@ struct fman_mac; struct mac_priv_s; +#define PORT_NUM 2 struct mac_device { void __iomem *vaddr; struct device *dev; struct resource *res; u8 addr[ETH_ALEN]; - struct fman_port *port[2]; + struct fman_port *port[PORT_NUM]; struct phylink *phylink; struct phylink_config phylink_config; phy_interface_t phy_if; @@ -52,6 +53,9 @@ struct mac_device { struct fman_mac *fman_mac; struct mac_priv_s *priv; + + struct device *fman_dev; + struct device *fman_port_devs[PORT_NUM]; }; static inline struct mac_device diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index f2d4669c81cf..58a3d28d938c 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -1012,6 +1012,7 @@ sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev) if(skb->len > XMIT_BUFF_SIZE) { printk("%s: Sorry, max. framelength is %d bytes. The length of your frame is %d bytes.\n",dev->name,XMIT_BUFF_SIZE,skb->len); + dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index 3c43f8078528..c7f4e3c058b7 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -337,6 +337,51 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, } /** + * octep_oq_next_pkt() - Move to the next packet in Rx queue. + * + * @oq: Octeon Rx queue data structure. + * @buff_info: Current packet buffer info. + * @read_idx: Current packet index in the ring. + * @desc_used: Current packet descriptor number. + * + * Free the resources associated with a packet. + * Increment packet index in the ring and packet descriptor number. + */ +static void octep_oq_next_pkt(struct octep_oq *oq, + struct octep_rx_buffer *buff_info, + u32 *read_idx, u32 *desc_used) +{ + dma_unmap_page(oq->dev, oq->desc_ring[*read_idx].buffer_ptr, + PAGE_SIZE, DMA_FROM_DEVICE); + buff_info->page = NULL; + (*read_idx)++; + (*desc_used)++; + if (*read_idx == oq->max_count) + *read_idx = 0; +} + +/** + * octep_oq_drop_rx() - Free the resources associated with a packet. + * + * @oq: Octeon Rx queue data structure. + * @buff_info: Current packet buffer info. + * @read_idx: Current packet index in the ring. + * @desc_used: Current packet descriptor number. + * + */ +static void octep_oq_drop_rx(struct octep_oq *oq, + struct octep_rx_buffer *buff_info, + u32 *read_idx, u32 *desc_used) +{ + int data_len = buff_info->len - oq->max_single_buffer_size; + + while (data_len > 0) { + octep_oq_next_pkt(oq, buff_info, read_idx, desc_used); + data_len -= oq->buffer_size; + }; +} + +/** * __octep_oq_process_rx() - Process hardware Rx queue and push to stack. * * @oct: Octeon device private data structure. @@ -365,10 +410,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { buff_info = (struct octep_rx_buffer *)&oq->buff_info[read_idx]; - dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr, - PAGE_SIZE, DMA_FROM_DEVICE); resp_hw = page_address(buff_info->page); - buff_info->page = NULL; /* Swap the length field that is in Big-Endian to CPU */ buff_info->len = be64_to_cpu(resp_hw->length); @@ -390,36 +432,33 @@ static int __octep_oq_process_rx(struct octep_device *oct, */ data_offset = OCTEP_OQ_RESP_HW_SIZE; } + + octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used); + + skb = build_skb((void *)resp_hw, PAGE_SIZE); + if (!skb) { + octep_oq_drop_rx(oq, buff_info, + &read_idx, &desc_used); + oq->stats.alloc_failures++; + continue; + } + skb_reserve(skb, data_offset); + rx_bytes += buff_info->len; if (buff_info->len <= oq->max_single_buffer_size) { - skb = build_skb((void *)resp_hw, PAGE_SIZE); - skb_reserve(skb, data_offset); skb_put(skb, buff_info->len); - read_idx++; - desc_used++; - if (read_idx == oq->max_count) - read_idx = 0; } else { struct skb_shared_info *shinfo; u16 data_len; - skb = build_skb((void *)resp_hw, PAGE_SIZE); - skb_reserve(skb, data_offset); /* Head fragment includes response header(s); * subsequent fragments contains only data. */ skb_put(skb, oq->max_single_buffer_size); - read_idx++; - desc_used++; - if (read_idx == oq->max_count) - read_idx = 0; - shinfo = skb_shinfo(skb); data_len = buff_info->len - oq->max_single_buffer_size; while (data_len) { - dma_unmap_page(oq->dev, oq->desc_ring[read_idx].buffer_ptr, - PAGE_SIZE, DMA_FROM_DEVICE); buff_info = (struct octep_rx_buffer *) &oq->buff_info[read_idx]; if (data_len < oq->buffer_size) { @@ -434,11 +473,8 @@ static int __octep_oq_process_rx(struct octep_device *oct, buff_info->page, 0, buff_info->len, buff_info->len); - buff_info->page = NULL; - read_idx++; - desc_used++; - if (read_idx == oq->max_count) - read_idx = 0; + + octep_oq_next_pkt(oq, buff_info, &read_idx, &desc_used); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 224a025283ca..29487518ca67 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2298,7 +2298,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link)); if (!(cfg & BIT_ULL(12))) continue; - bmap |= (1 << i); + bmap |= BIT_ULL(i); cfg &= ~BIT_ULL(12); rvu_write64(rvu, blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg); @@ -2319,7 +2319,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, /* Set NIX_AF_TL3_TL2_LINKX_CFG[ENA] for the TL3/TL2 queue */ for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) { - if (!(bmap & (1 << i))) + if (!(bmap & BIT_ULL(i))) continue; cfg = rvu_read64(rvu, blkaddr, NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 48dc4ae87af0..80af0fc7101f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1758,6 +1758,10 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force } } +#define MLX5_MAX_MANAGE_PAGES_CMD_ENT 1 +#define MLX5_CMD_MASK ((1UL << (cmd->vars.max_reg_cmds + \ + MLX5_MAX_MANAGE_PAGES_CMD_ENT)) - 1) + static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) { struct mlx5_cmd *cmd = &dev->cmd; @@ -1769,7 +1773,7 @@ static void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); spin_lock_irqsave(&dev->cmd.alloc_lock, flags); - vector = ~dev->cmd.vars.bitmask & ((1ul << (1 << dev->cmd.vars.log_sz)) - 1); + vector = ~dev->cmd.vars.bitmask & MLX5_CMD_MASK; if (!vector) goto no_trig; @@ -2275,7 +2279,7 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev) cmd->state = MLX5_CMDIF_STATE_DOWN; cmd->vars.max_reg_cmds = (1 << cmd->vars.log_sz) - 1; - cmd->vars.bitmask = (1UL << cmd->vars.max_reg_cmds) - 1; + cmd->vars.bitmask = MLX5_CMD_MASK; sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds); sema_init(&cmd->vars.pages_sem, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 40a6cb052a2d..07a041954909 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1073,6 +1073,12 @@ int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn) struct mlx5_eq_comp *eq; int ret = 0; + if (vecidx >= table->max_comp_eqs) { + mlx5_core_dbg(dev, "Requested vector index %u should be less than %u", + vecidx, table->max_comp_eqs); + return -EINVAL; + } + mutex_lock(&table->comp_lock); eq = xa_load(&table->comp_eqs, vecidx); if (eq) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1789800faaeb..f6022c135ec0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1489,7 +1489,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) } if (err) - goto abort; + goto err_esw_enable; esw->fdb_table.flags |= MLX5_ESW_FDB_CREATED; @@ -1503,7 +1503,8 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) return 0; -abort: +err_esw_enable: + mlx5_eq_notifier_unregister(esw->dev, &esw->nb); mlx5_esw_acls_ns_cleanup(esw); return err; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 6bdef3dfc42f..860de1866298 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4634,7 +4634,9 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) if ((status & 0xffff) == 0xffff || !(status & tp->irq_mask)) return IRQ_NONE; - if (unlikely(status & SYSErr)) { + /* At least RTL8168fp may unexpectedly set the SYSErr bit */ + if (unlikely(status & SYSErr && + tp->mac_version <= RTL_GIGA_MAC_VER_06)) { rtl8169_pcierr_interrupt(tp->dev); goto out; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index c6897e6ea362..58fdc4f8dd48 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1673,20 +1673,19 @@ static int ravb_get_ts_info(struct net_device *ndev, struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *hw_info = priv->info; - info->so_timestamping = - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | - SOF_TIMESTAMPING_TX_HARDWARE | - SOF_TIMESTAMPING_RX_HARDWARE | - SOF_TIMESTAMPING_RAW_HARDWARE; - info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); - info->rx_filters = - (1 << HWTSTAMP_FILTER_NONE) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | - (1 << HWTSTAMP_FILTER_ALL); - if (hw_info->gptp || hw_info->ccc_gac) + if (hw_info->gptp || hw_info->ccc_gac) { + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_ALL); info->phc_index = ptp_clock_index(priv->ptp.clock); + } return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index e0f3cbd36852..e2d61a3a7712 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -127,10 +127,12 @@ static int mgbe_uphy_lane_bringup_serdes_up(struct net_device *ndev, void *mgbe_ value &= ~XPCS_WRAP_UPHY_RX_CONTROL_AUX_RX_IDDQ; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + usleep_range(10, 20); /* 50ns min delay needed as per HW design */ value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_SLEEP; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + usleep_range(10, 20); /* 500ns min delay needed as per HW design */ value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_CAL_EN; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); @@ -143,22 +145,30 @@ static int mgbe_uphy_lane_bringup_serdes_up(struct net_device *ndev, void *mgbe_ return err; } + usleep_range(10, 20); /* 50ns min delay needed as per HW design */ value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_DATA_EN; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); - value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_PCS_PHY_RDY; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + usleep_range(10, 20); /* 50ns min delay needed as per HW design */ value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); - value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; + value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + usleep_range(10, 20); /* 50ns min delay needed as per HW design */ value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); value |= XPCS_WRAP_UPHY_RX_CONTROL_RX_PCS_PHY_RDY; writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + msleep(30); /* 30ms delay needed as per HW design */ + value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + value &= ~XPCS_WRAP_UPHY_RX_CONTROL_RX_CDR_RESET; + writel(value, mgbe->xpcs + XPCS_WRAP_UPHY_RX_CONTROL); + err = readl_poll_timeout(mgbe->xpcs + XPCS_WRAP_IRQ_STATUS, value, value & XPCS_WRAP_IRQ_STATUS_PCS_LINK_STS, 500, 500 * 2000); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 62c10eb4f0ad..9f779653ed62 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -845,6 +845,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (net_ratelimit()) netdev_err(ndev, "TX DMA mapping error\n"); ndev->stats.tx_dropped++; + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } desc_set_phys_addr(lp, phys, cur_p); @@ -865,6 +866,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) ndev->stats.tx_dropped++; axienet_free_tx_chain(lp, orig_tail_ptr, ii + 1, true, NULL, 0); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } desc_set_phys_addr(lp, phys, cur_p); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 9d2d66a4aafd..8698d2db3dc8 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2795,6 +2795,31 @@ static struct hv_driver netvsc_drv = { }, }; +/* Set VF's namespace same as the synthetic NIC */ +static void netvsc_event_set_vf_ns(struct net_device *ndev) +{ + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct net_device *vf_netdev; + int ret; + + vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); + if (!vf_netdev) + return; + + if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) { + ret = dev_change_net_namespace(vf_netdev, dev_net(ndev), + "eth%d"); + if (ret) + netdev_err(vf_netdev, + "Cannot move to same namespace as %s: %d\n", + ndev->name, ret); + else + netdev_info(vf_netdev, + "Moved VF to namespace with: %s\n", + ndev->name); + } +} + /* * On Hyper-V, every VF interface is matched with a corresponding * synthetic interface. The synthetic interface is presented first @@ -2807,6 +2832,11 @@ static int netvsc_netdev_event(struct notifier_block *this, struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); int ret = 0; + if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) { + netvsc_event_set_vf_ns(event_dev); + return NOTIFY_DONE; + } + ret = check_dev_is_matching_vf(event_dev); if (ret != 0) return NOTIFY_DONE; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 778fb77c5a93..2ada8baf815b 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -151,19 +151,6 @@ static struct macsec_rx_sa *macsec_rxsa_get(struct macsec_rx_sa __rcu *ptr) return sa; } -static struct macsec_rx_sa *macsec_active_rxsa_get(struct macsec_rx_sc *rx_sc) -{ - struct macsec_rx_sa *sa = NULL; - int an; - - for (an = 0; an < MACSEC_NUM_AN; an++) { - sa = macsec_rxsa_get(rx_sc->sa[an]); - if (sa) - break; - } - return sa; -} - static void free_rx_sc_rcu(struct rcu_head *head) { struct macsec_rx_sc *rx_sc = container_of(head, struct macsec_rx_sc, rcu_head); @@ -1205,15 +1192,12 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ - struct macsec_rx_sa *active_rx_sa = macsec_active_rxsa_get(rx_sc); if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(secy->netdev, rx_errors); - if (active_rx_sa) - this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; } @@ -1223,8 +1207,6 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsUnusedSA++; u64_stats_update_end(&rxsc_stats->syncp); - if (active_rx_sa) - this_cpu_inc(active_rx_sa->stats->InPktsUnusedSA); goto deliver; } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 92a7a36b93ac..3e0b61202f0c 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -836,7 +836,8 @@ static void nsim_dev_trap_report_work(struct work_struct *work) nsim_dev = nsim_trap_data->nsim_dev; if (!devl_trylock(priv_to_devlink(nsim_dev))) { - schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1); + queue_delayed_work(system_unbound_wq, + &nsim_dev->trap_data->trap_report_dw, 1); return; } @@ -848,11 +849,12 @@ static void nsim_dev_trap_report_work(struct work_struct *work) continue; nsim_dev_trap_report(nsim_dev_port); + cond_resched(); } devl_unlock(priv_to_devlink(nsim_dev)); - - schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, - msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); + queue_delayed_work(system_unbound_wq, + &nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); } static int nsim_dev_traps_init(struct devlink *devlink) @@ -907,8 +909,9 @@ static int nsim_dev_traps_init(struct devlink *devlink) INIT_DELAYED_WORK(&nsim_dev->trap_data->trap_report_dw, nsim_dev_trap_report_work); - schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, - msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); + queue_delayed_work(system_unbound_wq, + &nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); return 0; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 29e1cbea6dc0..507726a08f82 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -40,8 +40,8 @@ /* Control Register 2 bits */ #define DP83822_FX_ENABLE BIT(14) -#define DP83822_HW_RESET BIT(15) -#define DP83822_SW_RESET BIT(14) +#define DP83822_SW_RESET BIT(15) +#define DP83822_DIG_RESTART BIT(14) /* PHY STS bits */ #define DP83822_PHYSTS_DUPLEX BIT(2) diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index 40ce8abe6999..6019811920a4 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -815,7 +815,7 @@ plip_send_packet(struct net_device *dev, struct net_local *nl, return HS_TIMEOUT; } } - break; + fallthrough; case PLIP_PK_LENGTH_LSB: if (plip_send(nibble_timeout, dev, diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 60c58dd6d253..9f66c47dc58b 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1771,7 +1771,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) // can rename the link if it knows better. if ((dev->driver_info->flags & FLAG_ETHER) != 0 && ((dev->driver_info->flags & FLAG_POINTTOPOINT) == 0 || - (net->dev_addr [0] & 0x02) == 0)) + /* somebody touched it*/ + !is_zero_ether_addr(net->dev_addr))) strscpy(net->name, "eth%d", sizeof(net->name)); /* WLAN devices should always be named "wlan%d" */ if ((dev->driver_info->flags & FLAG_WLAN) != 0) @@ -1874,6 +1875,7 @@ out1: * may trigger an error resubmitting itself and, worse, * schedule a timer. So we kill it all just in case. */ + usbnet_mark_going_away(dev); cancel_work_sync(&dev->kevent); del_timer_sync(&dev->delay); free_percpu(net->tstats); diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c index a6c787454a1a..1341374a4588 100644 --- a/drivers/net/vmxnet3/vmxnet3_xdp.c +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -148,7 +148,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, } else { /* XDP buffer from page pool */ page = virt_to_page(xdpf->data); tbi->dma_addr = page_pool_get_dma_addr(page) + - VMXNET3_XDP_HEADROOM; + (xdpf->data - (void *)xdpf); dma_sync_single_for_device(&adapter->pdev->dev, tbi->dma_addr, buf_size, DMA_TO_DEVICE); diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 284ab1f56391..45ed3afc443d 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -1031,7 +1031,7 @@ static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = { static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = { .kind = "wwan", - .maxtype = __IFLA_WWAN_MAX, + .maxtype = IFLA_WWAN_MAX, .alloc = wwan_rtnl_alloc, .validate = wwan_rtnl_validate, .newlink = wwan_rtnl_newlink, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 32b5cc76a022..b701969cf1c2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2469,17 +2469,29 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev) return 1; } -static void nvme_pci_update_nr_queues(struct nvme_dev *dev) +static bool nvme_pci_update_nr_queues(struct nvme_dev *dev) { if (!dev->ctrl.tagset) { nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops, nvme_pci_nr_maps(dev), sizeof(struct nvme_iod)); - return; + return true; + } + + /* Give up if we are racing with nvme_dev_disable() */ + if (!mutex_trylock(&dev->shutdown_lock)) + return false; + + /* Check if nvme_dev_disable() has been executed already */ + if (!dev->online_queues) { + mutex_unlock(&dev->shutdown_lock); + return false; } blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1); /* free previously allocated queues that are no longer usable */ nvme_free_queues(dev, dev->online_queues); + mutex_unlock(&dev->shutdown_lock); + return true; } static int nvme_pci_enable(struct nvme_dev *dev) @@ -2757,10 +2769,11 @@ static void nvme_reset_work(struct work_struct *work) * controller around but remove all namespaces. */ if (dev->online_queues > 1) { + nvme_dbbuf_set(dev); nvme_unquiesce_io_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); - nvme_pci_update_nr_queues(dev); - nvme_dbbuf_set(dev); + if (!nvme_pci_update_nr_queues(dev)) + goto out; nvme_unfreeze(&dev->ctrl); } else { dev_warn(dev->ctrl.device, "IO queues lost\n"); diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 502783a7adb1..24fd7ffadda9 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -264,6 +264,15 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = { /*Speaker Mute*/ { KE_KEY, 0x109, { KEY_MUTE} }, + /* S2Idle screen off */ + { KE_IGNORE, 0x120, { KEY_RESERVED }}, + + /* Leaving S4 or S2Idle suspend */ + { KE_IGNORE, 0x130, { KEY_RESERVED }}, + + /* Entering S2Idle suspend */ + { KE_IGNORE, 0x140, { KEY_RESERVED }}, + /* Mic mute */ { KE_KEY, 0x150, { KEY_MICMUTE } }, diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index b929b4f82420..af49dd6b31ad 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -521,6 +521,7 @@ static int __init sysman_init(void) int ret = 0; if (!dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL) && + !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Alienware", NULL) && !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "www.dell.com", NULL)) { pr_err("Unable to run on non-Dell system\n"); return -ENODEV; diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c index 612c3b59dd5b..0ca53db7a90e 100644 --- a/drivers/powercap/dtpm_devfreq.c +++ b/drivers/powercap/dtpm_devfreq.c @@ -166,7 +166,7 @@ static int __dtpm_devfreq_setup(struct devfreq *devfreq, struct dtpm *parent) ret = dev_pm_qos_add_request(dev, &dtpm_devfreq->qos_req, DEV_PM_QOS_MAX_FREQUENCY, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); - if (ret) { + if (ret < 0) { pr_err("Failed to add QoS request: %d\n", ret); goto out_dtpm_unregister; } diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 86590a7e29f6..dd041ee18ac9 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -692,7 +692,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) dev->queues = kcalloc(nr_cpu_ids, sizeof(*dev->queues), GFP_KERNEL); if (!dev->queues) { - dev->transport->free_device(dev); + hba->backend->ops->free_device(dev); return NULL; } diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 22cc6cac0ba2..2e100b76914a 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -2130,7 +2130,7 @@ static int tcmu_netlink_event_send(struct tcmu_dev *udev, } ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0, - TCMU_MCGRP_CONFIG, GFP_KERNEL); + TCMU_MCGRP_CONFIG); /* Wait during an add as the listener may not be up yet */ if (ret == 0 || diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 92bed200f283..c3c5711316d2 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -2164,6 +2164,11 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) { u32 reg; + dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) & + DWC3_GUSB2PHYCFG_SUSPHY) || + (dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)) & + DWC3_GUSB3PIPECTL_SUSPHY); + switch (dwc->current_dr_role) { case DWC3_GCTL_PRTCAP_DEVICE: if (pm_runtime_suspended(dwc->dev)) @@ -2211,6 +2216,15 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg) break; } + if (!PMSG_IS_AUTO(msg)) { + /* + * TI AM62 platform requires SUSPHY to be + * enabled for system suspend to work. + */ + if (!dwc->susphy_state) + dwc3_enable_susphy(dwc, true); + } + return 0; } @@ -2273,6 +2287,11 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) break; } + if (!PMSG_IS_AUTO(msg)) { + /* restore SUSPHY state to that before system suspend. */ + dwc3_enable_susphy(dwc, dwc->susphy_state); + } + return 0; } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 56f46ebdd342..1338b30466af 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1134,6 +1134,8 @@ struct dwc3_scratchpad_array { * @sys_wakeup: set if the device may do system wakeup. * @wakeup_configured: set if the device is configured for remote wakeup. * @suspended: set to track suspend event due to U3/L2. + * @susphy_state: state of DWC3_GUSB2PHYCFG_SUSPHY + DWC3_GUSB3PIPECTL_SUSPHY + * before PM suspend. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1360,6 +1362,7 @@ struct dwc3 { unsigned sys_wakeup:1; unsigned wakeup_configured:1; unsigned suspended:1; + unsigned susphy_state:1; u16 imod_interval; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 0219cd79493a..b3dc5f5164f4 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -2042,7 +2042,7 @@ static ssize_t f_uac2_opts_##name##_show(struct config_item *item, \ int result; \ \ mutex_lock(&opts->lock); \ - result = snprintf(page, sizeof(opts->name), "%s", opts->name); \ + result = scnprintf(page, sizeof(opts->name), "%s", opts->name); \ mutex_unlock(&opts->lock); \ \ return result; \ @@ -2052,7 +2052,7 @@ static ssize_t f_uac2_opts_##name##_store(struct config_item *item, \ const char *page, size_t len) \ { \ struct f_uac2_opts *opts = to_f_uac2_opts(item); \ - int ret = 0; \ + int ret = len; \ \ mutex_lock(&opts->lock); \ if (opts->refcnt) { \ @@ -2060,8 +2060,11 @@ static ssize_t f_uac2_opts_##name##_store(struct config_item *item, \ goto end; \ } \ \ - ret = snprintf(opts->name, min(sizeof(opts->name), len), \ - "%s", page); \ + if (len && page[len - 1] == '\n') \ + len--; \ + \ + scnprintf(opts->name, min(sizeof(opts->name), len + 1), \ + "%s", page); \ \ end: \ mutex_unlock(&opts->lock); \ @@ -2178,7 +2181,7 @@ static struct usb_function_instance *afunc_alloc_inst(void) opts->req_number = UAC2_DEF_REQ_NUM; opts->fb_max = FBACK_FAST_MAX; - snprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink"); + scnprintf(opts->function_name, sizeof(opts->function_name), "Source/Sink"); return &opts->func_inst; } diff --git a/drivers/usb/host/xhci-caps.h b/drivers/usb/host/xhci-caps.h new file mode 100644 index 000000000000..9e94cebf4a56 --- /dev/null +++ b/drivers/usb/host/xhci-caps.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* hc_capbase bitmasks */ +/* bits 7:0 - how long is the Capabilities register */ +#define HC_LENGTH(p) XHCI_HC_LENGTH(p) +/* bits 31:16 */ +#define HC_VERSION(p) (((p) >> 16) & 0xffff) + +/* HCSPARAMS1 - hcs_params1 - bitmasks */ +/* bits 0:7, Max Device Slots */ +#define HCS_MAX_SLOTS(p) (((p) >> 0) & 0xff) +#define HCS_SLOTS_MASK 0xff +/* bits 8:18, Max Interrupters */ +#define HCS_MAX_INTRS(p) (((p) >> 8) & 0x7ff) +/* bits 24:31, Max Ports - max value is 0x7F = 127 ports */ +#define HCS_MAX_PORTS(p) (((p) >> 24) & 0x7f) + +/* HCSPARAMS2 - hcs_params2 - bitmasks */ +/* bits 0:3, frames or uframes that SW needs to queue transactions + * ahead of the HW to meet periodic deadlines */ +#define HCS_IST(p) (((p) >> 0) & 0xf) +/* bits 4:7, max number of Event Ring segments */ +#define HCS_ERST_MAX(p) (((p) >> 4) & 0xf) +/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */ +/* bit 26 Scratchpad restore - for save/restore HW state - not used yet */ +/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */ +#define HCS_MAX_SCRATCHPAD(p) ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f)) + +/* HCSPARAMS3 - hcs_params3 - bitmasks */ +/* bits 0:7, Max U1 to U0 latency for the roothub ports */ +#define HCS_U1_LATENCY(p) (((p) >> 0) & 0xff) +/* bits 16:31, Max U2 to U0 latency for the roothub ports */ +#define HCS_U2_LATENCY(p) (((p) >> 16) & 0xffff) + +/* HCCPARAMS - hcc_params - bitmasks */ +/* true: HC can use 64-bit address pointers */ +#define HCC_64BIT_ADDR(p) ((p) & (1 << 0)) +/* true: HC can do bandwidth negotiation */ +#define HCC_BANDWIDTH_NEG(p) ((p) & (1 << 1)) +/* true: HC uses 64-byte Device Context structures + * FIXME 64-byte context structures aren't supported yet. + */ +#define HCC_64BYTE_CONTEXT(p) ((p) & (1 << 2)) +/* true: HC has port power switches */ +#define HCC_PPC(p) ((p) & (1 << 3)) +/* true: HC has port indicators */ +#define HCS_INDICATOR(p) ((p) & (1 << 4)) +/* true: HC has Light HC Reset Capability */ +#define HCC_LIGHT_RESET(p) ((p) & (1 << 5)) +/* true: HC supports latency tolerance messaging */ +#define HCC_LTC(p) ((p) & (1 << 6)) +/* true: no secondary Stream ID Support */ +#define HCC_NSS(p) ((p) & (1 << 7)) +/* true: HC supports Stopped - Short Packet */ +#define HCC_SPC(p) ((p) & (1 << 9)) +/* true: HC has Contiguous Frame ID Capability */ +#define HCC_CFC(p) ((p) & (1 << 11)) +/* Max size for Primary Stream Arrays - 2^(n+1), where n is bits 12:15 */ +#define HCC_MAX_PSA(p) (1 << ((((p) >> 12) & 0xf) + 1)) +/* Extended Capabilities pointer from PCI base - section 5.3.6 */ +#define HCC_EXT_CAPS(p) XHCI_HCC_EXT_CAPS(p) + +#define CTX_SIZE(_hcc) (HCC_64BYTE_CONTEXT(_hcc) ? 64 : 32) + +/* db_off bitmask - bits 0:1 reserved */ +#define DBOFF_MASK (~0x3) + +/* run_regs_off bitmask - bits 0:4 reserved */ +#define RTSOFF_MASK (~0x1f) + +/* HCCPARAMS2 - hcc_params2 - bitmasks */ +/* true: HC supports U3 entry Capability */ +#define HCC2_U3C(p) ((p) & (1 << 0)) +/* true: HC supports Configure endpoint command Max exit latency too large */ +#define HCC2_CMC(p) ((p) & (1 << 1)) +/* true: HC supports Force Save context Capability */ +#define HCC2_FSC(p) ((p) & (1 << 2)) +/* true: HC supports Compliance Transition Capability */ +#define HCC2_CTC(p) ((p) & (1 << 3)) +/* true: HC support Large ESIT payload Capability > 48k */ +#define HCC2_LEC(p) ((p) & (1 << 4)) +/* true: HC support Configuration Information Capability */ +#define HCC2_CIC(p) ((p) & (1 << 5)) +/* true: HC support Extended TBC Capability, Isoc burst count > 65535 */ +#define HCC2_ETC(p) ((p) & (1 << 6)) diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index 51a7ab3ba0ca..76170d7a7e7c 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -108,7 +108,7 @@ struct dbc_port { struct tasklet_struct push; struct list_head write_pool; - struct kfifo write_fifo; + unsigned int tx_boundary; bool registered; }; diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index b74e98e94393..0266c2f5bc0d 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -25,16 +25,26 @@ static inline struct dbc_port *dbc_to_port(struct xhci_dbc *dbc) } static unsigned int -dbc_send_packet(struct dbc_port *port, char *packet, unsigned int size) +dbc_kfifo_to_req(struct dbc_port *port, char *packet) { - unsigned int len; - - len = kfifo_len(&port->write_fifo); - if (len < size) - size = len; - if (size != 0) - size = kfifo_out(&port->write_fifo, packet, size); - return size; + unsigned int len; + + len = kfifo_len(&port->port.xmit_fifo); + + if (len == 0) + return 0; + + len = min(len, DBC_MAX_PACKET); + + if (port->tx_boundary) + len = min(port->tx_boundary, len); + + len = kfifo_out(&port->port.xmit_fifo, packet, len); + + if (port->tx_boundary) + port->tx_boundary -= len; + + return len; } static int dbc_start_tx(struct dbc_port *port) @@ -49,7 +59,7 @@ static int dbc_start_tx(struct dbc_port *port) while (!list_empty(pool)) { req = list_entry(pool->next, struct dbc_request, list_pool); - len = dbc_send_packet(port, req->buf, DBC_MAX_PACKET); + len = dbc_kfifo_to_req(port, req->buf); if (len == 0) break; do_tty_wake = true; @@ -213,14 +223,32 @@ static ssize_t dbc_tty_write(struct tty_struct *tty, const u8 *buf, { struct dbc_port *port = tty->driver_data; unsigned long flags; + unsigned int written = 0; spin_lock_irqsave(&port->port_lock, flags); - if (count) - count = kfifo_in(&port->write_fifo, buf, count); - dbc_start_tx(port); + + /* + * Treat tty write as one usb transfer. Make sure the writes are turned + * into TRB request having the same size boundaries as the tty writes. + * Don't add data to kfifo before previous write is turned into TRBs + */ + if (port->tx_boundary) { + spin_unlock_irqrestore(&port->port_lock, flags); + return 0; + } + + if (count) { + written = kfifo_in(&port->port.xmit_fifo, buf, count); + + if (written == count) + port->tx_boundary = kfifo_len(&port->port.xmit_fifo); + + dbc_start_tx(port); + } + spin_unlock_irqrestore(&port->port_lock, flags); - return count; + return written; } static int dbc_tty_put_char(struct tty_struct *tty, u8 ch) @@ -230,7 +258,7 @@ static int dbc_tty_put_char(struct tty_struct *tty, u8 ch) int status; spin_lock_irqsave(&port->port_lock, flags); - status = kfifo_put(&port->write_fifo, ch); + status = kfifo_put(&port->port.xmit_fifo, ch); spin_unlock_irqrestore(&port->port_lock, flags); return status; @@ -253,7 +281,11 @@ static unsigned int dbc_tty_write_room(struct tty_struct *tty) unsigned int room; spin_lock_irqsave(&port->port_lock, flags); - room = kfifo_avail(&port->write_fifo); + room = kfifo_avail(&port->port.xmit_fifo); + + if (port->tx_boundary) + room = 0; + spin_unlock_irqrestore(&port->port_lock, flags); return room; @@ -266,7 +298,7 @@ static unsigned int dbc_tty_chars_in_buffer(struct tty_struct *tty) unsigned int chars; spin_lock_irqsave(&port->port_lock, flags); - chars = kfifo_len(&port->write_fifo); + chars = kfifo_len(&port->port.xmit_fifo); spin_unlock_irqrestore(&port->port_lock, flags); return chars; @@ -424,7 +456,8 @@ static int xhci_dbc_tty_register_device(struct xhci_dbc *dbc) goto err_idr; } - ret = kfifo_alloc(&port->write_fifo, DBC_WRITE_BUF_SIZE, GFP_KERNEL); + ret = kfifo_alloc(&port->port.xmit_fifo, DBC_WRITE_BUF_SIZE, + GFP_KERNEL); if (ret) goto err_exit_port; @@ -453,7 +486,7 @@ err_free_requests: xhci_dbc_free_requests(&port->read_pool); xhci_dbc_free_requests(&port->write_pool); err_free_fifo: - kfifo_free(&port->write_fifo); + kfifo_free(&port->port.xmit_fifo); err_exit_port: idr_remove(&dbc_tty_minors, port->minor); err_idr: @@ -478,7 +511,7 @@ static void xhci_dbc_tty_unregister_device(struct xhci_dbc *dbc) idr_remove(&dbc_tty_minors, port->minor); mutex_unlock(&dbc_tty_minors_lock); - kfifo_free(&port->write_fifo); + kfifo_free(&port->port.xmit_fifo); xhci_dbc_free_requests(&port->read_pool); xhci_dbc_free_requests(&port->read_queue); xhci_dbc_free_requests(&port->write_pool); diff --git a/drivers/usb/host/xhci-port.h b/drivers/usb/host/xhci-port.h new file mode 100644 index 000000000000..f19efb966d18 --- /dev/null +++ b/drivers/usb/host/xhci-port.h @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* PORTSC - Port Status and Control Register - port_status_base bitmasks */ +/* true: device connected */ +#define PORT_CONNECT (1 << 0) +/* true: port enabled */ +#define PORT_PE (1 << 1) +/* bit 2 reserved and zeroed */ +/* true: port has an over-current condition */ +#define PORT_OC (1 << 3) +/* true: port reset signaling asserted */ +#define PORT_RESET (1 << 4) +/* Port Link State - bits 5:8 + * A read gives the current link PM state of the port, + * a write with Link State Write Strobe set sets the link state. + */ +#define PORT_PLS_MASK (0xf << 5) +#define XDEV_U0 (0x0 << 5) +#define XDEV_U1 (0x1 << 5) +#define XDEV_U2 (0x2 << 5) +#define XDEV_U3 (0x3 << 5) +#define XDEV_DISABLED (0x4 << 5) +#define XDEV_RXDETECT (0x5 << 5) +#define XDEV_INACTIVE (0x6 << 5) +#define XDEV_POLLING (0x7 << 5) +#define XDEV_RECOVERY (0x8 << 5) +#define XDEV_HOT_RESET (0x9 << 5) +#define XDEV_COMP_MODE (0xa << 5) +#define XDEV_TEST_MODE (0xb << 5) +#define XDEV_RESUME (0xf << 5) + +/* true: port has power (see HCC_PPC) */ +#define PORT_POWER (1 << 9) +/* bits 10:13 indicate device speed: + * 0 - undefined speed - port hasn't be initialized by a reset yet + * 1 - full speed + * 2 - low speed + * 3 - high speed + * 4 - super speed + * 5-15 reserved + */ +#define DEV_SPEED_MASK (0xf << 10) +#define XDEV_FS (0x1 << 10) +#define XDEV_LS (0x2 << 10) +#define XDEV_HS (0x3 << 10) +#define XDEV_SS (0x4 << 10) +#define XDEV_SSP (0x5 << 10) +#define DEV_UNDEFSPEED(p) (((p) & DEV_SPEED_MASK) == (0x0<<10)) +#define DEV_FULLSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_FS) +#define DEV_LOWSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_LS) +#define DEV_HIGHSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_HS) +#define DEV_SUPERSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_SS) +#define DEV_SUPERSPEEDPLUS(p) (((p) & DEV_SPEED_MASK) == XDEV_SSP) +#define DEV_SUPERSPEED_ANY(p) (((p) & DEV_SPEED_MASK) >= XDEV_SS) +#define DEV_PORT_SPEED(p) (((p) >> 10) & 0x0f) + +/* Bits 20:23 in the Slot Context are the speed for the device */ +#define SLOT_SPEED_FS (XDEV_FS << 10) +#define SLOT_SPEED_LS (XDEV_LS << 10) +#define SLOT_SPEED_HS (XDEV_HS << 10) +#define SLOT_SPEED_SS (XDEV_SS << 10) +#define SLOT_SPEED_SSP (XDEV_SSP << 10) +/* Port Indicator Control */ +#define PORT_LED_OFF (0 << 14) +#define PORT_LED_AMBER (1 << 14) +#define PORT_LED_GREEN (2 << 14) +#define PORT_LED_MASK (3 << 14) +/* Port Link State Write Strobe - set this when changing link state */ +#define PORT_LINK_STROBE (1 << 16) +/* true: connect status change */ +#define PORT_CSC (1 << 17) +/* true: port enable change */ +#define PORT_PEC (1 << 18) +/* true: warm reset for a USB 3.0 device is done. A "hot" reset puts the port + * into an enabled state, and the device into the default state. A "warm" reset + * also resets the link, forcing the device through the link training sequence. + * SW can also look at the Port Reset register to see when warm reset is done. + */ +#define PORT_WRC (1 << 19) +/* true: over-current change */ +#define PORT_OCC (1 << 20) +/* true: reset change - 1 to 0 transition of PORT_RESET */ +#define PORT_RC (1 << 21) +/* port link status change - set on some port link state transitions: + * Transition Reason + * ------------------------------------------------------------------------------ + * - U3 to Resume Wakeup signaling from a device + * - Resume to Recovery to U0 USB 3.0 device resume + * - Resume to U0 USB 2.0 device resume + * - U3 to Recovery to U0 Software resume of USB 3.0 device complete + * - U3 to U0 Software resume of USB 2.0 device complete + * - U2 to U0 L1 resume of USB 2.1 device complete + * - U0 to U0 (???) L1 entry rejection by USB 2.1 device + * - U0 to disabled L1 entry error with USB 2.1 device + * - Any state to inactive Error on USB 3.0 port + */ +#define PORT_PLC (1 << 22) +/* port configure error change - port failed to configure its link partner */ +#define PORT_CEC (1 << 23) +#define PORT_CHANGE_MASK (PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \ + PORT_RC | PORT_PLC | PORT_CEC) + + +/* Cold Attach Status - xHC can set this bit to report device attached during + * Sx state. Warm port reset should be perfomed to clear this bit and move port + * to connected state. + */ +#define PORT_CAS (1 << 24) +/* wake on connect (enable) */ +#define PORT_WKCONN_E (1 << 25) +/* wake on disconnect (enable) */ +#define PORT_WKDISC_E (1 << 26) +/* wake on over-current (enable) */ +#define PORT_WKOC_E (1 << 27) +/* bits 28:29 reserved */ +/* true: device is non-removable - for USB 3.0 roothub emulation */ +#define PORT_DEV_REMOVE (1 << 30) +/* Initiate a warm port reset - complete when PORT_WRC is '1' */ +#define PORT_WR (1 << 31) + +/* We mark duplicate entries with -1 */ +#define DUPLICATE_ENTRY ((u8)(-1)) + +/* Port Power Management Status and Control - port_power_base bitmasks */ +/* Inactivity timer value for transitions into U1, in microseconds. + * Timeout can be up to 127us. 0xFF means an infinite timeout. + */ +#define PORT_U1_TIMEOUT(p) ((p) & 0xff) +#define PORT_U1_TIMEOUT_MASK 0xff +/* Inactivity timer value for transitions into U2 */ +#define PORT_U2_TIMEOUT(p) (((p) & 0xff) << 8) +#define PORT_U2_TIMEOUT_MASK (0xff << 8) +/* Bits 24:31 for port testing */ + +/* USB2 Protocol PORTSPMSC */ +#define PORT_L1S_MASK 7 +#define PORT_L1S_SUCCESS 1 +#define PORT_RWE (1 << 3) +#define PORT_HIRD(p) (((p) & 0xf) << 4) +#define PORT_HIRD_MASK (0xf << 4) +#define PORT_L1DS_MASK (0xff << 8) +#define PORT_L1DS(p) (((p) & 0xff) << 8) +#define PORT_HLE (1 << 16) +#define PORT_TEST_MODE_SHIFT 28 + +/* USB3 Protocol PORTLI Port Link Information */ +#define PORT_RX_LANES(p) (((p) >> 16) & 0xf) +#define PORT_TX_LANES(p) (((p) >> 20) & 0xf) + +/* USB2 Protocol PORTHLPMC */ +#define PORT_HIRDM(p)((p) & 3) +#define PORT_L1_TIMEOUT(p)(((p) & 0xff) << 2) +#define PORT_BESLD(p)(((p) & 0xf) << 10) + +/* use 512 microseconds as USB2 LPM L1 default timeout. */ +#define XHCI_L1_TIMEOUT 512 + +/* Set default HIRD/BESL value to 4 (350/400us) for USB2 L1 LPM resume latency. + * Safe to use with mixed HIRD and BESL systems (host and device) and is used + * by other operating systems. + * + * XHCI 1.0 errata 8/14/12 Table 13 notes: + * "Software should choose xHC BESL/BESLD field values that do not violate a + * device's resume latency requirements, + * e.g. not program values > '4' if BLC = '1' and a HIRD device is attached, + * or not program values < '4' if BLC = '0' and a BESL device is attached. + */ +#define XHCI_DEFAULT_BESL 4 + +/* + * USB3 specification define a 360ms tPollingLFPSTiemout for USB3 ports + * to complete link training. usually link trainig completes much faster + * so check status 10 times with 36ms sleep in places we need to wait for + * polling to complete. + */ +#define XHCI_PORT_POLLING_LFPS_TIME 36 diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 1badbb9bc035..9667c4f860cf 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -23,6 +23,9 @@ #include "xhci-ext-caps.h" #include "pci-quirks.h" +#include "xhci-port.h" +#include "xhci-caps.h" + /* max buffer size for trace and debug messages */ #define XHCI_MSG_MAX 500 @@ -63,90 +66,6 @@ struct xhci_cap_regs { /* Reserved up to (CAPLENGTH - 0x1C) */ }; -/* hc_capbase bitmasks */ -/* bits 7:0 - how long is the Capabilities register */ -#define HC_LENGTH(p) XHCI_HC_LENGTH(p) -/* bits 31:16 */ -#define HC_VERSION(p) (((p) >> 16) & 0xffff) - -/* HCSPARAMS1 - hcs_params1 - bitmasks */ -/* bits 0:7, Max Device Slots */ -#define HCS_MAX_SLOTS(p) (((p) >> 0) & 0xff) -#define HCS_SLOTS_MASK 0xff -/* bits 8:18, Max Interrupters */ -#define HCS_MAX_INTRS(p) (((p) >> 8) & 0x7ff) -/* bits 24:31, Max Ports - max value is 0x7F = 127 ports */ -#define HCS_MAX_PORTS(p) (((p) >> 24) & 0x7f) - -/* HCSPARAMS2 - hcs_params2 - bitmasks */ -/* bits 0:3, frames or uframes that SW needs to queue transactions - * ahead of the HW to meet periodic deadlines */ -#define HCS_IST(p) (((p) >> 0) & 0xf) -/* bits 4:7, max number of Event Ring segments */ -#define HCS_ERST_MAX(p) (((p) >> 4) & 0xf) -/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */ -/* bit 26 Scratchpad restore - for save/restore HW state - not used yet */ -/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */ -#define HCS_MAX_SCRATCHPAD(p) ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f)) - -/* HCSPARAMS3 - hcs_params3 - bitmasks */ -/* bits 0:7, Max U1 to U0 latency for the roothub ports */ -#define HCS_U1_LATENCY(p) (((p) >> 0) & 0xff) -/* bits 16:31, Max U2 to U0 latency for the roothub ports */ -#define HCS_U2_LATENCY(p) (((p) >> 16) & 0xffff) - -/* HCCPARAMS - hcc_params - bitmasks */ -/* true: HC can use 64-bit address pointers */ -#define HCC_64BIT_ADDR(p) ((p) & (1 << 0)) -/* true: HC can do bandwidth negotiation */ -#define HCC_BANDWIDTH_NEG(p) ((p) & (1 << 1)) -/* true: HC uses 64-byte Device Context structures - * FIXME 64-byte context structures aren't supported yet. - */ -#define HCC_64BYTE_CONTEXT(p) ((p) & (1 << 2)) -/* true: HC has port power switches */ -#define HCC_PPC(p) ((p) & (1 << 3)) -/* true: HC has port indicators */ -#define HCS_INDICATOR(p) ((p) & (1 << 4)) -/* true: HC has Light HC Reset Capability */ -#define HCC_LIGHT_RESET(p) ((p) & (1 << 5)) -/* true: HC supports latency tolerance messaging */ -#define HCC_LTC(p) ((p) & (1 << 6)) -/* true: no secondary Stream ID Support */ -#define HCC_NSS(p) ((p) & (1 << 7)) -/* true: HC supports Stopped - Short Packet */ -#define HCC_SPC(p) ((p) & (1 << 9)) -/* true: HC has Contiguous Frame ID Capability */ -#define HCC_CFC(p) ((p) & (1 << 11)) -/* Max size for Primary Stream Arrays - 2^(n+1), where n is bits 12:15 */ -#define HCC_MAX_PSA(p) (1 << ((((p) >> 12) & 0xf) + 1)) -/* Extended Capabilities pointer from PCI base - section 5.3.6 */ -#define HCC_EXT_CAPS(p) XHCI_HCC_EXT_CAPS(p) - -#define CTX_SIZE(_hcc) (HCC_64BYTE_CONTEXT(_hcc) ? 64 : 32) - -/* db_off bitmask - bits 0:1 reserved */ -#define DBOFF_MASK (~0x3) - -/* run_regs_off bitmask - bits 0:4 reserved */ -#define RTSOFF_MASK (~0x1f) - -/* HCCPARAMS2 - hcc_params2 - bitmasks */ -/* true: HC supports U3 entry Capability */ -#define HCC2_U3C(p) ((p) & (1 << 0)) -/* true: HC supports Configure endpoint command Max exit latency too large */ -#define HCC2_CMC(p) ((p) & (1 << 1)) -/* true: HC supports Force Save context Capability */ -#define HCC2_FSC(p) ((p) & (1 << 2)) -/* true: HC supports Compliance Transition Capability */ -#define HCC2_CTC(p) ((p) & (1 << 3)) -/* true: HC support Large ESIT payload Capability > 48k */ -#define HCC2_LEC(p) ((p) & (1 << 4)) -/* true: HC support Configuration Information Capability */ -#define HCC2_CIC(p) ((p) & (1 << 5)) -/* true: HC support Extended TBC Capability, Isoc burst count > 65535 */ -#define HCC2_ETC(p) ((p) & (1 << 6)) - /* Number of registers per port */ #define NUM_PORT_REGS 4 @@ -292,181 +211,6 @@ struct xhci_op_regs { #define CONFIG_CIE (1 << 9) /* bits 10:31 - reserved and should be preserved */ -/* PORTSC - Port Status and Control Register - port_status_base bitmasks */ -/* true: device connected */ -#define PORT_CONNECT (1 << 0) -/* true: port enabled */ -#define PORT_PE (1 << 1) -/* bit 2 reserved and zeroed */ -/* true: port has an over-current condition */ -#define PORT_OC (1 << 3) -/* true: port reset signaling asserted */ -#define PORT_RESET (1 << 4) -/* Port Link State - bits 5:8 - * A read gives the current link PM state of the port, - * a write with Link State Write Strobe set sets the link state. - */ -#define PORT_PLS_MASK (0xf << 5) -#define XDEV_U0 (0x0 << 5) -#define XDEV_U1 (0x1 << 5) -#define XDEV_U2 (0x2 << 5) -#define XDEV_U3 (0x3 << 5) -#define XDEV_DISABLED (0x4 << 5) -#define XDEV_RXDETECT (0x5 << 5) -#define XDEV_INACTIVE (0x6 << 5) -#define XDEV_POLLING (0x7 << 5) -#define XDEV_RECOVERY (0x8 << 5) -#define XDEV_HOT_RESET (0x9 << 5) -#define XDEV_COMP_MODE (0xa << 5) -#define XDEV_TEST_MODE (0xb << 5) -#define XDEV_RESUME (0xf << 5) - -/* true: port has power (see HCC_PPC) */ -#define PORT_POWER (1 << 9) -/* bits 10:13 indicate device speed: - * 0 - undefined speed - port hasn't be initialized by a reset yet - * 1 - full speed - * 2 - low speed - * 3 - high speed - * 4 - super speed - * 5-15 reserved - */ -#define DEV_SPEED_MASK (0xf << 10) -#define XDEV_FS (0x1 << 10) -#define XDEV_LS (0x2 << 10) -#define XDEV_HS (0x3 << 10) -#define XDEV_SS (0x4 << 10) -#define XDEV_SSP (0x5 << 10) -#define DEV_UNDEFSPEED(p) (((p) & DEV_SPEED_MASK) == (0x0<<10)) -#define DEV_FULLSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_FS) -#define DEV_LOWSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_LS) -#define DEV_HIGHSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_HS) -#define DEV_SUPERSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_SS) -#define DEV_SUPERSPEEDPLUS(p) (((p) & DEV_SPEED_MASK) == XDEV_SSP) -#define DEV_SUPERSPEED_ANY(p) (((p) & DEV_SPEED_MASK) >= XDEV_SS) -#define DEV_PORT_SPEED(p) (((p) >> 10) & 0x0f) - -/* Bits 20:23 in the Slot Context are the speed for the device */ -#define SLOT_SPEED_FS (XDEV_FS << 10) -#define SLOT_SPEED_LS (XDEV_LS << 10) -#define SLOT_SPEED_HS (XDEV_HS << 10) -#define SLOT_SPEED_SS (XDEV_SS << 10) -#define SLOT_SPEED_SSP (XDEV_SSP << 10) -/* Port Indicator Control */ -#define PORT_LED_OFF (0 << 14) -#define PORT_LED_AMBER (1 << 14) -#define PORT_LED_GREEN (2 << 14) -#define PORT_LED_MASK (3 << 14) -/* Port Link State Write Strobe - set this when changing link state */ -#define PORT_LINK_STROBE (1 << 16) -/* true: connect status change */ -#define PORT_CSC (1 << 17) -/* true: port enable change */ -#define PORT_PEC (1 << 18) -/* true: warm reset for a USB 3.0 device is done. A "hot" reset puts the port - * into an enabled state, and the device into the default state. A "warm" reset - * also resets the link, forcing the device through the link training sequence. - * SW can also look at the Port Reset register to see when warm reset is done. - */ -#define PORT_WRC (1 << 19) -/* true: over-current change */ -#define PORT_OCC (1 << 20) -/* true: reset change - 1 to 0 transition of PORT_RESET */ -#define PORT_RC (1 << 21) -/* port link status change - set on some port link state transitions: - * Transition Reason - * ------------------------------------------------------------------------------ - * - U3 to Resume Wakeup signaling from a device - * - Resume to Recovery to U0 USB 3.0 device resume - * - Resume to U0 USB 2.0 device resume - * - U3 to Recovery to U0 Software resume of USB 3.0 device complete - * - U3 to U0 Software resume of USB 2.0 device complete - * - U2 to U0 L1 resume of USB 2.1 device complete - * - U0 to U0 (???) L1 entry rejection by USB 2.1 device - * - U0 to disabled L1 entry error with USB 2.1 device - * - Any state to inactive Error on USB 3.0 port - */ -#define PORT_PLC (1 << 22) -/* port configure error change - port failed to configure its link partner */ -#define PORT_CEC (1 << 23) -#define PORT_CHANGE_MASK (PORT_CSC | PORT_PEC | PORT_WRC | PORT_OCC | \ - PORT_RC | PORT_PLC | PORT_CEC) - - -/* Cold Attach Status - xHC can set this bit to report device attached during - * Sx state. Warm port reset should be perfomed to clear this bit and move port - * to connected state. - */ -#define PORT_CAS (1 << 24) -/* wake on connect (enable) */ -#define PORT_WKCONN_E (1 << 25) -/* wake on disconnect (enable) */ -#define PORT_WKDISC_E (1 << 26) -/* wake on over-current (enable) */ -#define PORT_WKOC_E (1 << 27) -/* bits 28:29 reserved */ -/* true: device is non-removable - for USB 3.0 roothub emulation */ -#define PORT_DEV_REMOVE (1 << 30) -/* Initiate a warm port reset - complete when PORT_WRC is '1' */ -#define PORT_WR (1 << 31) - -/* We mark duplicate entries with -1 */ -#define DUPLICATE_ENTRY ((u8)(-1)) - -/* Port Power Management Status and Control - port_power_base bitmasks */ -/* Inactivity timer value for transitions into U1, in microseconds. - * Timeout can be up to 127us. 0xFF means an infinite timeout. - */ -#define PORT_U1_TIMEOUT(p) ((p) & 0xff) -#define PORT_U1_TIMEOUT_MASK 0xff -/* Inactivity timer value for transitions into U2 */ -#define PORT_U2_TIMEOUT(p) (((p) & 0xff) << 8) -#define PORT_U2_TIMEOUT_MASK (0xff << 8) -/* Bits 24:31 for port testing */ - -/* USB2 Protocol PORTSPMSC */ -#define PORT_L1S_MASK 7 -#define PORT_L1S_SUCCESS 1 -#define PORT_RWE (1 << 3) -#define PORT_HIRD(p) (((p) & 0xf) << 4) -#define PORT_HIRD_MASK (0xf << 4) -#define PORT_L1DS_MASK (0xff << 8) -#define PORT_L1DS(p) (((p) & 0xff) << 8) -#define PORT_HLE (1 << 16) -#define PORT_TEST_MODE_SHIFT 28 - -/* USB3 Protocol PORTLI Port Link Information */ -#define PORT_RX_LANES(p) (((p) >> 16) & 0xf) -#define PORT_TX_LANES(p) (((p) >> 20) & 0xf) - -/* USB2 Protocol PORTHLPMC */ -#define PORT_HIRDM(p)((p) & 3) -#define PORT_L1_TIMEOUT(p)(((p) & 0xff) << 2) -#define PORT_BESLD(p)(((p) & 0xf) << 10) - -/* use 512 microseconds as USB2 LPM L1 default timeout. */ -#define XHCI_L1_TIMEOUT 512 - -/* Set default HIRD/BESL value to 4 (350/400us) for USB2 L1 LPM resume latency. - * Safe to use with mixed HIRD and BESL systems (host and device) and is used - * by other operating systems. - * - * XHCI 1.0 errata 8/14/12 Table 13 notes: - * "Software should choose xHC BESL/BESLD field values that do not violate a - * device's resume latency requirements, - * e.g. not program values > '4' if BLC = '1' and a HIRD device is attached, - * or not program values < '4' if BLC = '0' and a BESL device is attached. - */ -#define XHCI_DEFAULT_BESL 4 - -/* - * USB3 specification define a 360ms tPollingLFPSTiemout for USB3 ports - * to complete link training. usually link trainig completes much faster - * so check status 10 times with 36ms sleep in places we need to wait for - * polling to complete. - */ -#define XHCI_PORT_POLLING_LFPS_TIME 36 - /** * struct xhci_intr_reg - Interrupt Register Set * @irq_pending: IMAN - Interrupt Management Register. Used to enable diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index f92fc2acfcba..79cad8d61dac 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -502,6 +502,7 @@ static void typec_altmode_release(struct device *dev) typec_altmode_put_partner(alt); altmode_id_remove(alt->adev.dev.parent, alt->id); + put_device(alt->adev.dev.parent); kfree(alt); } @@ -551,6 +552,8 @@ typec_register_altmode(struct device *parent, alt->adev.dev.type = &typec_altmode_dev_type; dev_set_name(&alt->adev.dev, "%s.%u", dev_name(parent), id); + get_device(alt->adev.dev.parent); + /* Link partners and plugs with the ports */ if (!is_port) typec_altmode_set_partner(alt); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 4e999e1c1407..434cf3d5f4cf 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3794,6 +3794,8 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, spin_lock(&cache->lock); if (cache->ro) space_info->bytes_readonly += num_bytes; + else if (btrfs_is_zoned(cache->fs_info)) + space_info->bytes_zone_unusable += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; space_info->max_extent_size = 0; diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 9c07d5c3e5ad..7066414be6ee 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -347,8 +347,8 @@ btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, return di; } /* Adjust return code if the key was not found in the next leaf. */ - if (ret > 0) - ret = 0; + if (ret >= 0) + ret = -ENOENT; return ERR_PTR(ret); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ee04185d8e0f..ea19ea75674d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4293,11 +4293,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, */ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) { di = btrfs_search_dir_index_item(root, path, dir_ino, &fname.disk_name); - if (IS_ERR_OR_NULL(di)) { - if (!di) - ret = -ENOENT; - else - ret = PTR_ERR(di); + if (IS_ERR(di)) { + ret = PTR_ERR(di); btrfs_abort_transaction(trans, ret); goto out; } diff --git a/fs/exec.c b/fs/exec.c index f49b352a6032..7776209d98c1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -143,13 +143,11 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) goto out; /* - * may_open() has already checked for this, so it should be - * impossible to trip now. But we need to be extra cautious - * and check again at the very end too. + * Check do_open_execat() for an explanation. */ error = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || + path_noexec(&file->f_path)) goto exit; error = -ENOEXEC; @@ -925,23 +923,22 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) - goto out; + return file; /* - * may_open() has already checked for this, so it should be - * impossible to trip now. But we need to be extra cautious - * and check again at the very end too. + * In the past the regular type check was here. It moved to may_open() in + * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is + * an invariant that all non-regular files error out before we get here. */ err = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || + path_noexec(&file->f_path)) goto exit; err = deny_write_access(file); if (err) goto exit; -out: return file; exit: diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 974ecf5e0d95..3ab410059dc2 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -187,7 +187,7 @@ int dbMount(struct inode *ipbmap) } bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); - if (!bmp->db_numag || bmp->db_numag >= MAXAG) { + if (!bmp->db_numag || bmp->db_numag > MAXAG) { err = -EINVAL; goto err_release_metapage; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f16bbbfcf672..975dd74a7a4d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -8254,7 +8254,7 @@ nfs4_state_shutdown_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); unregister_shrinker(&nn->nfsd_client_shrinker); - cancel_work(&nn->nfsd_shrinker_work); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index b4e54d079b7d..36d29c183bb7 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -77,7 +77,8 @@ void nilfs_forget_buffer(struct buffer_head *bh) const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | - BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected)); + BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | + BIT(BH_Delay)); lock_buffer(bh); set_mask_bits(&bh->b_state, clear_bits, 0); @@ -410,7 +411,8 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | - BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected)); + BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | + BIT(BH_Delay)); bh = head = page_buffers(page); do { diff --git a/fs/open.c b/fs/open.c index 59db720693f9..f9ac703ec1b2 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1461,6 +1461,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; + if (unlikely(usize > PAGE_SIZE)) + return -E2BIG; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 3bbac925d076..8d7484400fe8 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -918,8 +918,15 @@ static int smb3_reconfigure(struct fs_context *fc) else { kfree_sensitive(ses->password); ses->password = kstrdup(ctx->password, GFP_KERNEL); + if (!ses->password) + return -ENOMEM; kfree_sensitive(ses->password2); ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + if (!ses->password2) { + kfree_sensitive(ses->password); + ses->password = NULL; + return -ENOMEM; + } } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index ad0e0de9a165..7429b96a6ae5 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -330,6 +330,18 @@ static int parse_reparse_posix(struct reparse_posix_data *buf, switch ((type = le64_to_cpu(buf->InodeType))) { case NFS_SPECFILE_LNK: + if (len == 0 || (len % 2)) { + cifs_dbg(VFS, "srv returned malformed nfs symlink buffer\n"); + return -EIO; + } + /* + * Check that buffer does not contain UTF-16 null codepoint + * because Linux cannot process symlink with null byte. + */ + if (UniStrnlen((wchar_t *)buf->DataBuffer, len/2) != len/2) { + cifs_dbg(VFS, "srv returned null byte in nfs symlink target location\n"); + return -EIO; + } data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer, len, true, cifs_sb->local_nls); @@ -340,8 +352,19 @@ static int parse_reparse_posix(struct reparse_posix_data *buf, break; case NFS_SPECFILE_CHR: case NFS_SPECFILE_BLK: + /* DataBuffer for block and char devices contains two 32-bit numbers */ + if (len != 8) { + cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type); + return -EIO; + } + break; case NFS_SPECFILE_FIFO: case NFS_SPECFILE_SOCK: + /* DataBuffer for fifos and sockets is empty */ + if (len != 0) { + cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type); + return -EIO; + } break; default: cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n", diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 450e3050324c..ab6e79be2c15 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1122,7 +1122,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; unsigned int size[1]; void *data[1]; - struct smb2_file_full_ea_info *ea = NULL; + struct smb2_file_full_ea_info *ea; struct smb2_query_info_rsp *rsp; int rc, used_len = 0; int retries = 0, cur_sleep = 1; @@ -1143,6 +1143,7 @@ replay_again: if (!utf16_path) return -ENOMEM; + ea = NULL; resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; vars = kzalloc(sizeof(*vars), GFP_KERNEL); if (!vars) { diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 83a03201bb86..a86a3fbfb5a4 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3300,6 +3300,15 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, return rc; if (indatalen) { + unsigned int len; + + if (WARN_ON_ONCE(smb3_encryption_required(tcon) && + (check_add_overflow(total_len - 1, + ALIGN(indatalen, 8), &len) || + len > MAX_CIFS_SMALL_BUFFER_SIZE))) { + cifs_small_buf_release(req); + return -EIO; + } /* * indatalen is usually small at a couple of bytes max, so * just allocate through generic pool diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index bb471ec36404..f5de2030e769 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -387,6 +387,7 @@ static void udf_table_free_blocks(struct super_block *sb, struct extent_position oepos, epos; int8_t etype; struct udf_inode_info *iinfo; + int ret = 0; mutex_lock(&sbi->s_alloc_mutex); iinfo = UDF_I(table); @@ -400,8 +401,12 @@ static void udf_table_free_blocks(struct super_block *sb, epos.block = oepos.block = iinfo->i_location; epos.bh = oepos.bh = NULL; - while (count && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (count) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto error_return; + if (ret == 0) + break; if (((eloc.logicalBlockNum + (elen >> sb->s_blocksize_bits)) == start)) { if ((0x3FFFFFFF - elen) < @@ -476,11 +481,8 @@ static void udf_table_free_blocks(struct super_block *sb, adsize = sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) adsize = sizeof(struct long_ad); - else { - brelse(oepos.bh); - brelse(epos.bh); + else goto error_return; - } if (epos.offset + (2 * adsize) > sb->s_blocksize) { /* Steal a block from the extent being free'd */ @@ -496,10 +498,10 @@ static void udf_table_free_blocks(struct super_block *sb, __udf_add_aext(table, &epos, &eloc, elen, 1); } +error_return: brelse(epos.bh); brelse(oepos.bh); -error_return: mutex_unlock(&sbi->s_alloc_mutex); return; } @@ -515,6 +517,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, struct extent_position epos; int8_t etype = -1; struct udf_inode_info *iinfo; + int ret = 0; if (first_block >= sbi->s_partmaps[partition].s_partition_len) return 0; @@ -533,11 +536,14 @@ static int udf_table_prealloc_blocks(struct super_block *sb, epos.bh = NULL; eloc.logicalBlockNum = 0xFFFFFFFF; - while (first_block != eloc.logicalBlockNum && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (first_block != eloc.logicalBlockNum) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto err_out; + if (ret == 0) + break; udf_debug("eloc=%u, elen=%u, first_block=%u\n", eloc.logicalBlockNum, elen, first_block); - ; /* empty loop body */ } if (first_block == eloc.logicalBlockNum) { @@ -556,6 +562,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb, alloc_count = 0; } +err_out: brelse(epos.bh); if (alloc_count) @@ -577,6 +584,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, struct extent_position epos, goal_epos; int8_t etype; struct udf_inode_info *iinfo = UDF_I(table); + int ret = 0; *err = -ENOSPC; @@ -600,8 +608,10 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, epos.block = iinfo->i_location; epos.bh = goal_epos.bh = NULL; - while (spread && - (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) { + while (spread) { + ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1); + if (ret <= 0) + break; if (goal >= eloc.logicalBlockNum) { if (goal < eloc.logicalBlockNum + (elen >> sb->s_blocksize_bits)) @@ -629,9 +639,11 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, brelse(epos.bh); - if (spread == 0xFFFFFFFF) { + if (ret < 0 || spread == 0xFFFFFFFF) { brelse(goal_epos.bh); mutex_unlock(&sbi->s_alloc_mutex); + if (ret < 0) + *err = ret; return 0; } diff --git a/fs/udf/directory.c b/fs/udf/directory.c index 93153665eb37..632453aa3893 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -166,13 +166,19 @@ static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter) */ static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter) { + int8_t etype = -1; + int err = 0; + iter->loffset++; if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits)) return 0; iter->loffset = 0; - if (udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, 1) - != (EXT_RECORDED_ALLOCATED >> 30)) { + err = udf_next_aext(iter->dir, &iter->epos, &iter->eloc, + &iter->elen, &etype, 1); + if (err < 0) + return err; + else if (err == 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (iter->pos == iter->dir->i_size) { iter->elen = 0; return 0; @@ -240,6 +246,7 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, { struct udf_inode_info *iinfo = UDF_I(dir); int err = 0; + int8_t etype; iter->dir = dir; iter->bh[0] = iter->bh[1] = NULL; @@ -259,9 +266,9 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, goto out; } - if (inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, - &iter->eloc, &iter->elen, &iter->loffset) != - (EXT_RECORDED_ALLOCATED >> 30)) { + err = inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, + &iter->eloc, &iter->elen, &iter->loffset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { if (pos == dir->i_size) return 0; udf_err(dir->i_sb, @@ -457,6 +464,7 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) sector_t block; uint32_t old_elen = iter->elen; int err; + int8_t etype; if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) return -EINVAL; @@ -471,8 +479,9 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) udf_fiiter_update_elen(iter, old_elen); return err; } - if (inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, - &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) { + err = inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, + &iter->loffset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) { udf_err(iter->dir->i_sb, "block %llu not allocated in directory (ino %lu)\n", (unsigned long long)block, iter->dir->i_ino); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8db07d1f56bc..e98c198f85b9 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -408,7 +408,7 @@ struct udf_map_rq { static int udf_map_block(struct inode *inode, struct udf_map_rq *map) { - int err; + int ret; struct udf_inode_info *iinfo = UDF_I(inode); if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) @@ -420,18 +420,24 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map) uint32_t elen; sector_t offset; struct extent_position epos = {}; + int8_t etype; down_read(&iinfo->i_data_sem); - if (inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset) - == (EXT_RECORDED_ALLOCATED >> 30)) { + ret = inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset, + &etype); + if (ret < 0) + goto out_read; + if (ret > 0 && etype == (EXT_RECORDED_ALLOCATED >> 30)) { map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc, offset); map->oflags |= UDF_BLK_MAPPED; + ret = 0; } +out_read: up_read(&iinfo->i_data_sem); brelse(epos.bh); - return 0; + return ret; } down_write(&iinfo->i_data_sem); @@ -442,9 +448,9 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map) if (((loff_t)map->lblk) << inode->i_blkbits >= iinfo->i_lenExtents) udf_discard_prealloc(inode); udf_clear_extent_cache(inode); - err = inode_getblk(inode, map); + ret = inode_getblk(inode, map); up_write(&iinfo->i_data_sem); - return err; + return ret; } static int __udf_get_block(struct inode *inode, sector_t block, @@ -547,6 +553,7 @@ static int udf_do_extend_file(struct inode *inode, } else { struct kernel_lb_addr tmploc; uint32_t tmplen; + int8_t tmptype; udf_write_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); @@ -556,8 +563,12 @@ static int udf_do_extend_file(struct inode *inode, * more extents, we may need to enter possible following * empty indirect extent. */ - if (new_block_bytes) - udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); + if (new_block_bytes) { + err = udf_next_aext(inode, last_pos, &tmploc, &tmplen, + &tmptype, 0); + if (err < 0) + goto out_err; + } } iinfo->i_lenExtents += add; @@ -661,8 +672,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) */ udf_discard_prealloc(inode); - etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); - within_last_ext = (etype != -1); + err = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype); + if (err < 0) + goto out; + within_last_ext = (err == 1); /* We don't expect extents past EOF... */ WARN_ON_ONCE(within_last_ext && elen > ((loff_t)offset + 1) << inode->i_blkbits); @@ -676,8 +689,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) extent.extLength = EXT_NOT_RECORDED_NOT_ALLOCATED; } else { epos.offset -= adsize; - etype = udf_next_aext(inode, &epos, &extent.extLocation, - &extent.extLength, 0); + err = udf_next_aext(inode, &epos, &extent.extLocation, + &extent.extLength, &etype, 0); + if (err <= 0) + goto out; extent.extLength |= etype << 30; } @@ -714,11 +729,11 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) loff_t lbcount = 0, b_off = 0; udf_pblk_t newblocknum; sector_t offset = 0; - int8_t etype; + int8_t etype, tmpetype; struct udf_inode_info *iinfo = UDF_I(inode); udf_pblk_t goal = 0, pgoal = iinfo->i_location.logicalBlockNum; int lastblock = 0; - bool isBeyondEOF; + bool isBeyondEOF = false; int ret = 0; prev_epos.offset = udf_file_entry_alloc_offset(inode); @@ -750,9 +765,13 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) prev_epos.offset = cur_epos.offset; cur_epos.offset = next_epos.offset; - etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 1); - if (etype == -1) + ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 1); + if (ret < 0) { + goto out_free; + } else if (ret == 0) { + isBeyondEOF = true; break; + } c = !c; @@ -773,13 +792,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) * Move prev_epos and cur_epos into indirect extent if we are at * the pointer to it */ - udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, 0); - udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, 0); + ret = udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, &tmpetype, 0); + if (ret < 0) + goto out_free; + ret = udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, &tmpetype, 0); + if (ret < 0) + goto out_free; /* if the extent is allocated and recorded, return the block if the extent is not a multiple of the blocksize, round up */ - if (etype == (EXT_RECORDED_ALLOCATED >> 30)) { + if (!isBeyondEOF && etype == (EXT_RECORDED_ALLOCATED >> 30)) { if (elen & (inode->i_sb->s_blocksize - 1)) { elen = EXT_RECORDED_ALLOCATED | ((elen + inode->i_sb->s_blocksize - 1) & @@ -795,10 +818,9 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) } /* Are we beyond EOF and preallocated extent? */ - if (etype == -1) { + if (isBeyondEOF) { loff_t hole_len; - isBeyondEOF = true; if (count) { if (c) laarr[0] = laarr[1]; @@ -834,7 +856,6 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) endnum = c + 1; lastblock = 1; } else { - isBeyondEOF = false; endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, @@ -848,15 +869,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map) /* if the current block is located in an extent, read the next extent */ - etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 0); - if (etype != -1) { + ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 0); + if (ret > 0) { laarr[c + 1].extLength = (etype << 30) | elen; laarr[c + 1].extLocation = eloc; count++; startnum++; endnum++; - } else + } else if (ret == 0) lastblock = 1; + else + goto out_free; } /* if the current extent is not recorded but allocated, get the @@ -1174,6 +1197,7 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int8_t tmpetype; int err; if (startnum > endnum) { @@ -1191,14 +1215,19 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, */ if (err < 0) return err; - udf_next_aext(inode, epos, &laarr[i].extLocation, - &laarr[i].extLength, 1); + err = udf_next_aext(inode, epos, &laarr[i].extLocation, + &laarr[i].extLength, &tmpetype, 1); + if (err < 0) + return err; start++; } } for (i = start; i < endnum; i++) { - udf_next_aext(inode, epos, &tmploc, &tmplen, 0); + err = udf_next_aext(inode, epos, &tmploc, &tmplen, &tmpetype, 0); + if (err < 0) + return err; + udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } @@ -1953,6 +1982,7 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position nepos; struct kernel_lb_addr neloc; int ver, adsize; + int err = 0; if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -1997,10 +2027,12 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, if (epos->offset + adsize > sb->s_blocksize) { struct kernel_lb_addr cp_loc; uint32_t cp_len; - int cp_type; + int8_t cp_type; epos->offset -= adsize; - cp_type = udf_current_aext(inode, epos, &cp_loc, &cp_len, 0); + err = udf_current_aext(inode, epos, &cp_loc, &cp_len, &cp_type, 0); + if (err <= 0) + goto err_out; cp_len |= ((uint32_t)cp_type) << 30; __udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1); @@ -2015,6 +2047,9 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, *epos = nepos; return 0; +err_out: + brelse(bh); + return err; } /* @@ -2160,21 +2195,30 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, */ #define UDF_MAX_INDIR_EXTS 16 -int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t *elen, int inc) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int udf_next_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, + int inc) { - int8_t etype; unsigned int indirections = 0; + int ret = 0; + udf_pblk_t block; - while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == - (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) { - udf_pblk_t block; + while (1) { + ret = udf_current_aext(inode, epos, eloc, elen, + etype, inc); + if (ret <= 0) + return ret; + if (*etype != (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) + return ret; if (++indirections > UDF_MAX_INDIR_EXTS) { udf_err(inode->i_sb, "too many indirect extents in inode %lu\n", inode->i_ino); - return -1; + return -EFSCORRUPTED; } epos->block = *eloc; @@ -2184,18 +2228,19 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, epos->bh = sb_bread(inode->i_sb, block); if (!epos->bh) { udf_debug("reading block %u failed!\n", block); - return -1; + return -EIO; } } - - return etype; } -int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, - struct kernel_lb_addr *eloc, uint32_t *elen, int inc) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int udf_current_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype, + int inc) { int alen; - int8_t etype; uint8_t *ptr; struct short_ad *sad; struct long_ad *lad; @@ -2210,20 +2255,23 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, alen = udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc; } else { + struct allocExtDesc *header = + (struct allocExtDesc *)epos->bh->b_data; + if (!epos->offset) epos->offset = sizeof(struct allocExtDesc); ptr = epos->bh->b_data + epos->offset; - alen = sizeof(struct allocExtDesc) + - le32_to_cpu(((struct allocExtDesc *)epos->bh->b_data)-> - lengthAllocDescs); + if (check_add_overflow(sizeof(struct allocExtDesc), + le32_to_cpu(header->lengthAllocDescs), &alen)) + return -1; } switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: sad = udf_get_fileshortad(ptr, alen, &epos->offset, inc); if (!sad) - return -1; - etype = le32_to_cpu(sad->extLength) >> 30; + return 0; + *etype = le32_to_cpu(sad->extLength) >> 30; eloc->logicalBlockNum = le32_to_cpu(sad->extPosition); eloc->partitionReferenceNum = iinfo->i_location.partitionReferenceNum; @@ -2232,17 +2280,17 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, case ICBTAG_FLAG_AD_LONG: lad = udf_get_filelongad(ptr, alen, &epos->offset, inc); if (!lad) - return -1; - etype = le32_to_cpu(lad->extLength) >> 30; + return 0; + *etype = le32_to_cpu(lad->extLength) >> 30; *eloc = lelb_to_cpu(lad->extLocation); *elen = le32_to_cpu(lad->extLength) & UDF_EXTENT_LENGTH_MASK; break; default: udf_debug("alloc_type = %u unsupported\n", iinfo->i_alloc_type); - return -1; + return -EINVAL; } - return etype; + return 1; } static int udf_insert_aext(struct inode *inode, struct extent_position epos, @@ -2251,20 +2299,24 @@ static int udf_insert_aext(struct inode *inode, struct extent_position epos, struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; - int err; + int ret; if (epos.bh) get_bh(epos.bh); - while ((etype = udf_next_aext(inode, &epos, &oeloc, &oelen, 0)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &oeloc, &oelen, &etype, 0); + if (ret <= 0) + break; udf_write_aext(inode, &epos, &neloc, nelen, 1); neloc = oeloc; nelen = (etype << 30) | oelen; } - err = udf_add_aext(inode, &epos, &neloc, nelen, 1); + if (ret == 0) + ret = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return err; + return ret; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) @@ -2276,6 +2328,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) struct udf_inode_info *iinfo; struct kernel_lb_addr eloc; uint32_t elen; + int ret; if (epos.bh) { get_bh(epos.bh); @@ -2291,10 +2344,18 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) adsize = 0; oepos = epos; - if (udf_next_aext(inode, &epos, &eloc, &elen, 1) == -1) + if (udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1) <= 0) return -1; - while ((etype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) { + brelse(epos.bh); + brelse(oepos.bh); + return -1; + } + if (ret == 0) + break; udf_write_aext(inode, &oepos, &eloc, (etype << 30) | elen, 1); if (oepos.bh != epos.bh) { oepos.block = epos.block; @@ -2351,14 +2412,17 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) return (elen >> 30); } -int8_t inode_bmap(struct inode *inode, sector_t block, - struct extent_position *pos, struct kernel_lb_addr *eloc, - uint32_t *elen, sector_t *offset) +/* + * Returns 1 on success, -errno on error, 0 on hit EOF. + */ +int inode_bmap(struct inode *inode, sector_t block, struct extent_position *pos, + struct kernel_lb_addr *eloc, uint32_t *elen, sector_t *offset, + int8_t *etype) { unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits; - int8_t etype; struct udf_inode_info *iinfo; + int err = 0; iinfo = UDF_I(inode); if (!udf_read_extent_cache(inode, bcount, &lbcount, pos)) { @@ -2368,11 +2432,13 @@ int8_t inode_bmap(struct inode *inode, sector_t block, } *elen = 0; do { - etype = udf_next_aext(inode, pos, eloc, elen, 1); - if (etype == -1) { - *offset = (bcount - lbcount) >> blocksize_bits; - iinfo->i_lenExtents = lbcount; - return -1; + err = udf_next_aext(inode, pos, eloc, elen, etype, 1); + if (err <= 0) { + if (err == 0) { + *offset = (bcount - lbcount) >> blocksize_bits; + iinfo->i_lenExtents = lbcount; + } + return err; } lbcount += *elen; } while (lbcount <= bcount); @@ -2380,5 +2446,5 @@ int8_t inode_bmap(struct inode *inode, sector_t block, udf_update_extent_cache(inode, lbcount - *elen, pos); *offset = (bcount + *elen - lbcount) >> blocksize_bits; - return etype; + return 1; } diff --git a/fs/udf/partition.c b/fs/udf/partition.c index af877991edc1..2b85c9501bed 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -282,9 +282,11 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block, sector_t ext_offset; struct extent_position epos = {}; uint32_t phyblock; + int8_t etype; + int err = 0; - if (inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset) != - (EXT_RECORDED_ALLOCATED >> 30)) + err = inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset, &etype); + if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) phyblock = 0xFFFFFFFF; else { map = &UDF_SB(sb)->s_partmaps[partition]; diff --git a/fs/udf/super.c b/fs/udf/super.c index 3c78535f406b..20dff9ed2471 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2454,13 +2454,14 @@ static unsigned int udf_count_free_table(struct super_block *sb, uint32_t elen; struct kernel_lb_addr eloc; struct extent_position epos; + int8_t etype; mutex_lock(&UDF_SB(sb)->s_alloc_mutex); epos.block = UDF_I(table)->i_location; epos.offset = sizeof(struct unallocSpaceEntry); epos.bh = NULL; - while (udf_next_aext(table, &epos, &eloc, &elen, 1) != -1) + while (udf_next_aext(table, &epos, &eloc, &elen, &etype, 1) > 0) accum += (elen >> table->i_sb->s_blocksize_bits); brelse(epos.bh); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index a686c10fd709..4f33a4a48886 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -69,6 +69,7 @@ void udf_truncate_tail_extent(struct inode *inode) int8_t etype = -1, netype; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int ret; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || inode->i_size == iinfo->i_lenExtents) @@ -85,7 +86,10 @@ void udf_truncate_tail_extent(struct inode *inode) BUG(); /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &netype, 1); + if (ret <= 0) + break; etype = netype; lbcount += elen; if (lbcount > inode->i_size) { @@ -101,7 +105,8 @@ void udf_truncate_tail_extent(struct inode *inode) epos.offset -= adsize; extent_trunc(inode, &epos, &eloc, etype, elen, nelen); epos.offset += adsize; - if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1) + if (udf_next_aext(inode, &epos, &eloc, &elen, + &netype, 1) > 0) udf_err(inode->i_sb, "Extent after EOF in inode %u\n", (unsigned)inode->i_ino); @@ -110,7 +115,8 @@ void udf_truncate_tail_extent(struct inode *inode) } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ - iinfo->i_lenExtents = inode->i_size; + if (ret == 0) + iinfo->i_lenExtents = inode->i_size; brelse(epos.bh); } @@ -124,6 +130,8 @@ void udf_discard_prealloc(struct inode *inode) int8_t etype = -1; struct udf_inode_info *iinfo = UDF_I(inode); int bsize = i_blocksize(inode); + int8_t tmpetype = -1; + int ret; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize)) @@ -132,15 +140,23 @@ void udf_discard_prealloc(struct inode *inode) epos.block = iinfo->i_location; /* Find the last extent in the file */ - while (udf_next_aext(inode, &epos, &eloc, &elen, 0) != -1) { + while (1) { + ret = udf_next_aext(inode, &epos, &eloc, &elen, &tmpetype, 0); + if (ret < 0) + goto out; + if (ret == 0) + break; brelse(prev_epos.bh); prev_epos = epos; if (prev_epos.bh) get_bh(prev_epos.bh); - etype = udf_next_aext(inode, &epos, &eloc, &elen, 1); + ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1); + if (ret < 0) + goto out; lbcount += elen; } + if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { lbcount -= elen; udf_delete_aext(inode, prev_epos); @@ -150,6 +166,7 @@ void udf_discard_prealloc(struct inode *inode) /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ iinfo->i_lenExtents = lbcount; +out: brelse(epos.bh); brelse(prev_epos.bh); } @@ -188,6 +205,7 @@ int udf_truncate_extents(struct inode *inode) loff_t byte_offset; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int ret = 0; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -196,10 +214,12 @@ int udf_truncate_extents(struct inode *inode) else BUG(); - etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); + ret = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype); + if (ret < 0) + return ret; byte_offset = (offset << sb->s_blocksize_bits) + (inode->i_size & (sb->s_blocksize - 1)); - if (etype == -1) { + if (ret == 0) { /* We should extend the file? */ WARN_ON(byte_offset); return 0; @@ -217,8 +237,8 @@ int udf_truncate_extents(struct inode *inode) else lenalloc -= sizeof(struct allocExtDesc); - while ((etype = udf_current_aext(inode, &epos, &eloc, - &elen, 0)) != -1) { + while ((ret = udf_current_aext(inode, &epos, &eloc, + &elen, &etype, 0)) > 0) { if (etype == (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) { udf_write_aext(inode, &epos, &neloc, nelen, 0); if (indirect_ext_len) { @@ -253,6 +273,11 @@ int udf_truncate_extents(struct inode *inode) } } + if (ret < 0) { + brelse(epos.bh); + return ret; + } + if (indirect_ext_len) { BUG_ON(!epos.bh); udf_free_blocks(sb, NULL, &epos.block, 0, indirect_ext_len); diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 88692512a466..d159f20d61e8 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -157,8 +157,9 @@ extern struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, extern int udf_setsize(struct inode *, loff_t); extern void udf_evict_inode(struct inode *); extern int udf_write_inode(struct inode *, struct writeback_control *wbc); -extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, sector_t *); +extern int inode_bmap(struct inode *inode, sector_t block, + struct extent_position *pos, struct kernel_lb_addr *eloc, + uint32_t *elen, sector_t *offset, int8_t *etype); int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block, struct extent_position *epos); @@ -169,10 +170,12 @@ extern int udf_add_aext(struct inode *, struct extent_position *, extern void udf_write_aext(struct inode *, struct extent_position *, struct kernel_lb_addr *, uint32_t, int); extern int8_t udf_delete_aext(struct inode *, struct extent_position); -extern int8_t udf_next_aext(struct inode *, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, int); -extern int8_t udf_current_aext(struct inode *, struct extent_position *, - struct kernel_lb_addr *, uint32_t *, int); +extern int udf_next_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, + int8_t *etype, int inc); +extern int udf_current_aext(struct inode *inode, struct extent_position *epos, + struct kernel_lb_addr *eloc, uint32_t *elen, + int8_t *etype, int inc); extern void udf_update_extra_perms(struct inode *inode, umode_t mode); /* misc.c */ diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index ec425d2834f8..e1720d930666 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -147,6 +147,8 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern bool cppc_perf_ctrs_in_pcc(void); +extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf); +extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq); extern bool acpi_cpc_valid(void); extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e05cc80e048..5a27fd533fab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -616,6 +616,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -681,6 +682,13 @@ enum bpf_type_flag { */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -738,10 +746,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e4e24da16d2c..b1fdb1554f2f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1080,15 +1080,6 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, local_irq_restore(flags); } -static inline void count_memcg_page_event(struct page *page, - enum vm_event_item idx) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (memcg) - count_memcg_events(memcg, idx, 1); -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { @@ -1565,11 +1556,6 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, { } -static inline void count_memcg_page_event(struct page *page, - int idx) -{ -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8f5ac20b4c03..1576e7443eee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3363,6 +3363,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3479,6 +3485,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, if (likely(dql_avail(&dev_queue->dql) >= 0)) return; + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 26b8a47f41fc..2964171856e0 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -14,10 +14,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func) } enum task_work_notify_mode { - TWA_NONE, + TWA_NONE = 0, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, + TWA_NMI_CURRENT, + + TWA_FLAGS = 0xff00, + TWAF_NO_ALLOC = 0x0100, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index cb8bd759e800..9d799777c333 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -765,7 +765,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -805,7 +806,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -880,6 +881,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e4a6831133f8..4763a47bf8c8 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -403,6 +403,7 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); +bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index c53244f20437..e8c34aa4a640 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -478,13 +478,12 @@ static inline int genlmsg_multicast(const struct genl_family *family, * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array - * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, - unsigned int group, gfp_t flags); + unsigned int group); /** * genlmsg_unicast - unicast a netlink message diff --git a/include/net/sock.h b/include/net/sock.h index c3961050b8e3..e0be8bd98396 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2826,6 +2826,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk) return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b280e7c46011..93a9866ee481 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -342,20 +342,25 @@ struct xfrm_if_cb { void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); +struct xfrm_dst_lookup_params { + struct net *net; + int tos; + int oif; + xfrm_address_t *saddr; + xfrm_address_t *daddr; + u32 mark; + __u8 ipproto; + union flowi_uli uli; +}; + struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; - struct dst_entry *(*dst_lookup)(struct net *net, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark); - int (*get_saddr)(struct net *net, int oif, - xfrm_address_t *saddr, - xfrm_address_t *daddr, - u32 mark); + struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); + int (*get_saddr)(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); @@ -1728,10 +1733,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname, } #endif -struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family, u32 mark); +struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 6e2ef1d4b002..37f2443b3cdb 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -207,10 +207,10 @@ TRACE_EVENT(mm_khugepaged_scan_file, ); TRACE_EVENT(mm_khugepaged_collapse_file, - TP_PROTO(struct mm_struct *mm, struct page *hpage, pgoff_t index, - bool is_shmem, unsigned long addr, struct file *file, + TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, + unsigned long addr, bool is_shmem, struct file *file, int nr, int result), - TP_ARGS(mm, hpage, index, addr, is_shmem, file, nr, result), + TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(unsigned long, hpfn) @@ -224,7 +224,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, TP_fast_assign( __entry->mm = mm; - __entry->hpfn = hpage ? page_to_pfn(hpage) : -1; + __entry->hpfn = new_folio ? folio_pfn(new_folio) : -1; __entry->index = index; __entry->addr = addr; __entry->is_shmem = is_shmem; @@ -233,7 +233,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, __entry->result = result; ), - TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s", + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%lx, is_shmem=%d, filename=%s, nr=%d, result=%s", __entry->mm, __entry->hpfn, __entry->index, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba6e346c8d66..431bc700bcfb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5921,11 +5921,6 @@ enum { BPF_F_MARK_ENFORCE = (1ULL << 6), }; -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), -}; - /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ enum { BPF_F_TUNINFO_IPV6 = (1ULL << 0), @@ -6072,10 +6067,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ @@ -6559,20 +6556,27 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e0e4d4f490e8..c8828016a66f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8435,6 +8435,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, if (!type) { bpf_log(ctx->log, "relo #%u: bad type id %u\n", relo_idx, relo->type_id); + kfree(specs); return -EINVAL; } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 69e78dc4bb18..96b0345f76c2 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -322,9 +322,11 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, - struct net_device *dev) + struct net_device *tx_dev, + struct net_device *rx_dev) { - struct xdp_txq_info txq = { .dev = dev }; + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; @@ -335,6 +337,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; + xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { @@ -349,7 +352,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); + trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); @@ -377,7 +380,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) } if (bq->xdp_prog) { - to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3dba5bb294d8..41d62405c852 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -110,7 +110,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -123,7 +123,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) @@ -538,7 +538,7 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(s64), }; @@ -568,7 +568,7 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; @@ -1607,7 +1607,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 238d9b206bbd..246559c3e93d 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -632,7 +632,7 @@ const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b1933d074f05..8a1cadc1ff9d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3442,26 +3442,34 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) } static int bpf_perf_link_fill_common(const struct perf_event *event, - char __user *uname, u32 ulen, + char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, - u32 *fd_type) + u32 *fd_type, unsigned long *missed) { const char *buf; - u32 prog_id; + u32 prog_id, ulen; size_t len; int err; + ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, - probe_offset, probe_addr); + probe_offset, probe_addr, missed); if (err) return err; + + if (buf) { + len = strlen(buf); + *ulenp = len + 1; + } else { + *ulenp = 1; + } if (!uname) return 0; + if (buf) { - len = strlen(buf); err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; @@ -3478,6 +3486,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { + unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; @@ -3485,19 +3494,21 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; - err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, + &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; - + info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; + info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; + info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3513,8 +3524,8 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; - err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, + &type, NULL); if (err) return err; @@ -3522,7 +3533,9 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; + info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; + info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3546,11 +3559,18 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, { char __user *uname; u32 ulen; + int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; + err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); + if (err) + return err; + info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; - return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL); + info->perf_event.tracepoint.name_len = ulen; + info->perf_event.tracepoint.cookie = event->bpf_cookie; + return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, @@ -3558,6 +3578,7 @@ static int bpf_perf_link_fill_perf_event(const struct perf_event *event, { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; + info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } @@ -4897,7 +4918,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, - &probe_addr); + &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, @@ -5668,7 +5689,7 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index c4ab9d6cdbe9..f7ef58090c7d 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -119,7 +119,7 @@ static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *co rcu_read_lock(); pid = find_pid_ns(common->pid, common->ns); if (pid) { - task = get_pid_task(pid, PIDTYPE_TGID); + task = get_pid_task(pid, PIDTYPE_PID); *tid = common->pid; } rcu_read_unlock(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3032a464d31b..03b5797b8fca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2799,10 +2799,16 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, b->module = mod; b->offset = offset; + /* sort() reorders entries by value, so b may no longer point + * to the right entry after this + */ sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); + } else { + btf = b->btf; } - return b->btf; + + return btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) @@ -6137,10 +6143,10 @@ static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) /* both of s64_max/s64_min positive or negative */ if ((s64_max >= 0) == (s64_min >= 0)) { - reg->smin_value = reg->s32_min_value = s64_min; - reg->smax_value = reg->s32_max_value = s64_max; - reg->umin_value = reg->u32_min_value = s64_min; - reg->umax_value = reg->u32_max_value = s64_max; + reg->s32_min_value = reg->smin_value = s64_min; + reg->s32_max_value = reg->smax_value = s64_max; + reg->u32_min_value = reg->umin_value = s64_min; + reg->u32_max_value = reg->umax_value = s64_max; reg->var_off = tnum_range(s64_min, s64_max); return; } @@ -7192,7 +7198,8 @@ mark: } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, - int access_size, bool zero_size_allowed, + int access_size, enum bpf_access_type access_type, + bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; @@ -7204,7 +7211,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7212,15 +7219,13 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: - if (check_map_access_type(env, regno, reg->off, access_size, - meta && meta->raw_mode ? BPF_WRITE : - BPF_READ)) + if (check_map_access_type(env, regno, reg->off, access_size, access_type)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7231,7 +7236,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7259,7 +7264,6 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { - enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ @@ -7267,7 +7271,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, - atype, -1, false, false); + access_type, -1, false, false); } fallthrough; @@ -7286,6 +7290,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, + enum bpf_access_type access_type, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { @@ -7301,15 +7306,12 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, */ meta->msize_max_value = reg->umax_value; - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. + /* The register is SCALAR_VALUE; the access check happens using + * its boundaries. For unprivileged variable accesses, disable + * raw mode so that the program is required to initialize all + * the memory that the helper could just partially fill up. */ if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ meta = NULL; if (reg->smin_value < 0) { @@ -7318,12 +7320,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, return -EACCES; } - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; + if (reg->umin_value == 0 && !zero_size_allowed) { + verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n", + regno, reg->umin_value, reg->umax_value); + return -EACCES; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { @@ -7331,9 +7331,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, regno); return -EACCES; } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); + err = check_helper_mem_access(env, regno - 1, reg->umax_value, + access_type, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; @@ -7344,13 +7343,11 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; - struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; - memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -7360,10 +7357,8 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, mark_ptr_not_null_reg(reg); } - err = check_helper_mem_access(env, regno, mem_size, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + err = check_helper_mem_access(env, regno, mem_size, BPF_READ, true, NULL); + err = err ?: check_helper_mem_access(env, regno, mem_size, BPF_WRITE, true, NULL); if (may_be_null) *reg = saved_reg; @@ -7389,13 +7384,12 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); + err = check_mem_size_reg(env, reg, regno, BPF_READ, true, &meta); + err = err ?: check_mem_size_reg(env, reg, regno, BPF_WRITE, true, &meta); if (may_be_null) *mem_reg = saved_reg; + return err; } @@ -8581,9 +8575,8 @@ skip_type_check: verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_helper_mem_access(env, regno, - meta->map_ptr->key_size, false, - NULL); + err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, + BPF_READ, false, NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) @@ -8598,9 +8591,9 @@ skip_type_check: return -EACCES; } meta->raw_mode = arg_type & MEM_UNINIT; - err = check_helper_mem_access(env, regno, - meta->map_ptr->value_size, false, - meta); + err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { @@ -8642,7 +8635,9 @@ skip_type_check: */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { - err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); + err = check_helper_mem_access(env, regno, fn->arg_size[arg], + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); if (err) return err; if (arg_type & MEM_ALIGNED) @@ -8650,10 +8645,16 @@ skip_type_check: } break; case ARG_CONST_SIZE: - err = check_mem_size_reg(env, reg, regno, false, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + false, meta); break; case ARG_CONST_SIZE_OR_ZERO: - err = check_mem_size_reg(env, reg, regno, true, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + true, meta); break; case ARG_PTR_TO_DYNPTR: err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9b406d988654..b6f922a20f83 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -12050,7 +12050,9 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) return; if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan))) return; - task_work_add(curr, work, TWA_RESUME); + + /* No page allocation under rq lock */ + task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC); } void sched_mm_cid_exit_signals(struct task_struct *t) diff --git a/kernel/task_work.c b/kernel/task_work.c index 2134ac8057a9..c969f1f26be5 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -1,10 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/irq_work.h> #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ +#ifdef CONFIG_IRQ_WORK +static void task_work_set_notify_irq(struct irq_work *entry) +{ + test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); +} +static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = + IRQ_WORK_INIT_HARD(task_work_set_notify_irq); +#endif + /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback @@ -12,7 +22,7 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify - * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. + * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT. * * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted * task and run the task_work, regardless of whether the task is currently @@ -24,6 +34,8 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * kernel anyway. * @TWA_RESUME work is run only when the task exits the kernel and returns to * user mode, or before entering guest mode. + * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the + * current @task and if the current context is NMI. * * Fails if the @task is exiting/exited and thus it can't process this @work. * Otherwise @work->func() will be called when the @task goes through one of @@ -43,9 +55,27 @@ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; - - /* record the work call stack in order to print it in KASAN reports */ - kasan_record_aux_stack(work); + int flags = notify & TWA_FLAGS; + + notify &= ~TWA_FLAGS; + if (notify == TWA_NMI_CURRENT) { + if (WARN_ON_ONCE(task != current)) + return -EINVAL; + if (!IS_ENABLED(CONFIG_IRQ_WORK)) + return -EINVAL; + } else { + /* + * Record the work call stack in order to print it in KASAN + * reports. + * + * Note that stack allocation can fail if TWAF_NO_ALLOC flag + * is set and new page is needed to expand the stack buffer. + */ + if (flags & TWAF_NO_ALLOC) + kasan_record_aux_stack_noalloc(work); + else + kasan_record_aux_stack(work); + } head = READ_ONCE(task->task_works); do { @@ -66,6 +96,11 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; +#ifdef CONFIG_IRQ_WORK + case TWA_NMI_CURRENT: + irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); + break; +#endif default: WARN_ON_ONCE(1); break; diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 8127673bfc45..05e73d209aa8 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -290,6 +290,9 @@ static int pc_clock_settime(clockid_t id, const struct timespec64 *ts) struct posix_clock_desc cd; int err; + if (!timespec64_valid_strict(ts)) + return -EINVAL; + err = get_clock_desc(id, &cd); if (err) return err; @@ -299,9 +302,6 @@ static int pc_clock_settime(clockid_t id, const struct timespec64 *ts) goto out; } - if (!timespec64_valid_strict(ts)) - return -EINVAL; - if (cd.clk->ops.clock_settime) err = cd.clk->ops.clock_settime(cd.clk, ts); else diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index eca858bde804..9064f75de7e4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1220,7 +1220,7 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u64), }; @@ -1237,7 +1237,7 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg2_size = sizeof(u64), }; @@ -2217,8 +2217,6 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); - if (ret == -ENOENT) - goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { @@ -2389,7 +2387,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr) + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; @@ -2424,7 +2423,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, - probe_offset, probe_addr, + probe_offset, probe_addr, missed, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4f93d57cc029..ecd869ed2767 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5757,6 +5757,7 @@ static const char readme_msg[] = "\t $stack<index>, $stack, $retval, $comm,\n" #endif "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" + "\t kernel return probes support: $retval, $arg<N>, $comm\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t symstr, <type>\\[<array-size>\\]\n" diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 72714cbf475c..31bb977670bd 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -220,7 +220,7 @@ static struct trace_eprobe *alloc_event_probe(const char *group, if (!ep->event_system) goto error; - ret = trace_probe_init(&ep->tp, this_event, group, false); + ret = trace_probe_init(&ep->tp, this_event, group, false, nargs); if (ret < 0) goto error; @@ -390,8 +390,8 @@ static int get_eprobe_size(struct trace_probe *tp, void *rec) /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { unsigned long val; int ret; @@ -438,7 +438,7 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) return; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); - store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize); + store_trace_args(&entry[1], &edata->ep->tp, rec, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -915,6 +915,11 @@ static int __trace_eprobe_create(int argc, const char *argv[]) } } + if (argc - 2 > MAX_TRACE_ARGS) { + ret = -E2BIG; + goto error; + } + mutex_lock(&event_mutex); event_call = find_and_get_event(sys_name, sys_event); ep = alloc_event_probe(group, event, event_call, argc - 2); @@ -940,7 +945,7 @@ static int __trace_eprobe_create(int argc, const char *argv[]) argc -= 2; argv += 2; /* parse arguments */ - for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); ret = trace_eprobe_tp_update_arg(ep, argv, i); if (ret) diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 7d2ddbcfa377..f26bb8a90cb5 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -4,6 +4,7 @@ * Copyright (C) 2022 Google LLC. */ #define pr_fmt(fmt) "trace_fprobe: " fmt +#include <asm/ptrace.h> #include <linux/fprobe.h> #include <linux/module.h> @@ -129,8 +130,8 @@ static bool trace_fprobe_is_registered(struct trace_fprobe *tf) * from user space. */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -152,6 +153,9 @@ retry: case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); break; + case FETCH_OP_EDATA: + val = *(unsigned long *)((unsigned long)edata + code->offset); + break; #endif case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; @@ -184,7 +188,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); @@ -194,7 +198,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, fbuffer.regs = regs; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -210,11 +214,24 @@ fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, } NOKPROBE_SYMBOL(fentry_trace_func); -/* Kretprobe handler */ +/* function exit handler */ +static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data) +{ + struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + + if (tf->tp.entry_arg) + store_trace_entry_data(entry_data, &tf->tp, regs); + + return 0; +} +NOKPROBE_SYMBOL(trace_fprobe_entry_handler) + static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, - struct trace_event_file *trace_file) + void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; struct trace_event_buffer fbuffer; @@ -227,7 +244,7 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); @@ -238,19 +255,19 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs) + unsigned long ret_ip, struct pt_regs *regs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); @@ -269,7 +286,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -280,7 +297,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -289,7 +306,8 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs) + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; @@ -301,7 +319,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -312,7 +330,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -343,10 +361,10 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs); + fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs); + fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); @@ -389,7 +407,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->fp.nr_maxactive = maxactive; - ret = trace_probe_init(&tf->tp, event, group, false); + ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) goto error; @@ -1085,6 +1103,10 @@ static int __trace_fprobe_create(int argc, const char *argv[]) argc = new_argc; argv = new_argv; } + if (argc > MAX_TRACE_ARGS) { + ret = -E2BIG; + goto out; + } /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive, @@ -1101,7 +1123,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) (unsigned long)tf->tpoint->probestub); /* parse arguments */ - for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); ctx.offset = 0; ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx); @@ -1109,6 +1131,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) goto error; /* This can be -ENOMEM */ } + if (is_return && tf->tp.entry_arg) { + tf->fp.entry_handler = trace_fprobe_entry_handler; + tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp); + } + ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 47812aa16bb5..12d997bb3e78 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group, false); + ret = trace_probe_init(&tk->tp, event, group, false, nargs); if (ret < 0) goto error; @@ -740,6 +740,9 @@ static unsigned int number_of_same_symbols(char *func_name) return ctx.count; } +static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, + struct pt_regs *regs); + static int __trace_kprobe_create(int argc, const char *argv[]) { /* @@ -929,6 +932,10 @@ static int __trace_kprobe_create(int argc, const char *argv[]) argc = new_argc; argv = new_argv; } + if (argc > MAX_TRACE_ARGS) { + ret = -E2BIG; + goto out; + } /* setup a probe */ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, @@ -941,13 +948,18 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } /* parse arguments */ - for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); ctx.offset = 0; ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx); if (ret) goto error; /* This can be -ENOMEM */ } + /* entry handler for kretprobe */ + if (is_return && tk->tp.entry_arg) { + tk->rp.entry_handler = trace_kprobe_entry_handler; + tk->rp.data_size = traceprobe_get_entry_data_size(&tk->tp); + } ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tk->tp, ptype); @@ -1249,6 +1261,12 @@ static const struct file_operations kprobe_events_ops = { .write = probes_write, }; +static unsigned long trace_kprobe_missed(struct trace_kprobe *tk) +{ + return trace_kprobe_is_return(tk) ? + tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; +} + /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { @@ -1260,8 +1278,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) return 0; tk = to_trace_kprobe(ev); - nmissed = trace_kprobe_is_return(tk) ? - tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; + nmissed = trace_kprobe_missed(tk); seq_printf(m, " %-44s %15lu %15lu\n", trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), @@ -1298,8 +1315,8 @@ static const struct file_operations kprobe_profile_ops = { /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -1324,6 +1341,9 @@ retry: case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); break; + case FETCH_OP_EDATA: + val = *(unsigned long *)((unsigned long)edata + code->offset); + break; #endif case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; @@ -1354,7 +1374,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tk->tp.size + dsize); @@ -1363,7 +1383,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, fbuffer.regs = regs; entry->ip = (unsigned long)tk->rp.kp.addr; - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -1379,6 +1399,31 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) NOKPROBE_SYMBOL(kprobe_trace_func); /* Kretprobe handler */ + +static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct kretprobe *rp = get_kretprobe(ri); + struct trace_kprobe *tk; + + /* + * There is a small chance that get_kretprobe(ri) returns NULL when + * the kretprobe is unregister on another CPU between kretprobe's + * trampoline_handler and this function. + */ + if (unlikely(!rp)) + return -ENOENT; + + tk = container_of(rp, struct trace_kprobe, rp); + + /* store argument values into ri->data as entry data */ + if (tk->tp.entry_arg) + store_trace_entry_data(ri->data, &tk->tp, regs); + + return 0; +} + + static nokprobe_inline void __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs, @@ -1394,7 +1439,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, ri->data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tk->tp.size + dsize); @@ -1404,7 +1449,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, fbuffer.regs = regs; entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = get_kretprobe_retaddr(ri); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -1552,7 +1597,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, NULL); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -1563,7 +1608,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -1588,7 +1633,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (hlist_empty(head)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, ri->data); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -1599,7 +1644,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = get_kretprobe_retaddr(ri); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -1607,7 +1652,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func); int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, - u64 *probe_addr, bool perf_type_tracepoint) + u64 *probe_addr, unsigned long *missed, + bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1626,6 +1672,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, *probe_addr = kallsyms_show_value(current_cred()) ? (unsigned long)tk->rp.kp.addr : 0; *symbol = tk->symbol; + if (missed) + *missed = trace_kprobe_missed(tk); return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index ae162ba36a48..8c73156a7eb9 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -275,7 +275,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup, } trace_probe_log_err(offset, NO_EVENT_NAME); return -EINVAL; - } else if (len > MAX_EVENT_NAME_LEN) { + } else if (len >= MAX_EVENT_NAME_LEN) { trace_probe_log_err(offset, EVENT_TOO_LONG); return -EINVAL; } @@ -598,6 +598,8 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, return 0; } +static int __store_entry_arg(struct trace_probe *tp, int argnum); + static int parse_btf_arg(char *varname, struct fetch_insn **pcode, struct fetch_insn *end, struct traceprobe_parse_context *ctx) @@ -622,11 +624,7 @@ static int parse_btf_arg(char *varname, return -EOPNOTSUPP; } - if (ctx->flags & TPARG_FL_RETURN) { - if (strcmp(varname, "$retval") != 0) { - trace_probe_log_err(ctx->offset, NO_BTFARG); - return -ENOENT; - } + if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) { code->op = FETCH_OP_RETVAL; /* Check whether the function return type is not void */ if (query_btf_context(ctx) == 0) { @@ -658,11 +656,21 @@ static int parse_btf_arg(char *varname, const char *name = btf_name_by_offset(ctx->btf, params[i].name_off); if (name && !strcmp(name, varname)) { - code->op = FETCH_OP_ARG; - if (ctx->flags & TPARG_FL_TPOINT) - code->param = i + 1; - else - code->param = i; + if (tparg_is_function_entry(ctx->flags)) { + code->op = FETCH_OP_ARG; + if (ctx->flags & TPARG_FL_TPOINT) + code->param = i + 1; + else + code->param = i; + } else if (tparg_is_function_return(ctx->flags)) { + code->op = FETCH_OP_EDATA; + ret = __store_entry_arg(ctx->tp, i); + if (ret < 0) { + /* internal error */ + return ret; + } + code->offset = ret; + } tid = params[i].type; goto found; } @@ -759,6 +767,110 @@ static int check_prepare_btf_string_fetch(char *typename, #endif +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + +static int __store_entry_arg(struct trace_probe *tp, int argnum) +{ + struct probe_entry_arg *earg = tp->entry_arg; + bool match = false; + int i, offset; + + if (!earg) { + earg = kzalloc(sizeof(*tp->entry_arg), GFP_KERNEL); + if (!earg) + return -ENOMEM; + earg->size = 2 * tp->nr_args + 1; + earg->code = kcalloc(earg->size, sizeof(struct fetch_insn), + GFP_KERNEL); + if (!earg->code) { + kfree(earg); + return -ENOMEM; + } + /* Fill the code buffer with 'end' to simplify it */ + for (i = 0; i < earg->size; i++) + earg->code[i].op = FETCH_OP_END; + tp->entry_arg = earg; + } + + offset = 0; + for (i = 0; i < earg->size - 1; i++) { + switch (earg->code[i].op) { + case FETCH_OP_END: + earg->code[i].op = FETCH_OP_ARG; + earg->code[i].param = argnum; + earg->code[i + 1].op = FETCH_OP_ST_EDATA; + earg->code[i + 1].offset = offset; + return offset; + case FETCH_OP_ARG: + match = (earg->code[i].param == argnum); + break; + case FETCH_OP_ST_EDATA: + offset = earg->code[i].offset; + if (match) + return offset; + offset += sizeof(unsigned long); + break; + default: + break; + } + } + return -ENOSPC; +} + +int traceprobe_get_entry_data_size(struct trace_probe *tp) +{ + struct probe_entry_arg *earg = tp->entry_arg; + int i, size = 0; + + if (!earg) + return 0; + + for (i = 0; i < earg->size; i++) { + switch (earg->code[i].op) { + case FETCH_OP_END: + goto out; + case FETCH_OP_ST_EDATA: + size = earg->code[i].offset + sizeof(unsigned long); + break; + default: + break; + } + } +out: + return size; +} + +void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val = 0; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = regs_get_kernel_argument(regs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} +NOKPROBE_SYMBOL(store_trace_entry_data) +#endif + #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) /* Parse $vars. @orig_arg points '$', which syncs to @ctx->offset */ @@ -834,7 +946,7 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t, #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API len = str_has_prefix(arg, "arg"); - if (len && tparg_is_function_entry(ctx->flags)) { + if (len) { ret = kstrtoul(arg + len, 10, ¶m); if (ret) goto inval; @@ -843,15 +955,29 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t, err = TP_ERR_BAD_ARG_NUM; goto inval; } + param--; /* argN starts from 1, but internal arg[N] starts from 0 */ - code->op = FETCH_OP_ARG; - code->param = (unsigned int)param - 1; - /* - * The tracepoint probe will probe a stub function, and the - * first parameter of the stub is a dummy and should be ignored. - */ - if (ctx->flags & TPARG_FL_TPOINT) - code->param++; + if (tparg_is_function_entry(ctx->flags)) { + code->op = FETCH_OP_ARG; + code->param = (unsigned int)param; + /* + * The tracepoint probe will probe a stub function, and the + * first parameter of the stub is a dummy and should be ignored. + */ + if (ctx->flags & TPARG_FL_TPOINT) + code->param++; + } else if (tparg_is_function_return(ctx->flags)) { + /* function entry argument access from return probe */ + ret = __store_entry_arg(ctx->tp, param); + if (ret < 0) /* This error should be an internal error */ + return ret; + + code->op = FETCH_OP_EDATA; + code->offset = ret; + } else { + err = TP_ERR_NOFENTRY_ARGS; + goto inval; + } return 0; } #endif @@ -1041,7 +1167,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type, break; default: if (isalpha(arg[0]) || arg[0] == '_') { /* BTF variable */ - if (!tparg_is_function_entry(ctx->flags)) { + if (!tparg_is_function_entry(ctx->flags) && + !tparg_is_function_return(ctx->flags)) { trace_probe_log_err(ctx->offset, NOSUP_BTFARG); return -EINVAL; } @@ -1383,9 +1510,7 @@ int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg, struct probe_arg *parg = &tp->args[i]; const char *body; - /* Increment count for freeing args in error case */ - tp->nr_args++; - + ctx->tp = tp; body = strchr(arg, '='); if (body) { if (body - arg > MAX_ARG_NAME_LEN) { @@ -1442,7 +1567,8 @@ static int argv_has_var_arg(int argc, const char *argv[], int *args_idx, if (str_has_prefix(argv[i], "$arg")) { trace_probe_log_set_index(i + 2); - if (!tparg_is_function_entry(ctx->flags)) { + if (!tparg_is_function_entry(ctx->flags) && + !tparg_is_function_return(ctx->flags)) { trace_probe_log_err(0, NOFENTRY_ARGS); return -EINVAL; } @@ -1765,12 +1891,18 @@ void trace_probe_cleanup(struct trace_probe *tp) for (i = 0; i < tp->nr_args; i++) traceprobe_free_probe_arg(&tp->args[i]); + if (tp->entry_arg) { + kfree(tp->entry_arg->code); + kfree(tp->entry_arg); + tp->entry_arg = NULL; + } + if (tp->event) trace_probe_unlink(tp); } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group, bool alloc_filter) + const char *group, bool alloc_filter, int nargs) { struct trace_event_call *call; size_t size = sizeof(struct trace_probe_event); @@ -1806,6 +1938,11 @@ int trace_probe_init(struct trace_probe *tp, const char *event, goto error; } + tp->nr_args = nargs; + /* Make sure pointers in args[] are NULL */ + if (nargs) + memset(tp->args, 0, sizeof(tp->args[0]) * nargs); + return 0; error: diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index c1877d018269..cef3a50628a3 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -92,6 +92,7 @@ enum fetch_op { FETCH_OP_ARG, /* Function argument : .param */ FETCH_OP_FOFFS, /* File offset: .immediate */ FETCH_OP_DATA, /* Allocated data: .data */ + FETCH_OP_EDATA, /* Entry data: .offset */ // Stage 2 (dereference) op FETCH_OP_DEREF, /* Dereference: .offset */ FETCH_OP_UDEREF, /* User-space Dereference: .offset */ @@ -102,6 +103,7 @@ enum fetch_op { FETCH_OP_ST_STRING, /* String: .offset, .size */ FETCH_OP_ST_USTRING, /* User String: .offset, .size */ FETCH_OP_ST_SYMSTR, /* Kernel Symbol String: .offset, .size */ + FETCH_OP_ST_EDATA, /* Store Entry Data: .offset */ // Stage 4 (modify) op FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */ // Stage 5 (loop) op @@ -232,6 +234,11 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct probe_entry_arg { + struct fetch_insn *code; + unsigned int size; /* The entry data size */ +}; + struct trace_uprobe_filter { rwlock_t rwlock; int nr_systemwide; @@ -253,6 +260,7 @@ struct trace_probe { struct trace_probe_event *event; ssize_t size; /* trace entry size */ unsigned int nr_args; + struct probe_entry_arg *entry_arg; /* This is only for return probe */ struct probe_arg args[]; }; @@ -338,7 +346,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group, bool alloc_filter); + const char *group, bool alloc_filter, int nargs); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); @@ -355,6 +363,18 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, u8 *data, void *field); +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API +int traceprobe_get_entry_data_size(struct trace_probe *tp); +/* This is a runtime function to store entry data */ +void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs); +#else /* !CONFIG_HAVE_FUNCTION_ARG_ACCESS_API */ +static inline int traceprobe_get_entry_data_size(struct trace_probe *tp) +{ + return 0; +} +#define store_trace_entry_data(edata, tp, regs) do { } while (0) +#endif + #define trace_probe_for_each_link(pos, tp) \ list_for_each_entry(pos, &(tp)->event->files, list) #define trace_probe_for_each_link_rcu(pos, tp) \ @@ -381,6 +401,11 @@ static inline bool tparg_is_function_entry(unsigned int flags) return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_FENTRY); } +static inline bool tparg_is_function_return(unsigned int flags) +{ + return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_RETURN); +} + struct traceprobe_parse_context { struct trace_event_call *event; /* BTF related parameters */ @@ -392,6 +417,7 @@ struct traceprobe_parse_context { const struct btf_type *last_type; /* Saved type */ u32 last_bitoffs; /* Saved bitoffs */ u32 last_bitsize; /* Saved bitsize */ + struct trace_probe *tp; unsigned int flags; int offset; }; @@ -506,7 +532,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NO_BTFARG, "This variable is not found at this probe point"),\ C(NO_BTF_ENTRY, "No BTF entry for this probe point"), \ C(BAD_VAR_ARGS, "$arg* must be an independent parameter without name etc."),\ - C(NOFENTRY_ARGS, "$arg* can be used only on function entry"), \ + C(NOFENTRY_ARGS, "$arg* can be used only on function entry or exit"), \ C(DOUBLE_ARGS, "$arg* can be used only once in the parameters"), \ C(ARGS_2LONG, "$arg* failed because the argument list is too long"), \ C(ARGIDX_2BIG, "$argN index is too big"), \ diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 3935b347f874..2caf0d2afb32 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -54,7 +54,7 @@ fetch_apply_bitfield(struct fetch_insn *code, void *buf) * If dest is NULL, don't store result and return required dynamic data size. */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base); static nokprobe_inline int fetch_store_strlen(unsigned long addr); static nokprobe_inline int @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs) +__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; @@ -240,7 +240,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs) for (i = 0; i < tp->nr_args; i++) { arg = tp->args + i; if (unlikely(arg->dynamic)) { - len = process_fetch_insn(arg->code, regs, NULL, NULL); + len = process_fetch_insn(arg->code, regs, edata, NULL, NULL); if (len > 0) ret += len; } @@ -251,7 +251,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs) /* Store the value of each argument */ static nokprobe_inline void -store_trace_args(void *data, struct trace_probe *tp, void *rec, +store_trace_args(void *data, struct trace_probe *tp, void *rec, void *edata, int header_size, int maxlen) { struct probe_arg *arg; @@ -266,7 +266,7 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec, /* Point the dynamic data area if needed */ if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); - ret = process_fetch_insn(arg->code, rec, dl, base); + ret = process_fetch_insn(arg->code, rec, edata, dl, base); if (arg->dynamic && likely(ret > 0)) { dyndata += ret; maxlen -= ret; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 99c051de412a..3e7d92d2650b 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -211,8 +211,8 @@ static unsigned long translate_user_vaddr(unsigned long file_offset) /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -337,7 +337,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group, true); + ret = trace_probe_init(&tu->tp, event, group, true, nargs); if (ret < 0) goto error; @@ -556,6 +556,8 @@ static int __trace_uprobe_create(int argc, const char **argv) if (argc < 2) return -ECANCELED; + if (argc - 2 > MAX_TRACE_ARGS) + return -E2BIG; if (argv[0][1] == ':') event = &argv[0][2]; @@ -681,7 +683,7 @@ static int __trace_uprobe_create(int argc, const char **argv) tu->filename = filename; /* parse arguments */ - for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + for (i = 0; i < argc; i++) { struct traceprobe_parse_context ctx = { .flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER, }; @@ -854,9 +856,11 @@ static const struct file_operations uprobe_profile_ops = { struct uprobe_cpu_buffer { struct mutex mutex; void *buf; + int dsize; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; +#define MAX_UCB_BUFFER_SIZE PAGE_SIZE static int uprobe_buffer_init(void) { @@ -940,12 +944,41 @@ static struct uprobe_cpu_buffer *uprobe_buffer_get(void) static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) { + if (!ucb) + return; mutex_unlock(&ucb->mutex); } +static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, + struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) +{ + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + if (*ucbp) + return *ucbp; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + dsize = __get_data_size(&tu->tp, regs, NULL); + + ucb = uprobe_buffer_get(); + ucb->dsize = tu->tp.size + dsize; + + if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) { + ucb->dsize = MAX_UCB_BUFFER_SIZE; + dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size; + } + + store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); + + *ucbp = ucb; + return ucb; +} + static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize, + struct uprobe_cpu_buffer *ucb, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; @@ -956,14 +989,11 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, WARN_ON(call != trace_file->event_call); - if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) - return; - if (trace_trigger_soft_disabled(trace_file)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = esize + tu->tp.size + dsize; + size = esize + ucb->dsize; entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); if (!entry) return; @@ -977,23 +1007,26 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - memcpy(data, ucb->buf, tu->tp.size + dsize); + memcpy(data, ucb->buf, ucb->dsize); trace_event_buffer_commit(&fbuffer); } /* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; if (is_ret_probe(tu)) return 0; + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, 0, regs, ucb, link->file); rcu_read_unlock(); return 0; @@ -1001,13 +1034,16 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; + + ucb = prepare_uprobe_buffer(tu, regs, ucbp); rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + __uprobe_trace_func(tu, func, regs, ucb, link->file); rcu_read_unlock(); } @@ -1335,10 +1371,11 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc, static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; + struct uprobe_cpu_buffer *ucb; struct hlist_head *head; void *data; int size, esize; @@ -1356,7 +1393,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = esize + tu->tp.size + dsize; + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + size = esize + ucb->dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; @@ -1379,13 +1417,10 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - memcpy(data, ucb->buf, tu->tp.size + dsize); - - if (size - esize > tu->tp.size + dsize) { - int len = tu->tp.size + dsize; + memcpy(data, ucb->buf, ucb->dsize); - memset(data + len, 0, size - esize - len); - } + if (size - esize > ucb->dsize) + memset(data + ucb->dsize, 0, size - esize - ucb->dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); @@ -1395,21 +1430,21 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, /* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) - __uprobe_perf_func(tu, 0, regs, ucb, dsize); + __uprobe_perf_func(tu, 0, regs, ucbp); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer *ucb, int dsize) + struct uprobe_cpu_buffer **ucbp) { - __uprobe_perf_func(tu, func, regs, ucb, dsize); + __uprobe_perf_func(tu, func, regs, ucbp); } int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, @@ -1474,11 +1509,9 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; - struct uprobe_cpu_buffer *ucb; - int dsize, esize; + struct uprobe_cpu_buffer *ucb = NULL; int ret = 0; - tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; @@ -1490,18 +1523,12 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); - if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - ret |= uprobe_trace_func(tu, regs, ucb, dsize); + ret |= uprobe_trace_func(tu, regs, &ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - ret |= uprobe_perf_func(tu, regs, ucb, dsize); + ret |= uprobe_perf_func(tu, regs, &ucb); #endif uprobe_buffer_put(ucb); return ret; @@ -1512,8 +1539,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; - struct uprobe_cpu_buffer *ucb; - int dsize, esize; + struct uprobe_cpu_buffer *ucb = NULL; tu = container_of(con, struct trace_uprobe, consumer); @@ -1525,18 +1551,12 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs); - esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - - ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); - if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) - uretprobe_trace_func(tu, func, regs, ucb, dsize); + uretprobe_trace_func(tu, func, regs, &ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) - uretprobe_perf_func(tu, func, regs, ucb, dsize); + uretprobe_perf_func(tu, func, regs, &ucb); #endif uprobe_buffer_put(ucb); return 0; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index da5513cfc125..f94c3e957b82 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2999,7 +2999,7 @@ config RUST_BUILD_ASSERT_ALLOW bool "Allow unoptimized build-time assertions" depends on RUST help - Controls how are `build_error!` and `build_assert!` handled during build. + Controls how `build_error!` and `build_assert!` are handled during the build. If calls to them exist in the binary, it may indicate a violated invariant or that the optimizer failed to verify the invariant during compilation. diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 88433cc25d8a..a87cfe1d4b7b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -887,20 +887,6 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node, - nodemask_t *nmask) -{ - *hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask); - if (unlikely(!*hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - return false; - } - - folio_prep_large_rmappable((struct folio *)*hpage); - count_vm_event(THP_COLLAPSE_ALLOC); - return true; -} - /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. @@ -1055,7 +1041,7 @@ out: return result; } -static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, +static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : @@ -1063,17 +1049,23 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, int node = hpage_collapse_find_target_node(cc); struct folio *folio; - if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) + folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); + if (!folio) { + *foliop = NULL; + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; + } - folio = page_folio(*hpage); + count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); - *hpage = NULL; + *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } - count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC); + count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); + + *foliop = folio; return SCAN_SUCCEED; } @@ -1085,6 +1077,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; + struct folio *folio; struct page *hpage; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; @@ -1101,7 +1094,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, */ mmap_read_unlock(mm); - result = alloc_charge_hpage(&hpage, mm, cc); + result = alloc_charge_folio(&folio, mm, cc); + hpage = &folio->page; if (result != SCAN_SUCCEED) goto out_nolock; @@ -1205,12 +1199,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, goto out_up_write; /* - * spin_lock() below is not the equivalent of smp_wmb(), but - * the smp_wmb() inside __SetPageUptodate() can be reused to - * avoid the copy_huge_page writes to become visible after - * the set_pmd_at() write. + * The smp_wmb() inside __folio_mark_uptodate() ensures the + * copy_huge_page writes become visible before the set_pmd_at() + * write. */ - __SetPageUptodate(hpage); + __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(hpage, vma->vm_page_prot); @@ -1218,8 +1211,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(hpage, vma, address); - lru_cache_add_inactive_or_unevictable(hpage, vma); + folio_add_new_anon_rmap(folio, vma, address); + folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); @@ -1790,29 +1783,27 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; - struct page *hpage; struct page *page; - struct page *tmp; - struct folio *folio; + struct page *tmp, *dst; + struct folio *folio, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); - int nr = 0; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); - result = alloc_charge_hpage(&hpage, mm, cc); + result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; - __SetPageLocked(hpage); + __folio_set_locked(new_folio); if (is_shmem) - __SetPageSwapBacked(hpage); - hpage->index = start; - hpage->mapping = mapping; + __folio_set_swapbacked(new_folio); + new_folio->index = start; + new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is @@ -2045,20 +2036,24 @@ xa_unlocked: * The old pages are locked, so they won't change anymore. */ index = start; + dst = folio_page(new_folio, 0); list_for_each_entry(page, &pagelist, lru) { while (index < page->index) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); + clear_highpage(dst); index++; + dst++; } - if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), page) > 0) { + if (copy_mc_highpage(dst, page) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; + dst++; } while (index < end) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); + clear_highpage(dst); index++; + dst++; } if (nr_none) { @@ -2086,16 +2081,17 @@ xa_unlocked: } /* - * If userspace observed a missing page in a VMA with a MODE_MISSING - * userfaultfd, then it might expect a UFFD_EVENT_PAGEFAULT for that - * page. If so, we need to roll back to avoid suppressing such an - * event. Since wp/minor userfaultfds don't give userspace any - * guarantees that the kernel doesn't fill a missing page with a zero - * page, so they don't matter here. + * If userspace observed a missing page in a VMA with + * a MODE_MISSING userfaultfd, then it might expect a + * UFFD_EVENT_PAGEFAULT for that page. If so, we need to + * roll back to avoid suppressing such an event. Since + * wp/minor userfaultfds don't give userspace any + * guarantees that the kernel doesn't fill a missing + * page with a zero page, so they don't matter here. * - * Any userfaultfds registered after this point will not be able to - * observe any missing pages due to the previously inserted retry - * entries. + * Any userfaultfds registered after this point will + * not be able to observe any missing pages due to the + * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { @@ -2120,33 +2116,32 @@ immap_locked: xas_lock_irq(&xas); } - nr = thp_nr_pages(hpage); if (is_shmem) - __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); + __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else - __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr); + __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { - __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none); + __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ - __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); + __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* - * Mark hpage as uptodate before inserting it into the page cache so - * that it isn't mistaken for an fallocated but unwritten page. + * Mark new_folio as uptodate before inserting it into the + * page cache so that it isn't mistaken for an fallocated but + * unwritten page. */ - folio = page_folio(hpage); - folio_mark_uptodate(folio); - folio_ref_add(folio, HPAGE_PMD_NR - 1); + folio_mark_uptodate(new_folio); + folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) - folio_mark_dirty(folio); - folio_add_lru(folio); + folio_mark_dirty(new_folio); + folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); - xas_store(&xas, hpage); + xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); @@ -2157,7 +2152,7 @@ immap_locked: retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; - unlock_page(hpage); + folio_unlock(new_folio); /* * The collapse has succeeded, so free the old pages. @@ -2202,13 +2197,13 @@ rollback: smp_mb(); } - hpage->mapping = NULL; + new_folio->mapping = NULL; - unlock_page(hpage); - put_page(hpage); + folio_unlock(new_folio); + folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); - trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result); + trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index e39fba5565c5..0b4d0a8bd361 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -185,6 +185,28 @@ void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) } EXPORT_SYMBOL(bt_sock_unlink); +bool bt_sock_linked(struct bt_sock_list *l, struct sock *s) +{ + struct sock *sk; + + if (!l || !s) + return false; + + read_lock(&l->lock); + + sk_for_each(sk, &l->head) { + if (s == sk) { + read_unlock(&l->lock); + return true; + } + } + + read_unlock(&l->lock); + + return false; +} +EXPORT_SYMBOL(bt_sock_linked); + void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { const struct cred *old_cred; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index a660c428e220..38f542665f19 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -745,8 +745,7 @@ static int __init bnep_init(void) if (flt[0]) BT_INFO("BNEP filters: %s", flt); - bnep_sock_init(); - return 0; + return bnep_sock_init(); } static void __exit bnep_exit(void) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 9b365fb44fac..c2c80d600083 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -90,6 +90,16 @@ static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst, #define ISO_CONN_TIMEOUT (HZ * 40) #define ISO_DISCONN_TIMEOUT (HZ * 2) +static struct sock *iso_sock_hold(struct iso_conn *conn) +{ + if (!conn || !bt_sock_linked(&iso_sk_list, conn->sk)) + return NULL; + + sock_hold(conn->sk); + + return conn->sk; +} + static void iso_sock_timeout(struct work_struct *work) { struct iso_conn *conn = container_of(work, struct iso_conn, @@ -97,9 +107,7 @@ static void iso_sock_timeout(struct work_struct *work) struct sock *sk; iso_conn_lock(conn); - sk = conn->sk; - if (sk) - sock_hold(sk); + sk = iso_sock_hold(conn); iso_conn_unlock(conn); if (!sk) @@ -217,9 +225,7 @@ static void iso_conn_del(struct hci_conn *hcon, int err) /* Kill socket */ iso_conn_lock(conn); - sk = conn->sk; - if (sk) - sock_hold(sk); + sk = iso_sock_hold(conn); iso_conn_unlock(conn); if (sk) { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 3c3650902c83..fb368540139a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -76,6 +76,16 @@ struct sco_pinfo { #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) +static struct sock *sco_sock_hold(struct sco_conn *conn) +{ + if (!conn || !bt_sock_linked(&sco_sk_list, conn->sk)) + return NULL; + + sock_hold(conn->sk); + + return conn->sk; +} + static void sco_sock_timeout(struct work_struct *work) { struct sco_conn *conn = container_of(work, struct sco_conn, @@ -87,9 +97,7 @@ static void sco_sock_timeout(struct work_struct *work) sco_conn_unlock(conn); return; } - sk = conn->sk; - if (sk) - sock_hold(sk); + sk = sco_sock_hold(conn); sco_conn_unlock(conn); if (!sk) @@ -194,9 +202,7 @@ static void sco_conn_del(struct hci_conn *hcon, int err) /* Kill socket */ sco_conn_lock(conn); - sk = conn->sk; - if (sk) - sock_hold(sk); + sk = sco_sock_hold(conn); sco_conn_unlock(conn); if (sk) { diff --git a/net/core/filter.c b/net/core/filter.c index 8bfd46a070c1..a2467a7c01f9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2423,9 +2423,9 @@ out: /* Internal, non-exposed redirect flags. */ enum { - BPF_F_NEIGH = (1ULL << 1), - BPF_F_PEER = (1ULL << 2), - BPF_F_NEXTHOP = (1ULL << 3), + BPF_F_NEIGH = (1ULL << 16), + BPF_F_PEER = (1ULL << 17), + BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; @@ -2435,6 +2435,8 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) struct sk_buff *clone; int ret; + BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; @@ -6221,24 +6223,16 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; - int skb_len, dev_len; - int mtu = 0; - - if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) { - ret = -EINVAL; - goto out; - } + int mtu, dev_len, skb_len; - if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) { - ret = -EINVAL; - goto out; - } + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) + return -EINVAL; + if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) + return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) { - ret = -ENODEV; - goto out; - } + if (unlikely(!dev)) + return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; @@ -6273,19 +6267,15 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; - int mtu = 0, dev_len; + int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ - if (unlikely(flags)) { - ret = -EINVAL; - goto out; - } + if (unlikely(flags)) + return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) { - ret = -ENODEV; - goto out; - } + if (unlikely(!dev)) + return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; @@ -6297,7 +6287,7 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; -out: + *mtu_len = mtu; return ret; } @@ -6308,7 +6298,7 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6320,7 +6310,7 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 2afac40bb83c..2da881a8e798 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -644,6 +644,8 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) + return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; @@ -672,6 +674,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; + if (sk_is_vsock(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; @@ -1246,6 +1250,8 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) + return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; @@ -1274,6 +1280,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; + if (sk_is_vsock(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cb0c80328eeb..4822f68edbf0 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -283,17 +283,19 @@ static struct in_device *inetdev_init(struct net_device *dev) /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); - err = devinet_sysctl_register(in_dev); - if (err) { - in_dev->dead = 1; - neigh_parms_release(&arp_tbl, in_dev->arp_parms); - in_dev_put(in_dev); - in_dev = NULL; - goto out; + if (dev != blackhole_netdev) { + err = devinet_sysctl_register(in_dev); + if (err) { + in_dev->dead = 1; + neigh_parms_release(&arp_tbl, in_dev->arp_parms); + in_dev_put(in_dev); + in_dev = NULL; + goto out; + } + ip_mc_init_dev(in_dev); + if (dev->flags & IFF_UP) + ip_mc_up(in_dev); } - ip_mc_init_dev(in_dev); - if (dev->flags & IFF_UP) - ip_mc_up(in_dev); /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); @@ -332,6 +334,19 @@ static void inetdev_destroy(struct in_device *in_dev) in_dev_put(in_dev); } +static int __init inet_blackhole_dev_init(void) +{ + int err = 0; + + rtnl_lock(); + if (!inetdev_init(blackhole_netdev)) + err = -ENOMEM; + rtnl_unlock(); + + return err; +} +late_initcall(inet_blackhole_dev_init); + int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { const struct in_ifaddr *ifa; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8720f3840b69..ca8cc0988b61 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -980,21 +980,31 @@ static bool reqsk_queue_unlink(struct request_sock *req) found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); } - if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) - reqsk_put(req); + return found; } -bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +static bool __inet_csk_reqsk_queue_drop(struct sock *sk, + struct request_sock *req, + bool from_timer) { bool unlinked = reqsk_queue_unlink(req); + if (!from_timer && timer_delete_sync(&req->rsk_timer)) + reqsk_put(req); + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } + +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +{ + return __inet_csk_reqsk_queue_drop(sk, req, false); +} EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) @@ -1087,7 +1097,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ - inet_csk_reqsk_queue_drop(sk_listener, nreq); + __inet_csk_reqsk_queue_drop(sk_listener, nreq, true); goto no_ownership; } @@ -1113,7 +1123,8 @@ no_ownership: } drop: - inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); + __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); + reqsk_put(req); } static bool reqsk_queue_hash_req(struct request_sock *req, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c33bca2c3841..63bbc7f6a5a8 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -17,47 +17,43 @@ #include <net/ip.h> #include <net/l3mdev.h> -static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, - int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark) +static struct dst_entry *__xfrm4_dst_lookup(struct flowi4 *fl4, + const struct xfrm_dst_lookup_params *params) { struct rtable *rt; memset(fl4, 0, sizeof(*fl4)); - fl4->daddr = daddr->a4; - fl4->flowi4_tos = tos; - fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(net, oif); - fl4->flowi4_mark = mark; - if (saddr) - fl4->saddr = saddr->a4; - - rt = __ip_route_output_key(net, fl4); + fl4->daddr = params->daddr->a4; + fl4->flowi4_tos = params->tos; + fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(params->net, + params->oif); + fl4->flowi4_mark = params->mark; + if (params->saddr) + fl4->saddr = params->saddr->a4; + fl4->flowi4_proto = params->ipproto; + fl4->uli = params->uli; + + rt = __ip_route_output_key(params->net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } -static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark) +static struct dst_entry *xfrm4_dst_lookup(const struct xfrm_dst_lookup_params *params) { struct flowi4 fl4; - return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); + return __xfrm4_dst_lookup(&fl4, params); } -static int xfrm4_get_saddr(struct net *net, int oif, - xfrm_address_t *saddr, xfrm_address_t *daddr, - u32 mark) +static int xfrm4_get_saddr(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params) { struct dst_entry *dst; struct flowi4 fl4; - dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); + dst = __xfrm4_dst_lookup(&fl4, params); if (IS_ERR(dst)) return -EHOSTUNREACH; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 444b0b4469a4..4cd625af91e6 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -23,23 +23,24 @@ #include <net/ip6_route.h> #include <net/l3mdev.h> -static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - u32 mark) +static struct dst_entry *xfrm6_dst_lookup(const struct xfrm_dst_lookup_params *params) { struct flowi6 fl6; struct dst_entry *dst; int err; memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_l3mdev = l3mdev_master_ifindex_by_index(net, oif); - fl6.flowi6_mark = mark; - memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); - if (saddr) - memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); + fl6.flowi6_l3mdev = l3mdev_master_ifindex_by_index(params->net, + params->oif); + fl6.flowi6_mark = params->mark; + memcpy(&fl6.daddr, params->daddr, sizeof(fl6.daddr)); + if (params->saddr) + memcpy(&fl6.saddr, params->saddr, sizeof(fl6.saddr)); - dst = ip6_route_output(net, NULL, &fl6); + fl6.flowi4_proto = params->ipproto; + fl6.uli = params->uli; + + dst = ip6_route_output(params->net, NULL, &fl6); err = dst->error; if (dst->error) { @@ -50,15 +51,14 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, return dst; } -static int xfrm6_get_saddr(struct net *net, int oif, - xfrm_address_t *saddr, xfrm_address_t *daddr, - u32 mark) +static int xfrm6_get_saddr(xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params) { struct dst_entry *dst; struct net_device *dev; struct inet6_dev *idev; - dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); + dst = xfrm6_dst_lookup(params); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -68,7 +68,8 @@ static int xfrm6_get_saddr(struct net *net, int oif, return -EHOSTUNREACH; } dev = idev->dev; - ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); + ipv6_dev_get_saddr(dev_net(dev), dev, ¶ms->daddr->in6, 0, + &saddr->in6); dst_release(dst); return 0; } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index a901fd14fe3b..e27e00cb16c6 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -115,7 +115,7 @@ static int l2tp_tunnel_notify(struct genl_family *family, NLM_F_ACK, tunnel, cmd); if (ret >= 0) { - ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + ret = genlmsg_multicast_allns(family, msg, 0, 0); /* We don't care if no one is listening */ if (ret == -ESRCH) ret = 0; @@ -143,7 +143,7 @@ static int l2tp_session_notify(struct genl_family *family, NLM_F_ACK, session, cmd); if (ret >= 0) { - ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + ret = genlmsg_multicast_allns(family, msg, 0, 0); /* We don't care if no one is listening */ if (ret == -ESRCH) ret = 0; diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 0e4beae421f8..2aad0562a413 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -23,6 +23,7 @@ static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb, struct bpf_nf_link { struct bpf_link link; struct nf_hook_ops hook_ops; + netns_tracker ns_tracker; struct net *net; u32 dead; const struct nf_defrag_hook *defrag_hook; @@ -120,6 +121,7 @@ static void bpf_nf_link_release(struct bpf_link *link) if (!cmpxchg(&nf_link->dead, 0, 1)) { nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops); bpf_nf_disable_defrag(nf_link); + put_net_track(nf_link->net, &nf_link->ns_tracker); } } @@ -150,11 +152,12 @@ static int bpf_nf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); + const struct nf_defrag_hook *hook = nf_link->defrag_hook; info->netfilter.pf = nf_link->hook_ops.pf; info->netfilter.hooknum = nf_link->hook_ops.hooknum; info->netfilter.priority = nf_link->hook_ops.priority; - info->netfilter.flags = 0; + info->netfilter.flags = hook ? BPF_F_NETFILTER_IP_DEFRAG : 0; return 0; } @@ -257,6 +260,8 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) return err; } + get_net_track(net, &link->ns_tracker, GFP_KERNEL); + return bpf_link_settle(&link_primer); } diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index d80abd6ccaf8..6dcf4bc7e30b 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -79,7 +79,7 @@ static struct xt_target nflog_tg_reg[] __read_mostly = { { .name = "NFLOG", .revision = 0, - .family = NFPROTO_IPV4, + .family = NFPROTO_IPV6, .checkentry = nflog_tg_check, .destroy = nflog_tg_destroy, .target = nflog_tg, diff --git a/net/netfilter/xt_TRACE.c b/net/netfilter/xt_TRACE.c index f3fa4f11348c..a642ff09fc8e 100644 --- a/net/netfilter/xt_TRACE.c +++ b/net/netfilter/xt_TRACE.c @@ -49,6 +49,7 @@ static struct xt_target trace_tg_reg[] __read_mostly = { .target = trace_tg, .checkentry = trace_tg_check, .destroy = trace_tg_destroy, + .me = THIS_MODULE, }, #endif }; diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index f76fe04fc9a4..65b965ca40ea 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -62,7 +62,7 @@ static struct xt_target mark_tg_reg[] __read_mostly = { { .name = "MARK", .revision = 2, - .family = NFPROTO_IPV4, + .family = NFPROTO_IPV6, .target = mark_tg, .targetsize = sizeof(struct xt_mark_tginfo2), .me = THIS_MODULE, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d41c4a936ad0..d6eee5140c8b 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1355,15 +1355,11 @@ static int genl_ctrl_event(int event, const struct genl_family *family, if (IS_ERR(msg)) return PTR_ERR(msg); - if (!family->netnsok) { + if (!family->netnsok) genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0, 0, GFP_KERNEL); - } else { - rcu_read_lock(); - genlmsg_multicast_allns(&genl_ctrl, msg, 0, - 0, GFP_ATOMIC); - rcu_read_unlock(); - } + else + genlmsg_multicast_allns(&genl_ctrl, msg, 0, 0); return 0; } @@ -1752,23 +1748,23 @@ problem: core_initcall(genl_init); -static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, - gfp_t flags) +static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group) { struct sk_buff *tmp; struct net *net, *prev = NULL; bool delivered = false; int err; + rcu_read_lock(); for_each_net_rcu(net) { if (prev) { - tmp = skb_clone(skb, flags); + tmp = skb_clone(skb, GFP_ATOMIC); if (!tmp) { err = -ENOMEM; goto error; } err = nlmsg_multicast(prev->genl_sock, tmp, - portid, group, flags); + portid, group, GFP_ATOMIC); if (!err) delivered = true; else if (err != -ESRCH) @@ -1777,27 +1773,31 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, prev = net; } + err = nlmsg_multicast(prev->genl_sock, skb, portid, group, GFP_ATOMIC); + + rcu_read_unlock(); - err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); if (!err) delivered = true; else if (err != -ESRCH) return err; return delivered ? 0 : -ESRCH; error: + rcu_read_unlock(); + kfree_skb(skb); return err; } int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, - unsigned int group, gfp_t flags) + unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; - return genlmsg_mcast(skb, portid, group, flags); + return genlmsg_mcast(skb, portid, group); } EXPORT_SYMBOL(genlmsg_multicast_allns); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2d6d58e1b278..4572aa6e0273 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1489,8 +1489,29 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, bool skip_sw = tc_skip_sw(fl_flags); bool skip_hw = tc_skip_hw(fl_flags); - if (tc_act_bind(act->tcfa_flags)) + if (tc_act_bind(act->tcfa_flags)) { + /* Action is created by classifier and is not + * standalone. Check that the user did not set + * any action flags different than the + * classifier flags, and inherit the flags from + * the classifier for the compatibility case + * where no flags were specified at all. + */ + if ((tc_act_skip_sw(act->tcfa_flags) && !skip_sw) || + (tc_act_skip_hw(act->tcfa_flags) && !skip_hw)) { + NL_SET_ERR_MSG(extack, + "Mismatch between action and filter offload flags"); + err = -EINVAL; + goto err; + } + if (skip_sw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_SW; + if (skip_hw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_HW; continue; + } + + /* Action is standalone */ if (skip_sw != tc_act_skip_sw(act->tcfa_flags) || skip_hw != tc_act_skip_hw(act->tcfa_flags)) { NL_SET_ERR_MSG(extack, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6ab9359c1706..b51af871a621 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -505,19 +505,28 @@ static void dev_watchdog(struct timer_list *t) unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; + unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); + if (!netif_xmit_stopped(txq)) + continue; + + /* Paired with WRITE_ONCE() + smp_mb...() in + * netdev_tx_sent_queue() and netif_tx_stop_queue(). + */ + smp_mb(); trans_start = READ_ONCE(txq->trans_start); - if (netif_xmit_stopped(txq) && - time_after(jiffies, (trans_start + - dev->watchdog_timeo))) { + + if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { timedout_ms = jiffies_to_msecs(jiffies - trans_start); atomic_long_inc(&txq->trans_timeout); break; } + if (time_after(oldest_start, trans_start)) + oldest_start = trans_start; } if (unlikely(timedout_ms)) { @@ -530,7 +539,7 @@ static void dev_watchdog(struct timer_list *t) netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + + round_jiffies(oldest_start + dev->watchdog_timeo))) release = false; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 87090d679036..951a87909c29 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1988,7 +1988,8 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, taprio_start_sched(sch, start, new_admin); - rcu_assign_pointer(q->admin_sched, new_admin); + admin = rcu_replace_pointer(q->admin_sched, new_admin, + lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); @@ -2396,9 +2397,6 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; - oper = rtnl_dereference(q->oper_sched); - admin = rtnl_dereference(q->admin_sched); - mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -2419,18 +2417,23 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; + rcu_read_lock(); + + oper = rtnl_dereference(q->oper_sched); + admin = rtnl_dereference(q->admin_sched); + if (oper && taprio_dump_tc_entries(skb, q, oper)) - goto options_error; + goto options_error_rcu; if (oper && dump_schedule(skb, oper)) - goto options_error; + goto options_error_rcu; if (!admin) goto done; sched_nest = nla_nest_start_noflag(skb, TCA_TAPRIO_ATTR_ADMIN_SCHED); if (!sched_nest) - goto options_error; + goto options_error_rcu; if (dump_schedule(skb, admin)) goto admin_error; @@ -2438,11 +2441,15 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) nla_nest_end(skb, sched_nest); done: + rcu_read_unlock(); return nla_nest_end(skb, nest); admin_error: nla_nest_cancel(skb, sched_nest); +options_error_rcu: + rcu_read_unlock(); + options_error: nla_nest_cancel(skb, nest); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 306b536fa89e..284cec1e20ec 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -753,7 +753,7 @@ static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { - if (smc_pnet_match(pnetid, pe->pnetid)) { + if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 0021065a600a..994c0cd4fddb 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -648,8 +648,10 @@ void smc_wr_free_link(struct smc_link *lnk) smc_wr_tx_wait_no_pending_sends(lnk); percpu_ref_kill(&lnk->wr_reg_refs); wait_for_completion(&lnk->reg_ref_comp); + percpu_ref_exit(&lnk->wr_reg_refs); percpu_ref_kill(&lnk->wr_tx_refs); wait_for_completion(&lnk->tx_ref_comp); + percpu_ref_exit(&lnk->wr_tx_refs); if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, @@ -912,11 +914,13 @@ int smc_wr_create_link(struct smc_link *lnk) init_waitqueue_head(&lnk->wr_reg_wait); rc = percpu_ref_init(&lnk->wr_reg_refs, smcr_wr_reg_refs_free, 0, GFP_KERNEL); if (rc) - goto dma_unmap; + goto cancel_ref; init_completion(&lnk->reg_ref_comp); init_waitqueue_head(&lnk->wr_rx_empty_wait); return rc; +cancel_ref: + percpu_ref_exit(&lnk->wr_tx_refs); dma_unmap: if (lnk->wr_rx_v2_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e87fd9480acd..78b5f4f8808b 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1508,6 +1508,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto { struct virtio_vsock_sock *vvs = vsk->trans; struct sock *sk = sk_vsock(vsk); + struct virtio_vsock_hdr *hdr; struct sk_buff *skb; int off = 0; int err; @@ -1517,10 +1518,19 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto * works for types other than dgrams. */ skb = __skb_recv_datagram(sk, &vvs->rx_queue, MSG_DONTWAIT, &off, &err); + if (!skb) { + spin_unlock_bh(&vvs->rx_lock); + return err; + } + + hdr = virtio_vsock_hdr(skb); + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) + vvs->msg_count--; + + virtio_transport_dec_rx_pkt(vvs, le32_to_cpu(hdr->len)); spin_unlock_bh(&vvs->rx_lock); - if (!skb) - return err; + virtio_transport_send_credit_update(vsk); return recv_actor(sk, skb); } diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index c42c5cc18f32..4aa6e74ec295 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -114,14 +114,6 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, return copied; } -/* Copy of original proto with updated sock_map methods */ -static struct proto vsock_bpf_prot = { - .close = sock_map_close, - .recvmsg = vsock_bpf_recvmsg, - .sock_is_readable = sk_msg_is_readable, - .unhash = sock_map_unhash, -}; - static void vsock_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9e74f249cb45..797907303669 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17905,10 +17905,8 @@ void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, genlmsg_end(msg, hdr); - rcu_read_lock(); genlmsg_multicast_allns(&nl80211_fam, msg, 0, - NL80211_MCGRP_REGULATORY, GFP_ATOMIC); - rcu_read_unlock(); + NL80211_MCGRP_REGULATORY); return; @@ -18605,10 +18603,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, genlmsg_end(msg, hdr); - rcu_read_lock(); genlmsg_multicast_allns(&nl80211_fam, msg, 0, - NL80211_MCGRP_REGULATORY, GFP_ATOMIC); - rcu_read_unlock(); + NL80211_MCGRP_REGULATORY); return; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6346690d5c69..04dc0c8a8370 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -263,6 +263,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { + struct xfrm_dst_lookup_params params; + if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; @@ -271,9 +273,12 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, daddr = &x->props.saddr; } - dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, - x->props.family, - xfrm_smark_get(0, x)); + memset(¶ms, 0, sizeof(params)); + params.net = net; + params.saddr = saddr; + params.daddr = daddr; + params.mark = xfrm_smark_get(0, x); + dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b699cc2ec35a..d788baffbf10 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -251,10 +251,8 @@ static const struct xfrm_if_cb *xfrm_if_get_cb(void) return rcu_dereference(xfrm_if_cb); } -struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr, - int family, u32 mark) +struct dst_entry *__xfrm_dst_lookup(int family, + const struct xfrm_dst_lookup_params *params) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; @@ -263,7 +261,7 @@ struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); - dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark); + dst = afinfo->dst_lookup(params); rcu_read_unlock(); @@ -277,6 +275,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, xfrm_address_t *prev_daddr, int family, u32 mark) { + struct xfrm_dst_lookup_params params; struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; @@ -291,7 +290,29 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, daddr = x->coaddr; } - dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark); + params.net = net; + params.saddr = saddr; + params.daddr = daddr; + params.tos = tos; + params.oif = oif; + params.mark = mark; + params.ipproto = x->id.proto; + if (x->encap) { + switch (x->encap->encap_type) { + case UDP_ENCAP_ESPINUDP: + params.ipproto = IPPROTO_UDP; + params.uli.ports.sport = x->encap->encap_sport; + params.uli.ports.dport = x->encap->encap_dport; + break; + case TCP_ENCAP_ESPINTCP: + params.ipproto = IPPROTO_TCP; + params.uli.ports.sport = x->encap->encap_sport; + params.uli.ports.dport = x->encap->encap_dport; + break; + } + } + + dst = __xfrm_dst_lookup(family, ¶ms); if (!IS_ERR(dst)) { if (prev_saddr != saddr) @@ -2424,15 +2445,15 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) } static int -xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local, - xfrm_address_t *remote, unsigned short family, u32 mark) +xfrm_get_saddr(unsigned short family, xfrm_address_t *saddr, + const struct xfrm_dst_lookup_params *params) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; - err = afinfo->get_saddr(net, oif, local, remote, mark); + err = afinfo->get_saddr(saddr, params); rcu_read_unlock(); return err; } @@ -2461,9 +2482,14 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { - error = xfrm_get_saddr(net, fl->flowi_oif, - &tmp, remote, - tmpl->encap_family, 0); + struct xfrm_dst_lookup_params params; + + memset(¶ms, 0, sizeof(params)); + params.net = net; + params.oif = fl->flowi_oif; + params.daddr = remote; + error = xfrm_get_saddr(tmpl->encap_family, &tmp, + ¶ms); if (error) goto fail; local = &tmp; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 979f23cded40..1d91b42e7997 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -176,6 +176,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, struct netlink_ext_ack *extack) { int err; + u16 family = p->sel.family; err = -EINVAL; switch (p->family) { @@ -196,7 +197,10 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; } - switch (p->sel.family) { + if (!family && !(p->flags & XFRM_STATE_AF_UNSPEC)) + family = p->family; + + switch (family) { case AF_UNSPEC: break; @@ -995,7 +999,9 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) if (!nla) return -EMSGSIZE; ap = nla_data(nla); - memcpy(ap, auth, sizeof(struct xfrm_algo_auth)); + strscpy_pad(ap->alg_name, auth->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = auth->alg_key_len; + ap->alg_trunc_len = auth->alg_trunc_len; if (redact_secret && auth->alg_key_len) memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8); else diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 2c23a5a28608..54bc18e8164b 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -582,11 +582,18 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info; + struct selinux_fs_info *fsi; struct selinux_load_state load_state; ssize_t length; void *data = NULL; + /* no partial writes */ + if (*ppos) + return -EINVAL; + /* no empty policies */ + if (!count) + return -EINVAL; + mutex_lock(&selinux_state.policy_mutex); length = avc_has_perm(current_sid(), SECINITSID_SECURITY, @@ -594,26 +601,22 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, if (length) goto out; - /* No partial writes. */ - length = -EINVAL; - if (*ppos != 0) - goto out; - - length = -ENOMEM; data = vmalloc(count); - if (!data) + if (!data) { + length = -ENOMEM; goto out; - - length = -EFAULT; - if (copy_from_user(data, buf, count) != 0) + } + if (copy_from_user(data, buf, count) != 0) { + length = -EFAULT; goto out; + } length = security_load_policy(data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); goto out; } - + fsi = file_inode(file)->i_sb->s_fs_info; length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n"); @@ -622,13 +625,12 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, } selinux_policy_commit(&load_state); - length = count; - audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD, "auid=%u ses=%u lsm=selinux res=1", from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); + out: mutex_unlock(&selinux_state.policy_mutex); vfree(data); diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 5f0f8d9c08d1..8c6254ff143e 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -172,6 +172,9 @@ static int apply_constraint_to_size(struct snd_pcm_hw_params *params, step = max(step, amdtp_syt_intervals[i]); } + if (step == 0) + return -EINVAL; + t.min = roundup(s->min, step); t.max = rounddown(s->max, step); t.integer = 1; diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 9698ebe3fbc2..233b03bb4f98 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -173,7 +173,7 @@ config SND_HDA_SCODEC_TAS2781_I2C depends on SND_SOC select SND_SOC_TAS2781_COMLIB select SND_SOC_TAS2781_FMWLIB - select CRC32_SARWATE + select CRC32 help Say Y or M here to include TAS2781 I2C HD-audio side codec support in snd-hda-intel driver, such as ALC287. diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index e41316e2e983..892223d9e64a 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1411,8 +1411,9 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac kctrl = snd_hda_gen_add_kctl(&spec->gen, "Line Out Playback Volume", &cs42l42_dac_volume_mixer); /* Update Line Out kcontrol template */ - kctrl->private_value = HDA_COMPOSE_AMP_VAL_OFS(DOLPHIN_HP_PIN_NID, 3, CS8409_CODEC1, - HDA_OUTPUT, CS42L42_VOL_DAC) | HDA_AMP_VAL_MIN_MUTE; + if (kctrl) + kctrl->private_value = HDA_COMPOSE_AMP_VAL_OFS(DOLPHIN_HP_PIN_NID, 3, CS8409_CODEC1, + HDA_OUTPUT, CS42L42_VOL_DAC) | HDA_AMP_VAL_MIN_MUTE; cs8409_enable_ur(codec, 0); snd_hda_codec_set_name(codec, "CS8409/CS42L42"); break; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 07e1547fff2e..9be5a5c509f0 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3857,20 +3857,18 @@ static void alc_default_init(struct hda_codec *codec) hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); - if (hp_pin_sense) + if (hp_pin_sense) { msleep(2); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - if (hp_pin_sense) - msleep(85); + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT); + msleep(75); - if (hp_pin_sense) - msleep(100); + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE); + msleep(75); + } } static void alc_default_shutup(struct hda_codec *codec) @@ -3886,22 +3884,20 @@ static void alc_default_shutup(struct hda_codec *codec) hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); - if (hp_pin_sense) + if (hp_pin_sense) { msleep(2); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - if (hp_pin_sense) - msleep(85); - - if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - if (hp_pin_sense) - msleep(100); + msleep(75); + if (!spec->no_shutup_pins) + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + + msleep(75); + } alc_auto_setup_eapd(codec, false); alc_shutup_pins(codec); } @@ -7362,6 +7358,7 @@ enum { ALC286_FIXUP_ACER_AIO_HEADSET_MIC, ALC256_FIXUP_ASUS_HEADSET_MIC, ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + ALC255_FIXUP_PREDATOR_SUBWOOFER, ALC299_FIXUP_PREDATOR_SPK, ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, ALC289_FIXUP_DELL_SPK1, @@ -8709,6 +8706,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, + [ALC255_FIXUP_PREDATOR_SUBWOOFER] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x17, 0x90170151 }, /* use as internal speaker (LFE) */ + { 0x1b, 0x90170152 } /* use as internal speaker (back) */ + } + }, [ALC299_FIXUP_PREDATOR_SPK] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9682,6 +9686,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1166, "Acer Veriton N4640G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x1167, "Acer Veriton N6640G", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x1025, 0x1177, "Acer Predator G9-593", ALC255_FIXUP_PREDATOR_SUBWOOFER), + SND_PCI_QUIRK(0x1025, 0x1178, "Acer Predator G9-593", ALC255_FIXUP_PREDATOR_SUBWOOFER), SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK), SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 248e3bcbf386..76f5d926d1ea 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -448,6 +448,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8A7F"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_BOARD_NAME, "8B27"), } }, diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 29197d34ec09..7e9f0ab91412 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -909,7 +909,7 @@ static const struct reg_default rx_defaults[] = { { CDC_RX_BCL_VBAT_PK_EST2, 0x01 }, { CDC_RX_BCL_VBAT_PK_EST3, 0x40 }, { CDC_RX_BCL_VBAT_RF_PROC1, 0x2A }, - { CDC_RX_BCL_VBAT_RF_PROC1, 0x00 }, + { CDC_RX_BCL_VBAT_RF_PROC2, 0x00 }, { CDC_RX_BCL_VBAT_TAC1, 0x00 }, { CDC_RX_BCL_VBAT_TAC2, 0x18 }, { CDC_RX_BCL_VBAT_TAC3, 0x18 }, diff --git a/sound/soc/codecs/max98388.c b/sound/soc/codecs/max98388.c index cde5e85946cb..87386404129d 100644 --- a/sound/soc/codecs/max98388.c +++ b/sound/soc/codecs/max98388.c @@ -764,6 +764,7 @@ static int max98388_dai_tdm_slot(struct snd_soc_dai *dai, addr = MAX98388_R2044_PCM_TX_CTRL1 + (cnt / 8); bits = cnt % 8; regmap_update_bits(max98388->regmap, addr, bits, bits); + slot_found++; if (slot_found >= MAX_NUM_CH) break; } diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 0d37edb70261..9407179af5d5 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -67,6 +67,7 @@ struct fsl_micfil_soc_data { bool imx; bool use_edma; bool use_verid; + bool volume_sx; u64 formats; }; @@ -76,6 +77,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mm = { .fifo_depth = 8, .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S16_LE, + .volume_sx = true, }; static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { @@ -84,6 +86,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { .fifo_depth = 32, .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S32_LE, + .volume_sx = false, }; static struct fsl_micfil_soc_data fsl_micfil_imx93 = { @@ -94,6 +97,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx93 = { .formats = SNDRV_PCM_FMTBIT_S32_LE, .use_edma = true, .use_verid = true, + .volume_sx = false, }; static const struct of_device_id fsl_micfil_dt_ids[] = { @@ -317,7 +321,26 @@ static int hwvad_detected(struct snd_kcontrol *kcontrol, return 0; } -static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { +static const struct snd_kcontrol_new fsl_micfil_volume_controls[] = { + SOC_SINGLE_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0, gain_tlv), +}; + +static const struct snd_kcontrol_new fsl_micfil_volume_sx_controls[] = { SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, @@ -334,6 +357,9 @@ static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv), +}; + +static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { SOC_ENUM_EXT("MICFIL Quality Select", fsl_micfil_quality_enum, micfil_quality_get, micfil_quality_set), @@ -801,6 +827,20 @@ static int fsl_micfil_dai_probe(struct snd_soc_dai *cpu_dai) return 0; } +static int fsl_micfil_component_probe(struct snd_soc_component *component) +{ + struct fsl_micfil *micfil = snd_soc_component_get_drvdata(component); + + if (micfil->soc->volume_sx) + snd_soc_add_component_controls(component, fsl_micfil_volume_sx_controls, + ARRAY_SIZE(fsl_micfil_volume_sx_controls)); + else + snd_soc_add_component_controls(component, fsl_micfil_volume_controls, + ARRAY_SIZE(fsl_micfil_volume_controls)); + + return 0; +} + static const struct snd_soc_dai_ops fsl_micfil_dai_ops = { .probe = fsl_micfil_dai_probe, .startup = fsl_micfil_startup, @@ -821,6 +861,7 @@ static struct snd_soc_dai_driver fsl_micfil_dai = { static const struct snd_soc_component_driver fsl_micfil_component = { .name = "fsl-micfil-dai", + .probe = fsl_micfil_component_probe, .controls = fsl_micfil_snd_controls, .num_controls = ARRAY_SIZE(fsl_micfil_snd_controls), .legacy_dai_naming = 1, diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 3d202398c541..aa15f56ca139 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -604,6 +604,9 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, val_cr4 |= FSL_SAI_CR4_FRSZ(slots); + /* Set to avoid channel swap */ + val_cr4 |= FSL_SAI_CR4_FCONT; + /* Set to output mode to avoid tri-stated data pins */ if (tx) val_cr4 |= FSL_SAI_CR4_CHMOD; @@ -690,7 +693,7 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs), FSL_SAI_CR4_SYWD_MASK | FSL_SAI_CR4_FRSZ_MASK | - FSL_SAI_CR4_CHMOD_MASK, + FSL_SAI_CR4_CHMOD_MASK | FSL_SAI_CR4_FCONT_MASK, val_cr4); regmap_update_bits(sai->regmap, FSL_SAI_xCR5(tx, ofs), FSL_SAI_CR5_WNW_MASK | FSL_SAI_CR5_W0W_MASK | diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h index 550df87b6a06..eba465c2387b 100644 --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -137,6 +137,7 @@ /* SAI Transmit and Receive Configuration 4 Register */ +#define FSL_SAI_CR4_FCONT_MASK BIT(28) #define FSL_SAI_CR4_FCONT BIT(28) #define FSL_SAI_CR4_FCOMB_SHIFT BIT(26) #define FSL_SAI_CR4_FCOMB_SOFT BIT(27) diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c index 8cc54aedd002..010e959d4c69 100644 --- a/sound/soc/loongson/loongson_card.c +++ b/sound/soc/loongson/loongson_card.c @@ -137,6 +137,7 @@ static int loongson_card_parse_of(struct loongson_card_data *data) dev_err(dev, "getting cpu dlc error (%d)\n", ret); goto err; } + loongson_dai_links[i].platforms->of_node = loongson_dai_links[i].cpus->of_node; ret = snd_soc_of_get_dlc(codec, NULL, loongson_dai_links[i].codecs, 0); if (ret < 0) { diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 73b42d9ee244..e587455dc40a 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -1246,6 +1246,8 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) /* Allocation for i2sctl regmap fields */ drvdata->i2sctl = devm_kzalloc(&pdev->dev, sizeof(struct lpaif_i2sctl), GFP_KERNEL); + if (!drvdata->i2sctl) + return -ENOMEM; /* Initialize bitfields for dai I2SCTL register */ ret = lpass_cpu_init_i2sctl_bitfields(dev, drvdata->i2sctl, diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index 6558bf2e14e8..9eb8ae0196d9 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -153,6 +153,7 @@ static int sm8250_platform_probe(struct platform_device *pdev) static const struct of_device_id snd_sm8250_dt_match[] = { {.compatible = "qcom,sm8250-sndcard"}, + {.compatible = "qcom,qrb4210-rb2-sndcard"}, {.compatible = "qcom,qrb5165-rb5-sndcard"}, {} }; diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 1bd7114c472a..98c7be340a53 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1297,7 +1297,9 @@ audio_graph: if (!of_node_name_eq(ports, "ports") && !of_node_name_eq(ports, "port")) continue; - priv->component_dais[i] = of_graph_get_endpoint_count(ports); + priv->component_dais[i] = + of_graph_get_endpoint_count(of_node_name_eq(ports, "ports") ? + ports : np); nr += priv->component_dais[i]; i++; if (i >= RSND_MAX_COMPONENT) { @@ -1510,7 +1512,8 @@ static int rsnd_dai_probe(struct rsnd_priv *priv) if (!of_node_name_eq(ports, "ports") && !of_node_name_eq(ports, "port")) continue; - for_each_endpoint_of_node(ports, dai_np) { + for_each_endpoint_of_node(of_node_name_eq(ports, "ports") ? + ports : np, dai_np) { __rsnd_dai_probe(priv, dai_np, dai_np, 0, dai_i); if (rsnd_is_gen3(priv) || rsnd_is_gen4(priv)) { rdai = rsnd_rdai_get(priv, dai_i); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ba6e346c8d66..977ec094bc2a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6559,20 +6559,27 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ }; } perf_event; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index ab364e95a9b2..f5a3a84fac95 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -200,7 +200,7 @@ $(OUTPUT)/%:%.c ifeq ($(SRCARCH),x86) LLD := lld else -LLD := ld +LLD := $(shell command -v $(LD)) endif # Filter out -static for liburandom_read.so and its dependent targets so that static builds diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index 9d768e083714..5b0c6a04cdbf 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -30,6 +30,8 @@ static noinline void uprobe_func(void) asm volatile (""); } +#define PERF_EVENT_COOKIE 0xdeadbeef + static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr, ssize_t offset, ssize_t entry_offset) { @@ -61,8 +63,11 @@ again: ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset, "kprobe_addr"); + ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie"); + + ASSERT_EQ(info.perf_event.kprobe.name_len, strlen(KPROBE_FUNC) + 1, + "name_len"); if (!info.perf_event.kprobe.func_name) { - ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len"); info.perf_event.kprobe.func_name = ptr_to_u64(&buf); info.perf_event.kprobe.name_len = sizeof(buf); goto again; @@ -73,13 +78,16 @@ again: ASSERT_EQ(err, 0, "cmp_kprobe_func_name"); break; case BPF_PERF_EVENT_TRACEPOINT: + ASSERT_EQ(info.perf_event.tracepoint.name_len, strlen(TP_NAME) + 1, + "name_len"); if (!info.perf_event.tracepoint.tp_name) { - ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len"); info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); info.perf_event.tracepoint.name_len = sizeof(buf); goto again; } + ASSERT_EQ(info.perf_event.tracepoint.cookie, PERF_EVENT_COOKIE, "tracepoint_cookie"); + err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME, strlen(TP_NAME)); ASSERT_EQ(err, 0, "cmp_tp_name"); @@ -88,13 +96,16 @@ again: case BPF_PERF_EVENT_URETPROBE: ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset"); + ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1, + "name_len"); if (!info.perf_event.uprobe.file_name) { - ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len"); info.perf_event.uprobe.file_name = ptr_to_u64(&buf); info.perf_event.uprobe.name_len = sizeof(buf); goto again; } + ASSERT_EQ(info.perf_event.uprobe.cookie, PERF_EVENT_COOKIE, "uprobe_cookie"); + err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE, strlen(UPROBE_FILE)); ASSERT_EQ(err, 0, "cmp_file_name"); @@ -138,16 +149,17 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts, .attach_mode = PROBE_ATTACH_MODE_LINK, .retprobe = type == BPF_PERF_EVENT_KRETPROBE, + .bpf_cookie = PERF_EVENT_COOKIE, ); ssize_t entry_offset = 0; + struct bpf_link *link; int link_fd, err; - skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, - KPROBE_FUNC, &opts); - if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe")) + link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, KPROBE_FUNC, &opts); + if (!ASSERT_OK_PTR(link, "attach_kprobe")) return; - link_fd = bpf_link__fd(skel->links.kprobe_run); + link_fd = bpf_link__fd(link); if (!invalid) { /* See also arch_adjust_kprobe_addr(). */ if (skel->kconfig->CONFIG_X86_KERNEL_IBT) @@ -157,39 +169,48 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, } else { kprobe_fill_invalid_user_buffer(link_fd); } - bpf_link__detach(skel->links.kprobe_run); + bpf_link__destroy(link); } static void test_tp_fill_link_info(struct test_fill_link_info *skel) { + DECLARE_LIBBPF_OPTS(bpf_tracepoint_opts, opts, + .bpf_cookie = PERF_EVENT_COOKIE, + ); + struct bpf_link *link; int link_fd, err; - skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME); - if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp")) + link = bpf_program__attach_tracepoint_opts(skel->progs.tp_run, TP_CAT, TP_NAME, &opts); + if (!ASSERT_OK_PTR(link, "attach_tp")) return; - link_fd = bpf_link__fd(skel->links.tp_run); + link_fd = bpf_link__fd(link); err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0); ASSERT_OK(err, "verify_perf_link_info"); - bpf_link__detach(skel->links.tp_run); + bpf_link__destroy(link); } static void test_uprobe_fill_link_info(struct test_fill_link_info *skel, enum bpf_perf_event_type type) { + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts, + .retprobe = type == BPF_PERF_EVENT_URETPROBE, + .bpf_cookie = PERF_EVENT_COOKIE, + ); + struct bpf_link *link; int link_fd, err; - skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run, - type == BPF_PERF_EVENT_URETPROBE, - 0, /* self pid */ - UPROBE_FILE, uprobe_offset); - if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe")) + link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run, + 0, /* self pid */ + UPROBE_FILE, uprobe_offset, + &opts); + if (!ASSERT_OK_PTR(link, "attach_uprobe")) return; - link_fd = bpf_link__fd(skel->links.uprobe_run); + link_fd = bpf_link__fd(link); err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0); ASSERT_OK(err, "verify_perf_link_info"); - bpf_link__detach(skel->links.uprobe_run); + bpf_link__destroy(link); } static int verify_kmulti_link_info(int fd, bool retprobe) @@ -278,24 +299,24 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel, bool retprobe, bool invalid) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct bpf_link *link; int link_fd, err; opts.syms = kmulti_syms; opts.cnt = KMULTI_CNT; opts.retprobe = retprobe; - skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, - NULL, &opts); - if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi")) + link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts); + if (!ASSERT_OK_PTR(link, "attach_kprobe_multi")) return; - link_fd = bpf_link__fd(skel->links.kmulti_run); + link_fd = bpf_link__fd(link); if (!invalid) { err = verify_kmulti_link_info(link_fd, retprobe); ASSERT_OK(err, "verify_kmulti_link_info"); } else { verify_kmulti_invalid_user_buffer(link_fd); } - bpf_link__detach(skel->links.kmulti_run); + bpf_link__destroy(link); } void test_fill_link_info(void) diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c index 692216c0ad3d..3e8340c2408f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c @@ -91,7 +91,7 @@ l0_%=: exit; \ SEC("tracepoint") __description("helper access to map: empty range") -__failure __msg("invalid access to map value, value_size=48 off=0 size=0") +__failure __msg("R2 invalid zero-sized read") __naked void access_to_map_empty_range(void) { asm volatile (" \ @@ -221,7 +221,7 @@ l0_%=: exit; \ SEC("tracepoint") __description("helper access to adjusted map (via const imm): empty range") -__failure __msg("invalid access to map value, value_size=48 off=4 size=0") +__failure __msg("R2 invalid zero-sized read") __naked void via_const_imm_empty_range(void) { asm volatile (" \ @@ -386,7 +386,7 @@ l0_%=: exit; \ SEC("tracepoint") __description("helper access to adjusted map (via const reg): empty range") -__failure __msg("R1 min value is outside of the allowed memory range") +__failure __msg("R2 invalid zero-sized read") __naked void via_const_reg_empty_range(void) { asm volatile (" \ @@ -556,7 +556,7 @@ l0_%=: exit; \ SEC("tracepoint") __description("helper access to adjusted map (via variable): empty range") -__failure __msg("R1 min value is outside of the allowed memory range") +__failure __msg("R2 invalid zero-sized read") __naked void map_via_variable_empty_range(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c index f67390224a9c..7cc83acac727 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c @@ -64,7 +64,7 @@ __naked void load_bytes_negative_len_2(void) SEC("tc") __description("raw_stack: skb_load_bytes, zero len") -__failure __msg("invalid zero-sized read") +__failure __msg("R4 invalid zero-sized read: u64=[0,0]") __naked void skb_load_bytes_zero_len(void) { asm volatile (" \ diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc index 20e42c030095..61877d166451 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc @@ -34,7 +34,9 @@ check_error 'f vfs_read ^$stack10000' # BAD_STACK_NUM check_error 'f vfs_read ^$arg10000' # BAD_ARG_NUM +if !grep -q 'kernel return probes support:' README; then check_error 'f vfs_read $retval ^$arg1' # BAD_VAR +fi check_error 'f vfs_read ^$none_var' # BAD_VAR check_error 'f vfs_read ^'$REG # BAD_VAR @@ -99,7 +101,9 @@ if grep -q "<argname>" README; then check_error 'f vfs_read args=^$arg*' # BAD_VAR_ARGS check_error 'f vfs_read +0(^$arg*)' # BAD_VAR_ARGS check_error 'f vfs_read $arg* ^$arg*' # DOUBLE_ARGS +if !grep -q 'kernel return probes support:' README; then check_error 'f vfs_read%return ^$arg*' # NOFENTRY_ARGS +fi check_error 'f vfs_read ^hoge' # NO_BTFARG check_error 'f kfree ^$arg10' # NO_BTFARG (exceed the number of parameters) check_error 'f kfree%return ^$retval' # NO_RETVAL diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc index 65fbb26fd58c..a16c6a6f6055 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc @@ -108,7 +108,9 @@ if grep -q "<argname>" README; then check_error 'p vfs_read args=^$arg*' # BAD_VAR_ARGS check_error 'p vfs_read +0(^$arg*)' # BAD_VAR_ARGS check_error 'p vfs_read $arg* ^$arg*' # DOUBLE_ARGS +if !grep -q 'kernel return probes support:' README; then check_error 'r vfs_read ^$arg*' # NOFENTRY_ARGS +fi check_error 'p vfs_read+8 ^$arg*' # NOFENTRY_ARGS check_error 'p vfs_read ^hoge' # NO_BTFARG check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters) |